Improving the Diagnosis of Skin Biopsies Using Tissue Segmentation
Shima Nofallaha✉, Beibin Lib, Mojgan Mokhtaric, Wenjun Wud, Stevan R. Knezeviche, Caitlin J. Mayf, Oliver H. Changg, Joann G. Elmoreh, Linda G. Shapiroa b d
- aDepartment of Electrical and Computer Engineering, University of Washington, Seattle, WA 98195, USA
- bPaul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA 98195, USA
- cPathology Department, Isfahan University of Medical Sciences, Isfahan 8174673461, Iran
- dDepartment of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA 98195, USA
- ePathology Associates, Clovis, CA 983611, USA
- fDermatopathology Northwest, Bellevue, WA 98005, USA
- gDepartment of Pathology, University of Washington, Seattle, WA 98195, USA
- hDavid Geffen School of Medicine, UCLA, Los Angeles, CA 90024, USA
- ✉Corresponding author
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Invasive melanoma, a common type of skin cancer, is considered one of the deadliest. Pathologists routinely evaluate melanocytic lesions to determine the amount of atypia, and if the lesion represents an invasive melanoma, its stage. However, due to the complicated nature of these assessments, inter- and intra-observer variability among pathologists in their interpretation are very common. Machine-learning techniques have shown impressive and robust performance on various tasks including healthcare. In this work, we study the potential of including semantic segmentation of clinically important tissue structure in improving the diagnosis of skin biopsy images. Our experimental results show a 6% improvement in F-score when using whole slide images along with epidermal nests and cancerous dermal nest segmentation masks compared to using whole-slide images alone in training and testing the diagnosis pipeline.
TL;DRThis work studies the potential of including semantic segmentation of clinically important tissue structure in improving the diagnosis of skin biopsy images and shows a 6% improvement in F-score when using whole slide images along with epidermal nests and cancerous dermal nest segmentation masks. (Semantic Scholar)