Deep learning segmentation of invasive melanoma

Aman Shah; Amal Mehta; Michael Wang; Neil Neumann; Avideh Zakhor; Timothy McCalmont

doi:10.1117/12.2654672

6 April 2023 Deep learning segmentation of invasive melanoma

Aman Shah, Amal Mehta, Michael Wang, Neil Neumann, Avideh Zakhor, Timothy McCalmont

Proceedings Volume 12471, Medical Imaging 2023: Digital and Computational Pathology; 124711P (2023) https://doi.org/10.1117/12.2654672
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Melanoma is the deadliest skin cancer with the fastest rising incidence rate in the United States. The most important predictor of melanoma patient survival is the volume of invasive tumor at the initial biopsy. The appearance of in-situ melanoma in epidermis and invasive melanoma in dermis, which invades the underlying soft tissue and drives mortality, is often visually similar. We propose a novel two-stage method to segment invasive melanoma. The first stage computes two segmentation maps, one for tumor vs non-tumor and one for dermis vs epidermis. These two segmentation prediction maps of tumor and epidermis from the first stage combine to yield invasive melanoma predictions. Our method utilizes multiple resolutions and downscaling to increase information passed to the model and to improve model accuracy. Using an HRNet+OCR model for both epidermis and melanoma segmentation in our proposed two-stage system results in a marked improvement of F1 score (mIoU) to 0.44 (0.64) as compared to the current state-of-the-art of 0.14 (0.53).

Citation Download Citation

Aman Shah, Amal Mehta, Michael Wang, Neil Neumann, Avideh Zakhor, and Timothy McCalmont "Deep learning segmentation of invasive melanoma", Proc. SPIE 12471, Medical Imaging 2023: Digital and Computational Pathology, 124711P (6 April 2023); https://doi.org/10.1117/12.2654672

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

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.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available