Delineation of Skin Strata in Reflectance Confocal Microscopy Images using Recurrent Convolutional Networks with Toeplitz Attention
This work addresses the need for interpretable, quantitative tools in non-invasive skin cancer screening, representing a domain-specific advancement.
The paper tackled the problem of standardizing skin strata delineation in reflectance confocal microscopy images for cancer diagnosis by developing a recurrent convolutional network with a novel Toeplitz attention mechanism, achieving 88.17% image-wise classification accuracy on an expert-labeled dataset.
Reflectance confocal microscopy (RCM) is an effective, non-invasive pre-screening tool for skin cancer diagnosis, but it requires extensive training and experience to assess accurately. There are few quantitative tools available to standardize image acquisition and analysis, and the ones that are available are not interpretable. In this study, we use a recurrent neural network with attention on convolutional network features. We apply it to delineate skin strata in vertically-oriented stacks of transverse RCM image slices in an interpretable manner. We introduce a new attention mechanism called Toeplitz attention, which constrains the attention map to have a Toeplitz structure. Testing our model on an expert labeled dataset of 504 RCM stacks, we achieve 88.17% image-wise classification accuracy, which is the current state-of-art.