Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation

TL;DR

This paper presents a novel medical image segmentation pipeline combining FCNs and FC-ResNets, utilizing a trainable pre-processing step for normalized inputs, leading to state-of-the-art results across various modalities and organs.

Contribution

It introduces a simple, effective pipeline that leverages a low-capacity FCN for input normalization before iterative refinement with FC-ResNets, enhancing segmentation accuracy.

Findings

Achieves state-of-the-art results on Electron Microscopy benchmark.

Improves liver lesion segmentation on CT images.

Performs competitively on 3D MRI prostate segmentation.

Abstract

In this paper, we introduce a simple, yet powerful pipeline for medical image segmentation that combines Fully Convolutional Networks (FCNs) with Fully Convolutional Residual Networks (FC-ResNets). We propose and examine a design that takes particular advantage of recent advances in the understanding of both Convolutional Neural Networks as well as ResNets. Our approach focuses upon the importance of a trainable pre-processing when using FC-ResNets and we show that a low-capacity FCN model can serve as a pre-processor to normalize medical input data. In our image segmentation pipeline, we use FCNs to obtain normalized images, which are then iteratively refined by means of a FC-ResNet to generate a segmentation prediction. As in other fully convolutional approaches, our pipeline can be used off-the-shelf on different image modalities. We show that using this pipeline, we exhibit state-of-the-art performance on the challenging Electron Microscopy benchmark, when compared to other 2D methods. We improve segmentation results on CT images of liver lesions, when contrasting with standard FCN methods. Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods. The obtained results illustrate the strong potential and versatility of the pipeline by achieving highly accurate results on multi-modality images from different anatomical regions and organs.