Abstract
We evaluated the efficacy of a curriculum learning strategy using two steps to detect pulmonary abnormalities including nodule[s], consolidation, interstitial opacity, pleural effusion, and pneumothorax with chest-PA X-ray (CXR) images from two centres. CXR images of 6069 healthy subjects and 3417 patients at AMC and 1035 healthy subjects and 4404 patients at SNUBH were obtained. Our approach involved two steps. First, the regional patterns of thoracic abnormalities were identified by initial learning of patch images around abnormal lesions. Second, Resnet-50 was fine-tuned using the entire images. The network was weakly trained and modified to detect various disease patterns. Finally, class activation maps (CAM) were extracted to localise and visualise the abnormal patterns. For average disease, the sensitivity, specificity, and area under the curve (AUC) were 85.4%, 99.8%, and 0.947, respectively, in the AMC dataset and 97.9%, 100.0%, and 0.983, respectively, in the SNUBH dataset. This curriculum learning and weak labelling with high-scale CXR images requires less preparation to train the system and could be easily extended to include various diseases in actual clinical environments. This algorithm performed well for the detection and classification of five disease patterns in CXR images and could be helpful in image interpretation.
Highlights
Chest posterior-anterior (PA)-X-ray (CXR) is considered one of the most accessible types of radiological examinations to screen for and diagnose pulmonary problems and for secondary prevention
This study evaluated the efficacy of the curriculum strategy, which trains with two steps, for detecting pulmonary abnormalities on chest-PA X-ray (CXR) images from two hospitals
We evaluated the efficacy of a two-step curriculum strategy for detecting pulmonary abnormalities on CXR images from two hospitals and found that curriculum learning could guide the model toward a better local minimum
Summary
Chest posterior-anterior (PA)-X-ray (CXR) is considered one of the most accessible types of radiological examinations to screen for and diagnose pulmonary problems and for secondary prevention. Several studies to date have evaluated deep learning methods to detect pulmonary disease by CXR, including evaluations of the efficacy of convolutional neural networks (CNNs) to screen for tuberculosis on CXR1 and the construction of a CXR database, called ChestX-ray[14], for classification and localization of benchmark lesions[2]. Using these data, long short-term memory (LSTM)[3] has been applied to the encoded features using a type of DenseNet, allowing the model to exploit dependencies among labels. This study evaluated the efficacy of the curriculum strategy, which trains with two steps, for detecting pulmonary abnormalities on CXR images from two hospitals
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
