Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Segmentation-guided network for automatic thoracic pathology classification

Segmentation-guided network for automatic thoracic pathology classification IntroductionLung diseases are the top causes of death around the world nowadays. Chest X-rays (CXRs) provide an invaluable tool for diagnosing lung-related diseases at the earliest stage possible. However, the accuracy of the diagnosis results depends heavily on the skill of the radiologist and is inevitably time-consuming and subjective. Accordingly, the present study proposes a model-based learning approach for the automatic detection of thoracic disease from CXR images designated as Segmentation-Guided Thorax Classification (SGTC).MethodsThe proposed method consists of two stages, namely lung segmentation and thorax classification. The lung segmentation stage applies the U-Net model with ResNet-50 as the backbone to segment the lung region in the CXR. The thorax classification stage then utilizes the ChexNet model with DenseNet-121 as the backbone to evaluate the probability of 14 different thoracic pathologies.ResultsThe experimental results show that SGTC achieves an average area under the receiver operating characteristic (ROC) curve (AUC) of 0.844 when applied to the ChestX-ray14 dataset.ConclusionThe performance of the proposed method is comparable to that of other recent approaches. Moreover, SGTC additionally superimposes a localization heatmap on the CXR image, which further assists the radiologist in interpreting the image. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Research on Biomedical Engineering Springer Journals

Segmentation-guided network for automatic thoracic pathology classification

Download PDF
14 pages

Loading next page...
 
/lp/springer-journals/segmentation-guided-network-for-automatic-thoracic-pathology-0I9iYV0vW2
Publisher
Springer Journals
Copyright
Copyright © Sociedade Brasileira de Engenharia Biomedica 2021
ISSN
2446-4732
eISSN
2446-4740
DOI
10.1007/s42600-021-00152-5
Publisher site
See Article on Publisher Site

Abstract

IntroductionLung diseases are the top causes of death around the world nowadays. Chest X-rays (CXRs) provide an invaluable tool for diagnosing lung-related diseases at the earliest stage possible. However, the accuracy of the diagnosis results depends heavily on the skill of the radiologist and is inevitably time-consuming and subjective. Accordingly, the present study proposes a model-based learning approach for the automatic detection of thoracic disease from CXR images designated as Segmentation-Guided Thorax Classification (SGTC).MethodsThe proposed method consists of two stages, namely lung segmentation and thorax classification. The lung segmentation stage applies the U-Net model with ResNet-50 as the backbone to segment the lung region in the CXR. The thorax classification stage then utilizes the ChexNet model with DenseNet-121 as the backbone to evaluate the probability of 14 different thoracic pathologies.ResultsThe experimental results show that SGTC achieves an average area under the receiver operating characteristic (ROC) curve (AUC) of 0.844 when applied to the ChestX-ray14 dataset.ConclusionThe performance of the proposed method is comparable to that of other recent approaches. Moreover, SGTC additionally superimposes a localization heatmap on the CXR image, which further assists the radiologist in interpreting the image.

Journal

Research on Biomedical Engineering – Springer Journals

Published: May 6, 2021

There are no references for this article.