{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T08:16:12Z","timestamp":1789546572959,"version":"build-2803163510"},"reference-count":49,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2023,8,6]],"date-time":"2023-08-06T00:00:00Z","timestamp":1691280000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2167209"],"award-info":[{"award-number":["U2167209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12175114"],"award-info":[{"award-number":["12175114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2023,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>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\u2010consuming, labor\u2010intensive, and prone to interobserver differences, making it less reliable.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>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\u2010based convolutional neural network \u03c0\u2010ResUNet, 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\u2010supervised 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\u201014 and object\u2010CXR datasets were used throughout the process.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>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\u2010response ROC) of 0.77 on the test dataset.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The experimental results show that our proposed system is well\u2010suited for radiograph quality evaluation, with the semi\u2010supervised learning method further improving the network's performance. The proposed method can evaluate the quality of a chest radiograph from two aspects\u2014patient positioning and foreign body detection\u2014within 1 s, offering a promising tool in radiograph quality evaluation.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16663","type":"journal-article","created":{"date-parts":[[2023,8,6]],"date-time":"2023-08-06T16:19:00Z","timestamp":1691338740000},"page":"6789-6800","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A semi\u2010supervised learning\u2010based quality evaluation system for digital chest radiographs"],"prefix":"10.1002","volume":"50","author":[{"given":"Shuoyang","family":"Wei","sequence":"first","affiliation":[{"name":"Department of Engineering Physics Tsinghua University Beijing China"},{"name":"Key Laboratory of Particle &amp; Radiation Imaging (Tsinghua University) Ministry of Education Beijing China"},{"name":"Department of Radiotherapy Peking Union Medical College Hospital Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Engineering Physics Tsinghua University Beijing China"},{"name":"Key Laboratory of Particle &amp; Radiation Imaging (Tsinghua University) Ministry of Education Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanheng","family":"Pu","sequence":"additional","affiliation":[{"name":"Department of Engineering Physics Tsinghua University Beijing China"},{"name":"Key Laboratory of Particle &amp; Radiation Imaging (Tsinghua University) Ministry of Education Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankang","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Engineering Physics Tsinghua University Beijing China"},{"name":"Key Laboratory of Particle &amp; Radiation Imaging (Tsinghua University) Ministry of Education Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yantao","family":"Niu","sequence":"additional","affiliation":[{"name":"Beijing Tongren Hospital CMU Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Engineering Physics Tsinghua University Beijing China"},{"name":"Key Laboratory of Particle &amp; Radiation Imaging (Tsinghua University) Ministry of Education Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Engineering Physics Tsinghua University Beijing China"},{"name":"Key Laboratory of Particle &amp; Radiation Imaging (Tsinghua University) Ministry of Education Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junli","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Engineering Physics Tsinghua University Beijing China"},{"name":"Key Laboratory of Particle &amp; Radiation Imaging (Tsinghua University) Ministry of Education Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,8,6]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4932623"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmrs.343"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmrs.654"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1093\/rpd\/ncq032"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.72.859.10624322"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordjournals.rpd.a006482"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-009-9236-2"},{"issue":"3","key":"e_1_2_8_9_1","first-page":"164","article-title":"Frequency of common causes of rejected\/repeated chest x\u2013rays in radiology department of a teaching hospital","volume":"14","author":"Khan S","year":"2016","journal-title":"Gomal J Med Sci"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrras.2014.09.012"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2016.07.011"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1177\/2058460115604339"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-008-9112-5"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-005-8733-1"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1078-8174(98)80027-8"},{"key":"e_1_2_8_16_1","doi-asserted-by":"crossref","unstructured":"KashyapS MoradiM KarargyrisA et\u00a0al.Artificial intelligence for point of care radiograph quality assessment.SPIE;2019:893\u2010899.","DOI":"10.1117\/12.2513092"},{"issue":"5","key":"e_1_2_8_17_1","first-page":"784","article-title":"Application value of convolutional neural network in quality control of direct digital chest X\u2010ray images","author":"Xiaoqian