A Mobile App for Wound Localization using Deep Learning
This work addresses wound localization for medical diagnostics, but it is incremental as it applies an existing method (YOLOv3) to a new domain (wound images).
The researchers tackled wound localization from 2D images using a YOLOv3-based deep learning model, achieving a mAP of 93.9% on their dataset, which outperformed an SSD model (86.4%), and developed it into an iOS mobile app for automated wound diagnostics.
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.