Explaining Uncertainty in Multiple Sclerosis Cortical Lesion Segmentation Beyond Prediction Errors
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914489880805376 |
|---|---|
| author | Molchanova, Nataliia Gordaliza, Pedro M. Cagol, Alessandro Ocampo--Pineda, Mario Lu, Po--Jui Weigel, Matthias Chen, Xinjie Beck, Erin S. Tsagkas, Haris Reich, Daniel Stölting, Anna Maggi, Pietro Ribes, Delphine Depeursinge, Adrien Granziera, Cristina Müller, Henning Cuadra, Meritxell Bach |
| author_facet | Molchanova, Nataliia Gordaliza, Pedro M. Cagol, Alessandro Ocampo--Pineda, Mario Lu, Po--Jui Weigel, Matthias Chen, Xinjie Beck, Erin S. Tsagkas, Haris Reich, Daniel Stölting, Anna Maggi, Pietro Ribes, Delphine Depeursinge, Adrien Granziera, Cristina Müller, Henning Cuadra, Meritxell Bach |
| contents | Trustworthy artificial intelligence (AI) is essential in healthcare, particularly for high-stakes tasks like medical image segmentation. Explainable AI and uncertainty quantification significantly enhance AI reliability by addressing key attributes such as robustness, usability, and explainability. Despite extensive technical advances in uncertainty quantification for medical imaging, understanding the clinical informativeness and interpretability of uncertainty remains limited. This study presents an interpretability framework for analyzing lesion-scale predictive uncertainty in cortical lesion segmentation in multiple sclerosis using deep ensembles. The analysis shifts the focus from the uncertainty--error relationship towards clinically relevant medical and engineering factors. Our findings reveal that instance-wise uncertainty is strongly related to lesion size, shape, and cortical involvement. Expert rater feedback confirms that similar factors impede annotator confidence. Evaluations conducted on two datasets (206 patients, almost 2000 lesions) under both in-domain and distribution-shift conditions highlight the utility of the framework in different scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04814 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explaining Uncertainty in Multiple Sclerosis Cortical Lesion Segmentation Beyond Prediction Errors Molchanova, Nataliia Gordaliza, Pedro M. Cagol, Alessandro Ocampo--Pineda, Mario Lu, Po--Jui Weigel, Matthias Chen, Xinjie Beck, Erin S. Tsagkas, Haris Reich, Daniel Stölting, Anna Maggi, Pietro Ribes, Delphine Depeursinge, Adrien Granziera, Cristina Müller, Henning Cuadra, Meritxell Bach Image and Video Processing Computer Vision and Pattern Recognition Trustworthy artificial intelligence (AI) is essential in healthcare, particularly for high-stakes tasks like medical image segmentation. Explainable AI and uncertainty quantification significantly enhance AI reliability by addressing key attributes such as robustness, usability, and explainability. Despite extensive technical advances in uncertainty quantification for medical imaging, understanding the clinical informativeness and interpretability of uncertainty remains limited. This study presents an interpretability framework for analyzing lesion-scale predictive uncertainty in cortical lesion segmentation in multiple sclerosis using deep ensembles. The analysis shifts the focus from the uncertainty--error relationship towards clinically relevant medical and engineering factors. Our findings reveal that instance-wise uncertainty is strongly related to lesion size, shape, and cortical involvement. Expert rater feedback confirms that similar factors impede annotator confidence. Evaluations conducted on two datasets (206 patients, almost 2000 lesions) under both in-domain and distribution-shift conditions highlight the utility of the framework in different scenarios. |
| title | Explaining Uncertainty in Multiple Sclerosis Cortical Lesion Segmentation Beyond Prediction Errors |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.04814 |