{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T09:16:10Z","timestamp":1783329370005,"version":"3.54.6"},"reference-count":52,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia","award":["PNURSP2026R234"],"award-info":[{"award-number":["PNURSP2026R234"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Automated segmentation of skin lesions is a critical task in the computer-aided diagnosis of skin cancer. This article presents a novel deep learning model, Attention-Attention Residual U-Net (AA-ResUNet), designed to improve the precision and effectiveness of dermatoscopic image segmentation. The proposed model integrates a dual attention mechanism, spatial and channel-wise, within a residual U-Net framework to enhance feature extraction and suppress irrelevant information to enable fine-grained segmentation. The performance of the model is validated on the human against machine with 10000 training images (HAM10000), international skin imaging collaboration (ISIC) 2018, ISIC2016, and Pedro Hispano hospital (PH2) dermatological datasets. The experiment results show that AA-ResUNet obtains a test accuracy of 98.8%, Dice Similarity Coefficient of 93.6%, and mIoU of 95.7%. The dual attention mechanism dramatically improves segmentation accuracy and boundary accuracy, with better generalized performance than the state-of-the-art, confirmed by computer simulations.<\/jats:p>","DOI":"10.7717\/peerj-cs.3969","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T08:27:47Z","timestamp":1783326467000},"page":"e3969","source":"Crossref","is-referenced-by-count":0,"title":["AA-ResUNet: an automatic skin lesion segmentation method based on fine-grained encoder-decoder architecture"],"prefix":"10.7717","volume":"12","author":[{"given":"Usman","family":"Zia","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Institute of Space Technology, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madiha","family":"Tahir","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Institute of Space Technology, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Ali","family":"Irtaza","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Institute of Space Technology, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9687-1385","authenticated-orcid":true,"given":"Mohammad","family":"Arif","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam-si, Gyeonggi-do, Republic of South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6907-2318","authenticated-orcid":true,"given":"Sadique","family":"Ahmad","sequence":"additional","affiliation":[{"name":"EIAS: Data Science and Blockchain Laboratory, College of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6829-9705","authenticated-orcid":true,"given":"Ala Saleh","family":"Alluhaidan","sequence":"additional","affiliation":[{"name":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"issue":"5","key":"10.7717\/peerj-cs.3969\/ref-1","doi-asserted-by":"publisher","first-page":"100193","DOI":"10.1016\/j.slast.2024.100193","article-title":"CardioGuard: AI-driven ECG authentication hybrid neural network for predictive health monitoring in telehealth systems","volume":"29","author":"Ahmed","year":"2024","journal-title":"SLAS Technology"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-2","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.cmpb.2018.05.027","article-title":"Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks","volume":"162","author":"Al-Masni","year":"2018","journal-title":"Computers in Methods and Programs in Biomedicine"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-3","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1038\/s41598-025-15655-9","article-title":"A deep learning framework for automated early diagnosis and classification of skin cancer lesions in dermoscopy images","volume":"15","author":"Al-Waisy","year":"2025","journal-title":"Scientific Reports"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-4","doi-asserted-by":"publisher","first-page":"2554","DOI":"10.1038\/s41598-025-00655-6","article-title":"Visual impairment prevention by early detection of diabetic retinopathy based on stacked auto-encoder","volume":"15","author":"Almas","year":"2025","journal-title":"Scientific Reports"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-5","doi-asserted-by":"publisher","first-page":"102358","DOI":"10.1016\/j.bspc.2020.102358","article-title":"Automated skin lesion segmentation using attention-based deep convolutional neural network","volume":"65","author":"Arora","year":"2021","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.7717\/peerj-cs.3969\/ref-6","first-page":"111","article-title":"Skin lesion segmentation using deep