{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T12:53:44Z","timestamp":1782824024462,"version":"3.54.5"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:00:00Z","timestamp":1743033600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019266","name":"Korea Medical Device Development Fund","doi-asserted-by":"publisher","award":["1711179383, RS-2022-00141185"],"award-info":[{"award-number":["1711179383, RS-2022-00141185"]}],"id":[{"id":"10.13039\/100019266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec>\n<jats:title>\nBackground\n<\/jats:title>\n<jats:p>Developmental Dysplasia of the Hip (DDH) is a relatively common hip joint disorders in infants, affecting one to three per a thousand births. If found early, it can be treated preemptively by simple non-invasive methods. But if not, then several surgical procedures may be required that can cause high economic burden. The accuracy of diagnosis using ultrasound (US) images heavily relies on locating anatomical landmarks on the image. However, there is an intra-observer\/inter-observer variability in determining the exact location of the landmarks. In this study, an automated scan quality assessment system of pelvic US image by evaluating quality of five landmarks using transfer learning models was proposed.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>\nMethods\n<\/jats:title>\n<jats:p>US images from 1,891 subjects were obtained at two hospitals in the Republic of Korea (henceforth Korea). Also, an ensemble system was developed using transfer learning models to automatically evaluate the scan quality by scoring five anatomical landmarks. Gradient-weighted class activation mapping was used for verifying whether models that reflect the geographical features of the images had been properly trained. Considering the applicability in the real-time environment, this study proposes an alternative sequence method (ASM) that has been discovered to have improved the lapse of scan quality assessment.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>\nResults\n<\/jats:title>\n<jats:p>All the selected models achieved kappa values of 0.6 or higher, indicating substantial agreement, and the AUC score for classifying standard images based on the total score was 0.89. The activation map of the trained models properly reflected the structural features of the image. The time lapse for standard image classification was 0.35 second per image in full sequence method, and that of the three versions - ASM-1, ASM-2, ASM-3 - were 0.27, 0.22, and 0.20, respectively.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0317251","type":"journal-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:23:08Z","timestamp":1743096188000},"page":"e0317251","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automated scan quality evaluation for DDH using transfer learning: Development of a novel ensemble system"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6758-9935","authenticated-orcid":true,"given":"Yeon-Kyoung","family":"Ko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung-Bo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2733-6992","authenticated-orcid":true,"given":"Si-Wook","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,3,27]]},"reference":[{"issue":"9572","key":"pone.0317251.ref001","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1016\/S0140-6736(07)60710-7","article-title":"Developmental dysplasia of the hip","volume":"369","author":"C Dezateux","year":"2007","journal-title":"The Lancet"},{"issue":"2","key":"pone.0317251.ref002","doi-asserted-by":"crossref","first-page":"196","DOI":"10.4055\/cios21032","article-title":"Three-dimensional evaluation of innominate bone rotation in female patients with developmental dysplasia of the hip","volume":"14","author":"N Sako","year":"2022","journal-title":"Clin Orthop Surg"},{"issue":"4","key":"pone.0317251.ref003","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1302\/0301-620X.83B4.0830579","article-title":"Hip disease and the prognosis of total hip replacements. A review of 53,698 primary total hip replacements reported to the Norwegian Arthroplasty Register 1987-99","volume":"83","author":"O Furnes","year":"2001","journal-title":"J Bone Joint Surg Br"},{"issue":"1","key":"pone.0317251.ref004","doi-asserted-by":"crossref","first-page":"141","DOI":"10.4055\/cios21075","article-title":"An upgrade of the international hip dysplasia institute classification for developmental dysplasia of the hip","volume":"14","author":"J Doski","year":"2022","journal-title":"Clin Orthop Surg"},{"issue":"2","key":"pone.0317251.ref005","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/s00264-006-0097-8","article-title":"Indicators of successful use of the Pavlik harness in infants with developmental dysplasia of the hip","volume":"31","author":"H Atalar","year":"2007","journal-title":"Int Orthop"},{"issue":"1","key":"pone.0317251.ref006","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1002\/ebch.1891","article-title":"Cochrane review: screening programmes for developmental dysplasia of the hip in newborn infants","volume":"8","author":"D Shorter","year":"2013","journal-title":"Evid Based Child Health"},{"issue":"6","key":"pone.0317251.ref007","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.1007\/s43465-021-00455-w","article-title":"Artificial intelligence to automatically assess scan quality in hip ultrasound","volume":"55","author":"AR Hareendranathan","year":"2021","journal-title":"Indian J Orthop"},{"issue":"1","key":"pone.0317251.ref008","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s11548-015-1239-5","article-title":"A technique for semiautomatic segmentation of echogenic structures in 3D ultrasound, applied to infant hip dysplasia","volume":"11","author":"AR