Early Explorations of Lightweight Models for Wound Segmentation on Mobile Devices

TL;DR

This paper explores lightweight deep learning models for wound segmentation on smartphones, demonstrating that certain transformer-based architectures can achieve performance comparable to traditional models, enabling accessible mobile healthcare solutions.

Contribution

It introduces and evaluates lightweight transformer architectures for mobile wound segmentation, filling a gap in research on efficient models suitable for smartphones.

Findings

ENet and TopFormer perform comparably to UNet.

Models successfully deployed in a smartphone app for live wound segmentation.

TopFormer effectively distinguishes wounds from similar-colored objects.

Abstract

The aging population poses numerous challenges to healthcare, including the increase in chronic wounds in the elderly. The current approach to wound assessment by therapists based on photographic documentation is subjective, highlighting the need for computer-aided wound recognition from smartphone photos. This offers objective and convenient therapy monitoring, while being accessible to patients from their home at any time. However, despite research in mobile image segmentation, there is a lack of focus on mobile wound segmentation. To address this gap, we conduct initial research on three lightweight architectures to investigate their suitability for smartphone-based wound segmentation. Using public datasets and UNet as a baseline, our results are promising, with both ENet and TopFormer, as well as the larger UNeXt variant, showing comparable performance to UNet. Furthermore, we deploy the models into a smartphone app for visual assessment of live segmentation, where results demonstrate the effectiveness of TopFormer in distinguishing wounds from wound-coloured objects. While our study highlights the potential of transformer models for mobile wound segmentation, future work should aim to further improve the mask contours.