A lightweight u-net model for accurate skin lesion segmentation
In this paper, a new lightweight U-Net deep learning-based neural network designed for the segmentation of skin lesions is proposed. Segmentation of skin lesions is the most critical step in computer-aided dermatology diagnosis for the early detection of melanoma and other diseases. However, we ad...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
College of Education, Al-Iraqia University
2025
|
| Online Access: | http://eprints.utem.edu.my/id/eprint/29568/2/0277416042025858271749.pdf http://eprints.utem.edu.my/id/eprint/29568/ https://ijcsm.researchcommons.org/cgi/viewcontent.cgi?article=1230&context=ijcsm https://doi.org/10.52866/2788-7421.1230 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1858062982200688640 |
|---|---|
| author | Mohamed, Farhan H. Najjar, Fallah Abdulameer Kadhim, Karrar Mohd Rahim, Mohd Shafry Abdullah, Asniyani Nur Haidar |
| author_facet | Mohamed, Farhan H. Najjar, Fallah Abdulameer Kadhim, Karrar Mohd Rahim, Mohd Shafry Abdullah, Asniyani Nur Haidar |
| author_sort | Mohamed, Farhan |
| building | UTEM Library |
| collection | Institutional Repository |
| content_provider | Universiti Teknikal Malaysia Melaka |
| content_source | UTEM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | In this paper, a new lightweight U-Net deep learning-based neural network designed for the segmentation of skin
lesions is proposed. Segmentation of skin lesions is the most critical step in computer-aided dermatology diagnosis for
the early detection of melanoma and other diseases. However, we address the difficulty related to the precise definition of the lesion margins with an eye on the computation cost. We have demonstrated the state-of-the-art performance of DeepSkinSeg in most metrics on dermoscopic images using the PH2 and Human Against Machine (HAM10000) datasets. The metrics of the DeepSkinSeg model were robustness measured as the Intersection over Union (IoU) at 91.49, Dice coefficient at 95.56, precision at 97.97, sensitivity at 96.84, and accuracy at 96.71 for the PH2 dataset. Other standard generalization capabilities for the HAM10000 dataset could be an IoU of 92.97, a Dice coefficient of 96.36, precision at 97.64, sensitivity at 95.10, and an accuracy of 94.59. DeepSkinSeg has a very efficient inference because the model itself is lightweight, proving to be very helpful for real-time dermatological analysis. This work further advanced the computer-aided diagnosis in the task of skin lesion classification, guaranteeing even more promising clinical applications |
| format | Article |
| id | my.utem.eprints-29568 |
| institution | Universiti Teknikal Malaysia Melaka |
| language | en |
| publishDate | 2025 |
| publisher | College of Education, Al-Iraqia University |
| record_format | eprints |
| spelling | my.utem.eprints-295682026-02-23T04:48:47Z http://eprints.utem.edu.my/id/eprint/29568/ A lightweight u-net model for accurate skin lesion segmentation Mohamed, Farhan H. Najjar, Fallah Abdulameer Kadhim, Karrar Mohd Rahim, Mohd Shafry Abdullah, Asniyani Nur Haidar In this paper, a new lightweight U-Net deep learning-based neural network designed for the segmentation of skin lesions is proposed. Segmentation of skin lesions is the most critical step in computer-aided dermatology diagnosis for the early detection of melanoma and other diseases. However, we address the difficulty related to the precise definition of the lesion margins with an eye on the computation cost. We have demonstrated the state-of-the-art performance of DeepSkinSeg in most metrics on dermoscopic images using the PH2 and Human Against Machine (HAM10000) datasets. The metrics of the DeepSkinSeg model were robustness measured as the Intersection over Union (IoU) at 91.49, Dice coefficient at 95.56, precision at 97.97, sensitivity at 96.84, and accuracy at 96.71 for the PH2 dataset. Other standard generalization capabilities for the HAM10000 dataset could be an IoU of 92.97, a Dice coefficient of 96.36, precision at 97.64, sensitivity at 95.10, and an accuracy of 94.59. DeepSkinSeg has a very efficient inference because the model itself is lightweight, proving to be very helpful for real-time dermatological analysis. This work further advanced the computer-aided diagnosis in the task of skin lesion classification, guaranteeing even more promising clinical applications College of Education, Al-Iraqia University 2025 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/29568/2/0277416042025858271749.pdf Mohamed, Farhan and H. Najjar, Fallah and Abdulameer Kadhim, Karrar and Mohd Rahim, Mohd Shafry and Abdullah, Asniyani Nur Haidar (2025) A lightweight u-net model for accurate skin lesion segmentation. Iraqi Journal for Computer Science and Mathematics, 6 (2). pp. 1-11. ISSN 2788-7421 https://ijcsm.researchcommons.org/cgi/viewcontent.cgi?article=1230&context=ijcsm https://doi.org/10.52866/2788-7421.1230 |
| spellingShingle | Mohamed, Farhan H. Najjar, Fallah Abdulameer Kadhim, Karrar Mohd Rahim, Mohd Shafry Abdullah, Asniyani Nur Haidar A lightweight u-net model for accurate skin lesion segmentation |
| title | A lightweight u-net model for accurate skin lesion segmentation |
| title_full | A lightweight u-net model for accurate skin lesion segmentation |
| title_fullStr | A lightweight u-net model for accurate skin lesion segmentation |
| title_full_unstemmed | A lightweight u-net model for accurate skin lesion segmentation |
| title_short | A lightweight u-net model for accurate skin lesion segmentation |
| title_sort | lightweight u-net model for accurate skin lesion segmentation |
| url | http://eprints.utem.edu.my/id/eprint/29568/2/0277416042025858271749.pdf http://eprints.utem.edu.my/id/eprint/29568/ https://ijcsm.researchcommons.org/cgi/viewcontent.cgi?article=1230&context=ijcsm https://doi.org/10.52866/2788-7421.1230 |
| url_provider | http://eprints.utem.edu.my/ |