Label-set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation (2021-07-08T00:00:00.000000Z)

TL;DR

It is proved 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, and the leaf-Dice loss is defined, a label- set generalization of the Dice loss particularly suited for partial supervision with only missing labels.

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

Authors

References27 items

A spatio-temporal atlas of the developing fetal brain with spina bifida aperta

MONAIfbs: MONAI-based fetal brain MRI deep learning segmentation

A comparison of automatic multi-tissue segmentation methods of the human fetal brain using the FeTA Dataset

Efficient Multi-class Fetal Brain Segmentation in High Resolution MRI Reconstructions with Noisy Labels

Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets

A deep learning approach to segmentation of the developing cortex in fetal brain MRI with minimal manual labeling

Multi-Organ Segmentation Over Partially Labeled Datasets With Multi-Scale Feature Abstraction

Fetal surgical intervention for myelomeningocele: lessons learned, outcomes, and future implications

An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI

Longitudinal Analysis of Fetal MRI in Patients with Prenatal Spina Bifida Repair

Fetal surgery for open spina bifida

Automatic brain tissue segmentation in fetal MRI using convolutional neural networks

Learning Multi-Class Segmentations From Single-Class Datasets

Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation

Prenatal brain imaging for predicting need for postnatal hydrocephalus treatment in fetuses that had neural tube defect repair in utero

Reliability of MR Imaging–Based Posterior Fossa and Brain Stem Measurements in Open Spinal Dysraphism in the Era of Fetal Surgery

Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets

Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks

Toward the automatic quantification of in utero brain development in 3D structural MRI: A review

A normative spatiotemporal MRI atlas of the fetal brain for automatic segmentation and analysis of early brain growth

Instance Normalization: The Missing Ingredient for Fast Stylization

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Current Selection Criteria and Perioperative Therapy Used for Fetal Myelomeningocele Surgery

Adam: A Method for Stochastic Optimization

Medical Image Analysis

Label-set

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