Adaptive Noise-Tolerant Network for Image Segmentation

TL;DR

This paper introduces an Adaptive Noise-Tolerant Network (ANTN) that effectively leverages multiple noisy segmentation labels and adapts to image appearance, improving biomedical image segmentation without relying on perfect ground-truth labels.

Contribution

The paper presents a novel deep learning model that integrates multiple noisy labels and adaptively models noise, specifically designed for challenging biomedical image segmentation tasks.

Findings

ANTN outperforms existing segmentation algorithms on synthetic data.

ANTN demonstrates superior results on real-world histo-images.

The adaptive noise modeling improves segmentation accuracy with noisy labels.

Abstract

Unlike image classification and annotation, for which deep network models have achieved dominating superior performances compared to traditional computer vision algorithms, deep learning for automatic image segmentation still faces critical challenges. One of such hurdles is to obtain ground-truth segmentations as the training labels for deep network training. Especially when we study biomedical images, such as histopathological images (histo-images), it is unrealistic to ask for manual segmentation labels as the ground truth for training due to the fine image resolution as well as the large image size and complexity. In this paper, instead of relying on clean segmentation labels, we study whether and how integrating imperfect or noisy segmentation results from off-the-shelf segmentation algorithms may help achieve better segmentation results through a new Adaptive Noise-Tolerant Network (ANTN) model. We extend the noisy label deep learning to image segmentation with two novel aspects: (1) multiple noisy labels can be integrated into one deep learning model; (2) noisy segmentation modeling, including probabilistic parameters, is adaptive, depending on the given testing image appearance. Implementation of the new ANTN model on both the synthetic data and real-world histo-images demonstrates its effectiveness and superiority over off-the-shelf and other existing deep-learning-based image segmentation algorithms.