Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Analysis Towards Classification of Infection and Ischaemia of Diabetic Foot Ulcers
AU - Yap, Moi Hoon
AU - Cassidy, Bill
AU - Pappachan, Joseph M
AU - O'Shea, Claire
AU - Gillespie, David
AU - Reeves, Neil
PY - 2021/8/10
Y1 - 2021/8/10
N2 - This paper introduces the Diabetic Foot Ulcers dataset (DFUC2021) for analysis of pathology, focusing on infection and ischaemia. We describe the data preparation of DFUC2021 for ground truth annotation, data curation and data analysis. The final release of DFUC2021 consists of 15,683 DFU patches, with 5,955 training, 5,734 for testing and 3,994 unlabeled DFU patches. The ground truth labels are four classes, i.e. control, infection, ischaemia and both conditions. We curate the dataset using image hashing techniques and analyse the separability using UMAP projection. We benchmark the performance of five key backbones of deep learning, i.e. VGG16, ResNet101, InceptionV3, DenseNet121 and EfficientNet on DFUC2021. We report the optimised results of these key backbones with different strategies. Based on our observations, we conclude that Efficient-NetB0 with data augmentation and transfer learning provided the best results for multi-class (4-class) classification with macro-average Precision, Recall and F1-Score of 0.57, 0.62 and 0.55, respectively. In ischaemia and infection recognition, when trained on one-versus-all, EfficientNetB0 achieved comparable results with the state of the art. Finally, we interpret the results with statistical analysis and Grad-CAM visualisation.
AB - This paper introduces the Diabetic Foot Ulcers dataset (DFUC2021) for analysis of pathology, focusing on infection and ischaemia. We describe the data preparation of DFUC2021 for ground truth annotation, data curation and data analysis. The final release of DFUC2021 consists of 15,683 DFU patches, with 5,955 training, 5,734 for testing and 3,994 unlabeled DFU patches. The ground truth labels are four classes, i.e. control, infection, ischaemia and both conditions. We curate the dataset using image hashing techniques and analyse the separability using UMAP projection. We benchmark the performance of five key backbones of deep learning, i.e. VGG16, ResNet101, InceptionV3, DenseNet121 and EfficientNet on DFUC2021. We report the optimised results of these key backbones with different strategies. Based on our observations, we conclude that Efficient-NetB0 with data augmentation and transfer learning provided the best results for multi-class (4-class) classification with macro-average Precision, Recall and F1-Score of 0.57, 0.62 and 0.55, respectively. In ischaemia and infection recognition, when trained on one-versus-all, EfficientNetB0 achieved comparable results with the state of the art. Finally, we interpret the results with statistical analysis and Grad-CAM visualisation.
U2 - 10.1109/bhi50953.2021.9508563
DO - 10.1109/bhi50953.2021.9508563
M3 - Conference contribution/Paper
SN - 9781665447706
T3 - IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)
BT - 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)
PB - IEEE
ER -