A semi‐supervised learning‐based quality evaluation system for digital chest radiographs
Medical Physics · 2023-11 · 50 (11) · 6789-6800
DOI: 10.1002/mp.16663 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, online erschienen am 06.08.2023. Verfasst von Shuoyang Wei und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering Physics, Tsinghua University, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning, Foreign Bodies. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Tsinghua University Initiative Scientific Research Program.
Abstract (Originalsprache)
Background
Digital radiography is the most commonly utilized medical imaging technique worldwide, and the quality of radiographs plays a crucial role in accurate disease diagnosis. Therefore, evaluating the quality of radiographs is an essential step in medical examinations. However, manual evaluation can be time‐consuming, labor‐intensive, and prone to interobserver differences, making it less reliable.
Purpose
To alleviate the workload of radiographic technologists and enhance the efficiency of radiograph quality evaluation, it is crucial to develop rapid and reliable quality evaluation methods and establish a set of quantitative evaluation standards. To address this, we have proposed a quality evaluation system for digital radiographs that utilizes deep learning techniques to achieve fast and precise evaluation.
Methods
The evaluation of frontal chest radiograph quality involves assessing patient positioning through semantic segmentation and foreign body detection. For lung, scapula, and clavicle segmentation in digital chest radiographs, a residual connection‐based convolutional neural network π‐ResUNet, was proposed. Criteria for patient positioning evaluation were established based on the segmentation and manual evaluation results. A convolutional neural network, FasterRCNN, was utilized to detect and localize foreign bodies in digital chest radiographs. To enhance the performance of both neural networks, a semi‐supervised learning (SSL) strategy was implemented by incorporating a consistency loss that leverages a large number of unlabeled digital radiographs. We also trained the network using the fully supervised learning (FSL) strategy and compared their performance on the test set. The ChestXRay‐14 and object‐CXR datasets were used throughout the process.
Results
By comparing with the manual annotation, the proposed network, trained using the SSL method, achieved a high Dice similarity coefficient (DSC) of 0.96, 0.88, and 0.88 for lung, scapula, and clavicle segmentation, respectively, outperforming the network trained with the FSL method. In addition, for foreign body detection, the proposed SSL method was superior to the FSL method, achieving an AUC (Area under receiver operating characteristic curve, Area under ROC curve) of 0.90 and an FROC (Free‐response ROC) of 0.77 on the test dataset.
Conclusions
The experimental results show that our proposed system is well‐suited for radiograph quality evaluation, with the semi‐supervised learning method further improving the network's performance. The proposed method can evaluate the quality of a chest radiograph from two aspects—patient positioning and foreign body detection—within 1 s, offering a promising tool in radiograph quality evaluation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Engineering Physics, Tsinghua University, Beijing, China.
- Key Laboratory of Particle & Radiation Imaging (Tsinghua University), Ministry of Education, Beijing, China.
- Department of Radiotherapy, Peking Union Medical College Hospital, Beijing, China.
- Beijing Tongren Hospital, CMU, Beijing, China.
Förderung
- National Natural Science Foundation of China
- National Key R&D Program of China
- Tsinghua University Initiative Scientific Research Program
Zitieren
APA
Wei, S., Qiu, R., Pu, Y., Hu, A., Niu, Y., Wu, Z., Zhang, H., & Li, J. (2023). A semi‐supervised learning‐based quality evaluation system for digital chest radiographs. Medical Physics, 50(11), 6789-6800. https://doi.org/10.1002/mp.16663
Vancouver
Wei S, Qiu R, Pu Y, Hu A, Niu Y, Wu Z, et al. A semi‐supervised learning‐based quality evaluation system for digital chest radiographs. Medical Physics. 2023;50(11):6789-6800. doi:10.1002/mp.16663
BibTeX
@article{Wei2023,
author = {Wei, Shuoyang and Qiu, Rui and Pu, Yanheng and Hu, Ankang and Niu, Yantao and Wu, Zhen and Zhang, Hui and Li, Junli},
title = {A semi‐supervised learning‐based quality evaluation system for digital chest radiographs},
journal = {Medical Physics},
year = {2023},
volume = {50},
number = {11},
pages = {6789--6800},
doi = {10.1002/mp.16663}
}
EUVIMED