5 papers
Causal Attribution of Model Performance Gaps in Medical Imaging Under Distribution Shifts
Pedro M. Gordaliza, Nataliia Molchanova, Jaume Banus +2
Deep learning models for medical image segmentation suffer significant performance drops due to distribution shifts, but the causal mechanisms behind these drops remain poorly unde…
Exploiting XAI maps to improve MS lesion segmentation and detection in MRI
Federico Spagnolo, Nataliia Molchanova, Mario Ocampo Pineda +5
To date, several methods have been developed to explain deep learning algorithms for classification tasks. Recently, an adaptation of two of such methods has been proposed to gener…
Interpretability of Uncertainty: Exploring Cortical Lesion Segmentation in Multiple Sclerosis
Nataliia Molchanova, Alessandro Cagol, Pedro M. Gordaliza +8
Uncertainty quantification (UQ) has become critical for evaluating the reliability of artificial intelligence systems, especially in medical image segmentation. This study addresse…
Instance-level quantitative saliency in multiple sclerosis lesion segmentation
Federico Spagnolo, Nataliia Molchanova, Meritxell Bach Cuadra +5
Explainable artificial intelligence (XAI) methods have been proposed to interpret model decisions in classification and, more recently, in semantic segmentation. However, instance-…
Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentation
Nataliia Molchanova, Vatsal Raina, Andrey Malinin +7
This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning (DL) tools in the context of white matter lesion (WML) segment…