Amirreza Mahbod, Post-Doc in the group of Isabella Ellinger, has achieved PLACE 1 in the leaderboard of the MICCAI 2021 Foot Ulcer Segmentation Challenge.

Foot ulcer is a common complication of diabetes mellitus; it is associated with substantial morbidity and mortality and remains a major risk factor for lower leg amputation. Extracting accurate morphological features from the foot wounds is crucial for proper treatment. Computer-mediated approaches enable segmentation of the lesions and extraction  of related morphological features. Deep learning-based methods and more specifically convolutional neural networks (CNN) have shown excellent performances for various image segmentation tasks including medical image segmentation. In this work, Amirreza Mahbod, Rupert Ecker and Isabella Ellinger proposed an ensemble approach based on two encoder-decoder-based CNN models, namely LinkNet and UNet, to perform foot ulcer segmentation. Our method achieved the first rank in the FUSeg challenge leaderboard.

Leaderboard link: https://uwm-bigdata.github.io/wound-segmentation/

Challenge link: https://fusc.grand-challenge.org/

Method description: https://arxiv.org/abs/2109.01408