J","year":"2019","journal-title":"Xi'an jiao tong da xue xue bao Yi xue ban"},{"issue":"1","key":"e_1_2_8_18_1","first-page":"158","article-title":"Research and application of orthotopic DR chest radiograph quality control system based on artificial intelligence","volume":"37","author":"Wang J","year":"2020","journal-title":"Sheng Wu Yi Xue Gong Cheng Xue Za Zhi"},{"issue":"5","key":"e_1_2_8_19_1","first-page":"489","article-title":"Artificial intelligence in medical imaging","volume":"90","author":"Wagner JB","year":"2019","journal-title":"Radiol Technol"},{"issue":"2","key":"e_1_2_8_20_1","first-page":"376","article-title":"Current and potential applications of artificial intelligence in medical imaging practice: a narrative review","volume":"54","author":"Poto\u010dnik J","year":"2023","journal-title":"J Med Radiat Sci"},{"key":"e_1_2_8_21_1","article-title":"How artificial intelligence is empowering medical imaging at one company","author":"Stephens K","year":"2021","journal-title":"AXIS Imaging News"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmir.2023.03.033"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00247-021-05013-y"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000904"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07097-w"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000482"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1965.1053799"},{"key":"e_1_2_8_28_1","article-title":"Temporal ensembling for semi\u2010supervised learning","author":"Laine S","year":"2016","journal-title":"arXiv preprint arXiv:161002242"},{"key":"e_1_2_8_29_1","unstructured":"TarvainenA ValpolaH Mean teachers are better role models: weight\u2010averaged consistency targets improve semi\u2010supervised deep learning results. Presented at:31st Conference on Neural Information Processing Systems (NIPS 2017);2017."},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"NigamK GhaniR.Analyzing the effectiveness and applicability of co\u2010training. Proceedings of the ninth international conference on Information and knowledge management.2000:86\u201093.","DOI":"10.1145\/354756.354805"},{"key":"e_1_2_8_31_1","unstructured":"SummersR.NIH chest X\u2010ray dataset of 14 common thorax disease categories.2019.https:\/\/www.kaggle.com\/datasets\/nih\u2010chest\u2010xrays\/data"},{"key":"e_1_2_8_32_1","unstructured":"JFHealthcare.Automatic detection of foreign objects on chest x\u2010rays.2020.https:\/\/academictorrents.com\/details\/fdc91f11d7010f7259a05403fc9d00079a09f5d5"},{"key":"e_1_2_8_33_1","first-page":"14","volume-title":"Transfuse: Fusing Transformers and CNNs for Medical Image Segmentation","author":"Zhang Y","year":"2021"},{"key":"e_1_2_8_34_1","first-page":"517","volume-title":"SMESwin Unet: Merging CNN and Transformer for Medical Image Segmentation","author":"Wang Z","year":"2022"},{"key":"e_1_2_8_35_1","first-page":"36","volume-title":"Medical Transformer: Gated Axial\u2010Attention for Medical Image Segmentation","author":"Valanarasu JMJ","year":"2021"},{"key":"e_1_2_8_36_1","first-page":"61","volume-title":"UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation","author":"Gao Y","year":"2021"},{"key":"e_1_2_8_37_1","first-page":"234","volume-title":"U\u2010net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger O","year":"2015"},{"key":"e_1_2_8_38_1","unstructured":"LaineS AilaT.Temporal ensembling for semi\u2010supervised learning. arXiv preprint arXiv:1610.02242.2016."},{"key":"e_1_2_8_39_1","unstructured":"AbadiM AgarwalA BarhamP et\u00a0al.Tensorflow: Large\u2010scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:160304467.2016"},{"key":"e_1_2_8_40_1","unstructured":"KingmaDP AdamBJ.A method for stochastic optimization. arXiv preprint arXiv:14126980.2014"},{"key":"e_1_2_8_41_1","first-page":"329","volume-title":"AUC: A Better Measure Than Accuracy in Comparing Learning Algorithms","author":"Ling CX","year":"2003"},{"key":"e_1_2_8_42_1","first-page":"650","article-title":"Face detection with the faster R\u2010CNN","author":"Jiang H","year":"2017","journal-title":"IEEE"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.03.030"},{"key":"e_1_2_8_44_1","first-page":"124","article-title":"A closer look at Faster R\u2010CNN for vehicle detection","author":"Fan Q","year":"2016","journal-title":"IEEE"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_8_46_1","doi-asserted-by":"crossref","unstructured":"SzegedyC IoffeS VanhouckeV AlemiAA.Inception\u2010v4 inception\u2010resnet and the impact of residual connections on learning. Proceedings of the AAAI conference on artificial intelligence.2017;31(1):4278\u20104284.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_2_8_47_1","first-page":"740","volume-title":"Microsoft Coco: Common Objects in Context","author":"Lin T\u2010Y","year":"2014"},{"key":"e_1_2_8_48_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition.2016:770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1911889"},{"key":"e_1_2_8_50_1","first-page":"8026","article-title":"Pytorch: an imperative style, high\u2010performance deep learning library","volume":"32","author":"Paszke A","year":"2019","journal-title":"Adv Neural Inf Process"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T17:51:54Z","timestamp":1699379514000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16663"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,6]]},"references-count":49,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["10.1002\/mp.16663"],"URL":"https:\/\/doi.org\/10.1002\/mp.16663","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,6]]},"assertion":[{"value":"2023-05-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-20","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}