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

Autor:	Avi Ben-Cohen, Maayan Frid-Adar, Rula Amer, Hayit Greenspan
Rok vydání:	2018
Předmět:	Jaccard index Artificial neural network medicine.diagnostic_test business.industry Computer science Radiography Pattern recognition Field (computer science) medicine Benchmark (computing) Segmentation Artificial intelligence Chest radiograph business Encoder
Zdroj:	Image Analysis for Moving Organ, Breast, and Thoracic Images ISBN: 9783030009458 RAMBO+BIA+TIA@MICCAI
Popis:	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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::62f6e8dde84f2951f4e4a9d12f8e7444 https://doi.org/10.1007/978-3-030-00946-5_17 Zobrazit plný text záznamu