Nov 15, 2023 · This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning (DL) tools in the context of white matter ...

This repository contains the code used for the study of voxel-, lesion-, and patient- scale uncertainty in application to white matter multiple sclerosis ...

This paper focuses on the uncertainty estimation for white matter lesions (WML) segmentation in magnetic resonance imaging (MRI). Lesion Detection ...

Two models are adopted based on a similar 3D U-Net architecture: deep ensemble (DE) and Monte Carlo Dropout (MCDP).

This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning tools in the context of white matter ...

and Bach Cuadra, M.: Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentation, arXiv (2024).

Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentation. CoRR abs/2311.08931 (2023); 2022. [i15].

Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentation. medical-image-analysis-laboratory ...

Abstract:This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning (DL) tools in the context of ...

In recent years, deep learning with convolutional neural networks (CNNs) has achieved SOTA performance for many medical image segmentation tasks, including WMH ...