Repository logo
  • English
  • 中文
  • Log In
    New user? Click here to register.Have you forgotten your password?
Repository logo
    Communities & Collections
    Research Outputs
    Fundings & Projects
    People
    Organizations
    Statistics
  • English
  • 中文
  • Log In
    New user? Click here to register.Have you forgotten your password?
  1. Home
  2. Chung Shan Medical University
  3. Pure學術人才庫轉入
  4. Ensemble Artificial Intelligence for Dermoscopic Decision Support
 
  • Details
Options

Ensemble Artificial Intelligence for Dermoscopic Decision Support

Other Title
Development and External Validation of the HAM20000 Dataset
Journal
Electronics (Switzerland)
Date Issued
2026-06-01
Author(s)
MING-HSENG TSENG  
DOI
10.3390/electronics15112367
URI
https://www.scopus.com/pages/publications/105041381416
https://scholars.csmu.edu.tw/handle/123456789/23215
Abstract
Artificial intelligence (AI) has shown strong potential in dermoscopic image classification; however, reliable clinical deployment remains challenging due to limited generalizability across populations and institutions. This challenge is further compounded by the performance saturation of single models: continued architectural scaling often results in diminishing returns within the training domain and fails to yield corresponding gains in cross-domain robustness. Previous work often relies on a single benchmark dataset and evaluate models under matched data distributions, which can overestimate real-world performance. In this study, we examine the robustness and generalizability of dermoscopic AI systems under realistic deployment conditions. We curate HAM20000, a controlled expansion of the HAM10000 dataset integrating multiple public ISIC releases from 2017 to 2024, designed as a stress-test dataset to analyze performance saturation and architectural sensitivity. A total of 27 pretrained deep learning models, including convolutional neural networks, Vision Transformers, and hybrid CNN–Transformer architectures, were systematically evaluated. To mitigate the limitations of single-model optimization, we applied greedy ensemble selection to construct a compact heterogeneous ensemble using soft voting. All models were trained and selected exclusively on HAM20000 and evaluated under strict zero-shot external validation on two independent datasets: CSMUH (East Asian population) and BCN20000 (European cohort). Although the proposed ensemble achieved over 93% accuracy on the HAM20000 dataset, its performance declined substantially under external validation, highlighting a pronounced cross-population domain gap. On the BCN20000 external validation set, the ensemble reached 62% accuracy, outperforming the strongest individual model (59%) by 3%. On the CSMUH external validation set, the proposed GES achieved an accuracy of approximately 57%, demonstrating improved performance over representative single-model baselines, although it did not exceed the best-performing individual architecture in this dataset. These results indicate that, despite a marked absolute performance drop under distribution shift, the ensemble provides a modest yet consistent improvement over single-model baselines rather than a substantial performance leap. This finding underscores the importance of rigorous external validation and suggests that heterogeneous ensemble learning represents a practical and promising strategy for achieving incremental robustness gains in clinically applicable dermoscopic decision support systems.
Type
journal article
Make it your own

DSpace-CRIS can be extensively configured to meet your needs. Decide which information need to be collected and available with fine-grained security. Start updating the theme to match your Institution's web identity.

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Cookie settings
  • Privacy policy
  • End User Agreement
  • Send Feedback