Brain Tumor Type Classification via Capsule Networks

@article{Afshar2018BrainTT,
  title={Brain Tumor Type Classification via Capsule Networks},
  author={Parnian Afshar and Arash Mohammadi and Konstantinos N. Plataniotis},
  journal={2018 25th IEEE International Conference on Image Processing (ICIP)},
  year={2018},
  pages={3129-3133}
}
Brain tumor is considered as one of the deadliest and most common form of cancer both in children and in adults. [] Key Result Our results show that the proposed approach can successfully overcome CNNs for the brain tumor classification problem.

Figures and Tables from this paper

Dilated Capsule Network for Brain Tumor Type Classification Via MRI Segmented Tumor Region

TLDR
This work proposed a less trainable CapsNet architecture for brain tumor classification, which takes the segmented tumor regions as inputs within the structure and has the capability of ensuring an increase focus of the CapsNets.

Capsule Networks for Brain Tumor Classification Based on MRI Images and Coarse Tumor Boundaries

TLDR
A modified CapsNet architecture is proposed for brain tumor classification, which takes the tumor coarse boundaries as extra inputs within its pipeline to increase the CapsNet’s focus, and noticeably outperforms its counterparts.

Brain Tumor Diagnosis Using Machine Learning, Convolutional Neural Networks, Capsule Neural Networks and Vision Transformers, Applied to MRI: A Survey

TLDR
This survey provides a comprehensive overview of brain tumor classification and segmentation techniques, with a focus on ML-based, CNN- based, CapsNet-based and ViT-based techniques.

BoostCaps: A Boosted Capsule Network for Brain Tumor Classification

TLDR
BosCaps, to the best of the knowledge, is the first capsule network model that incorporates an internal boosting mechanism, and the results show that the proposed BoostCaps framework outperforms its single capsule network counterpart.

Effect of Data Pre-processing on Brain Tumor Classification Using Capsulenet

TLDR
The proposed method shows that the data pre-processing plays a vital role in the improvement of the capsulenet architecture used for brain tumor classification, showing that the diagnosis of the brain tumor type at the early stage may lead to effective treatment.

Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN Augmentation

TLDR
A progressive growing generative adversarial network (PGGAN) augmentation model is used to produce ‘realistic’ MRIs of brain tumors and help overcome the shortage of images needed for deep learning.

BayesCap: A Bayesian Approach to Brain Tumor Classification Using Capsule Networks

TLDR
A Bayesian CapsNet framework is proposed, referred to as the $\text{BayesCap}$, that can provide not only the mean predictions, but also entropy as a measure of prediction uncertainty, to improve the accuracy and interpretability of the network.

A Transfer Learning–Based Active Learning Framework for Brain Tumor Classification

TLDR
This work proposes a novel transfer learning–based active learning framework to reduce the annotation cost while maintaining stability and robustness of the model performance for brain tumor classification, and employs a 2D slice–based approach to train and fine-tune the model.

Triplet Contrastive Learning for Brain Tumor Classification

TLDR
This paper presents a novel approach of directly learning deep embeddings for brain tumor types, which can be used for downstream tasks such as classification and evaluates the effectiveness of this approach on an extensive brain tumor dataset.

Brain Tumor Classification Using MRI Images and Convolutional Neural Networks

TLDR
A 15 layers CNN model for the classification of three types of brain tumors from a publicly available dataset that contains 3064 T1-weighted brain CE-MRI images collected from 233 patients is proposed and obtained an accuracy, precision, recall, and f1-score of 98.6%, 99%, 98.3%, and 98.4% which is higher than previously reported results.
...

References

SHOWING 1-10 OF 23 REFERENCES

Deep learning for brain tumor classification

TLDR
This research demonstrates that a more general method (i.e. deep learning) can outperform specialized methods that require image dilation and ring-forming subregions on tumors.

Brain tumor segmentation with Deep Neural Networks

Enhanced Performance of Brain Tumor Classification via Tumor Region Augmentation and Partition

TLDR
The augmented tumor region via image dilation is used as the ROI instead of the original tumor region because tumor surrounding tissues can also offer important clues for tumor types.

Brain tumor classification from multi-modality MRI using wavelets and machine learning

TLDR
A leave-one-out cross-validation was performed and achieved 88% Dice overlap for the complete tumor region, 75% for the core tumor region and 95% for enhancing tumors region, which is higher than the Dice overlap reported from MICCAI BraTS challenge.

Classification using deep learning neural networks for brain tumors

Brain Cancer classification Based on Features and Artificial Neural Network

TLDR
The proposed algorithm is trained with 50 images of Sarcoma, Anaplastic Astrocytoma, Meningioma, and Benign and tested with 65 images, the accuracy of this method was up to 98%.

Automated identification of brain tumors from single MR images based on segmentation with refined patient-specific priors

TLDR
A modified automatic lesion identification (ALI) procedure which enables brain tumor identification from single MR images and increases the flexibility and robustness of the ALI tool and will be particularly useful for lesion-behavior mapping studies, or when lesions identification and/or spatial normalization are problematic.

Retrieval of Brain Tumors by Adaptive Spatial Pooling and Fisher Vector Representation

TLDR
This paper proposes a novel feature extraction framework for retrieving brain tumors in T1-weighted contrast-enhanced MRI images and demonstrates the power of the proposed algorithm against some related state-of-the-art methods on the same dataset.

Improve Glioblastoma Multiforme Prognosis Prediction by Using Feature Selection and Multiple Kernel Learning

TLDR
The goal is to establish an integrated model which could predict GBM prognosis with high accuracy by taking advantage of the minimum redundancy feature selection method (mRMR) and Multiple Kernel Machine (MKL) learning method.

Manifold Embedding and Semantic Segmentation for Intraoperative Guidance With Hyperspectral Brain Imaging

TLDR
A novel dimensionality reduction scheme and a new processing pipeline are introduced to obtain a detailed tumor classification map for intra-operative margin definition during brain surgery.