Automated uncertainty estimation of lesion segmentation

Methods and systems are provided for automatically estimating image-level uncertainty for MS lesion segmentation data. A segmentation network is trained to segment MS lesions. The trained segmentation network is then used to estimate voxel level measures of uncertainty by performing Monte-Carlo (MC)...

Full description

Saved in:
Bibliographic Details
Main Authors Nadar, Mariappan S, Yoo, Youngjin
Format Patent
LanguageEnglish
Published 06.04.2021
Subjects
CALCULATING
COMPUTING
COUNTING
DIAGNOSIS
HANDLING RECORD CARRIERS
HUMAN NECESSITIES
HYGIENE
IDENTIFICATION
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
MEDICAL OR VETERINARY SCIENCE
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
SURGERY
Online AccessGet full text

Cover

More Information
Summary:Methods and systems are provided for automatically estimating image-level uncertainty for MS lesion segmentation data. A segmentation network is trained to segment MS lesions. The trained segmentation network is then used to estimate voxel level measures of uncertainty by performing Monte-Carlo (MC) dropout. The estimated voxel level uncertainty measures are converted into lesion level uncertainty measures. The information density of the lesion mask, the voxel level measures, and the lesion level measures is increased. A trained network receives input images, the segmented lesion masks, the voxel level uncertainty measures, and the lesion level uncertainty measures and outputs an image level uncertainty measure. The network is trained with a segmentation performance metric to predict an image level uncertainty measure on the segmented lesion mask that is produced by the trained segmentation network.
Bibliography:Application Number: US201916355881