{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:51:17Z","timestamp":1790790677850,"version":"4.1.0"},"reference-count":67,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Early recognition of skin lesions, including diverse abnormalities and life-threatening skin cancers, is critical for effective treatment and improved clinical outcomes. However, existing skin lesion datasets exhibit significant class imbalance, and there is no standardized guideline for optimal data augmentation strategies. This study aims to establish a robust and interpretable framework that addresses these limitations while enhancing diagnostic performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We propose a novel transfer learning-based framework termed\n                      <jats:italic toggle=\"yes\">Tri-Path Attention Stacked Ensemble (TASE)<\/jats:italic>\n                      , which integrates multiple EfficientNetV2 backbones through three distinct stacking strategies: TASE: Independent TA, TASE: Serial Stacked TA, and TASE: Parallel Stacked TA. Here,\n                      <jats:italic toggle=\"yes\">TA<\/jats:italic>\n                      refers to the Triple-Attention mechanism, comprising soft attention integration, channel attention integration, and squeeze-excitation attention integration. To optimize ensemble prediction fusion, we introduce an advanced aggregation method\u2014\n                      <jats:italic toggle=\"yes\">Cohen\u2019s Kappa Proportioned Averaging (CKPA)<\/jats:italic>\n                      \u2014which is further extended into a\n                      <jats:italic toggle=\"yes\">Multi-Layer CKPA (ML-CKPA)<\/jats:italic>\n                      framework to enhance weight distribution across hierarchical model outputs. Additionally, four augmentation strategies were systematically evaluated to determine the most effective ensemble configuration.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental validation on the HAM10000 dataset demonstrated that the proposed framework achieved a superior accuracy of 94.44%, outperforming several state-of-the-art methods. Grad-CAM visualizations were employed to enhance interpretability by highlighting lesion-relevant regions, thereby improving model transparency and reliability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed TASE framework delivers enhanced diagnostic accuracy while effectively mitigating challenges related to class imbalance, dataset variability, and computational efficiency. By combining hierarchical triple-attention mechanisms with multi-layer ensemble weighting, it offers a reliable and interpretable solution for early and precise skin lesion classification, supporting real-world dermatological applications and improved patient care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261462026","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T23:39:03Z","timestamp":1781653143000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing skin lesion classification using a Tri-Path Attention Stacked Ensemble architecture with Cohen\u2019s Kappa Proportioned Averaging"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8828-4272","authenticated-orcid":false,"given":"Md. Shifaul","family":"Hasan","sequence":"first","affiliation":[{"name":"IUBAT - International University of Business Agriculture and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7999-1512","authenticated-orcid":false,"given":"Anwar Hossain","family":"Efat","sequence":"additional","affiliation":[{"name":"IUBAT - International University of Business Agriculture and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7673-1102","authenticated-orcid":false,"given":"Jubaer Ahamed","family":"Bhuiyan","sequence":"additional","affiliation":[{"name":"IUBAT - International University of Business Agriculture and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faniyam Maria","family":"Mansia","sequence":"additional","affiliation":[{"name":"IUBAT - International University of Business Agriculture and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"e_1_3_9_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13193063"},{"key":"e_1_3_9_3_2","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12267"},{"key":"e_1_3_9_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13182869"},{"key":"e_1_3_9_5_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0309430"},{"key":"e_1_3_9_6_2","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1151257"},{"key":"e_1_3_9_7_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13071285"},{"key":"e_1_3_9_8_2","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241312936"},{"key":"e_1_3_9_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fraope.2026.100546"},{"key":"e_1_3_9_10_2","first-page":"225","volume-title":"International conference on trends in electronics and health informatics","author":"Montashir FA","year":"2024","unstructured":"Montashir FA, Efat AH, Mahedy Hasan S, et al. Tri focus net: A cnn-based model with integrated attention modules for pest and insect detection in agriculture. In: International conference on trends in electronics and health informatics. Springer, 2024, pp. 225\u2013240."},{"key":"e_1_3_9_11_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0321803"},{"key":"e_1_3_9_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2026.3657954"},{"key":"e_1_3_9_13_2","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/5146543"},{"key":"e_1_3_9_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105475"},{"key":"e_1_3_9_15_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0284437"},{"key":"e_1_3_9_16_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0217293"},{"key":"e_1_3_9_17_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22124399"},{"key":"e_1_3_9_18_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0295151"},{"key":"e_1_3_9_19_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0277578"},{"key":"e_1_3_9_20_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13010072"},{"key":"e_1_3_9_21_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0276836"},{"key":"e_1_3_9_22_2","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22863"},{"key":"e_1_3_9_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/app12199545"},{"key":"e_1_3_9_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMPAS60761.2024.10796988"},{"key":"e_1_3_9_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICISET62123.2024.10941566"},{"key":"e_1_3_9_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/PEEIACON63629.2024.10800672"},{"key":"e_1_3_9_27_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22197530"},{"key":"e_1_3_9_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87444-5_2"},{"key":"e_1_3_9_29_2","first-page":"1183","volume-title":"Healthcare","author":"Gouda W","year":"2022","unstructured":"Gouda W, Sama NU, Al-Waakid G et al. Detection of skin cancer based on skin lesion images using deep learning. In: Healthcare. MDPI, 2022, Vol. 10, p. 1183."