convolutional networks","author":"Arora","year":"2021"},{"issue":"3","key":"10.7717\/peerj-cs.3969\/ref-7","doi-asserted-by":"publisher","first-page":"468","DOI":"10.3390\/diagnostics16030468","article-title":"Foundation-model-driven skin lesion segmentation and classification using SAM-adapters and vision transformers","volume":"16","author":"Binzagr","year":"2026","journal-title":"Diagnostics"},{"key":"10.7717\/peerj-cs.3969\/ref-8","article-title":"Encoder\u2013decoder with Atrous separable convolution for semantic image segmentation (DeepLabv3+)","author":"Chen","year":"2018"},{"issue":"23","key":"10.7717\/peerj-cs.3969\/ref-9","doi-asserted-by":"publisher","first-page":"235001","DOI":"10.1088\/1361-6560\/abc363","article-title":"Deep learning-based medical image segmentation with limited labels","volume":"65","author":"Chi","year":"2020","journal-title":"Physics in Medicine & Biology"},{"issue":"10","key":"10.7717\/peerj-cs.3969\/ref-10","doi-asserted-by":"publisher","first-page":"3008","DOI":"10.1109\/tmi.2020.2983721","article-title":"CPFNet: context pyramid fusion network for medical image segmentation","volume":"39","author":"Feng","year":"2020","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3969\/ref-11","first-page":"3146","article-title":"Dual attention network for scene segmentation","author":"Fu","year":"2019"},{"issue":"2","key":"10.7717\/peerj-cs.3969\/ref-12","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/TMI.2020.3035253","article-title":"CA-Net: comprehensive attention convolutional neural networks for explainable medical image segmentation","volume":"40","author":"Gu","year":"2021","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3969\/ref-13","doi-asserted-by":"publisher","first-page":"44872","DOI":"10.1109\/ACCESS.2025.3548431","article-title":"An effective adaptive downsampling method for high-resolution multi-panel image segmentation","volume":"13","author":"Gul","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-14","doi-asserted-by":"publisher","first-page":"32099","DOI":"10.1038\/s41598-025-06653-y","article-title":"Improving lung cancer detection with enhanced convolutional sequential networks","volume":"15","author":"Haziq","year":"2025","journal-title":"Scientific Reports"},{"key":"10.7717\/peerj-cs.3969\/ref-15","doi-asserted-by":"publisher","first-page":"40290","DOI":"10.1109\/ACCESS.2024.3374108","article-title":"MAGRes-UNet: improved medical image segmentation through a deep learning paradigm of multi-attention gated residual U-Net","volume":"12","author":"Hussain","year":"2024","journal-title":"IEEE Access"},{"issue":"9","key":"10.7717\/peerj-cs.3969\/ref-16","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1109\/34.232073","article-title":"Comparing images using the Hausdorff distance","volume":"15","author":"Huttenlocher","year":"1993","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.3969\/ref-17","first-page":"313","article-title":"TESL-Net: a transformer-enhanced CNN for accurate skin lesion segmentation","author":"Iqbal","year":"2024"},{"key":"10.7717\/peerj-cs.3969\/ref-18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.14255","article-title":"AttResDU-Net: attention-based residual double U-Net for skin lesion segmentation","author":"Islam","year":"2023"},{"issue":"12","key":"10.7717\/peerj-cs.3969\/ref-19","doi-asserted-by":"publisher","first-page":"3548","DOI":"10.1111\/jgh.15673","article-title":"Diagnostic performance of endoscopic ultrasound-artificial intelligence using deep learning analysis of gallbladder polypoid lesions","volume":"36","author":"Jang","year":"2021","journal-title":"Journal of Gastroenterology and Hepatology"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-20","doi-asserted-by":"publisher","first-page":"41554","DOI":"10.1038\/s41598-025-25428-z","article-title":"DSSCC net enhanced skin cancer classification using SMOTE Tomek and optimized convolutional neural network","volume":"15","author":"Javaid","year":"2025","journal-title":"Scientific Reports"},{"issue":"6","key":"10.7717\/peerj-cs.3969\/ref-21","first-page":"1208","article-title":"Attention squeeze U-Net for automatic skin lesion segmentation","volume":"35","author":"Jha","year":"2022","journal-title":"Journal of Digital Imaging"},{"issue":"11","key":"10.7717\/peerj-cs.3969\/ref-22","doi-asserted-by":"publisher","first-page":"e0314000","DOI":"10.1371\/journal.pone.0314000","article-title":"AFCF-Net: a novel U-Net based asymmetric feature calibration and fusion network for skin lesion image segmentation","volume":"19","author":"Ji","year":"2024","journal-title":"PLOS ONE"},{"key":"10.7717\/peerj-cs.3969\/ref-23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/WiSPNET61464.2024.10532992","article-title":"Skin