EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable Skin Cancer Identification Using a Hybrid Deep Learning and XAI Framework on HAM10000

Bhagyashri S Sonune, R Udaya Kumar, K Sankar iD, Puja S Agrawal iD, Shon G Nemane iD, Dhiraj P Tulaskar iD, Manish Bhaiyya, Madhusudan B Kulkarni iD

Bioengineering · 11.06.2026 · 13 (6) · 677

DOI: 10.3390/bioengineering13060677 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 11.06.2026. Verfasst von Bhagyashri S Sonune und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Kalinga University, Raipur 492101, Chhattisgarh, India. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning-based automated classification of dermatoscopic skin lesions has exhibited promising potential in diagnostics. However, two prominent issues need to be addressed before achieving high-quality diagnostic tools: inconsistent performance in the case of imbalanced classes and poor clinical interpretability of models. Even though some studies have attempted to leverage both deep and shallow learning by combining pretrained convolutional neural networks (CNNs)-based feature extraction with classical machine learning (ML) models, very few of them systematically explore several model combinations based on various clinically important metrics, such as F1-score, precision, recall, accuracy, etc., and utilize decision threshold calibration techniques. In this research, we present an evaluation of a systematic framework with threshold calibration for the comparison of several hybrid models on seven-class skin lesion classification (multi-class) on the HAM10000 dataset. In particular, we used deep features extracted from three pretrained CNN architectures, i.e., DenseNet201, InceptionV3 and EfficientNet-B4. These deep features were used as inputs for six different classical classifiers. As a result, we obtained 18 comparable hybrid models that were then systematically compared by multiple clinically relevant metrics: accuracy, macro-precision, macro-recall, macro-F1, ROC-AUC, Precision-Recall-AUC, and log loss. Also, fold-wise optimization of decision thresholds was performed, which was based on the maximization of the macro-F1 score. Finally, we found out that DenseNet201 with an SVM-RBF classifier yielded the highest performance among all 18 tested models, showing 90.88% accuracy, 90.7% macro-precision, and 0.921 ROC-AUC. To analyze the clinical plausibility, top-performing models were further explained with explainable artificial intelligence (XAI) techniques: Grad-CAM, LIME and Occlusion Sensitivity. Results show that the most successful models concentrated mostly on lesion-specific areas. Overall, this study contributes a reproducible hybrid-XAI model-selection framework rather than a single black-box classifier, supporting more transparent and clinically meaningful skin lesion diagnosis.

Schlagwörter

Stichwörter der Autor:innen

cancer detectionconvolutional neural networks (CNNs)deep learning (DL)explainable artificial intelligence (XAI)image analysismachine learning (ML)skin lesion classification

Autor:innen und Institutionen

  • Department of Computer Science, Kalinga University, Raipur 492101, Chhattisgarh, India.
  • Department of Artificial Intelligence and Data Science, Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College, Avadi, Chennai 600062, Tamil Nadu, India.
  • Department of Electronics and Communication Engineering, School of Electrical and Electronics Engineering, Ramdeobaba University, Nagpur 440013, Maharashtra, India.
  • Department of Electronics and Telecommunication Engineering, Shri Sant Gajanan Maharaj College of Engineering, Shegaon 444203, Maharashtra, India.
  • Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal 576104, Karnataka, India.

ORCID-Profile: K Sankar, Puja S Agrawal, Shon G Nemane, Dhiraj P Tulaskar, Madhusudan B Kulkarni

Zitieren

APA

Sonune, B. S., Kumar, R. U., Sankar, K., Agrawal, P. S., Nemane, S. G., Tulaskar, D. P., Bhaiyya, M., & Kulkarni, M. B. (2026). Interpretable Skin Cancer Identification Using a Hybrid Deep Learning and XAI Framework on HAM10000. Bioengineering, 13(6), 677. https://doi.org/10.3390/bioengineering13060677

Vancouver

Sonune BS, Kumar RU, Sankar K, Agrawal PS, Nemane SG, Tulaskar DP, et al. Interpretable Skin Cancer Identification Using a Hybrid Deep Learning and XAI Framework on HAM10000. Bioengineering. 2026;13(6):677. doi:10.3390/bioengineering13060677

BibTeX
@article{Sonune2026,
  author = {Sonune, Bhagyashri S and Kumar, R Udaya and Sankar, K and Agrawal, Puja S and Nemane, Shon G and Tulaskar, Dhiraj P and Bhaiyya, Manish and Kulkarni, Madhusudan B},
  title = {Interpretable Skin Cancer Identification Using a Hybrid Deep Learning and XAI Framework on HAM10000},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {6},
  pages = {677},
  doi = {10.3390/bioengineering13060677}
}
Kostenlos starten →