A Lightweight U-Net Model for Accurate Skin Lesion Segmentation

Authors

Fallah H. Najjar, Department of Emergent Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia AND Department of Computer Systems Techniques, Technical Institute of Najaf, Al-Furat Al-Awsat Technical University, Najaf, 54001, Iraq
Karrar A. Kadhim, Department of Emergent Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia AND Computer Techniques Engineering Department, Faculty of Information Technology, Imam Ja'afar Al-Sadiq University, Baghdad, Iraq
Farhan Mohamed, Department of Emergent Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, MalaysiaFollow
Mohd Shafry Mohd Rahim, Department of Emergent Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia
Asniyani Nur Haidar Abdullah, Department of Emergent Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia AND Faculty of Information & Communication Technology, Universiti Teknikal Malaysia Melaka Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia

Abstract

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.

Reason for Expression of Concern: The Editors wish to alert readers to potential concerns regarding the reliability of the findings reported in ``A Lightweight U-Net Model for Accurate Skin Lesion Segmentation (Manuscript 1230)''. the journal has initiated an additional editorial assessment of the article's methodology, data provenance, and reported outcomes to confirm their reliability and reproducibility.
This notice is issued to ensure transparency while the review is ongoing. The Expression of Concern does not constitute a final determination regarding the validity of the work. The journal will update readers once the assessment is completed and will take any necessary editorial action in accordance with the journal's policies and COPE guidance. See expression of concern available at:
DOI: https://doi.org/10.52866/2788-7421.1378.
Available at: http://ijcsm.researchcommons.org/ijcsm/vol7/iss1/32

Recommended Citation

Najjar, Fallah H.; Kadhim, Karrar A.; Mohamed, Farhan; Mohd Rahim, Mohd Shafry; and Haidar Abdullah, Asniyani Nur (2025) "A Lightweight U-Net Model for Accurate Skin Lesion Segmentation," Iraqi Journal for Computer Science and Mathematics: Vol. 6: Iss. 2, Article 1.
DOI: https://doi.org/10.52866/2788-7421.1230
Available at: https://ijcsm.researchcommons.org/ijcsm/vol6/iss2/1