lesion segmentation detection using U-Net architecture","author":"Kamalam","year":"2024"},{"key":"10.7717\/peerj-cs.3969\/ref-24","doi-asserted-by":"publisher","first-page":"134804\u2013134821","DOI":"10.1109\/access.2023.3337528","article-title":"DEU-Net: dual-encoder U-Net for automated skin lesion segmentation","volume":"11","author":"Karimi","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3969\/ref-25","first-page":"106762","article-title":"Multi-scale fusion and residual attention-based CNN for skin lesion classification and segmentation","volume":"157","author":"Khan","year":"2023","journal-title":"Computers in Biology and Medicine"},{"issue":"4","key":"10.7717\/peerj-cs.3969\/ref-26","doi-asserted-by":"publisher","first-page":"6287","DOI":"10.1109\/access.2025.3641868","article-title":"SynthraXCoreNet: an interpretable, well-calibrated six-CNN ensemble for dermoscopic skin-lesion classification","volume":"14","author":"Khan","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-27","doi-asserted-by":"publisher","first-page":"12258","DOI":"10.1038\/s41598-024-63093-w","article-title":"Deep-learning-based pelvic automatic segmentation in pelvic fractures","volume":"14","author":"Lee","year":"2024","journal-title":"Scientific Reports"},{"issue":"10","key":"10.7717\/peerj-cs.3969\/ref-28","doi-asserted-by":"publisher","first-page":"102812","DOI":"10.1016\/j.media.2023.102812","article-title":"Transformer-based hybrid U-Net with cross-attention for skin lesion segmentation","volume":"87","author":"Li","year":"2023","journal-title":"Medical Image Analysis"},{"issue":"20","key":"10.7717\/peerj-cs.3969\/ref-29","doi-asserted-by":"publisher","first-page":"108433","DOI":"10.1016\/j.bspc.2025.108433","article-title":"Reliable multi-source contrastive pseudo-labels interaction network for unsupervised skin lesion segmentation","volume":"112","author":"Li","year":"2026","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.7717\/peerj-cs.3969\/ref-30","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017"},{"issue":"9","key":"10.7717\/peerj-cs.3969\/ref-31","doi-asserted-by":"publisher","first-page":"867","DOI":"10.3390\/bioengineering11090867","article-title":"High-precision skin disease diagnosis through deep learning on dermoscopic images","volume":"11","author":"Malik","year":"2024","journal-title":"Bioengineering"},{"key":"10.7717\/peerj-cs.3969\/ref-32","doi-asserted-by":"publisher","first-page":"102073","DOI":"10.1016\/j.artmed.2021.102073","article-title":"Uncertainty-aware temporal self-learning (UATS): semi-supervised learning for segmentation of prostate zones and beyond","volume":"116","author":"Meyer","year":"2021","journal-title":"Artificial Intelligence in Medicine"},{"issue":"35","key":"10.7717\/peerj-cs.3969\/ref-33","doi-asserted-by":"publisher","first-page":"43643","DOI":"10.1007\/s11042-025-20854-7","article-title":"A comprehensive deep learning approach for skin cancer diagnosis: integrating interpretability and advanced techniques","volume":"84","author":"Nambiar","year":"2025","journal-title":"Multimedia Tools and Applications"},{"key":"10.7717\/peerj-cs.3969\/ref-34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.03999","article-title":"Attention U-Net: learning where to look for the pancreas","author":"Oktay","year":"2018"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-35","doi-asserted-by":"publisher","first-page":"37823","DOI":"10.1038\/s41598-025-21783-z","article-title":"A deep learning-based dual-branch framework for automated skin lesion segmentation and classification via dermoscopic images","volume":"15","author":"Owida","year":"2025","journal-title":"Scientific Reports"},{"key":"10.7717\/peerj-cs.3969\/ref-36","doi-asserted-by":"publisher","first-page":"106462","DOI":"10.1016\/j.compbiomed.2022.106462","article-title":"GFANet: gated fusion attention network for skin lesion segmentation","volume":"155","author":"Qiu","year":"2023","journal-title":"Computers in Biology and Medicine"},{"issue":"7","key":"10.7717\/peerj-cs.3969\/ref-37","doi-asserted-by":"publisher","first-page":"701","DOI":"10.3390\/bioengineering11070701","article-title":"Integrating convolutional neural networks with attention mechanisms for magnetic resonance imaging-based classification of brain tumors","volume":"11","author":"Rasheed","year":"2024","journal-title":"Bioengineering"},{"key":"10.7717\/peerj-cs.3969\/ref-38","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","volume":"9351","author":"Ronneberger","year":"2015"},{"issue":"2","key":"10.7717\/peerj-cs.3969\/ref-39","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1109\/iccv.2017.74","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"10.7717\/peerj-cs.3969\/ref-40","doi-asserted-by":"publisher","first-page":"9262","DOI":"10.1038\/s41598-025-94380-9","article-title":"ARCUNet: