AI-Driven 3D Visualization for Intracranial Tumour Analysis

This project delves into the application of 3D visualization techniques, enhanced by artificial intelligence, to aid in the detection and analysis of intracranial tumours. The study utilizes radiological images, including MRI and CT scans, and employs image segmentation and registration techniques to create detailed 3D models of the brain and tumours. The integration of AI, particularly deep learning algorithms, enhances the accuracy of segmentation and provides quantitative assessments of radiographic characteristics. The research highlights the benefits of 3D visualization in overcoming the limitations of 2D medical images, improving diagnostic accuracy, and assisting surgeons in surgical planning. The project also explores the use of AI in identifying biological features and automating the segmentation process, ultimately improving the efficiency and effectiveness of medical image processing. Various algorithms and techniques such as FCM algorithm, SLANT-27 whole brain segmentation method and DeepMedicUS are discussed and compared. The goal is to develop image guidance and visualization methods to overcome the complexities in brain tumour surgery and improve patient outcomes.

3D visualization in aiding intracranial tumour through radiological images
and image segmentation by using image registration and AI
Highlights
The highlights of the work are as follows:
1) The area on which this project focuses is Virtual Reality and Augmented Reality. Virtual reality
(VR) and augmented reality (AR) act as the opposite sides of a same coin. Both of these are there to
extend sensitive environment of any person by the medium of reality via the help of technology.
Virtual Reality depends on the alternative way of setting in order to provide experience while
Augmented Reality is there to improve the existing elements by adding more layers of meaning.
These are the thriving technologies and as per the reports of Augmented/Virtual Report of the year
2017, the VR/AR market would be reaching $108 billion of revenue by the year 2021 while as per the
overview given by () this business will reach a market value of $80 in the year 2025.
2) Radiological images and image segmentation will also be discussed upon. Computerised
tomography (CT), magnetic resonance imaging (MRI), ultrasound and positron emission tomography
(PET) are some of the examples of modalities related to imaging. A radiologist provides views on the
images that are produced by a scanner (Lee & Wong, 2019). Segmentation refers to extracting
specific region of the images as these are required in partitioning image data to associated elements.
Image segmentation gives quantitative data about some relevant anatomy such as to determine the
volume or the size and many more. This enables 3D visualization of a specific structure with accuracy
by making use of surface triangulation and volume rendering.
3) Extraction of 3D models by making use of various image registration techniques and AI will also
be included.
4) The main topic if the paper is combining the above said techniques that is “3D visualization in
aiding intracranial tumour through radiological images and image segmentation by using image
registration and AI”
Abstract
Background and Aim
The advancements in the sphere of imaging in medical science are a revolution for the
medicines. It is helpful in determining the presence or the level of severity of any disease that has an
impact on the clinical care of patients or the related outcomes in a specific study. Three dimensional
techniques has been a great help in intracranial tumour through the help of radiological images and
image segmentation technique. Accuracy is a vital factor in segmentation and thus 3D visualization
makes the technique more appropriate and perfect. The use of artificial intelligence in this sphere will
also be a part of the study.
1

Methodology
Artificial Intelligence algorithms have specifically deep learning have shown remarkable
progress in the field of image recognition. In radiological practice the trained physicians used to
visually assess the medical images for detecting, characterizing and monitoring diseases. The AI
implementation in image segmentation enhances the process of recognizing patterns in the data that
has been imaged thus providing quantitative assessments of radiographic characteristics. It is difficult
to find the exact location of intracranial tumours based on the 2D medical images thus the 3D
technology of visualizing medical images is being used to obtain accuracy in the field.
Introduction
Guidance and visualization of images are a vital part in the sphere of modern surgery and this
helps the surgeons in performing surgical procedures. In this paper the focus is on intracranial tumour
detection by the help of radiological images. 3D technology in visualization has enhanced the process.
To understand the system, intracranial tumour needs to be understood. The images help locating the
tumour and these images help in surgery. In brain surgery, the brain changed shape when the skull is
opened and this kind of deformation of the brain is termed as brain shift. The boundaries of these
tumours are not easy to identify thus developing image guidance as well as visualization methods in
case of the surgery of tumour will help in overcoming the complicacies in this specific type of
surgery. Medical visualization of the organs is essential for accuracy in the diagnosis being made and
surgery requires perfect 3D visualization of parts of the brain. The detection as well as 3D
visualization of parts of the brain and the tumours by the MRI method requires a lot of time and it is
also prone to errors. The system helps in detecting and presenting 3D reconstruction model of brain
and tumours. This in turn aids the radiologist to diagnose as well as analyse the brain tumours.
Segmentation and visualization technique overcome the complicacies in the 3D volume segmentation
methods such as some fine details missing. Three phase segmentation reduces the probability of the
errors in the process of segmentation. The method involved detects contours for brain, tumour and
skull. These contours are then stacked one over the other and two techniques are made use of to find
out the 3D visualization models. The results of the above said methods are impressive in nature.
Tumour refers to collection of the abnormal cells in any of the organs of the body. Brain tumour
detection is difficult and in order to detect the place of tumour knowledge and experience on the field
of radiology is required in case of medical imaging. MRI is the image diagnostic modality that is
widely used having the ability to provide characterization on a range of parameters in the living
subject providing exquisite spatial resolution. Segmentation is one of the essential but difficult steps
in the classification as well as analysis in the field of medical imaging. Artificial intelligence can be
made use of in identification of the biological features and process of segmentation. These methods
are of high value in the process of Medical Image Segmentation. Features of segmentation depend on
2

factors such as type of diseases and the features of the images. Recent advancements in techniques of
artificial intelligence such as machine learning, processing of image, recognition of pattern result in
considering the need of MIS to enhance the diagnosis. The informations that are desired for in case of
biological objects relates to basic features and thus is essential to apply image processing techniques
for the process of segmentation and visualization of the medical images.
Huo, Y., Xu, Z., Xiong, Y., Aboud, K., Parvathaneni, P., Bao, S., ... & Landman, B. A. (2019). 3d
whole brain segmentation using spatially localized atlas network tiles. NeuroImage, 194,
105-119.
Medical images have important role in the process of diagnosis and treatment of ailments.
Processing of such images increases the efficiency as well as effectiveness of processes. Segmentation
is considered to be as the initial step in case of medical image processing and this is made use of in
extracting Region of Interest (ROI) from a certain image. The author discusses about its effectiveness
and segmentation algorithm named Fuzzy C-Means (FCM) algorithm. FCM is time consuming in
case of processing the 3D models. This specific problem can be resolved by making use of parallel
programming by the use of Graphics Processing Unit. The article provides a hybrid parallel
implementation of the algorithm for the extraction of the volume objects form the medical files.
Algorithm proposed is effective in improving the performance five times as compared to the
sequential version. The article considers image segmentation that is the process involved in
partitioning digital image into certain set of different regions and this is said to be as a vital step in
many applications. Image segmentation is used which is referred to as early pre-processing steps
which can separate all the existing different areas that represent different tissues. This finds its
application in the extraction of Region of Interest that aids in providing directions to the attention of
the physician resulting in abnormalities in the tissues of the body for example tumours.
Figure 1: The proposed SLANT-27 whole brain segmentation method
3

