Interactive thyroid whole slide image diagnostic system using deep representation. (October 2020)

• Record Type: Journal Article
• Authors: Chen, Pingjun; Shi, Xiaoshuang; Liang, Yun; Li, Yuan; Yang, Lin; Gader, Paul D.
• Is Part Of: Computer methods and programs in biomedicine. Volume 195(2020)
• Publication Date: 2020-10
• Subjects: Thyroid frozen section -- Whole slide image -- Suspicious region -- Deep representation -- Region retrieval; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105630
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We develop an interactive thyroid whole slide image classification and retrieval system using deep representation. With the participation of pathologists, the proposed system can focus on the suspicious regions in thyroid frozen sections, thus speeding up the analysis and improving the diagnostic performance. We propose retrieval of the whole slide image to base on the region of interest (ROI), which is more fine-grained, precise, and reliable. We introduce a win-win scheme for pathologists and the AI system, enable the diagnostic system to be more easily accepted by both pathologists and patients. Abstract: Background and objectives: The vast size of the histopathology whole slide image poses formidable challenges to its automatic diagnosis. With the goal of computer-aided diagnosis and the insights that suspicious regions are generally easy to identify in thyroid whole slide images (WSIs), we develop an interactive whole slide diagnostic system for thyroid frozen sections based on the suspicious regions preselected by pathologists. Methods: We propose to generate feature representations for the suspicious regions via extracting and fusing patch features using deep neural networks. We then evaluate region classification and retrieval on four classifiers and three supervised hashing methods based on the feature representations. The code is released at https://github.com/PingjunChen/ThyroidInteractive . Results: We evaluate the proposed system on 345 thyroid frozen sections and achieve 96.1% cross-validated classification accuracy, and retrieval mean average precision (MAP) of 0.972. Conclusions: With the participation of pathologists, the system possesses the following four notable advantages compared to directly handling whole slide images: 1) Reduced interference of irrelevant regions; 2) Alleviated computation and memory cost. 3) Fine-grained and precise suspicious region retrieval. 4) Cooperative relationship between pathologists and the diagnostic system. Additionally, experimental results demonstrate the potential of the proposed system on the practical thyroid frozen section diagnosis.