A Mobile App for Wound Localization using Deep Learning

TL;DR

This paper introduces a deep learning-based mobile app for wound localization using YOLOv3, demonstrating high accuracy and robustness in detecting wounds from images, aiding automated wound diagnosis.

Contribution

It develops the first mobile application for wound localization using YOLOv3, with improved accuracy over SSD and validated on multiple datasets.

Findings

YOLOv3 achieves 93.9% mAP, outperforming SSD.

The app successfully detects wounds in images and videos.

Model tested on proprietary and public datasets with high robustness.

Abstract

We present an automated wound localizer from 2D wound and ulcer images by using deep neural network, as the first step towards building an automated and complete wound diagnostic system. The wound localizer has been developed by using YOLOv3 model, which is then turned into an iOS mobile application. The developed localizer can detect the wound and its surrounding tissues and isolate the localized wounded region from images, which would be very helpful for future processing such as wound segmentation and classification due to the removal of unnecessary regions from wound images. For Mobile App development with video processing, a lighter version of YOLOv3 named tiny-YOLOv3 has been used. The model is trained and tested on our own image dataset in collaboration with AZH Wound and Vascular Center, Milwaukee, Wisconsin. The YOLOv3 model is compared with SSD model, showing that YOLOv3 gives a mAP value of 93.9%, which is much better than the SSD model (86.4%). The robustness and reliability of these models are also tested on a publicly available dataset named Medetec and shows a very good performance as well.