Demiray, B., Rackerseder, J., Bozhinoski, S., & Navab, N. (2019). Weakly-Supervised
White and Grey Matter Segmentation in 3D Brain Ultrasound. arXiv preprint
arXiv:1904.05191.
The article compares 2D visualization with that of 3D visualization in case of image
processing application in medical. The adoption of the 3D models in the process of medical imaging
is becoming popular. The 2D Fuzzy algorithm is extensively being used in the process of
segmentation of the medical images owing to its effectiveness. There were many extensions that have
been proposed throughout the years. The article provides its readers with modified versions of the
algorithm for the process of segmenting the 3D medical volumes which in rare case are implemented
in 3D medical image segmentation. An alternative way of implementing this algorithm by making use
of GPU has also been included in the article. Efficiency is the main problem in using the FCM
algorithm for the process of medical imaging in case of the 3D models. A hybrid case of parallel
implementation of the algorithm is made use of in extracting objects form the medical files. This
specific algorithm is validated by making use of real medical data along with the phantom data
simulations. Accuracy in segmentation of the predefined datasets and the real patient datasets are the
primary factors for validating system. The time of processing of the sequential and parallel
implementations is analyzed illustrating the efficiency of each of the implementations.
Figure 2: DeepMedicUS with three pathways at different input resolutions
Mazurowski, M. A., Buda, M., Saha, A., & Bashir, M. R. (2019). Deep learning in radiology: An
overview of the concepts and a survey of the state of the art with focus on MRI. Journal
of Magnetic Resonance Imaging, 49(4), 939-954.
The article discusses on the usage of radiology in capturing the images of brain tumours. The
authors are of the opinion that clinical imaging is able to capture volumes of information but majority
of these radiological data get reported in qualitative terms. The use of radiomics in the field of neuro-
oncology helps in improvising the concept of biology and related treatment in brain tumours. This is
4

done by the extraction of the quantitative features from the clinical imaging arrays. These specific
data are in turn mined along with the methods of machine learning. The data then are validated in the
form of quantitative imaging biomarkers helping in characterizing the dynamics of intra-cranial
tumours in the course of the treatment. In recent times the image-based models of computation are
therefore becoming a vital technology that helps in identifying, analysing as well as validating the
quantitative features that have been extracted. The article discusses on the prevalent methodologies in
the field of radiomics that can possibly be used as the markers of prediction in the sphere of
therapeutic planning, diagnosis and prognosis in case of brain tumours in adults. The article also
discusses on the possible challenges emerging from data that are computationally generated by the
radiomic models.
Figure 3: A diagram of typical architecture of a convolutional neural network
Huang, R. Y., Bi, W. L., Griffith, B., Kaufmann, T. J., la Fougère, C., Schmidt, N. O., ... &
Nassiri, F. (2019). Imaging and diagnostic advances for intracranial
meningiomas. Neuro-oncology, 21(Supplement_1), i44-i61.
The article discusses on the imaging technology for intracranial meningiomas. It also considers the
advances that have been made in this field. The authors highlight the fact that in this particular sphere
that is ventriculography, imaging was done only when mass was doubted. The results of this imaging
used to more suggestive rather than being definitive. The article speaks about the journey that took
almost more than a century to reach the position where medical science can depend on imaging
technology to diagnose intracranial tumours such as menigioma. The use of radiology and 3D
imaging has been of great help in not just identifying the location of the tumours but also their types.
The modern techniques of radiology are continuously improving the power in the imaging
technology. Previous techniques could detect and monitor tumours but at present the techniques used
can extract biological informations from the parameters of radiology. The article explains
meningiomas describing it to be intracranial extra-axial masses that are attached to dura matter of the
brain.
5

Figure 4: (A) Noncontrast CT (B) T1-weighted gadolinium-enhanced MRI (C) T2-weighted
MRI of partially calcified right falcine meningioma
Kao, P. Y., Chen, J. W., & Manjunath, B. S. (2019). Improving 3D U-Net for Brain Tumor
Segmentation by Utilizing Lesion Prior. arXiv preprint arXiv:1907.00281.
The article discusses on the 3D MRI brain tumour segmentation by making use of auto
encoder regularization. The automatic process involved in segmentation of brain tumours from the 3D
magnetic resonance images is essential for diagnosing, treating as well as monitoring the disease.
Manually delineating requires good knowledge of anatomy and the process is expensive as well as
time consuming. Owing to its dependence on humans it can also give erroneous results. Here comes
the play of Artificial Intelligence in the segmentation process. The article refers to the segmentation
based on the 3D MRIs that are based on the architecture of encoder and decoder. The segmentation
process included in this article follows the encoder and decoder based CNN architecture. The encoder
extracts the features of the images and the decoder reconstructs the mark of segmentation.
Figure 5: The workflow diagram
6
Register to
MNI space of
1mm
Extracting the
binary masks of
necrosis
Extracting the
binary masks of
edema
Extracting the
binary masks of
enhancing tumour
Applying
element-wise
summation to
binary masks
Applying
element-wise
summation to
the binary
masks
Applying
element-wise
summation to
the binary
masks
Heat
map of
necro-
sis
Heat
Map of
edema
Heat
Map of
tumour

Mazurowski, M. A., Buda, M., Saha, A., & Bashir, M. R. (2019). Deep learning in radiology: An
overview of the concepts and a survey of the state of the art with focus on MRI. Journal
of Magnetic Resonance Imaging, 49(4), 939-954.
The article discusses about glioma that is a common type of intracranial tumour.
Segmentation needs to be accurate in case of the study of sub cortical brain structures. A large amount
of human labour is required in case of obtaining manual segmented Magnetic Resonance Imaging
(MRI) data that limits the use of quantitative data in the clinical practices. In this article, the authors
try to look into this particular problem and thereby consider an alternative that is 3D Convolutional
Neural Network on the basis of the automatically segmented gliomas. The difficulty in this process is
that in different patients the structure, location and shape of the gliomas differ. The article compares
the other 3D based models with that of 3D CNN. The authors introduce modern approach for the
segmentation of brain tumour in the MRI scans. DenseNet was developed for image classification
problem. The proposed model has been shown to have great potential for the process of MRI
segmentation or other such medical segmentation tasks. The article addresses the challenges that pop
up during the process of brain tumour segmentation by making use of the MRI scans. Class imbalance
problem is recognized as the major problem in this case.
Figure 6: An illustration depicting the difference between traditional and deep learning
machine learning
Sahiner, B., Pezeshk, A., Hadjiiski, L. M., Wang, X., Drukker, K., Cha, K. H., ... & Giger, M. L.
(2019). Deep learning in medical imaging and radiation therapy. Medical physics, 46(1),
e1-e36.
The article discusses on the segmentation process of brain tissues form the 3D medical images. This is
of great use for diagnosis of brain diseases. Segmentation also includes progression assessment as
well as monitoring of the neurological conditions. Manual segmentation is time consuming as well as
laborious. It provides subjective data while in case of automatic segmentation, there exists various
challenges such as complicated anatomical environment of brain along with the larger variations of
7

