DFUNet: Convolutional Neural Networks for Diabetic Foot Ulcer Classification

no code implementations • 28 Nov 2017 • Manu Goyal, Neil D. Reeves, Adrian K. Davison, Satyan Rajbhandari, Jennifer Spragg, Moi Hoon Yap

In this paper, we have proposed the use of traditional computer vision features for detecting foot ulcers among diabetic patients, which represent a cost-effective, remote and convenient healthcare solution.

Classification General Classification

Fully Convolutional Networks for Diabetic Foot Ulcer Segmentation

no code implementations • 6 Aug 2017 • Manu Goyal, Neil D. Reeves, Satyan Rajbhandari, Jennifer Spragg, Moi Hoon Yap

Using 5-fold cross-validation, the proposed two-tier transfer learning FCN Models achieve a Dice Similarity Coefficient of 0. 794 ($\pm$0. 104) for ulcer region, 0. 851 ($\pm$0. 148) for surrounding skin region, and 0. 899 ($\pm$0. 072) for the combination of both regions.

Transfer Learning