CancerNet-SCa: Tailored Deep Neural Network Designs for Detection of Skin Cancer from Dermoscopy Images

TL;DR

CancerNet-SCa introduces the first machine-designed deep neural networks tailored specifically for skin cancer detection from dermoscopy images, promoting open research and transparency in this critical medical application.

Contribution

The paper presents novel, machine-designed deep neural network architectures specifically tailored for skin cancer detection, including a self-attention model, and provides open-source tools for the community.

Findings

First machine-designed neural networks for skin cancer detection

Inclusion of a self-attention architecture with attention condensers

Open source release to facilitate further research

Abstract

Skin cancer continues to be the most frequently diagnosed form of cancer in the U.S., with not only significant effects on health and well-being but also significant economic costs associated with treatment. A crucial step to the treatment and management of skin cancer is effective skin cancer detection due to strong prognosis when treated at an early stage, with one of the key screening approaches being dermoscopy examination. Motivated by the advances of deep learning and inspired by the open source initiatives in the research community, in this study we introduce CancerNet-SCa, a suite of deep neural network designs tailored for the detection of skin cancer from dermoscopy images that is open source and available to the general public as part of the Cancer-Net initiative. To the best of the authors' knowledge, CancerNet-SCa comprises of the first machine-designed deep neural network architecture designs tailored specifically for skin cancer detection, one of which possessing a self-attention architecture design with attention condensers. Furthermore, we investigate and audit the behaviour of CancerNet-SCa in a responsible and transparent manner via explainability-driven model auditing. While CancerNet-SCa is not a production-ready screening solution, the hope is that the release of CancerNet-SCa in open source, open access form will encourage researchers, clinicians, and citizen data scientists alike to leverage and build upon them.