the tissues of brain. The authors address to this problem by proposing novel voxelwise residual
network that includes a set of training schemes. Manual segmentation of the structures of the brain
from the 3D images is laborious as well as time consuming and requires sophisticated and sound
knowledge in anatomy of brain. Manual segmentation is error-prone as it is low in reproducibility.
Thus automated segmentation methods are desirable as this provide consistent measurements along
with quantitative analysis.
Figure 7: CNN-extracted and conventional features: ways of combination
Prevedello, L. M., Halabi, S. S., Shih, G., Wu, C. C., Kohli, M. D., Chokshi, F. H., ... & Flanders,
A. E. (2019). Challenges related to artificial intelligence research in medical imaging and
the importance of image analysis competitions. Radiology: Artificial Intelligence, 1(1),
e180031.
The recent advancements along with the future perspectives of the machine learning
techniques provide some significant applications in the sphere of medical imaging. Machine learning
can make improvisations in the different steps of radiology. The article discusses on the facts of
radiological works such as scheduling of order and triage, detection and interpretation of findings of
data, clinical decision support systems, and quality control in the various examinations and
radiological reporting. In this particular article the authors highlight various applications of artificial
intelligence along with machine learning in the sphere of diagnostic radiology. The future impacts and
the natural extension of the techniques that related to radiological practices have also been discussed.
More and more availability of the imaging data from the machine learning techniques have been of
great significance in medical imaging. Medical imaging has progressed in post processing tasks for
example; segmentation, quantification and image registration. A medical imaging paradigm that is
intelligent is driven by data and medical images provide informations that aid in clinics. Extractions
8
Pretrained CNN
features
SVM Classifier 1
ROC analysis
and evaluation
Ensemble
Classifier
ROI image
Analytically
extracted
Features
SVM Classifier 2

of those data that are clinically relevant from the medical images require being accurate in case of
image registration and segmentation. Thus there are studies that make use of the techniques of
machine learning approaches for segmenting the medical images.
Continuous Output from
Deep Learning Algorithm
Cancer Benign Disease
0 0 5
0.1 2 103
0.2 6 90
0.3 5 21
0.4 5 8
0.5 8 5
0.6 15 8
0.7 20 5
0.8 25 4
0.9 11 1
1.0 3 0
Total 100 250
Table 1: Results from the hypothetical research study evaluating performance of hypothetical
deep learning algorithm in the differentiation of cancer.
S Tandel, G., Biswas, M., G Kakde, O., Tiwari, A., S Suri, H., Turk, M., ... & K Madhusudhan,
B. (2019). A review on a deep learning perspective in brain cancer
classification. Cancers, 11(1), 111.
In the article an overview has been provided in neurosurgical care. Background Machine
Learning is the branch of the artificial intelligence allowing computers to learn from the large
complex data sets without being programmed in an explicit way. In the day to day chores of medical
research and clinical care the technology is in its emerging stage. The complicacy in the diagnostic
and the therapeutic modalities that are made use of in neurosurgery generate volumes of data that in
ideal cases suits Machine Learning models. This article discusses on the systematic review which
effectively explores machine learning’s inherent potential in assisting and improving neurosurgical
care. Machine learning being a branch of artificial intelligence has the potential to enable computer
based algorithms to study and improve large databases without any such need of explicit
programming. This particular branch of artificial intelligence has become popular as here the
9

computers have the required computational power in building the complicated models that can help in
processing and learning from the unstructured data.
Figure 8: Work Flow Diagram of ML-based algorithms
Dos Santos, D. P., Giese, D., Brodehl, S., Chon, S. H., Staab, W., Kleinert, R., ... & Baeßler, B.
(2019). Medical students' attitude towards artificial intelligence: a multicentre
survey. European radiology, 29(4), 1640-1646.
The authors research on Artificial Intelligence demonstrates there are myriad applications found in the
field of medical images which pushed it forward. AI can automatically recognize complex methods
which provides quantitative rather than qualitative analysis and pattern matching however historically
trained doctors practiced radiology by visually assessing images that were medical. In the article the
author describes a general understanding of AI methodology, especially tasks that are image-based.
The authors have gracefully explored how these methods impacts multiple facets of radiology. There
is a general focus on the demonstration of these methods and advancements in applications on
oncology. The authors also describes about the challenges that are faced while clinical
implementation of radiology and AI merged together and perspectives on the advancements of these
domains. There are methodologies ranging from convolutional networks that are neural to auto
encoders that are vibrational. This research article also plots the performance level of Artificial
Intelligence as compared to a human intelligence starting from earliest computer science use and
breaking into the future.
10
Texture
Contrast
Classifiers
Brain MRI
Image Features
Performance
Parameters
Curvature Based
Shape Based
Extraction of
Feature
Classification Training

Figure 9: MRI brain images, pink circle- tumour region
Anaraki, A. K., Ayati, M., & Kazemi, F. (2019). Magnetic resonance imaging-based brain tumor
grades classification and grading via convolutional neural networks and genetic
algorithms. Biocybernetics and Biomedical Engineering, 39(1), 63-74.
The authors, researches objective of the paper is to show the tumor grade classifications and the
segmentation. The authors mention that the motive of the study is for the requirement of the early
detection of brain tumor and the grade the motivation. Physicians always need a quantification of the
area where the tumor has occurred, even after the tumor appears clear during the MRI (Magnetic
Resonance Testing). This area is where the technique like digital image processing is used along with
machine learning aids are used between the computer and the radiologist. This technique involves
diagnosis, prior and post-surgical procedures that synergies between the human intelligence and
machine intelligence. The diagnostic accuracy can be achieved by the hybrid methodology of
analyzing using both AI and human intelligence and provides great assistance to radiologists for
further understanding. In this article the author talks about the retrospect and the current occurrences
in human brain that is tumor infected MR images which includes astrocytoma. The methods that are
used to clinically examine the tumors and grading them can be integrated into protocols of standard
imaging techniques and elucidated. The state of art assessments and the future developments are
disserted along with the trends.
Figure 10: Three different grades of Gliomas axial brain images
11

