UncerKAN-Mamba: A Clinically Robust, Transparent, and Explainable AI Framework for Low-Latency Skin Lesion Segmentation with Deterministic Single-Pass Uncertainty Estimation
Machine Learning and Knowledge Extraction · 03.06.2026 · 8 (6) · 153
DOI: 10.3390/make8060153 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 03.06.2026. Verfasst von Hüseyin Kutlu und 1 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: İnönü University.
Abstract (Originalsprache)
Background
Accurate skin lesion segmentation is central to early melanoma detection, yet existing uncertainty estimation methods such as Monte Carlo (MC) Dropout and Deep Ensembles impose heavy computational overhead, and most segmentation architectures offer no insight into where or why predictions may fail.
Methods
We present UncerKAN-Mamba, an explainable segmentation architecture integrating an EfficientNet-B4 encoder with Mamba state space model (SSM) blocks inside a UNet++ decoder, augmented by a Kolmogorov–Arnold Network (KAN) uncertainty head. The KAN head uses spline variance across multiple basis degrees as a deterministic, single-pass uncertainty proxy. Explainability is assessed via Grad-CAM, error–uncertainty overlap, and boundary uncertainty profiling.
Results
Trained on the ISIC 2018 training partition (n = 1815 of 2594 total images) and externally validated on PH2 (n = 200) and ISIC 2016 (n = 1279), UncerKAN-Mamba achieved Dice = 0.8958, 0.9214, and 0.9360, respectively, achieving segmentation performance statistically comparable to the strongest contemporary baselines on ISIC 2018 and PH2, and ranking second to Attention U-Net on ISIC 2016 (Bonferroni-corrected Wilcoxon and paired bootstrap tests). KAN uncertainty yielded the strongest Pearson correlation with segmentation error (r = 0.674–0.731, best on ISIC 2016)—1.7–2.0× higher than MC Dropout and 1.3–1.4× higher than Deep Ensembles. Quantitative XAI metrics (AUROC = 0.971, PAvPU = 0.554, ECE = 0.0126–0.0419) confirmed strong interpretability and excellent calibration at 36–47 FPS.
Conclusions
UncerKAN-Mamba delivers clinically robust, transparent, low-latency skin lesion segmentation suitable for interactive clinical review with deterministic single-pass uncertainty—the first use of KAN spline variance for uncertainty quantification in medical image segmentation.
Förderung
- İnönü University
Zitieren
APA
Kutlu, H., & Çolak, C. (2026). UncerKAN-Mamba: A Clinically Robust, Transparent, and Explainable AI Framework for Low-Latency Skin Lesion Segmentation with Deterministic Single-Pass Uncertainty Estimation. Machine Learning and Knowledge Extraction, 8(6), 153. https://doi.org/10.3390/make8060153
Vancouver
Kutlu H, Çolak C. UncerKAN-Mamba: A Clinically Robust, Transparent, and Explainable AI Framework for Low-Latency Skin Lesion Segmentation with Deterministic Single-Pass Uncertainty Estimation. Machine Learning and Knowledge Extraction. 2026;8(6):153. doi:10.3390/make8060153
BibTeX
@article{Kutlu2026,
author = {Kutlu, Hüseyin and Çolak, Cemil},
title = {UncerKAN-Mamba: A Clinically Robust, Transparent, and Explainable AI Framework for Low-Latency Skin Lesion Segmentation with Deterministic Single-Pass Uncertainty Estimation},
journal = {Machine Learning and Knowledge Extraction},
year = {2026},
volume = {8},
number = {6},
pages = {153},
doi = {10.3390/make8060153}
}
EUVIMED