Brain Tumor Type Classification via Capsule Networks

By Parnian Afshar, Arash Mohammadi, K. Plataniotis. International Conference on Information Photonics, 2018

510 citations recorded by the source corpus.

Brain tumor is considered as one of the deadliest and most common form of cancer both in children and in adults. Consequently, determining the correct type of brain tumor in early stages is of significant importance to devise a precise treatment plan and predict patient's response to the adopted treatment. In this regard, there has been a recent surge of interest in designing Convolutional Neural Networks (CNNs) for the problem of brain tumor type classification. However, CNNs typically require large amount of training data and can not properly handle input transformations. Capsule networks (referred to as CapsNets) are brand new machine learning architectures proposed very recently to overcome these shortcomings of CNNs, and posed to revolutionize deep learning solutions. Of particular interest to this work is that Capsule networks are robust to rotation and affine transformation, and require far less training data, which is the case for processing medical image datasets including brain Magnetic Resonance Imaging (MRI) images. In this paper, we focus to achieve the following four objectives: (i) Adopt and incorporate CapsNets for the problem of brain tumor classification to design an improved architecture which maximizes the accuracy of the classification problem at hand; (ii) Investigate the over-fitting problem of CapsNets based on a real set of MRI images; (iii) Explore whether or not CapsNets are capable of providing better fit for the whole brain images or just the segmented tumor, and; (iv) Develop a visualization paradigm for the output of the CapsNet to better explain the learned features. Our results show that the proposed approach can successfully overcome CNNs for the brain tumor classification problem.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Neurology

View Paper: https://www.semanticscholar.org/paper/b1328df3c0d1262d500ed734f8bf977094c3b087

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Computer Vision and Pattern Recognition

In Neurology

Citations in the corpus

Secure and Robust Machine Learning for Healthcare: A Survey (2020, background): “, brain tumor [35] and lung nodules [36].”
Deep CNN for Brain Tumor Classification (2021, methodology): “From the confusion matrix in Table 13, we noticed that most of the [33] No 989 (axial only) 90.26 Tahir et al. [29] No 3064 86 Afshar et al. [34] Both 3064 86.56 using segmentation 72.13 using raw images Afshar et al. [70] Bounding box 3064 90.89 Cheng et al. [27] Yes 3064 91.28 Ismael et al. [28]…”
Deep convolutional neural network based medical image classification for disease diagnosis (2019, methodology): “[18] also evaluated the different options of CapsNet.”
Building Deep, Equivariant Capsule Networks (2019, unknown): “(2019); or application Afshar et al. (2018).”
COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images (2020, methodology): “Through several studies[13]-[18], we have shown the superiority of the CapsNets for di ﬀ erent medical problems such as brain tumor [13]-[17] and lung tumor classiﬁcation [18].”
A Deep Learning-Based Framework for Automatic Brain Tumors Classification Using Transfer Learning (2019, methodology): “[3] proposed a novel model Capsule networks”
Capsule Networks for Brain Tumor Classification Based on MRI Images and Coarse Tumor Boundaries (2018, background): “CapsNet given brain image as input [16].”
Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey (2020, background): “[57] attempted to address the major two problems of CNNs for the BTC problem, i.”
MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques (2023, methodology): “Many studies have been conducted on the detection of brain tumors by various methods and models [5, 15–21].”