{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T18:14:02Z","timestamp":1792692842974,"version":"4.5.0"},"reference-count":29,"publisher":"SPIE-Intl Soc Optical Eng","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Med. Imag."],"published-print":{"date-parts":[[2023,7,25]]},"abstract":"<jats:p>PurposeThoracic radiographs are commonly used to evaluate patients with confirmed or suspected thoracic pathology. Proper patient positioning is more challenging in canine and feline radiography than in humans due to less patient cooperation and body shape variation. Improper patient positioning during radiograph acquisition has the potential to lead to a misdiagnosis. Asymmetrical hemithoraces are one of the indications of obliquity for which we propose an automatic classification method.ApproachWe propose a hemithoraces segmentation method based on convolutional neural networks and active contours. We utilized the U-Net model to segment the ribs and spine and then utilized active contours to find left and right hemithoraces. We then extracted features from the left and right hemithoraces to train an ensemble classifier, which include support vector machine, gradient boosting, and multi-layer perceptron. Five-fold cross-validation was used, thorax segmentation was evaluated by intersection over union (IoU), and symmetry classification was evaluated using precision, recall, area under curve, and F1 score.ResultsClassification of symmetry for 900 radiographs reported an F1 score of 82.8%. To test the robustness of the proposed thorax segmentation method to underexposure and overexposure, we synthetically corrupted properly exposed radiographs and evaluated results using IoU. The results showed that the model\u2019s IoU for underexposure and overexposure dropped by 2.1% and 1.2%, respectively.ConclusionsOur results indicate that the proposed thorax segmentation method is robust to poor exposure radiographs. The proposed thorax segmentation method can be applied to human radiography with minimal changes.<\/jats:p>","DOI":"10.1117\/1.jmi.10.4.044004","type":"journal-article","created":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T16:38:34Z","timestamp":1690303114000},"page":"1-15","source":"Crossref","is-referenced-by-count":6,"title":["Automatic classification of symmetry of hemithoraces in canine and feline radiographs"],"prefix":"10.1117","volume":"10","author":[{"given":"Peyman","family":"Tahghighi","sequence":"first","affiliation":[{"name":"Univ. of Guelph"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole","family":"Norena","sequence":"additional","affiliation":[{"name":"Univ. of Guelph"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0180-4716","authenticated-orcid":false,"given":"Eran","family":"Ukwatta","sequence":"additional","affiliation":[{"name":"Univ. of Guelph"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan B.","family":"Appleby","sequence":"additional","affiliation":[{"name":"Univ. of Guelph"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0938-6099","authenticated-orcid":false,"given":"Amin","family":"Komeili","sequence":"additional","affiliation":[{"name":"Univ. of Calgary"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"r1","article-title":"Diagnostic imaging for technicians: positioning and technique for thoracic and abdominal","author":"Axam","year":"2017"},{"key":"r2","first-page":"533","article-title":"Reducing error in radiographic interpretation","author":"Alexander","year":"2010"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-34380-9"},{"key":"r4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tvjl.2018.05.009"},{"key":"r5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPS49255.2021.9468228"},{"key":"r6","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5\u00a0mb model size","author":"Iandola","year":"2016"},{"key":"r7","article-title":"Mobilenets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"r8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-83515-3"},{"key":"r9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"r11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-44871-6_125"},{"key":"r12","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2775636"},{"key":"r13","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"r14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"r15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"r16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00133570"},{"key":"r17","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-015-1242-x"},{"key":"r18","article-title":"AGFA HealthCare","year":"2023"},{"key":"r19","article-title":"Automatic differentiation in pytorch","author":"Paszke","year":"2017"},{"key":"r20","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"r21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"r22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67389-9_44"},{"key":"r23","first-page":"6105","article-title":"Efficientnet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"r24","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-018-2303-4"},{"key":"r25","doi-asserted-by":"publisher","DOI":"10.1007\/s10237-019-01149-x"},{"key":"r26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jspd.2015.02.002"},{"key":"r27","doi-asserted-by":"publisher","DOI":"10.1016\/j.spinee.2015.01.018"},{"key":"r28","doi-asserted-by":"publisher","DOI":"10.1177\/0954411914531115"},{"key":"r29","doi-asserted-by":"publisher","DOI":"10.1186\/1748-7161-8-S2-O25"}],"container-title":["Journal of Medical Imaging"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-10\/issue-04\/044004\/Automatic-classification-of-symmetry-of-hemithoraces-in-canine-and-feline\/10.1117\/1.JMI.10.4.044004.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:35:19Z","timestamp":1790210119000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-10\/issue-04\/044004\/Automatic-classification-of-symmetry-of-hemithoraces-in-canine-and-feline\/10.1117\/1.JMI.10.4.044004.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,25]]},"references-count":29,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2023,7,1]]}},"URL":"https:\/\/doi.org\/10.1117\/1.jmi.10.4.044004","relation":{},"ISSN":["2329-4302","2329-4310"],"issn-type":[{"value":"2329-4302","type":"print"},{"value":"2329-4310","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,25]]}}}