Quality Quantification in Deep Convolutional Neural Networks for Skin Lesion Segmentation using Fuzzy Uncertainty Measurement

Lin, Qiao; Chen, Xin; Chen, Chao; Garibaldi, Jonathan M.

Abstract

Deep convolutional neural networks (DCNN)-based methods have achieved promising performance in semantic image segmentation. However, in practical applications, it is important not only to produce the segmentation result but also to inform the segmentation quality (e.g. confidence of the segmentation result). In this paper, we propose to utilize fuzzy sets for estimating segmentation uncertainty, therefore to infer the quality of segmentation produced by a DCNN model. The proposed method combines test-time augmentation and fuzzy sets to estimate an image-level uncertainty. Six different fuzziness measures are implemented and compared, in order to select the best fuzzy uncertainty metric for the proposed method. A public skin lesion dataset is used to evaluate the method. The results show a strong correlation (Pearson correlation coefficient of 0.736) between our proposed uncertainty measure and image segmentation quality measured by Dice coefficient.

Citation

Lin, Q., Chen, X., Chen, C., & Garibaldi, J. M. (2022, July). Quality Quantification in Deep Convolutional Neural Networks for Skin Lesion Segmentation using Fuzzy Uncertainty Measurement. Presented at 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Padua, Italy

• Presentation Conference Type: Edited Proceedings
• Conference Name: 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
• Start Date: Jul 18, 2022
• End Date: Jul 23, 2022
• Acceptance Date: Jul 18, 2022
• Online Publication Date: Sep 14, 2022
• Publication Date: Jul 18, 2022
• Deposit Date: Nov 5, 2024
• Publicly Available Date: Dec 17, 2024
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Pages: 115-122
• Book Title: 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2022)
• ISBN: 978-1-6654-6711-7
• DOI: https://doi.org/10.1109/FUZZ-IEEE55066.2022.9882728
• Public URL: https://nottingham-repository.worktribe.com/output/11742645
• Publisher URL: https://ieeexplore.ieee.org/document/9882728