Apurva S. Shinde; Sangita S. Chaudhari

DS-MelNet: An Enhanced Dual Stream Semi-Supervised Mechanism for Melanoma Classification

PDF (1376KB), PP.110-132

Views: 0 Downloads: 0

Author(s)

Apurva S. Shinde ^1,* Sangita S. Chaudhari ²

1. Ramrao Adik Institute of Technology, D Y Patil Deemed to be University, Computer Engineering Department, Navi Mumbai, 400706, India

2. Ramrao Adik Institute of Technology, D Y Patil Deemed to be University, Computer Science Engineering Department, Navi Mumbai, 400706, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2026.03.06

Received: 8 Jul. 2025 / Revised: 20 Sep. 2025 / Accepted: 18 Dec. 2025 / Published: 8 Jun. 2026

Index Terms

Convolutional Neural Network, Dermatological Diagnostics, Melanoma Detection, Semi-Supervised Learning, VGG-16 Architecture

Abstract

Melanoma skin disease is a major concern for skin cancer-related deaths worldwide. Early diagnosis and detection are crucial for improving patient outcomes. However, existing detection methods often result in false alarms, highlighting the need for more accurate and reliable approaches. This paper proposes a Dual-Stream Semi-Supervised Melanoma Network (DS-MelNet) for melanoma detection. The DS-MelNet utilizes a semi-supervised learning framework to incorporate both labeled and unlabeled data, enhancing detection accuracy. The model's performance is evaluated on the SIIM-ISIC Melanoma Classification Challenge dataset. The dataset undergoes hair detection and removal from skin lesion images using three algorithms proposed in literature viz. Modified Dull Razor, Modified E-shaver and Adaptive principle curvature with Modified dull razor fusion. Performance of the proposed models is assessed through commonly used metrics that include Accuracy, Recall, Precision, and F1-score. Comparative analysis of the DS-MelNet is performed against two benchmarks: Simple Convolutional Neural Network (SCNN) and a Fine-tuned VGG-16 model proposed in this paper. The results clearly indicate that the DS-MelNet demonstrates superior performance, achieving an accuracy of 86% and outperforming both SCNN (76%) and VGG-16 (82%) models. This exceptional performance underscores the potential of the DS-MelNet for effective melanoma classification. The study highlights the promise of semi-supervised learning frameworks and sophisticated neural networks in enhancing melanoma diagnostics. The ability of the proposed model to learn from a small set of labeled data makes it highly suitable for real-world applications where annotated datasets are limited.

Cite This Paper

Apurva S. Shinde, Sangita S. Chaudhari, "DS-MelNet: An Enhanced Dual Stream Semi-Supervised Mechanism for Melanoma Classification", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.3, pp. 110-132, 2026. DOI:10.5815/ijigsp.2026.03.06

