Lightweight Explainable and Reliable Deep Learning for Multiclass Skin Lesion ClassificationA Systematic Review of Metadata Fusion Class Imbalance Calibration and Leakage Safe Evaluation
DOI:
https://doi.org/10.68307/z27de086Keywords:
Skin lesion classification, dermoscopy, lightweight deep learning, metadata fusion, class imbalance, explainable artificial intelligence, calibration, data leakage, systematic reviewAbstract
Deep learning has improved automated skin lesion classification while practical clinical research still requires efficient models reliable confidence estimates interpretable predictions and evaluation designs that prevent information leakage; therefore this review examines lightweight architectures patient metadata fusion class imbalance strategies explainable artificial intelligence probability calibration and lesion grouped validation within multiclass dermoscopic classification; the review protocol covers major scientific databases with structured screening and evidence extraction while the current evidence map contains 68 deduplicated seed records with 30 priority studies and 29 completed abstract level extractions; preliminary synthesis shows rapid progress in convolutional and transformer models although direct comparison remains limited by inconsistent datasets split units class definitions metrics and reporting practices; moreover calibration and quantitative explanation assessment appear less common than accuracy reporting while lesion or patient grouped splitting is not always stated clearly; consequently future studies should combine class sensitive metrics transparent split governance calibration analysis explanation validation and measured computational efficiency within one reproducible protocol.
References
[1] A Esteva et al Dermatologist level classification of skin cancer with deep neural networks Nature vol 542 pp 115 to 118 2017
[2] H A Haenssle et al Man against machine diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists Annals of Oncology vol 29 no 8 pp 1836 to 1842 2018
[3] P Tschandl C Rosendahl and H Kittler The HAM10000 dataset a large collection of multisource dermatoscopic images of common pigmented skin lesions Scientific Data vol 5 article 180161 2018
[4] Z Hu W Mei H Chen and W Hou Multi scale feature fusion and class weight loss for skin lesion classification 2024
[5] D P Yadav et al Dual scale lightweight cross attention transformer for skin lesion classification 2024
[6] R R Selvaraju et al Grad CAM visual explanations from deep networks via gradient based localization in Proceedings of the IEEE International Conference on Computer Vision 2017
[7] C Guo G Pleiss Y Sun and K Q Weinberger On calibration of modern neural networks in Proceedings of the International Conference on Machine Learning 2017
[8] Z Li et al Artificial intelligence in dermatology image analysis current developments and future trends Journal of Clinical Medicine 2022
[9] N Melarkode K Srinivasan S M Qaisar and P Plawiak AI powered diagnosis of skin cancer a contemporary review open challenges and future research directions Cancers 2023
[10] B C R S Furriel et al Artificial intelligence for skin cancer detection and classification for clinical environment a systematic review 2024
[11] M J Page et al The PRISMA 2020 statement an updated guideline for reporting systematic reviews BMJ vol 372 2021
[12] P Tschandl et al Human computer collaboration for skin cancer recognition Nature Medicine vol 26 pp 1229 to 1234 2020
[13] A Howard et al Searching for MobileNetV3 in Proceedings of the IEEE International Conference on Computer Vision 2019
[14] M Tan and Q V Le EfficientNet rethinking model scaling for convolutional neural networks in Proceedings of the International Conference on Machine Learning 2019
[15] Y Nie P Sommella M Carratu M O Nils and J Lundgren A deep CNN transformer hybrid model for skin lesion classification of dermoscopic images using focal loss 2022
[16] M A Pavel et al Multi stage knowledge distillation with layer fusion based deep learning approach for skin cancer classification 2025
[17] M A Javaid et al DSSCC Net enhanced skin cancer classification using SMOTE Tomek and optimized convolutional neural network 2025
[18] B Van Calster et al Calibration the Achilles heel of predictive analytics BMC Medicine vol 17 article 230 2019
[19] C Hernandez Perez et al BCN20000 dermoscopic lesions in the wild Scientific Data 2024 doi 10.1038/s41597-024-03387-w
[20] Y Liu et al A deep learning system for differential diagnosis of skin diseases Nature Medicine vol 26 pp 900 to 908 2020
[21] R H Patel E A Foltz A Witkowski and J Ludzik Analysis of artificial intelligence based approaches applied to non invasive imaging for early detection of melanoma a systematic review 2023
[22] M Mateen S Hayat F Arshad Y H Gu and M A Al Antari Hybrid deep learning framework for melanoma diagnosis using dermoscopic medical images 2024
[23] S Bibi et al MSRNet multiclass skin lesion recognition using additional residual block based fine tuned deep models information fusion and best feature selection 2023
[24] A Naeem and T Anees DVFNet a deep feature fusion based model for the multiclassification of skin cancer utilizing dermoscopy images 2024
[25] H Cheng J Lian and W Jiao Enhanced MobileNet for skin cancer image classification with fused spatial channel attention mechanism 2024
[26] S Bakheet S Alsubai A El Nagar and A Alqahtani A multi feature fusion framework for automatic skin cancer diagnostics 2023
[27] A H Efat S M Hasan M P Uddin and M Mamun A multi level ensemble approach for skin lesion classification using customized transfer learning with triple attention 2024
[28] M Hussain et al SkinNet INIO multiclass skin lesion localization and classification using fusion assisted deep neural networks and improved nature inspired optimization algorithm 2023
[29] M Azeem K Kiani T Mansouri and N Topping SkinLesNet classification of skin lesions and detection of melanoma cancer using a novel multilayer deep convolutional neural network 2023
[30] A Ray F Sarkar F Schwenker and R Sarkar Decoding skin cancer classification perspectives insights and advances through researchers lens 2024
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mr. Baibhav Tiwari
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies (IJAICET) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Under this license, users are free to share, copy, redistribute, adapt, and build upon the published material for any purpose, including commercial use, provided appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.
Authors retain copyright of their work while granting IJAICET the right to publish, archive, distribute, and index the article. The journal supports the free exchange of scientific knowledge through open access publishing and encourages the widest possible dissemination of research.