Bakas, S., Akbari, H., Sotiras, A., Bilello, M., Rozycki, M., Kirby, J. S., ... & Davatzikos, C.
(2017). Advancing the cancer genome atlas glioma MRI collections with expert segmentation
labels and radiomic features. Scientific data, 4, 170117.
The authors, describe that Gliomas are a category of the central nervous system tumors and it
has various sub-regions. The radiographic imaging is the gold standard labeling which is used for the
purpose of computational studies as well as clinical studies. This process as the authors describe it
also includes radio genomic and radiomic analysis. Doe all the pre-operative multi-model magnetic
resonance imaging segmentation labels are released labels at the end (MRI) (n=243) is the multi-
institutional collections of glioma which is collected in the Cancer Genome Atlas (TCGA). There is a
publicly available (TCIA) The Cancer Imaging Technique. The authors also explain that the scans that
are pre-operative could be identified in both TCGA-GBM, n=135 (gliblastoma) and TCGA-LGG,
n=108 (low grade glioma) that are collected using an assessment that is radiological. The sub-regions
of glioma was put into picture and was manually looked upon by an expert certified neuroradiologist
in the automatic state-of-art. Functions related to radiomic features were manually extracted using
methods of revised-labels. There is a performance evaluation of the segmentation methods by the use
of computer-aided tools which effectively compare the state-of-the-art methodologies. The new
prognostic assessments including predictive as well as diagnostic assessments are done by the direct
utilization of the TCGA/TCIA glioma collections.
Figure 11: Automatic Brain Tumour Segmentation using CNNs (Cascaded Anisotropic)
12

Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., ... & Sánchez,
C. I. (2017). A survey on deep learning in medical image analysis. Medical image
analysis, 42, 60-88.
The authors, refer to algorithms of deep learning has become an imminent method to analyze
the medical images mainly in convolution networks. The paper shows the concepts that are major
regarding the deep learning and has a summarization of about 300 contributions in the same field in
the medical images analysis. The authors have surveyed the usages of various learnings of tasks like
classification of images, detection of objects, segmentations and many more including registrations.
The authors have also mentioned concise views regarding the studies of applications area like, digital
pathology, cardiac, abdominal, musculoskeletal, retina and so on. The researches have built some kind
of automated analysis tool to check the advanced imaging of the brain. The artificial intelligence
analogy of expert systems that worked on if-else-statements was developed in to see a clear case study
that includes over 300 papers showing a variation of applications related to deep learning and foe
medical image processing. The authors end up the paper with the most hot topic state-of-art that is a
critical study on the challenges for the future studies. The authors in the paper aimed to show the
challenges that concern the medical imaging and successful implementation of deep learning tools.
They also have put brief highlights to the applications for a successful to circumvent the challenges
and solve them. The report ends with the critical analysis and discussion regarding the researches that
will be performed in the future.
Figure 12: Proposed algorithm of input brain MRI image
13
Input Brain MRI Image
Pre-processing of image
2D Adaptive Filter
Segmentation
Morphology
Fusion of image

Erickson, B. J., Korfiatis, P., Akkus, Z., & Kline, T. L. (2017). Machine learning for medical
imaging. Radiographics, 37(2), 505-515.
The authors, in this article talk about the machine learning and also talk about the various
methods for pattern recognition that are applied in the medical images processing. The machine
learning is a powerful tool that could be easily misused. Algorithm of machine learning is merely the
tool of machine learning system that computes the features of the images and predicts the diagnosis of
the region. The machine learning algorithm after identifies the combinations of the patterns and
features and classifies the images using some computational image metric for the regions of brain.
The author mentions that machine learning algorithm uses a combination of tools and procedures that
have its own advantages and disadvantage. There are versions like open source that makes this
machine learning algorithms easy to work with or try several tasks on images analysis. There are
matrices of several kinds for performance measurements of the existing algorithms. There authors
also mentions that there are certain matrices that can be the pitfall, to mislead the user. Machine
learning analysis of imaging is the process that uses a series of metrics and formulas to see the
characteristically featuring processes and recognize the pattern before an imaging technique could be
used. This process is an emerging and is identified as one of the learning processes. Medical imaging
used machine learning and it has a great potential of influencing the future with greater and better
techniques. The author in this paper also describes that individuals practicing medical imaging should
be aware of hoe the machine learning techniques work.
14
Start
Input Brain Image
Extract (row x
col)
Apply Orthogonal Gamma
distribution with machine
learning
Trained coefficients to check the
over segmented image
Estimation of variance
Output-Region Identification
End

Figure 13: Architectural flow of orthogonal gamma distribution in machine learning model
Chartrand, G., Cheng, P. M., Vorontsov, E., Drozdzal, M., Turcotte, S., Pal, C. J., ... & Tang, A.
(2017). Deep learning: a primer for radiologists. Radiographics, 37(7), 2113-2131.
The researchers/authors, in this article talk about the deep learning that is a very useful
domain when it comes to image processing and helps the radiologists diagnoses a tumor easily. Deep
learning is a domain of Machine learning that basically works on the success gaining’s and attracting
interests to the domains like radiography. The authors mention that deep learning procedures
provides a mapping technique that uses raw inputs and processes it accordingly resulting in the
desired outputs. Deep-learning methodology unlike the traditional machine learning technique does
not require a hand-engineered extraction from inputs but rather it takes the features directly from the
data. There is an increase in technologies and the advent of enormous datasets and increase of
computational power results in models that have exceptional performances. These models are inspired
by the biologic neural systems and consist of the multilayer artificial, neural networks. The author
describes how connections between neurons are adjusted based on the examples provided by the
example pairs of inputs and the targeted outcomes that are done by the method of back propagation of
the corrective signal errors from these networks. Convolutional Neural Networks (CNNs) are an
effective for vision tasks related to computer. There have recently being proposals and studies in
radiology in several clinical uses for classification and detection of tasks. In this article the authors
highlights the key concepts of technical requirements, and emerging applications of the clinical
radiologists which imitates the directions in future and limitations of the field. The author suggests
that radiologists should be aware and familiar of the procedures and principles of deep learning in the
medical imaging.
Figure 14: Classic machine learning relies on deep learning features
15
Rule-based
systems
Classic
machine
learning
Representati
on learning
Deep
Learning
I
N
P
U
T
Explicit Computer Program
Human-
engineered
features
Features
Mapping from
features
Mapping from
features
Simple
Feature
Complex
Features Mapping from
features
O
U
T
P
U
T

Choy, G., Khalilzadeh, O., Michalski, M., Do, S., Samir, A. E., Pianykh, O. S., ... & Dreyer, K. J.
(2018). Current applications and future impact of machine learning in radiology.
Radiology, 288(2), 318-328.
The researchers, in this article talk about the future visions and advancements made recently
of machine learning methodologies for a promising application when it comes to the medical imaging.
There is a huge potential for machine learning to improve steps that are differentiated in the radiology
which includes the following; support of clinical decisions, triage and scheduling tasks, findings
interpretations and discussions regarding the same, estimation of doses and processing, quality control
and reporting of the radiology. In the article the authors describes the reviews and examples of
applications that are currently used and in machine learning and AI. Artificial Intelligence plays a
major role while diagnosing radiology. The authors also discuss the future impact and extension of
natural techniques in radiology practices. The advances in the machine learning are a growing process
and it promises medical imaging in numerous applications and also industries as written by the author.
First thing the authors, in the article define machine learning on different levels which proves as a
very feasible method of images interpretations. Secondly they give various examples of the
applications and diagnostic technology in machine learning. And then the authors discuss about the
key barriers and challenges in machine learning applications in radiology diagnostics.
Wagner, J. B. (2019). Artificial Intelligence in Medical Imaging. Radiologic technology, 90(5),
489-501.
The authors, in this article talk about tools that are powerful and help professionals to take decisions.
The global market has seen a rise in the intelligent robotics, AI and interfaces that are smart. The
advancements in recent years in the area of the field of imaging techniques that are medical helps
trained professionals with the tasks they earlier performed manually. Brain diseases diagnosis are
normally done from brain scan images by doctors or designated individuals but by the help of tools
like AI, machine learning and computer vision show a new vision in the science and technology and
provides opportunities for intellect decision support tools. The authors n the article describe about the
MRI images and diagnosis of brain disease using MRI imaging. The authors talk about the existing
imaging techniques of brain that are detailed information regarding the resulting images that are
further analyzed by radiologist. There are various challenges when it comes to comparing the results
of categorizing natural scenes and medical imaging analysis domain. There is a huge knowledge gap
as the authors say it when it comes to the survey conducted in medical image processing methods.
There is also a difference in health tissues when it comes to pathology and also identification of brain
structures. The author says that this study report is laid on the brain tumor analysis cases and different
approaches that need to be done to define, synthesize and information that are meaningful for multiple
MRI sets of diagnosis.
16