},{"key":"e_1_3_9_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-08084-6"},{"key":"e_1_3_9_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100659"},{"key":"e_1_3_9_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/PEEIACON63629.2024.10800046"},{"key":"e_1_3_9_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/PEEIACON63629.2024.10800647"},{"key":"e_1_3_9_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/PEEIACON63629.2024.10800726"},{"key":"e_1_3_9_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICISET62123.2024.10939426"},{"key":"e_1_3_9_36_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6673852"},{"key":"e_1_3_9_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-4520-6_11"},{"key":"e_1_3_9_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3543028"},{"key":"e_1_3_9_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2025.104168"},{"key":"e_1_3_9_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-025-10973-5"},{"key":"e_1_3_9_41_2","doi-asserted-by":"publisher","DOI":"10.24815\/jpsi.v13i2.44826"},{"issue":"2","key":"e_1_3_9_42_2","article-title":"Explainable transformer framework for fast cotton leaf diagnostics and fabric defect detection","volume":"29","author":"Swapno SMR","year":"2026","unstructured":"Swapno SMR, Sakib A, Hossain A, et al. Explainable transformer framework for fast cotton leaf diagnostics and fabric defect detection. Iscience 2026; 29(2).","journal-title":"Iscience"},{"key":"e_1_3_9_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2025.114605"},{"key":"e_1_3_9_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2025.101706"},{"key":"e_1_3_9_45_2","first-page":"485","volume-title":"International Conference on Trends in Electronics and Health Informatics","author":"Bappi MBR","year":"2024","unstructured":"Bappi MBR, Swapno SMR, Rabbi MF. Deploying densenet for cotton leaf disease detection on deep learning. In: International Conference on Trends in Electronics and Health Informatics. Springer, 2024, pp. 485\u2013498."},{"key":"e_1_3_9_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2025.101657"},{"key":"e_1_3_9_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2025.101669"},{"key":"e_1_3_9_48_2","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12060651"},{"key":"e_1_3_9_49_2","doi-asserted-by":"publisher","DOI":"10.1177\/20552076261433750"},{"key":"e_1_3_9_50_2","doi-asserted-by":"crossref","unstructured":"Tschandl P Rosendahl C Kittler H. The ham10000 dataset a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data 2018; 5(1): 1\u20139. https:\/\/doi.org\/10.1038\/sdata.2018.161","DOI":"10.1038\/sdata.2018.161"},{"key":"e_1_3_9_51_2","unstructured":"Ham10000: Split and augmented. https:\/\/www.kaggle.com\/datasets\/ahefatresearch\/ham10000-split-and-augmented. [Online; accessed 2026-02-12]."},{"key":"e_1_3_9_52_2","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241309947"},{"key":"e_1_3_9_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT60459.2023.10441290"},{"key":"e_1_3_9_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT60459.2023.10441171"},{"key":"e_1_3_9_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT64611.2024.11021776"},{"key":"e_1_3_9_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT60459.2023.10440975"},{"key":"e_1_3_9_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT60459.2023.10441280"},{"key":"e_1_3_9_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICISET62123.2024.10939433"},{"key":"e_1_3_9_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT64611.2024.11021788"},{"key":"e_1_3_9_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMI65310.2025.11141266"},{"key":"e_1_3_9_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICECTE57896.2022.10114543"},{"key":"e_1_3_9_62_2","first-page":"407","volume-title":"International conference on trends in electronics and health informatics","author":"Hossain Efat A","year":"2026","unstructured":"Hossain Efat A, Faysal Ferdous S, Islam Nayem S, et al. From data to diagnosis: a journey with machine learning, hyperparameter tuning, and ensemble learning for disease prognostication. In: International conference on trends in electronics and health informatics. Springer, 2026, pp. 407\u2013420."},{"key":"e_1_3_9_63_2","first-page":"341","volume-title":"International Conference on Trends in Electronics and Health Informatics","author":"Ferdous SF","year":"2023","unstructured":"Ferdous SF, Efat AH. Unlocking insights in healthcare: A comparative study of hyperparameter tuned machine learning algorithms. In: International Conference on Trends in Electronics and Health Informatics. Springer, 2023, pp. 341\u2013356."},{"key":"e_1_3_9_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05929-4"},{"key":"e_1_3_9_65_2","doi-asserted-by":"publisher","DOI":"10.3390\/app12052677"},{"key":"e_1_3_9_66_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102041"},{"key":"e_1_3_9_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3217217"},{"key":"e_1_3_9_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2020.106956"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261462026","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261462026","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261462026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T06:16:47Z","timestamp":1781849807000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261462026"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":67,"alternative-id":["10.1177\/20552076261462026"],"URL":"https:\/\/doi.org\/10.1177\/20552076261462026","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261462026"}}