Implementation of Deep Transfer Learning and Explainable AI in Skin Cancer Classification

Muhammad Eky Ramadhan, Junta Zeniarja

Abstract


Kanker kulit merupakan salah satu penyakit yang prevalensinya terus meningkat, khususnya di wilayah dengan paparan sinar ultraviolet (UV) tinggi. Tantangan utama diagnosis kanker kulit terletak pada kemiripan visual antara lesi jinak dan ganas, menyebabkan tingginya tingkat kesalahan diagnosis, bahkan oleh tenaga medis berpengalaman. Pendekatan diagnosis berbasis kecerdasan buatan (AI) saat ini masih dianggap sebagai sistem “black box” karena kurangnya transparansi dalam proses pengambilan keputusan. Studi ini bertujuan untuk mengembangkan sistem klasifikasi kanker kulit berbasis deep transfer learning yang terintegrasi dengan Explainable Artificial Intelligence (XAI). Model pretrained CNN, ResNet101 dan DenseNet201 diterapkan untuk klasifikasi citra dari dataset ISIC2020 dalam dua kelas, yaitu benign dan malignant. Evaluasi kinerja dilakukan menggunakan accuracy, precision, recall, F1-score, confusion matrix, dan kurva ROC. Hasil penelitian menunjukkan bahwa ResNet101 memberikan performa klasifikasi terbaik dengan accuracy 87,00%, AUC 0,943, dan recall 89,6% dalam mendeteksi malignant. Untuk mendukung interpretabilitas, teknik Grad-CAM dan LIME diterapkan untuk visualisasi area penting dalam citra yang menjadi dasar keputusan model. Temuan ini menekankan pendekatan yang menjanjikan untuk mendukung sistem pendukung keputusan medis yang lebih akurat, transparan, dan dapat dijelaskan, khususnya dalam konteks diagnosis kanker kulit.

Keywords


image classification;skin cancer;transfer learning;Grad-CAM;explainable AI

Full Text:

PDF

References


M. N. Alnuaimi et al., “Transfer Learning Empowered Skin Diseases Detection in Children,” CMES - Computer Modeling in Engineering and Sciences, Vol. 141, No. 3, pp. 2609–2623, 2024, doi: 10.32604/cmes.2024.055303.

S. Gondhowiardjo et al., “Five-Year Cancer Epidemiology at the National Referral Hospital: Hospital-based Cancer Registry Data in Indonesia,” JCO Global Oncol, Vol. 7, pp. 190–203, 2021, doi: 10.1200/GO.20.

Y. L. Vechtomova, T. A. Telegina, A. A. Buglak, and M. S. Kritsky, “UV Radiation in dna Damage and Repair Involving Dna-Photolyases and Cryptochromes,” Nov. 01, 2021, MDPI. doi: 10.3390/biomedicines9111564.

R. Dandu, M. Vinayaka Murthy, and Y. B. Ravi Kumar, “Transfer learning for segmentation with hybrid classification to Detect Melanoma Skin Cancer,” Heliyon, Vol. 9, No. 4, Apr. 2023, doi: 10.1016/j.heliyon.2023.e15416.

D. Aharwal, R. Changulani, A. Pathak, and D. Shukla, “Psychiatric Morbidity among Dermatological Patients Attending a Tertiary Care Hospital in Central India,” National Journal of Community Medicine, Vol. 14, No. 7, pp. 440–445, Jul. 2023, doi: 10.55489/njcm.140720232918.

R. Shreberk-Hassidim, S. M. Ostrowski, and D. E. Fisher, “The Complex Interplay between Nevi and Melanoma: Risk Factors and Precursors,” Feb. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/ijms24043541.

P. Spyridonos, G. Gaitanis, A. Likas, and I. Bassukas, “Characterizing malignant melanoma clinically resembling seborrheic keratosis using deep knowledge transfer,” Cancers (Basel), Vol. 13, No. 24, Dec. 2021, doi: 10.3390/cancers13246300.

Y. Zhang, Y. Weng, and J. Lund, “Applications of Explainable Artificial Intelligence in Diagnosis and Surgery,” Feb. 01, 2022, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/diagnostics12020237.

D. F. Santos-Bustos, B. M. Nguyen, and H. E. Espitia, “Towards Automated Eye Cancer Classification via VGG and ResNet Networks Using Transfer Learning,” Engineering Science and Technology, an International Journal, Vol. 35, Nov. 2022, doi: 10.1016/j.jestch.2022.101214.

