International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Comprehensive Survey on Deep Learning Techniques for Skin Cancer Segmentation and Classification |
|---|---|
| ABSTRACT | Skin cancer, particularly melanoma, poses a significant global health challenge due to its rapid progression and high mortality rate if not detected early. Recent advancements in deep learning have enabled automated systems for accurate segmentation and classification of skin lesions. This survey presents a comprehensive review of 39 recent research studies focusing on deep learning techniques for skin cancer detection. The paper analyzes methodologies including convolutional neural networks, transformer-based models, hybrid architectures, and ensemble learning. Additionally, it evaluates performance using metrics such as accuracy, precision, recall, F1-score, and AUC. The study highlights dataset usage, preprocessing techniques, segmentation strategies, classification models, and explainability methods. Finally, key challenges, limitations, and future research directions are discussed to guide the development of robust and clinically applicable diagnostic systems. |
| AUTHOR | JADHAV HANMANT BALU, PROF. DR. S. A. ITKAR Department of Computer Engineering, P. E. S. Modern College of Engineering, Affiliated to Savitribai Phule Pune University (SPPU), Pune, India HOD, Department of Computer Engineering, P. E. S. Modern College of Engineering, Affiliated to Savitribai Phule Pune University (SPPU), Pune, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404141 |
| pdf/141_A Comprehensive Survey on Deep Learning Techniques for Skin Cancer Segmentation and Classification.pdf | |
| KEYWORDS | |
| References | [1] E. Farea et al., “A hybrid deep learning skin cancer prediction framework,” 2024. [2] F. Ullah et al., “Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images,” IEEE Access, 2024. [3] R. Karthik et al., “A Hybrid Deep Learning Approach for Skin Cancer Classification Using Swin Transformer and Dense Group Shuffle Non-Local Attention Network,” IEEE Access, 2024. [4] Z. Ji et al., “EFAM-Net: A Multi-Class Skin Lesion Classification Model Utilizing Enhanced Feature Fusion and Attention Mechanisms,” IEEE Access, 2024. [5] S. Chatterjee et al., “Early Detection of Multiclass Skin Lesions Using Transfer Learning-Based IncepX-Ensemble Model,” IEEE Access, 2024. [6] M. I. Faizi and S. M. Adnan, “Improved Segmentation Model for Melanoma Lesion Detection Using Normalized Cross-Correlation-Based k-Means Clustering,” IEEE Access, 2024. [7] M. I. Marie et al., “A Hybrid Model for Early Melanoma Detection: Integrating YOLOv9 and Faster R-CNN,” IEEE Access, 2025. [8] J. S. T. Purni and R. Vedhapriyavadhana, “EOSA-Net: A Deep Learning Framework for Enhanced Multi-Class Skin Cancer Classification,” 2024. [9] W. Gouda et al., “Detection of Skin Cancer Based on Skin Lesion Images Using Deep Learning,” 2023. [10] M. A. Albahar, “Skin Lesion Classification Using CNN With Novel Regularizer,” IEEE Access, 2023. [11] A. Naeem et al., “Malignant Melanoma Classification Using Deep Learning,” IEEE Access, 2023. [12] A. A. Adegun and S. Viriri, “FCN-Based DenseNet Framework for Automated Detection and Classification of Skin Lesions,” IEEE Access, 2023. [13] G. Wang et al., “Multi-Scale DCNN With Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion Diagnosis,” IEEE Access, 2024. [14] V. S. Narayanan et al., “IARS SegNet: Interpretable Attention Residual Skip Connection SegNet for Melanoma Segmentation,” IEEE Access, 2024. [15] V. S. S. B. T. Sathvika et al., “Pipelined Structure in Skin Lesion Classification Based on AlexNet CNN and SVM,” IEEE Access, 2024. [16] R. Mittal et al., “DermCDSM: Clinical Decision Support Model for Dermatosis,” IEEE Access, 2024. [17] X. Qian et al., “SPCB-Net: A Multi-Scale Skin Cancer Image Identification Network,” IEEE Access, 2023. [18] T. Kim et al., “Toward Better Ear Disease Diagnosis,” IEEE Access, 2023. [19] H. L. Gururaj et al., “DeepSkin: A Deep Learning Approach for Skin Cancer Classification,” IEEE Access, 2023. [20] K. Mridha et al., “An Interpretable Skin Cancer Classification Using Optimized CNN,” IEEE Access, 2023. [21] L. Riaz et al., “A Comprehensive Joint Learning System to Detect Skin Cancer,” IEEE Access, 2023. [22] A. Magdy et al., “Performance Enhancement of Skin Cancer Classification Using Computer Vision,” IEEE Access, 2023. [23] A. Imran et al., “Skin Cancer Detection Using Combined Decision of Deep Learners,” IEEE Access, 2022. [24] A. Gong et al., “Classification for Dermoscopy Images Using CNN Ensemble,” IEEE Access, 2020. [25] P. M. M. Pereira et al., “Multiple Instance Learning Using 3D Features for Melanoma Detection,” IEEE Access, 2022. [26] E. S. Flores and J. Scharcanski, “Skin Lesion Segmentation in Clinical Images Using NMF,” IEEE Access, 2025. [27] A. D. Khalaf et al., “Segmentation and Classification of Skin Cancer Diseases Based on Deep Learning,” IEEE Access, 2025. [28] DeepSkin: A Deep Learning Approach for Skin Cancer Classification. [29] An Interpretable Skin Cancer Classification Using Optimized CNN. [30] A Comprehensive Joint Learning System to Detect Skin Cancer. [31] Performance Enhancement of Skin Cancer Classification Using Computer Vision. [32] Skin Cancer Detection Using Combined Decision of Deep Learners. [33] Hybrid Model for Early Melanoma Detection Integrating YOLOv9 and Faster R-CNN. [34] Improved Segmentation Model for Melanoma Lesion Detection Using k-Means. [35] EFAM-Net: Multi-Class Skin Lesion Classification. [36] Early Detection of Multiclass Skin Lesions Using Transfer Learning. [37] Hybrid Deep Learning Using Swin Transformer and Shuffle Attention. [38] Quantum Chebyshev Feature Extraction for Skin Lesion Classification. [39] Multi-Scale DCNN With Dynamic Weight for Skin Lesion Diagnosis. |
