Improving the Segmentation of Anatomical Structures in Chest Radiographs using U-Net with an ImageNet Pre-trained Encoder

TL;DR

This study enhances chest radiograph segmentation by employing a U-Net with a pre-trained encoder, achieving state-of-the-art accuracy in delineating lungs, heart, and clavicles on a standard benchmark.

Contribution

It introduces a modified U-Net architecture with a pre-trained encoder and evaluates different loss functions for improved multi-class segmentation performance.

Findings

Achieved Jaccard scores of 96.1% for lungs

Achieved Jaccard scores of 90.6% for heart

Achieved Jaccard scores of 85.5% for clavicles

Abstract

Accurate segmentation of anatomical structures in chest radiographs is essential for many computer-aided diagnosis tasks. In this paper we investigate the latest fully-convolutional architectures for the task of multi-class segmentation of the lungs field, heart and clavicles in a chest radiograph. In addition, we explore the influence of using different loss functions in the training process of a neural network for semantic segmentation. We evaluate all models on a common benchmark of 247 X-ray images from the JSRT database and ground-truth segmentation masks from the SCR dataset. Our best performing architecture, is a modified U-Net that benefits from pre-trained encoder weights. This model outperformed the current state-of-the-art methods tested on the same benchmark, with Jaccard overlap scores of 96.1% for lung fields, 90.6% for heart and 85.5% for clavicles.