Reference

[1]Labani, S., Asthana, S., & Jain, M., “Incidence of melanoma and other skin cancers in India,” Asian Pacific Journal of Cancer Prevention, vol. 21, no. 3, pp. 707–712, 2020.
[2]Halladja, M., et al., “Impact of delayed diagnosis on melanoma outcomes,” European Journal of Dermatology, vol. 35, no. 1, pp. 45–53, 2025.
[3]Yang, J., Sun, J., & Li, Y., “Sampling-based dermoscopic image analysis for melanoma detection,” Computerized Medical Imaging and Graphics, vol. 75, pp. 23–32, 2019.
[4]Huang, C., et al., “Skin lesion analysis using deep learning techniques,” IEEE Reviews in Biomedical Engineering, vol. 12, pp. 123–137, 2019.
[5]Wang, Z., et al., “Non-invasive image-based techniques for melanoma detection,” Biomedical Signal Processing and Control, vol. 71, 103162, 2022.
[6]Hussein, S., et al., “Binary classification of melanoma using deep learning,” Artificial Intelligence in Medicine, vol. 148, 102745, 2024.
[7]Dakhli, A., et al., “Convolutional neural networks for skin cancer classification,” Expert Systems with Applications, vol. 212, 118657, 2023.
[8]Baykal, B., et al., “CNN-based melanoma detection using dermoscopic images,” Diagnostics, vol. 14, no. 2, p. 180, 2024.
[9]Ngo, T., et al., “Machine learning approaches for melanoma diagnosis,” Computers in Biology and Medicine, vol. 142, 105220, 2022.
[10]Yi, X., et al., “Semi-supervised learning for skin lesion classification,” IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 2, pp. 434–445, 2018.
[11]Oliveira, R. B., Papa, J. P., Pereira, A. S., & Tavares, J. M. R. S., “Computational methods for pigmented skin lesion classification in images: Review and future trends,” Neural Computing and Applications, vol. 27, no. 8, pp. 2101–2117, 2016.
[12]Noroozi, N., et al., “Computer-aided detection of basal cell carcinoma in histopathological images using Z-transform features,” Journal of Medical Imaging and Health Informatics, vol. 6, no. 4, pp. 1060–1066, 2016.
[13]Anas, A., et al., “Skin cancer classification using color and texture features,” International Journal of Computer Applications, vol. 170, no. 3, pp. 1–6, 2017.
[14]Ghahfarrokhi, B. S., et al., “Malignant skin cancer detection using machine learning from dermoscopic images,” Biomedical Signal Processing and Control, vol. 79, 104108, 2023.
[15]Yu, Z., Jiang, X., Zhou, F., Qin, J., Ni, D., Chen, S., Lei, B., & Wang, T., “Melanoma recognition in dermoscopy images via aggregated deep convolutional features,” IEEE Transactions on Biomedical Engineering, vol. 66, no. 4, pp. 1006–1016, 2018.
[16]Daghrir, J., Tlig, L., Bouchouicha, M., & Sayadi, M., “Melanoma skin cancer detection using deep learning and classical machine learning techniques: A hybrid approach,” in Proceedings of the 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), IEEE, pp. 1–5, 2020.
[17]Agarwal, N., Singh, V., & Singh, P., “Semi-supervised learning with GANs for melanoma detection,” in Proceedings of the 6th International Conference on Intelligent Computing and Control Systems (ICICCS), IEEE, pp. 141–147, 2022.
[18]Gajera, H. K., Nayak, D. R., & Zaveri, M. A., “A comprehensive analysis of dermoscopy images for melanoma detection via deep CNN features,” Biomedical Signal Processing and Control, vol. 79, p. 104186, 2023.
[19]Bassel, A., Abdulkareem, A. B., Alyasseri, Z. A. A., Sani, N. S., & Mohammed, H. J., “Automatic malignant and benign skin cancer classification using a hybrid deep learning approach,” Diagnostics, vol. 12, no. 10, p. 2472, 2022.
[20]Tembhurne, J. V., Hebbar, N., Patil, H. Y., & Diwan, T., “Skin cancer detection using ensemble of machine learning and deep learning techniques,” Multimedia Tools and Applications, vol. 82, no. 18, pp. 27501–27524, 2023.
[21]Rotemberg, V., Kurtansky, N., Betz-Stablein, B., Caffery, L., Chousakos, E., Codella, N., Combalia, M., Dusza, S., Guitera, P., Gutman, D., et al., “A patient-centric dataset of images and metadata for identifying melanomas using clinical context,” Scientific Data, vol. 8, no. 1, p. 34, 2021.
[22]Apurva Shinde and Sangita Chaudhari. Statistical analysis of hair detection and removal techniques using dermoscopic images. In International Conference on Computer Vision and Image Processing, pages 402–414. Springer,2022.
[23]Namrata Verma and Pankaj Kumar Mishra. Design of an efficient unet-based transfer learning model for enhancing skin cancer segmentation and classification performance. International Journal of Image, Graphics and Signal Processing, 2025.
[24]Momina Shaheen, Usman Saif, Shahid M Awan, Faizan Ahmad, and Aimen Anum. Classification of images of skin lesion using deep learning. International Journal of Intelligent Systems and Applications, 15(2):23, 2023.
[25]Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang, and Colin Raffel. Fixmatch: Simplifying semi-supervised learning with consistency and confidence, 2020.
[26]Teresa Mendonc¸a, M Celebi, T Mendonca, and J Marques. Ph2: A public database for the analysis of dermoscopic images. Dermoscopy image analysis, 2, 2015.
[27]Rajdeep Kaur and Sukhjeet Kaur Ranade. Du-net+: a fully convolutional neural network architecture for semantic segmentation of skin lesions. Signal, Image and Video Processing, 19(1):152, 2025.
[28]Maryam Tahir, Ahmad Naeem, Hassaan Malik, Jawad Tanveer, Rizwan Ali Naqvi, and Seung-Won Lee. Dscc net: multi-classification deep learning models for diagnosing of skin cancer using dermoscopic images. Cancers, 15(7):2179, 2023.
[29]Hatice Catal Reis, Veysel Turk, Kourosh Khoshelham, and Serhat Kaya. Insinet: a deep convolutional approach to skin cancer detection and segmentation. Medical & Biological Engineering & Computing, pages 1–20, 2022.

International Journal of Image, Graphics and Signal Processing (IJIGSP)