3D Multimodal Brain Tumor Segmentation and Grading Scheme based on Machine, Deep, and Transfer Learning Approaches

Abstract

Glioma is one of the most common tumors of the brain. The detection and grading of glioma at an early stage is very critical for increasing the survival rate of the patients. Computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems are essential and important tools that provide more accurate and systematic results to speed up the decision-making process of clinicians. In this paper, we introduce a method consisting of the variations of the machine, deep, and transfer learning approaches for the effective brain tumor (i.e., glioma) segmentation and grading on the multimodal brain tumor segmentation (BRATS) 2020 dataset. We apply popular and efficient 3D U-Net architecture for the brain tumor segmentation phase. We also utilize 23 different combinations of deep feature sets and machine learning/fine-tuned deep learning CNN models based on Xception, IncResNetv2, and EfficientNet by using 4 different feature sets and 6 learning models for the tumor grading phase. The experimental results demonstrate that the proposed method achieves 99.5% accuracy rate for slice-based tumor grading on BraTS 2020 dataset. Moreover, our method is found to have competitive performance with similar recent works.

Authors and Affiliations

Erdal Tasci, Aybars Ugur, Kevin Camphausen, Ying Zhuge, Rachel Zhao, Andra Krauze

Keywords

Related Articles

A Comparative Analysis of Application of Genetic Algorithm and Particle Swarm Optimization in Solving Traveling Tournament Problem (TTP)

Traveling Tournament Problem (TTP) has been a major area of research due to its huge application in developing smooth and healthy match schedules in a tournament. The primary objective of a similar problem is to minimize...

3D Multimodal Brain Tumor Segmentation and Grading Scheme based on Machine, Deep, and Transfer Learning Approaches

Glioma is one of the most common tumors of the brain. The detection and grading of glioma at an early stage is very critical for increasing the survival rate of the patients. Computer-aided detection (CADe) and computer-...

Review on DNA Cryptography

Cryptography is the science that secures data and communication over the network by applying mathematics and logic to design strong encryption methods. In the modern era of e-business and e-commerce the protection of con...

Facial Skin Disease Detection using Image Processing

Busy lifestyle, modernization, increasing pollution and unhealthy diet have led to problems which people are neglecting. Not drinking enough water, stress and hormonal changes are causing problems to skin. Causes may be...

Natural Language Processing – Finding the Missing Link for Oncologic Data, 2022

Oncology like most medical specialties, is undergoing a data revolution at the center of which lie vast and growing amounts of clinical data in unstructured, semi-structured and structed formats. Artificial intelligence...

Download PDF file
  • EP ID EP724395
  • DOI https://doi.org/10.61797/ijbic.v1i2.153
  • Views 87
  • Downloads 0

How To Cite

Erdal Tasci, Aybars Ugur, Kevin Camphausen, Ying Zhuge, Rachel Zhao, Andra Krauze (2022). 3D Multimodal Brain Tumor Segmentation and Grading Scheme based on Machine, Deep, and Transfer Learning Approaches. International Journal of Bioinformatics and Intelligent Computing, 1(2), -. https://europub.co.uk/articles/-A-724395