A. T. Ibrahim, M. Abdullahi, A. F. Donfack Kana, M. T. Mohammed, and I. H. Hassan, “Categorical Classification of Skin Cancer using a Weighted Ensemble of Transfer Learning with Test Time Augmentation,” Data Science and Management, Nov. 2024, doi: 10.1016/j.dsm.2024.10.002.

R. O. Ogundokun et al., “Enhancing Skin Cancer Detection and Classification in Dermoscopic Images through Concatenated MobileNetV2 and Xception Models,” Bioengineering, Vol. 10, No. 8, Aug. 2023, doi: 10.3390/bioengineering10080979.

O. E. Adebayo, B. Chatelain, D. Trucu, and R. Eftimie, “Deep Learning Approaches for the Classification of Keloid Images in the Context of Malignant and Benign Skin Disorders,” Diagnostics, Vol. 15, No. 6, Mar. 2025, doi: 10.3390/diagnostics15060710.

P. N. Hai, N. C. Thanh, N. T. Trung, and T. T. Kien, “Transfer Learning for Disease Diagnosis from Myocardial Perfusion SPECT Imaging,” Computers, Materials and Continua, Vol. 73, No. 3, pp. 5925–5941, 2022, doi: 10.32604/cmc.2022.031027.

K. M. Adnan et al., “Deep Learning Driven Interpretable and Informed Decision Making Model for Brain Tumour Prediction using Explainable AI,” Sci Rep, Vol. 15, No. 1, Dec. 2025, doi: 10.1038/s41598-025-03358-0.

S. Alkhalaf et al., “Adaptive Aquila Optimizer with Explainable Artificial Intelligence-Enabled Cancer Diagnosis on Medical Imaging,” Cancers (Basel), Vol. 15, No. 5, Mar. 2023, doi: 10.3390/cancers15051492.

A. Gramegna and P. Giudici, “SHAP and LIME: An Evaluation of Discriminative Power in Credit Risk,” Front Artif Intell, Vol. 4, 2021, doi: 10.3389/frai.2021.752558.

S. Khiat, S. A. Mahmoudi, S. Stassin, L. Boukerroui, B. Senaï, and S. Mahmoudi, “An Efficient Explainability of Deep Models on Medical Images,” Algorithms, Vol. 18, No. 4, Apr. 2025, doi: 10.3390/a18040210.

S. Jain, U. Singhania, B. Tripathy, E. A. Nasr, M. K. Aboudaif, and A. K. Kamrani, “Deep Learning-based Transfer Learning for Classification of Skin Cancer,” Sensors, Vol. 21, No. 23, Dec. 2021, doi: 10.3390/s21238142.

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,” Diagnostics, Vol. 14, No. 19, Oct. 2024, doi: 10.3390/diagnostics14192242.

S. M. Thwin and H. S. Park, “Skin Lesion Classification using a Deep Ensemble Model,” Applied Sciences (Switzerland), Vol. 14, No. 13, Jul. 2024, doi: 10.3390/app14135599.

A. Alrabai, A. Echtioui, and F. Kallel, “Exploring Pre-Trained Models for Skin Cancer Classification,” Applied System Innovation, Vol. 8, No. 2, Apr. 2025, doi: 10.3390/asi8020035.

M. A. Khan et al., “COVID-19 Classification from Chest X-Ray Images: A Framework of Deep Explainable Artificial Intelligence,” Comput Intell Neurosci, Vol. 2022, 2022, doi: 10.1155/2022/4254631.

Luqman Hakim, Z. Sari, and H. Handhajani, “Klasifikasi Citra Pigmen Kanker Kulit Menggunakan Convolutional Neural Network,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), Vol. 5, No. 2, pp. 379–385, Apr. 2021, doi: 10.29207/resti.v5i2.3001.

K. Maharana, S. Mondal, and B. Nemade, “A review: Data pre-Processing and Data Augmentation Techniques,” Global Transitions Proceedings, Vol. 3, No. 1, pp. 91–99, Jun. 2022, doi: 10.1016/j.gltp.2022.04.020.

Y. Shu, J. Zhang, Y. Wang, and Y. Wei, “Fruit Freshness Classification and Detection Based on the ResNet-101 Network and Non-Local Attention Mechanism,” Foods, Vol. 14, no. 11, p. 1987, Jun. 2025, doi: 10.3390/foods14111987.




DOI: https://doi.org/10.32520/stmsi.v14i5.5425

Article Metrics

Abstract view : 125 times
PDF - 56 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.