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

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.

arXiv commentPresented at the First International Workshop on Thoracic Image Analysis (TIA), MICCAI 2018

Cited by in corpus (8)

• U-Net and its variants for medical image segmentation: theory and applications
• Modality specific U-Net variants for biomedical image segmentation: A survey
• Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations
• Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images
• COVID-19 in CXR: from Detection and Severity Scoring to Patient Disease Monitoring
• Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising
• An Automated Approach for Timely Diagnosis and Prognosis of Coronavirus Disease
• Out-of-distribution data supervision towards biomedical semantic segmentation