Label-set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation

Abstract

Deep neural networks have increased the accuracy of automatic segmentation, however, their accuracy depends on the availability of a large number of fully segmented images. Methods to train deep neural networks using images for which some, but not all, regions of interest are segmented are necessary to make better use of partially annotated datasets. In this paper, we propose the first axiomatic definition of label-set loss functions that are the loss functions that can handle partially segmented images. We prove that there is one and only one method to convert a classical loss function for fully segmented images into a proper label-set loss function. Our theory also allows us to define the leaf-Dice loss, a label-set generalization of the Dice loss particularly suited for partial supervision with only missing labels. Using the leaf-Dice loss, we set a new state of the art in partially supervised learning for fetal brain 3D MRI segmentation. We achieve a deep neural network able to segment white matter, ventricles, cerebellum, extra-ventricular CSF, cortical gray matter, deep gray matter, brainstem, and corpus callosum based on fetal brain 3D MRI of anatomically normal fetuses or with open spina bifida. Our implementation of the proposed label-set loss functions is available at https://github.com/LucasFidon/label-set-loss-functions

Accepted at MICCAI 2021

References in corpus (3)

• Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
• MONAIfbs: MONAI-based fetal brain MRI deep learning segmentation
• Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets

Cited by in corpus (7)

• MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation
• A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation
• Distributionally Robust Segmentation of Abnormal Fetal Brain 3D MRI
• The Dice loss in the context of missing or empty labels: Introducing $\Phi$ and $\epsilon$
• OOD-SEG: Exploiting out-of-distribution detection techniques for learning image segmentation from sparse multi-class positive-only annotations
• Partial supervision for the FeTA challenge 2021
• Enhancing Corpus Callosum Segmentation in Fetal MRI via Pathology-Informed Domain Randomization