Distributionally Robust Segmentation of Abnormal Fetal Brain 3D MRI

by   Lucas Fidon, et al.

The performance of deep neural networks typically increases with the number of training images. However, not all images have the same importance towards improved performance and robustness. In fetal brain MRI, abnormalities exacerbate the variability of the developing brain anatomy compared to non-pathological cases. A small number of abnormal cases, as is typically available in clinical datasets used for training, are unlikely to fairly represent the rich variability of abnormal developing brains. This leads machine learning systems trained by maximizing the average performance to be biased toward non-pathological cases. This problem was recently referred to as hidden stratification. To be suited for clinical use, automatic segmentation methods need to reliably achieve high-quality segmentation outcomes also for pathological cases. In this paper, we show that the state-of-the-art deep learning pipeline nnU-Net has difficulties to generalize to unseen abnormal cases. To mitigate this problem, we propose to train a deep neural network to minimize a percentile of the distribution of per-volume loss over the dataset. We show that this can be achieved by using Distributionally Robust Optimization (DRO). DRO automatically reweights the training samples with lower performance, encouraging nnU-Net to perform more consistently on all cases. We validated our approach using a dataset of 368 fetal brain T2w MRIs, including 124 MRIs of open spina bifida cases and 51 MRIs of cases with other severe abnormalities of brain development.


page 2

page 7

page 13


Real-Time Automatic Fetal Brain Extraction in Fetal MRI by Deep Learning

Brain segmentation is a fundamental first step in neuroimage analysis. I...

Hydrocephalus verification on brain magnetic resonance images with deep convolutional neural networks and "transfer learning" technique

The hydrocephalus can be either an independent disease or a concomitant ...

Computational Modeling of Deep Multiresolution-Fractal Texture and Its Application to Abnormal Brain Tissue Segmentation

Computational modeling of Multiresolution- Fractional Brownian motion (f...

FAST-AID Brain: Fast and Accurate Segmentation Tool using Artificial Intelligence Developed for Brain

Medical images used in clinical practice are heterogeneous and not the s...

Brain MRI Segmentation using Template-Based Training and Visual Perception Augmentation

Deep learning models usually require sufficient training data to achieve...

Automated Detection of Abnormal EEGs in Epilepsy With a Compact and Efficient CNN Model

Electroencephalography (EEG) is essential for the diagnosis of epilepsy,...

Is good old GRAPPA dead?

We perform a qualitative analysis of performance of XPDNet, a state-of-t...

Please sign up or login with your details

Forgot password? Click here to reset