Texture-based Deep Neural Network for Histopathology Cancer Whole Slide Image (WSI) Classification

<p>Automatic histopathological Whole Slide Image (WSI) analysis for cancer classification has been highlighted along with the advancements in microscopic imaging techniques. However, manual examination and diagnosis with WSIs is time-consuming and tiresome. Recently, deep convolutional neural networks have succeeded in histopathological image analysis. In this paper, we propose a novel cancer texture-based deep neural network (CAT-Net) that learns scalable texture features from histopathological WSIs. The innovation of CAT-Net is twofold: (1) capturing invariant spatial patterns by dilated convolutional layers and (2) Reducing model complexity while improving performance. Moreover, CAT-Net can provide discriminative texture patterns formed on cancerous regions of histopathological images compared to normal regions. The proposed method outperformed the current state-of-the-art benchmark methods on accuracy, precision, recall, and F1 score.</p>

Name thesis:degree_name

Master of Science in Computer Science (MSCS)

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Year dc:date.available

2019

Author dc:creator

• TSAKU, NELSON Zange

Contributors dc:contributor

• Dr. Mingon Kang
• Dr. Dan Chia-Tien Lo
• Dr. Chih-Cheng Hung

• Whole Slide Images
• Texture Based CNN
• Deep Learning
• Applied Statistics
• Artificial Intelligence and Robotics
• Bioinformatics
• Numerical Analysis and Scientific Computing
• Software Engineering
• Statistical Models
• Theory and Algorithms

Repository record dc:identifier

https://digitalcommons.kennesaw.edu/cs_etd/29

OAI identifier oai:identifier

oai:digitalcommons.kennesaw.edu:cs_etd-1031