Faisal Mahmood,1 Richard Chen,1 Daniel Borders,1 Gregory N. McKay,1 Kevan Salimian,2 Alexander Baras,2 Nicholas J. Durrhttps://orcid.org/0000-0001-9808-73831
1Johns Hopkins Univ. (United States) 2Johns Hopkins School of Medicine (United States)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Automated segmentation of tissue and cellular structure in H&E images is an important first step towards automated histopathology slide analysis. For example, nuclei segmentation can aid with detecting pleomorphism and epithelium segmentation can aid in identification of tumor infiltrating lymphocytes etc. Existing deep learning-based approaches are often trained organ-wise and lack diversity of training data for multi-organ segmentation networks. In this work, we propose to augment existing nuclei segmentation datasets using cycleGANs. We learn an unpaired mapping from perturbed randomized polygon masks to pseudo-H&E images. We generate over synthetic H&E patches from several different organs for nuclei segmentation. We then use an adversarial U-Net with spectral normalization for increased training stability for segmentation. This paired image-to-image translation style network not only learns the mapping form H&E patches to segmentation masks but also learns an optimal loss function. Such an approach eliminates the need for a hand-crafted loss which has been explored significantly for nuclei segmentation. We demonstrate that the average accuracy for multi-organ nuclei segmentation increases to 94.43% using the proposed synthetic data generation and adversarial U-Net-based segmentation pipeline as compared to 79.81% when no synthetic data and adversarial loss was used.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Faisal Mahmood, Richard Chen, Daniel Borders, Gregory N. McKay, Kevan Salimian, Alexander Baras, Nicholas J. Durr, "Adversarial U-net with spectral normalization for histopathology image segmentation using synthetic data," Proc. SPIE 10956, Medical Imaging 2019: Digital Pathology, 109560N (18 March 2019); https://doi.org/10.1117/12.2512918