Hareendranathan","year":"2016","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"3","key":"pone.0317251.ref009","first-page":"212","article-title":"Risk factors for developmental dysplasia of the hip: ultrasonographic findings in the neonatal period","volume":"11","author":"CE Bache","year":"2002","journal-title":"J Pediatr Orthop B"},{"issue":"1","key":"pone.0317251.ref010","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1302\/0301-620X.71B1.2644290","article-title":"Ultrasound screening of hips at risk for CDH. Failure to reduce the incidence of late cases","volume":"71","author":"NM Clarke","year":"1989","journal-title":"J Bone Joint Surg Br"},{"issue":"6","key":"pone.0317251.ref011","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1097\/01241398-198411000-00015","article-title":"Fundamentals of sonographic diagnosis of infant hip dysplasia","volume":"4","author":"R Graf","year":"1984","journal-title":"J Pediatr Orthop"},{"issue":"4","key":"pone.0317251.ref012","doi-asserted-by":"crossref","first-page":"e315","DOI":"10.1097\/BPO.0000000000002065","article-title":"Interobserver variability of hip dysplasia indices on sweep ultrasound for novices, experts, and artificial intelligence","volume":"42","author":"S Ghasseminia","year":"2022","journal-title":"Journal of Pediatric Orthopaedics"},{"issue":"7","key":"pone.0317251.ref013","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1016\/j.media.2013.05.003","article-title":"Localizing target structures in ultrasound video - a phantom study","volume":"17","author":"R Kwitt","year":"2013","journal-title":"Med Image Anal"},{"issue":"11","key":"pone.0317251.ref014","doi-asserted-by":"crossref","first-page":"2728","DOI":"10.1016\/j.ultrasmedbio.2014.06.006","article-title":"Standard plane localization in ultrasound by radial component model and selective search","volume":"40","author":"D Ni","year":"2014","journal-title":"Ultrasound Med Biol"},{"key":"pone.0317251.ref015","first-page":"402","article-title":"Integration of local and global features for anatomical object detection in ultrasound.","author":"B Rahmatullah","year":"2012"},{"key":"pone.0317251.ref016","first-page":"133","article-title":"Searching for structures of interest in an ultrasound video sequence.","author":"MA Maraci","year":"2014,"},{"issue":"6","key":"pone.0317251.ref017","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.1109\/TCYB.2017.2685080","article-title":"Ultrasound Standard Plane Detection Using a Composite Neural Network Framework","volume":"47","author":"H Chen","year":"2017","journal-title":"IEEE Trans Cybern"},{"key":"pone.0317251.ref018","first-page":"124","article-title":"Automatic near real-time evaluation of 3D ultrasound scan adequacy for developmental dysplasia of the hip.","author":"O Paserin","year":"2017"},{"key":"pone.0317251.ref019","first-page":"365","article-title":"Real time RNN based 3D ultrasound scan adequacy for developmental dysplasia of the hip.","author":"O Paserin","year":"2018"},{"key":"pone.0317251.ref020","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision. 2017, pp. 618\u201326.","DOI":"10.1109\/ICCV.2017.74"},{"key":"pone.0317251.ref021","author":"Industry-Academic Cooperation Foundation, K.U., Pediatric hip data.","year":"2021"},{"key":"pone.0317251.ref022","first-page":"1","article-title":"Impact of scan quality on AI assessment of hip dysplasia ultrasound","author":"AR Hareendranathan","year":"2022","journal-title":"Journal of Ultrasound"},{"key":"pone.0317251.ref023","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"O Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"pone.0317251.ref024","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1186\/s12880-022-00793-7","article-title":"Transfer learning for medical image classification: a literature review","volume":"22","author":"HE Kim","year":"2022","journal-title":"BMC Med Imaging"},{"issue":"1602.07360","key":"pone.0317251.ref025","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size","volume":"abs","author":"FN Iandola","year":"2016","journal-title":"arXiv"},{"key":"pone.0317251.ref026","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, pp. 770\u201378.","DOI":"10.1109\/CVPR.2016.90"},{"key":"pone.0317251.ref027","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2017, pp. 4700\u20138.","DOI":"10.1109\/CVPR.2017.243"},{"issue":"1","key":"pone.0317251.ref028","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.aci.2018.08.003","article-title":"Classification assessment methods","volume":"17","author":"A Tharwat","year":"2020","journal-title":"Applied computing and informatics"},{"issue":"1","key":"pone.0317251.ref029","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"JR Landis","year":"n.d","journal-title":"Biometrics"},{"issue":"2","key":"pone.0317251.ref030","doi-asserted-by":"crossref","first-page":"2397","DOI":"10.1007\/s13369-021-06182-6","article-title":"Comparative analysis of AlexNet, ResNet18 and SqueezeNet with diverse modification and arduous implementation","volume":"47","author":"A Ullah","year":"2022","journal-title":"Arabian Journal for Science and Engineering"},{"key":"pone.0317251.ref031","doi-asserted-by":"crossref","first-page":"104887","DOI":"10.1016\/j.compbiomed.2021.104887","article-title":"A comparative analysis of eleven neural networks architectures for small datasets of lung images of COVID-19 patients toward improved clinical decisions","volume":"139","author":"Y Yang","year":"2021","journal-title":"Comput Biol Med"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:24:34Z","timestamp":1743096274000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317251"}},"subtitle":[],"editor":[{"given":"Fahad Farhan","family":"Almutairi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,3,27]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0317251","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,27]]}}}