Shaver, M. M., Kohanteb, P. A., Chiou, C., Bardis, M. D., Chantaduly, C., Bota, D., ... & Chang,
P. D. (2019). Optimizing Neuro-Oncology Imaging: A Review of Deep Learning
Approaches for Glioma Imaging. Cancers, 11(6), 829.
The researchers, talk about the radiographic assessment done with magnetic resonance
imaging (MRI) in this article. They talk about how MRI is being used in order to characterize
gliomas. The primary malignant brain tumor is characterized 80% by MRI scans. Glioma in biology is
marked by following characteristics as discussed in the paper and these are as follows: heterogeneous
angiogenesis, proliferations of cells, invasions of cells and apoptosis. There is a varying degree of
imaging assessment challenges that translates the enhancement, edema, necrosis, and reliable services.
The authors also talk about deep learning method that happens to be a subset of machine learning; this
is an effective method of solving image-related issues which includes those in medical imaging. The
authors in this article review talk about the applications that are used to detect the glioma detection
and the prediction outcomes which puts its focus in the following: Tumor segmentation both pre- and
post, characterization of tissue in genetic order, prognostication. The authors demonstrate that deep
learning methods of segmenting and predicting survival in gliomas are opportunities that enhance
both researches as well as clinical activities.
Figure 15: Image of brain tumour
Afshar, P., Plataniotis, K. N., & Mohammadi, A. (2019, May). Capsule Networks for Brain
Tumor Classification Based on Mri Images and Coarse Tumor Boundaries. In ICASSP
2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP) (pp. 1368-1372). IEEE.
In this article the author discusses on the nature of brain tumours and their deadliest nature. In order to
determine the type of brain tumour numerous techniques are being used. In the recent times designing
Convolutional Neural Networks for classifying the type of brain tumour are being used. CNN require
huge volumes of data and they are not able to handle the various input transformations. The capsule
networks are the modern machine learning architectures that have been developed to overcome the
17

challenges being faced in case of CNN. The paper has four main objectives. They are as follows: (i)
adopting and incorporating CapsNet for classifying brain tumour. (ii) Investigating the problem of
over-fitting on the basis of imaging. (iii) Finding out whether the CapsNet have the potential to
provide better fit in case of the images of the brain or do they just focus on the segmented tumour. (iv)
Developing a visualization paradigm that determines the output of CapsNet.
Figure 16: Proposed CapsNet architecture for classification of brain tumour by Adam optimizer
Anaraki, A. K., Ayati, M., & Kazemi, F. (2019). Magnetic resonance imaging-based brain
tumor grades classification and grading via convolutional neural networks and genetic
algorithms. Biocybernetics and Biomedical Engineering, 39(1), 63-74.
In the recent years, deep convolution neural networks or CNNs have provided good performance in
problems related to computer vision for example segmentation, visual object recognition and
segmentation. These specific methods make utilization of the analysis of medical image for
anatomical segmentation, classification and lesion segmentation. The paper provides a literature
review of the CNN techniques that can be applied to magnetic resonance imaging, architecture
focusing, preparing data, analysis and certain post-processing strategies. Convolutional neural
networks help in imaging and segmentation. CNNs help in learning the relationships that exist among
pixels of the images by extraction of the features making use of the convolution and related pooling
operations. Convolution neural network are popular for their inbuilt potential in extracting the
discriminative features by making use of learned weights in each of the layer. This particular process
18

is reinforced by the help of loss functions. These loss functions have been developed to provide
encouragement in intra-class similarity as well as inter-class separability.
Wang, Z., Chen, J., & Hoi, S. C. (2019). Deep learning for image super-resolution: A
survey. arXiv preprint arXiv:1902.06068.
Convolution neural networks have got state-of-art performance for bringing automation in the medical
image segmentation. Still CNN have not been able to demonstrate accurate and perfect results for
usage in case of clinical purposes. The article highlights the fact that there are certain limitations
owing to the lack in adapting to image-specific features as well as lack in generalizability. In order
address to this specific problem the authors provide deep learning-based segmentation framework that
is interactive in nature. The article provides image-specific fine tuning that makes convolution neural
networks transform into bounding box and segmentation pipeline. One of the main challenges that is
faced when using CNN is that this technique does not have the capability of generalizing the unseen
object classes that are present in the sets available for training.
Simpson, A. L., Antonelli, M., Bakas, S., Bilello, M., Farahani, K., van Ginneken, B., ... &
Ronneberger, O. (2019). A large annotated medical image dataset for the development
and evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063.
In this article one type of brain tumour are been spoken about that is gliomas. It is one of the most
common brain malignancies and has different types of degree of aggressiveness. These have an
intrinsic level of heterogeneity that is revealed from their imaging phenotype. The brain tumour
challenges mainly focus on the way of evaluation of associated state-of-art methods used in
segmenting the same by making use of multi-parametric magnetic resonance imaging scans. The brain
tumours have a highly heterogeneous appearance as well as shape and their sub-regions have different
intensity profiles. This is challenging in case of segmenting the tumours by the help of multimodal
MRI scans in case of medical image analysis.
Suh, C. H., Kim, H. S., Jung, S. C., Choi, C. G., & Kim, S. J. (2019). Imaging prediction of
isocitrate dehydrogenase (IDH) mutation in patients with glioma: a systemic review and
meta-analysis. European radiology, 29(2), 745-758.
The article is about low-grade glioma that is a very rare case of cerebral tumour in adults. The
imaging department of medical science is well aware of the role of segmentation algorithms and thus
conferences are being organised since the year 2007. The challenges that are there in segmentation of
brain tumour are the topic of discussion in these conferences. The challenges have forced different
teams to work on automatic segmentation algorithms and here comes the role of artificial intelligence.
There have been many solutions proposed for the process of segmenting brain tumours that includes
the support vector machines and methods such as the level set method. Manual segmentation is
19