enhancing skin lesion segmentation with residual convolutions and attention mechanisms for improved accuracy and robustness","volume":"15","author":"Soni","year":"2025","journal-title":"Scientific Reports"},{"issue":"3","key":"10.7717\/peerj-cs.3969\/ref-41","doi-asserted-by":"publisher","first-page":"501","DOI":"10.3390\/diagnostics11030501","article-title":"ASCU-Net: attention gate, spatial and channel attention U-Net for skin lesion segmentation","volume":"11","author":"Tong","year":"2021","journal-title":"Diagnostics"},{"key":"10.7717\/peerj-cs.3969\/ref-42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.04335","article-title":"UCTransNet: rethinking the skip connections in U-Net from a channel-wise perspective with transformer","author":"Wang","year":"2021"},{"issue":"12","key":"10.7717\/peerj-cs.3969\/ref-43","doi-asserted-by":"publisher","first-page":"112306","DOI":"10.1016\/j.engappai.2025.112306","article-title":"Feature-enhanced edge-inverse attention network for skin lesion segmentation","volume":"162","author":"Warambhey","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3969\/ref-44","doi-asserted-by":"publisher","first-page":"100640","DOI":"10.1016\/j.imu.2021.100640","article-title":"Lightweight encoder-decoder model for automatic skin lesion segmentation","volume":"25","author":"Wibowo","year":"2021","journal-title":"Informatics in Medicine Unlocked"},{"issue":"2","key":"10.7717\/peerj-cs.3969\/ref-45","first-page":"1156","article-title":"Attention-guided dual-path U-Net for robust skin lesion segmentation","volume":"43","author":"Xie","year":"2024","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3969\/ref-46","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/ICECE64886.2024.11024876","article-title":"ADTNet: attention-guided U-Net with dynamic CNN and transformers for skin cancer detection","author":"Yeafi","year":"2024"},{"issue":"2","key":"10.7717\/peerj-cs.3969\/ref-47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10278-025-01553-z","article-title":"Performance comparison of machine learning using radiomic features and CNN-based deep learning in benign and malignant classification of vertebral compression fractures using CT scans","volume":"39","author":"Yeom","year":"2025","journal-title":"Journal of Imaging Informatics in Medicine"},{"issue":"24","key":"10.7717\/peerj-cs.3969\/ref-48","doi-asserted-by":"publisher","first-page":"e031321","DOI":"10.1161\/JAHA.123.031321","article-title":"Risk of ischemic heart disease in patients with postpancreatectomy diabetes and pancreatic cancer: a population-based study","volume":"12","author":"Yoo","year":"2023","journal-title":"Journal of the American Heart Association"},{"issue":"9","key":"10.7717\/peerj-cs.3969\/ref-49","doi-asserted-by":"publisher","first-page":"1876","DOI":"10.1109\/TMI.2017.2695227","article-title":"Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance","volume":"36","author":"Yuan","year":"2017","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"2","key":"10.7717\/peerj-cs.3969\/ref-50","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1109\/JBHI.2017.2787487","article-title":"Improving dermoscopic image segmentation with enhanced convolutional-deconvolutional networks","volume":"23","author":"Yuan","year":"2019","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.7717\/peerj-cs.3969\/ref-51","first-page":"3","article-title":"UNet++: a nested U-Net architecture for medical image segmentation","volume":"11045","author":"Zhou","year":"2018"},{"issue":"10","key":"10.7717\/peerj-cs.3969\/ref-52","doi-asserted-by":"publisher","first-page":"2615","DOI":"10.1007\/978-3-030-00889-5_1","article-title":"UNet++: a nested U-Net architecture for medical image segmentation","volume":"38","author":"Zhou","year":"2019","journal-title":"IEEE Transactions on Medical Imaging"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3969.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3969.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3969.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3969.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T08:27:54Z","timestamp":1783326474000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3969"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,6]]},"references-count":52,"alternative-id":["10.7717\/peerj-cs.3969"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3969","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,6]]},"article-number":"e3969"}}