Clinically Validated XAI for Calcified Plaque Segmentation in Coronary CT Angiography
Journal of Clinical Medicine · 03.08.2026 · 15 (15) · 6039
DOI: 10.3390/jcm15156039 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 03.08.2026. Verfasst von Julius Siaulys und 4 weiteren Autor:innen. Beteiligte Einrichtung: Artificial Intelligence Centre, Faculty of Informatics, Kaunas University of Technology, LT-44249 Kaunas, Lithuania. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union.
Abstract (Originalsprache)
Background
Accurate segmentation of calcified plaques in coronary computed tomography angiography (CCTA) images is critical for reliable assessment of coronary atherosclerotic burden and for supporting interpretation of luminal stenosis, yet it remains a challenging task due to annotation inconsistencies, blooming artifacts and low contrast at lesion boundaries. These limitations may affect both automated model performance and the clinical trustworthiness of AI systems. This study explores the impact of annotation refinement on segmentation performance and model explainability, as well as the influence of representation learning on explanation quality.
Methods
We trained a deep convolutional neural network to segment calcified plaques in coronary arteries using a dataset of expert-labeled CT slices. Initial training on radiologist-provided annotations yielded suboptimal results. To address this, annotations were manually revised and validated by radiologists. In addition to a standard ImageNet-pretrained model, we evaluated a self-supervised representation learning approach using DINOv2. Grad-CAM was used to generate visual explanations for model predictions before and after annotation refinement.
Results
Models trained with refined annotations achieved notably improved segmentation accuracy, with clearer delineation of calcified regions. Grad-CAM localization analysis demonstrated improved concentration of model attention within plaque and vessel regions. Furthermore, models incorporating DINOv2 representations produced more spatially coherent attention maps, with improved anatomical localization consistent with coronary vessel regions and reduced off-target activations, as qualitatively confirmed by expert radiologists.
Conclusions
Our findings emphasize the importance of high-quality, validated annotations in developing accurate and interpretable AI models for medical imaging. In addition, the results suggest that representation learning influences the reliability and clinical relevance of explainability outputs. The combination of manual annotation refinement, expert validation, and improved feature representations provides a practical workflow for human-in-the-loop AI development in cardiovascular imaging. This study demonstrates that annotation quality is a critical and often underestimated determinant of XAI reliability, and suggests that explainability methods can serve as feedback tools for iterative, clinician-guided dataset curation in cardiovascular imaging.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Artificial Intelligence Centre, Faculty of Informatics, Kaunas University of Technology, LT-44249 Kaunas, Lithuania.
- Centre of Excellence for Sustainable Living and Working (SustAInLivWork), LT-51423 Kaunas, Lithuania.
- Institute of Cardiology, Lithuanian University of Health Sciences, LT-50161 Kaunas, Lithuania.
- Laboratory for Automation of Cardiovascular Investigation, Lithuanian University of Health Sciences, LT-50161 Kaunas, Lithuania.
ORCID-Profile: Julius Siaulys, Agne Paulauskaite-Taraseviciene, Dovydas Verikas
Förderung
- European Union
Zitieren
APA
Siaulys, J., Paulauskaite-Taraseviciene, A., Jankauskas, A., Sakalyte, G., & Verikas, D. (2026). Clinically Validated XAI for Calcified Plaque Segmentation in Coronary CT Angiography. Journal of Clinical Medicine, 15(15), 6039. https://doi.org/10.3390/jcm15156039
Vancouver
Siaulys J, Paulauskaite-Taraseviciene A, Jankauskas A, Sakalyte G, Verikas D. Clinically Validated XAI for Calcified Plaque Segmentation in Coronary CT Angiography. Journal of Clinical Medicine. 2026;15(15):6039. doi:10.3390/jcm15156039
BibTeX
@article{Siaulys2026,
author = {Siaulys, Julius and Paulauskaite-Taraseviciene, Agne and Jankauskas, Antanas and Sakalyte, Gintare and Verikas, Dovydas},
title = {Clinically Validated XAI for Calcified Plaque Segmentation in Coronary CT Angiography},
journal = {Journal of Clinical Medicine},
year = {2026},
volume = {15},
number = {15},
pages = {6039},
doi = {10.3390/jcm15156039}
}
EUVIMED