EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Causal Uncertainty-Decomposed Ensemble Learning for Confounding-Aware Skin Cancer Detection in Dermoscopic Images

Mohd Faheem Khan iD, Khurshid Ahmad iD

Diagnostics · 03.08.2026 · 16 (15) · 2453

DOI: 10.3390/diagnostics16152453 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 03.08.2026. Verfasst von Mohd Faheem Khan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biotechnology and Microbiology, Khandelwal College of Management, Science and Technology, M.J.P. Rohilkhand University, Bareilly 243122…. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Automated dermoscopic image analysis can assist research on early skin cancer detection, but deep learning models may learn acquisition-related shortcuts, including terminal hairs, illumination gradients, gel bubbles, shadows and measurement markings. This study evaluates a causal uncertainty-decomposed ensemble (CUDE) for confounding-aware skin-lesion classification within the ISIC 2019 benchmark setting.

Methods

CUDE uses a structured variational autoencoder (SVAE) to impose separate lesion-relevant and acquisition-related nuisance latent heads. Three stochastic latent-space experts are trained on complementary streams and are integrated by a Dirichlet-based fusion module trained with nuisance sampling. The causal graph is used as a modeling prior rather than proof of causal identification.

Results

Using a stratified internal split of the labeled ISIC 2019 training collection, CUDE achieved a balanced accuracy of 89.7% and an AUROC of 0.972. Under the predefined synthetic artifact protocol, CUDE showed a relative performance drop of 5.0%, compared with 9.6% for the deep ensemble. Deferring the 10% most uncertain cases increased non-deferred accuracy from 89.7% to 93.2% and reduced false-negative rates for melanoma, BCC and SCC in the non-deferred subset.

Conclusions

Within the evaluated ISIC 2019 split and controlled synthetic corruption protocol, structured latent separation, stochastic expert diversity and Dirichlet fusion were associated with improved benchmark robustness and calibration. These results should not be interpreted as evidence of broad real-world robustness or clinical deployment readiness; external multi-center, device-diverse and skin-tone-diverse validation remains required.

Schlagwörter

Stichwörter der Autor:innen

Bayesian neural networksISIC 2019calibrationcausal representation learningconfoundingdermoscopyensemble learningselective classificationskin cancer detectionuncertainty quantification

Autor:innen und Institutionen

  • Department of Biotechnology and Microbiology, Khandelwal College of Management, Science and Technology, M.J.P. Rohilkhand University, Bareilly 243122, Uttar Pradesh, India.
  • Department of Health Informatics, College of Applied Medical Sciences, Qassim University, Buraydah 51452, Saudi Arabia.

ORCID-Profile: Mohd Faheem Khan, Khurshid Ahmad

Zitieren

APA

Khan, M. F., & Ahmad, K. (2026). Causal Uncertainty-Decomposed Ensemble Learning for Confounding-Aware Skin Cancer Detection in Dermoscopic Images. Diagnostics, 16(15), 2453. https://doi.org/10.3390/diagnostics16152453

Vancouver

Khan MF, Ahmad K. Causal Uncertainty-Decomposed Ensemble Learning for Confounding-Aware Skin Cancer Detection in Dermoscopic Images. Diagnostics. 2026;16(15):2453. doi:10.3390/diagnostics16152453

BibTeX
@article{Khan2026,
  author = {Khan, Mohd Faheem and Ahmad, Khurshid},
  title = {Causal Uncertainty-Decomposed Ensemble Learning for Confounding-Aware Skin Cancer Detection in Dermoscopic Images},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {2453},
  doi = {10.3390/diagnostics16152453}
}
Kostenlos starten →