Semi-Supervised Classification of Noisy, Gigapixel Histology Images
- Resource Type
- Conference
- Authors
- Pulido, J. Vince; Guleria, Shan; Ehsan, Lubaina; Fasullo, Matthew; Lippman, Robert; Mutha, Pritesh; Shah, Tilak; Syed, Sana; Brown, Donald E.
- Source
- 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE) BIBE Bioinformatics and Bioengineering (BIBE), 2020 IEEE 20th International Conference on. :563-568 Oct, 2020
- Subject
- Bioengineering
Components, Circuits, Devices and Systems
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Training
Histopathology
Neural networks
Medical services
Semisupervised learning
Noise measurement
Biomedical imaging
Histology
Machine Learning
Semi-supervised Learning
- Language
- ISSN
- 2471-7819
One of the greatest obstacles in the adoption of deep neural networks for new medical applications is that training these models typically require a large amount of manually labeled training samples. In this body of work, we investigate the semi-supervised scenario where one has access to large amounts of unlabeled data and only a few labeled samples. We study the performance of MixMatch and FixMatch-two popular semi-supervised learning methods-on a histology dataset. More specifically, we study these models’ impact under a highly noisy and imbalanced setting. The findings here motivate the development of semi-supervised methods to ameliorate problems commonly encountered in medical data applications.