subjective and qualitative in nature while making use of these techniques makes the process
quantitative in nature.
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019). A
survey of methods for explaining black box models. ACM computing surveys
(CSUR), 51(5), 93.
The article discusses on the various analysis technique of images improving the labelling accuracy of
medical image classification. The medical images consist of region of interest that is ROI and is
obtained from the area that is affected. This provides vital information that support clinical decision-
making for the diagnostics along with the planning of treatment. The challenge in this case is that the
image data in medical science contains noises, certain missing values and inhomogeneous region of
interest that provide inaccurate diagnosis. Thus it requires image analysis techniques and there have
been limited works in this sphere. The paper aims at gathering information as well as presenting
general overview on the process of analysing images and related techniques. Image processing in this
sphere is the operations that are conducted to transform, improve and manipulate the images of
different organs of the human body especially brain tumours.
Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J., & Dalca, A. V. (2019). VoxelMorph: a
learning framework for deformable medical image registration. IEEE transactions on
medical imaging.
In this article the authors introduce a powerful pipeline for the process of segmentation of medical
images along with the combination of Fully Convolutional Networks (FCNs) and Fully Convolutional
Residual Networks (FC-ResNets). The authors examine a design that has certain advantages in
providing an understanding of FCNs and FC-ResNets. Image segmentation is considered to be an
active area of research in the field of medical image analysis. The article highlights the fact that there
have been significant improvements in the performance after the development of Convolutional
Neural Networks. The common view about the CNN models is supported by representation of
learning perspective. The deep learning methods have shown their ability in image segmentation but
their potential relies on the quality involved in the pre-processing and the post-processing steps.
Inum, R., Rana, M., Shushama, K. N., & Quader, M. (2018). EBG based microstrip patch
antenna for brain tumor detection via scattering parameters in microwave imaging
system. International journal of biomedical imaging, 2018.
The article discusses on the microwave brain imaging system that detects as well as visualizes
tumours that may be present inside the brain. In this technique an efficient as well as compact patch of
micro strip antenna is made use of in the technique of imaging. This transmits signals as well as
20

receives back the scattering signals from the stratified head model of human beings. In order to get an
enhanced performance electromagnetic band gap structure is made use of on the ground plane of
antenna. Rectangular and circular electromagnetic band gap structure has been proposed to check on
the performance of the antenna. Microwave imaging in the field of medical science is active and non-
invasive method of imaging.
Han, C., Rundo, L., Araki, R., Nagano, Y., Furukawa, Y., Mauri, G., ... & Hayashi, H. (2019).
Combining noise-to-image and image-to-image GANs: Brain MR image augmentation
for tumor detection. arXiv preprint arXiv:1905.13456.
This article discusses on data augmentation, image generation and brain tumour detection. The
authors consider CNN to be the main element in the field of medical image analysis, the state-of-art
being updated in many tasks in those cases where volumes of data are available. Practically preparing
such amount of medical data demands much therefore for better level of diagnosis, researchers take
the way of classis Data Augmentation techniques that include geometric transformations of the
original images. The images that are augmented have similar distributions to that of the original ones
and result in very limited improvement in performance. The major drawback in case of computer-
assisted diagnosis is that it falls under small fragmented medical imaging datasets obtained from the
scanners. This in turn has forced the researchers to improve the classification by augmenting the
images by substituting the same with noise-to-image GANs and image-to-image GANs.
Subramanian, S., Gholami, A., & Biros, G. (2019). Simulation of glioblastoma growth using a
3D multispecies tumor model with mass effect. Journal of mathematical biology, 1-27.
In this article the authors provide multispecies reaction-advection-diffusion partial differential
equation (PDE) that is coupled with linear elasticity in order to model the growth of tumour. The
model has been developed to capture various features of glioblastoma multiforme that is noticed in
case of magnetic resonance imaging scans also termed as the MRI scans. These consider the
enhancing as well as the necrotic structures of tumour, brain edema along with the mass effect.
Glioblastomas are categorized as aggressive tumours that account for maximum of the malignant
primary brain tumours in the adults. The main aim of the article is to combine this particular model
with the estimated parameters methodologies also with the MRIs of patient to provide assistance in
diagnosis as well as prognosis. The particular model finds its usage in MR image segmentation of the
glioblastomas.
S Tandel, G., Biswas, M., G Kakde, O., Tiwari, A., S Suri, H., Turk, M., ... & K Madhusudhan,
B. (2019). A review on a deep learning perspective in brain cancer
classification. Cancers, 11(1), 111.
21

This article discusses on brain tumours and the mortality rate owing to it. As per the records of World
Health Organization of the year 2018, the rate of mortality has been at its peak in the Asian continent.
It is important that brain tumours be detected in the initial stages so that these can be treated at its
early stage. The main part in detecting brain tumours is proper imaging. Diagnosis of cancer is
invasive, consumes a lot of time and it is expensive at the same time. Thus the researchers are
developing tools for characterizing brain cancer and estimating their grade that will be cost effective
as well as non-invasive. The authors are of the opinion that scanning of brain by making use of
magnetic resonance imaging (MRI) and other such imaging modalities which are better methods to
detect brain tumours. The paper focuses on the pathophysiology of brain tumours, the imaging
modalities of brain tumours along with the automatic computer assisted techniques for characterizing
brain tumour in deep learning paradigm.
Kolařík, M., Burget, R., Uher, V., Říha, K., & Dutta, M. K. (2019). Optimized high resolution
3D dense-U-Net network for brain and spine segmentation. Applied Sciences, 9(3), 404.
The article discusses on 3D image segmentation technique. The authors define it as the process
involved in partitioning digital 3D volumes into various segments. This paper provides a method for
the process of high resolution of 3D volumetric segmentation of image data by making use of modern
supervised approaches of deep learning. 3D Dense U-Net neural network architectures have been
introduced that implement densely connected layers. This has also been optimized for graphic related
processes with unit accelerated images having high resolution. The images can be processed on the
hardware that is available at present times. The methods have undergone evaluation on MRI brain 3D
volumetric dataset as well as CT thoracic scan dataset for the process of spine segmentation.
Contrasting to the available previous methods, the authors approach in this article is having the
potential of segmentation of the image data serving as the input in original resolution, without any
such pre-processes done to the input images. Image segmentation has a lot of importance in case of
automated image processing that relies on the principle of partitioning the images serving as input
into those areas that share similar features thereby extracting the informations that the input image
consists of. The segmentation is a method that labels each pixel and is made use of as a basic method
of processing images.
Truong, D., Fiorelli, R., Barrientos, E. S., Melendez, E. L., Sanai, N., Mehta, S., & Nikkhah, M.
(2019). A three-dimensional (3D) organotypic microfluidic model for glioma stem cells–
vascular interactions. Biomaterials, 198, 63-77.
In this article the author talks about glioblastoma and is categorized under the deadliest forms of
cancer. It is the deadliest forms of brain cancer in case of adults. Inspite of the aggressive treatment
that include surgery, chemotherapy and radiation, prognosis for the patients is said to be dismal with
chances to survive for 5 years and the survival rate is 4.7%. These types of tumours are recurrent and
22

