Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation.
IEEE Trans Med Imaging
; 39(12): 3868-3878, 2020 12.
Article
en En
| MEDLINE
| ID: mdl-32746129
ABSTRACT
Fully convolutional neural networks (FCNs), and in particular U-Nets, have achieved state-of-the-art results in semantic segmentation for numerous medical imaging applications. Moreover, batch normalization and Dice loss have been used successfully to stabilize and accelerate training. However, these networks are poorly calibrated i.e. they tend to produce overconfident predictions for both correct and erroneous classifications, making them unreliable and hard to interpret. In this paper, we study predictive uncertainty estimation in FCNs for medical image segmentation. We make the following contributions 1) We systematically compare cross-entropy loss with Dice loss in terms of segmentation quality and uncertainty estimation of FCNs; 2) We propose model ensembling for confidence calibration of the FCNs trained with batch normalization and Dice loss; 3) We assess the ability of calibrated FCNs to predict segmentation quality of structures and detect out-of-distribution test examples. We conduct extensive experiments across three medical image segmentation applications of the brain, the heart, and the prostate to evaluate our contributions. The results of this study offer considerable insight into the predictive uncertainty estimation and out-of-distribution detection in medical image segmentation and provide practical recipes for confidence calibration. Moreover, we consistently demonstrate that model ensembling improves confidence calibration.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Procesamiento de Imagen Asistido por Computador
/
Redes Neurales de la Computación
Tipo de estudio:
Prognostic_studies
/
Risk_factors_studies
Límite:
Humans
/
Male
Idioma:
En
Revista:
IEEE Trans Med Imaging
Año:
2020
Tipo del documento:
Article