Skin Lesion Image Segmentation Algorithm Based on MC-UNet
Aiming at the situation of dermatoscopic images with fuzzy lesion boundaries, variable morphology and high similarity to background, this paper proposes a skin lesion segmentation algorithm that achieves higher segmentation accuracy by combining existing convolutional neural network methods. The alg...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10845775/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583983211216896 |
|---|---|
| author | Guihua Yang Bingxing Pan |
| author_facet | Guihua Yang Bingxing Pan |
| author_sort | Guihua Yang |
| collection | DOAJ |
| description | Aiming at the situation of dermatoscopic images with fuzzy lesion boundaries, variable morphology and high similarity to background, this paper proposes a skin lesion segmentation algorithm that achieves higher segmentation accuracy by combining existing convolutional neural network methods. The algorithm begins by using a Multiscale Residual Block (MRB) with different-sized convolutional kernels to enlarge the receptive field and extract multi-scale features of dermatoscopic images. Secondly, the skip connections are enhanced with a Bidirectional Information Fusion Module (BFM) to refine features by bidirectionally fusing semantic information from high-level feature maps and spatial information from low-level feature maps. Finally, the network’s segmentation accuracy is improved through the use of a new loss function called MixLoss, which combines BceLoss and DiceLoss. Specifically, it achieves a Dice coefficient of 92.37% and an accuracy of 95.32% with a sensitivity of 93.41% on the ISIC2016 dataset. On the ISIC2017 dataset, it achieves a Dice coefficient of 89.43%, an accuracy of 94.81%, and a sensitivity of 90.41%. The experimental results show that the proposed algorithm outperforms other mainstream algorithms and exhibits superior performance in skin lesion segmentation. |
| format | Article |
| id | doaj-art-7388504462a04cd1ac303b4430b10e7c |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7388504462a04cd1ac303b4430b10e7c2025-01-28T00:01:47ZengIEEEIEEE Access2169-35362025-01-0113147601476910.1109/ACCESS.2025.353150810845775Skin Lesion Image Segmentation Algorithm Based on MC-UNetGuihua Yang0https://orcid.org/0009-0007-4470-9977Bingxing Pan1https://orcid.org/0009-0008-1978-071XEducation Department of Guangxi Zhuang Autonomous Region, Key Laboratory of Advanced Manufacturing and Automation Technology, Guilin University of Technology, Guilin, ChinaEducation Department of Guangxi Zhuang Autonomous Region, Key Laboratory of Advanced Manufacturing and Automation Technology, Guilin University of Technology, Guilin, ChinaAiming at the situation of dermatoscopic images with fuzzy lesion boundaries, variable morphology and high similarity to background, this paper proposes a skin lesion segmentation algorithm that achieves higher segmentation accuracy by combining existing convolutional neural network methods. The algorithm begins by using a Multiscale Residual Block (MRB) with different-sized convolutional kernels to enlarge the receptive field and extract multi-scale features of dermatoscopic images. Secondly, the skip connections are enhanced with a Bidirectional Information Fusion Module (BFM) to refine features by bidirectionally fusing semantic information from high-level feature maps and spatial information from low-level feature maps. Finally, the network’s segmentation accuracy is improved through the use of a new loss function called MixLoss, which combines BceLoss and DiceLoss. Specifically, it achieves a Dice coefficient of 92.37% and an accuracy of 95.32% with a sensitivity of 93.41% on the ISIC2016 dataset. On the ISIC2017 dataset, it achieves a Dice coefficient of 89.43%, an accuracy of 94.81%, and a sensitivity of 90.41%. The experimental results show that the proposed algorithm outperforms other mainstream algorithms and exhibits superior performance in skin lesion segmentation.https://ieeexplore.ieee.org/document/10845775/Dermatoscopic imagesimage segmentationmultiscalebidirectional information fusion |
| spellingShingle | Guihua Yang Bingxing Pan Skin Lesion Image Segmentation Algorithm Based on MC-UNet IEEE Access Dermatoscopic images image segmentation multiscale bidirectional information fusion |
| title | Skin Lesion Image Segmentation Algorithm Based on MC-UNet |
| title_full | Skin Lesion Image Segmentation Algorithm Based on MC-UNet |
| title_fullStr | Skin Lesion Image Segmentation Algorithm Based on MC-UNet |
| title_full_unstemmed | Skin Lesion Image Segmentation Algorithm Based on MC-UNet |
| title_short | Skin Lesion Image Segmentation Algorithm Based on MC-UNet |
| title_sort | skin lesion image segmentation algorithm based on mc unet |
| topic | Dermatoscopic images image segmentation multiscale bidirectional information fusion |
| url | https://ieeexplore.ieee.org/document/10845775/ |
| work_keys_str_mv | AT guihuayang skinlesionimagesegmentationalgorithmbasedonmcunet AT bingxingpan skinlesionimagesegmentationalgorithmbasedonmcunet |