the time they take to recur is few months after these are treated. Imaging of these tumours is an
essential step to detect their exact location and also helps in classifying their nature. 3D imaging is of
great help in locating the tumour and this in turn helps in its treatment. Artificial intelligence can be
used in this case as in the manual process of extracting the images errors can be committed.
Teleanu, D. M., Chircov, C., Grumezescu, A. M., Volceanov, A., & Teleanu, R. I. (2019).
Contrast Agents Delivery: An Up-to-Date Review of Nanodiagnostics in
Neuroimaging. Nanomaterials, 9(4), 542.
In this article neuroimaging is discussed upon as it is an important field in case of neuroscience and it
has direct implications for diagnosis at an early stage with progression monitoring of the diseases that
are associated with the brain. The neuroimaging techniques have been divided into functional,
molecular and structural techniques and each of these techniques has their own advantages and
disadvantages. The paper highlights conventional modalities that are made used in case of imaging
and the various applications of nanotechnology have also been considered for the development of
certain novel strategies to perform neuroimaging. The paper focuses on the various roles of
nanocarriers in order to enhance or overcome the prevalent limitations that are linked to the generally
used modalities of neuroimaging. Proper and appropriate imaging technologies are required to start
with the treatment of brain tumours.
Hwang, H., Rehman, H. Z. U., & Lee, S. (2019). 3D U-Net for skull stripping in brain
MRI. Applied Sciences, 9(3), 569.
The article highlights the topic of skull stripping in case of brain magnetic resonance imaging which
is one of the basic as well as essential steps that helps in analysing the images of the brain. Manual
segmentation has high rate of accuracy in this case but it is time consuming. Many automatic
segmentation algorithms have been proposed that related to the MRI of brain. Still there are no such
methods that can successfully extract the images of the brain satisfying the diverse amount of datasets
available in an appropriate and perfect way. In order to overcome these problems the authors
proposed the usage of 3D-UNet for skull stripping in case of brain MRI. The 3D-UNet is a recent
development and has already captured the market owing to the performance it has shown. It is an
extension of the previous 2D-UNet version that relies on the deep learning network especially the
convolutional neural network.
Sakinis, T., Milletari, F., Roth, H., Korfiatis, P., Kostandy, P., Philbrick, K., ... &
Erickson, B. J. (2019). Interactive segmentation of medical images through fully
convolutional neural networks. arXiv preprint arXiv:1903.08205.
This article highlights the importance of image segmentation as it has a vital role in the
sphere of medicine for diagnostic as well as interventional tasks. There exist three different
23

approaches of the process of segmentation that are manual, fully-automatic and semi-
automatic. Manually done segmentation provides full control over the quality of the results
obtained but its major drawback is that it takes long time and gets affected if the operator is
biased. The fully automated techniques do not require any human intervention but these
provide sub-optimal results and the users are not given any such opportunity to correct these
errors. The semi-automated approaches give the users the control to handle the results as it
provides means to interact. In the semi-automated approaches the challenge is that they
cannot provide better trade off in between precision and required interaction. This paper
provides semi-automated segmentation approach that relies on deep learning. Image
segmentation is becoming important task in the field of radiological research and clinical
purposes.
Kaushik, A., Dwarakanath, T. A., Bhutani, G., Venkata, P. P. K., & Moiyadi, A. (2019).
Image-Based Data Preparation for Robot-Based Neurosurgery. In Machines,
Mechanism and Robotics (pp. 27-38). Springer, Singapore.
This article focuses on preparing data based on images for neurosurgery that relies on
robotics. This shows the combination of artificial intelligence to medical imaging. The
DICOM tags of data are identified and made use of in building optimum robotic surgical
framework that has been developed to bring in accuracy in neuro-registration and neuro
navigation. Algorithm is developed using GUI to make use in neuro registration and neuro
navigation. Robotic neurosurgery involves technologies guiding the neurosurgeons to locate
on the problematic area that fall under the confinement of the brain. The medical images
generated by the help of the imaging modalities are in DICOM format. DICOM is just a set
of standards that have been formulated in order to maintain a standard among the various
stack of the images, types of data and the existing communication in between the various
modalities.
Sriramakrishnan, P., Kalaiselvi, T., & Rajeswaran, R. Modified Local Ternary Pattern
Technique for Brain Tumor Segmentation and Volume Estimation from MRI
Multisequence Scans with GPU CUDA Machine.
This article discusses on a particular technique involved in the segmentation of brain along
with the estimating of volume from the MRI Multisequence Scans with the help of GPU
CUDA Machine. In order to analyse brain tumours magnetic resonance images are required
that follow well-defined pipelined processes including extraction of features, classification,
24

segmentation, estimating volume and visualization. The work builds up a fully automatic as
well as rapid method for detecting brain tumour and segmenting the same using the datasets
of multimodal BraTS. The method that has been proposed in this article consists of three
main phases that include timorous slice detection, region of extraction of tumour and
segmentation if the substructures of the tumour. To detect tumour at the early phase is most
important and then comes the part of diagnosis. These vital steps depend on imaging and 3D
visualization can help in this case. 3D visualization helps locate the location of the tumour as
well as it can classify the nature of the tumours.
Figure 17: MRI multisequence tumour scans, regions of tumour and substructures of
tumour
(a) T1 Scan (b) T1c Scan (c) T2 Scan (d) FLAIR Scan (e) Tumour region (f) Tumour
substructures
25

Bibliography
Afshar, P., Plataniotis, K. N., & Mohammadi, A. (2019, May). Capsule Networks for Brain Tumor
Classification Based on Mri Images and Coarse Tumor Boundaries. In ICASSP 2019-2019
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp.
1368-1372). IEEE.
Anaraki, A. K., Ayati, M., & Kazemi, F. (2019). Magnetic resonance imaging-based brain tumor
grades classification and grading via convolutional neural networks and genetic
algorithms. Biocybernetics and Biomedical Engineering, 39(1), 63-74.
Anaraki, A. K., Ayati, M., & Kazemi, F. (2019). Magnetic resonance imaging-based brain tumor
grades classification and grading via convolutional neural networks and genetic
algorithms. Biocybernetics and Biomedical Engineering, 39(1), 63-74.
Bakas, S., Akbari, H., Sotiras, A., Bilello, M., Rozycki, M., Kirby, J. S., ... & Davatzikos, C. (2017).
Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels
and radiomic features. Scientific data, 4, 170117.
Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J., & Dalca, A. V. (2019). VoxelMorph: a
learning framework for deformable medical image registration. IEEE transactions on medical
imaging.
Chartrand, G., Cheng, P. M., Vorontsov, E., Drozdzal, M., Turcotte, S., Pal, C. J., ... & Tang, A.
(2017). Deep learning: a primer for radiologists. Radiographics, 37(7), 2113-2131.
Choy, G., Khalilzadeh, O., Michalski, M., Do, S., Samir, A. E., Pianykh, O. S., ... & Dreyer, K. J.
(2018). Current applications and future impact of machine learning in radiology. Radiology,
288(2), 318-328.
Demiray, B., Rackerseder, J., Bozhinoski, S., & Navab, N. (2019). Weakly-Supervised White and
Grey Matter Segmentation in 3D Brain Ultrasound. arXiv preprint arXiv:1904.05191.
Dos Santos, D. P., Giese, D., Brodehl, S., Chon, S. H., Staab, W., Kleinert, R., ... & Baeßler, B.
(2019). Medical students' attitude towards artificial intelligence: a multicentre
survey. European radiology, 29(4), 1640-1646.
Erickson, B. J., Korfiatis, P., Akkus, Z., & Kline, T. L. (2017). Machine learning for medical imaging.
Radiographics, 37(2), 505-515.
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019). A survey of
methods for explaining black box models. ACM computing surveys (CSUR), 51(5), 93.
Han, C., Rundo, L., Araki, R., Nagano, Y., Furukawa, Y., Mauri, G., ... & Hayashi, H. (2019).
Combining noise-to-image and image-to-image GANs: Brain MR image augmentation for
tumor detection. arXiv preprint arXiv:1905.13456
Huang, R. Y., Bi, W. L., Griffith, B., Kaufmann, T. J., la Fougère, C., Schmidt, N. O., ... & Nassiri, F.
(2019). Imaging and diagnostic advances for intracranial meningiomas. Neuro-
oncology, 21(Supplement_1), i44-i61.
26

