Histopathological image analysis of stained tissue slides is routinely used in tumor detection and classification. However, diagnosis requires a highly trained pathologist and can thus be time-consuming, labor-intensive, and potentially risk bias. Here, we demonstrate a potential complementary approach for diagnosis. We show that multiphoton microscopy images from unstained, reproductive tissues can be robustly classified using deep learning techniques. We fine-train four pretrained convolutional neural networks using over 200 murine tissue images based on combined second-harmonic generation and two-photon excitation fluorescence contrast, to classify the tissues either as healthy or associated with high-grade serous carcinoma with over 95% sensitivity and 97% specificity. Our approach shows promise for applications involving automated disease diagnosis. It could also be readily applied to other tissues, diseases, and related classification problems.

convolutional neural networks, medical and biological imaging, nonlinear microscopy, optical pathology, ovarian cancer, tissue characterization
Journal of Biomedical Optics
Department of Physics

Huttunen, M.J. (Mikko J.), Hassan, A. (Abdurahman), McCloskey, C.W. (Curtis W.), Fasih, S. (Sijyl), Upham, J. (Jeremy), Vanderhyden, B.C. (Barbara C.), … Murugkar, S. (2018). Automated classification of multiphoton microscopy images of ovarian tissue using deep learning. Journal of Biomedical Optics, 23(6). doi:10.1117/1.JBO.23.6.066002