Open Access Presentation
9 March 2020 Machine-learning with a small training set for classification of quantitative phase images of cancer cells (Conference Presentation)
Author Affiliations +
Proceedings Volume 11299, AI and Optical Data Sciences; 112990Q (2020) https://doi.org/10.1117/12.2550957
Event: SPIE OPTO, 2020, San Francisco, California, United States
Abstract
One of the main bottlenecks of deep learning is the requirement for many training examples. In medical imaging, these examples are not always available. I will present our latest advances in the development of machine learning classification on interferometric phase microscopy (IPM) quantitative tomographic maps to obtain grading of cancer cells without staining. We first applied principle component analysis (PCA) followed by support vector machine (SVM) classifiers. To apply deep learning with small training sets, we proposed a new deep learning method, TOP-GAN, which is a hybridization between transfer learning and generative adversarial networks.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Natan T. Shaked "Machine-learning with a small training set for classification of quantitative phase images of cancer cells (Conference Presentation)", Proc. SPIE 11299, AI and Optical Data Sciences, 112990Q (9 March 2020); https://doi.org/10.1117/12.2550957
Advertisement
Advertisement
KEYWORDS
Cancer

Machine learning

Image classification

Microscopy

Refractive index

Interferometry

Medical imaging

Back to Top