Huo, Y., Xu, Z., Xiong, Y., Aboud, K., Parvathaneni, P., Bao, S., ... & Landman, B. A. (2019). 3d
whole brain segmentation using spatially localized atlas network tiles. NeuroImage, 194, 105-
119.
Hwang, H., Rehman, H. Z. U., & Lee, S. (2019). 3D U-Net for skull stripping in brain MRI. Applied
Sciences, 9(3), 569.
Inum, R., Rana, M., Shushama, K. N., & Quader, M. (2018). EBG based microstrip patch antenna for
brain tumor detection via scattering parameters in microwave imaging system. International
journal of biomedical imaging, 2018.
Kao, P. Y., Chen, J. W., & Manjunath, B. S. (2019). Improving 3D U-Net for Brain Tumor
Segmentation by Utilizing Lesion Prior. arXiv preprint arXiv:1907.00281.
Kaushik, A., Dwarakanath, T. A., Bhutani, G., Venkata, P. P. K., & Moiyadi, A. (2019). Image-Based
Data Preparation for Robot-Based Neurosurgery. In Machines, Mechanism and Robotics (pp.
27-38). Springer, Singapore.
Kolařík, M., Burget, R., Uher, V., Říha, K., & Dutta, M. K. (2019). Optimized high resolution 3D
dense-U-Net network for brain and spine segmentation. Applied Sciences, 9(3), 404
Lee, C., & Wong, G. K. C. (2019). Virtual reality and augmented reality in the management of
intracranial tumors: A review. Journal of Clinical Neuroscience.
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., ... & Sánchez, C. I.
(2017). A survey on deep learning in medical image analysis. Medical image analysis, 42, 60-
88.
Mazurowski, M. A., Buda, M., Saha, A., & Bashir, M. R. (2019). Deep learning in radiology: An
overview of the concepts and a survey of the state of the art with focus on MRI. Journal of
Magnetic Resonance Imaging, 49(4), 939-954.
Mazurowski, M. A., Buda, M., Saha, A., & Bashir, M. R. (2019). Deep learning in radiology: An
overview of the concepts and a survey of the state of the art with focus on MRI. Journal of
Magnetic Resonance Imaging, 49(4), 939-954.
Prevedello, L. M., Halabi, S. S., Shih, G., Wu, C. C., Kohli, M. D., Chokshi, F. H., ... & Flanders, A.
E. (2019). Challenges related to artificial intelligence research in medical imaging and the
importance of image analysis competitions. Radiology: Artificial Intelligence, 1(1), e180031.
S Tandel, G., Biswas, M., G Kakde, O., Tiwari, A., S Suri, H., Turk, M., ... & K Madhusudhan, B.
(2019). A review on a deep learning perspective in brain cancer classification. Cancers, 11(1),
111.
S Tandel, G., Biswas, M., G Kakde, O., Tiwari, A., S Suri, H., Turk, M., ... & K Madhusudhan, B.
(2019). A review on a deep learning perspective in brain cancer classification. Cancers, 11(1),
111.
Sahiner, B., Pezeshk, A., Hadjiiski, L. M., Wang, X., Drukker, K., Cha, K. H., ... & Giger, M. L.
(2019). Deep learning in medical imaging and radiation therapy. Medical physics, 46(1), e1-
e36.
Sakinis, T., Milletari, F., Roth, H., Korfiatis, P., Kostandy, P., Philbrick, K., ... & Erickson, B. J.
(2019). Interactive segmentation of medical images through fully convolutional neural
networks. arXiv preprint arXiv:1903.08205
27

Shaver, M. M., Kohanteb, P. A., Chiou, C., Bardis, M. D., Chantaduly, C., Bota, D., ... & Chang, P.
D. (2019). Optimizing Neuro-Oncology Imaging: A Review of Deep Learning Approaches
for Glioma Imaging. Cancers, 11(6), 829.
Simpson, A. L., Antonelli, M., Bakas, S., Bilello, M., Farahani, K., van Ginneken, B., ... &
Ronneberger, O. (2019). A large annotated medical image dataset for the development and
evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063.
Sriramakrishnan, P., Kalaiselvi, T., & Rajeswaran, R. Modified Local Ternary Pattern Technique for
Brain Tumor Segmentation and Volume Estimation from MRI Multisequence Scans with
GPU CUDA Machine.
Subramanian, S., Gholami, A., & Biros, G. (2019). Simulation of glioblastoma growth using a 3D
multispecies tumor model with mass effect. Journal of mathematical biology, 1-27.
Suh, C. H., Kim, H. S., Jung, S. C., Choi, C. G., & Kim, S. J. (2019). Imaging prediction of isocitrate
dehydrogenase (IDH) mutation in patients with glioma: a systemic review and meta-
analysis. European radiology, 29(2), 745-758.
Teleanu, D. M., Chircov, C., Grumezescu, A. M., Volceanov, A., & Teleanu, R. I. (2019). Contrast
Agents Delivery: An Up-to-Date Review of Nanodiagnostics in
Neuroimaging. Nanomaterials, 9(4), 542.
Truong, D., Fiorelli, R., Barrientos, E. S., Melendez, E. L., Sanai, N., Mehta, S., & Nikkhah, M.
(2019). A three-dimensional (3D) organotypic microfluidic model for glioma stem cells–
vascular interactions. Biomaterials, 198, 63-77
Wagner, J. B. (2019). Artificial Intelligence in Medical Imaging. Radiologic technology, 90(5), 489-
501.
Wang, Z., Chen, J., & Hoi, S. C. (2019). Deep learning for image super-resolution: A survey. arXiv
preprint arXiv:1902.06068.
28