Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives

TL;DR

This paper introduces a novel loss function for deep learning in medical image segmentation that effectively handles false negatives in annotations, significantly improving sensitivity even with noisy labels.

Contribution

The authors propose a lopsided entropy-based loss function that models false negative rates, enabling robust brain metastasis segmentation despite noisy or incomplete annotations.

Findings

Maintains 97% sensitivity with 50% false negatives in random censoring.

Restores 88% performance with size-based lesion censorship.

Outperforms standard loss functions in noisy annotation scenarios.

Abstract

Deep learning has proven to be an essential tool for medical image analysis. However, the need for accurately labeled input data, often requiring time- and labor-intensive annotation by experts, is a major limitation to the use of deep learning. One solution to this challenge is to allow for use of coarse or noisy labels, which could permit more efficient and scalable labeling of images. In this work, we develop a lopsided loss function based on entropy regularization that assumes the existence of a nontrivial false negative rate in the target annotations. Starting with a carefully annotated brain metastasis lesion dataset, we simulate data with false negatives by (1) randomly censoring the annotated lesions and (2) systematically censoring the smallest lesions. The latter better models true physician error because smaller lesions are harder to notice than the larger ones. Even with a simulated false negative rate as high as 50%, applying our loss function to randomly censored data preserves maximum sensitivity at 97% of the baseline with uncensored training data, compared to just 10% for a standard loss function. For the size-based censorship, performance is restored from 17% with the current standard to 88% with our lopsided bootstrap loss. Our work will enable more efficient scaling of the image labeling process, in parallel with other approaches on creating more efficient user interfaces and tools for annotation.