{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T04:08:16Z","timestamp":1751602096632,"version":"3.41.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T00:00:00Z","timestamp":1747353600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T00:00:00Z","timestamp":1747353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>\n              <jats:bold>Purpose<\/jats:bold>\n            <\/jats:title>\n            <jats:p>Trauma-induced rib fractures are a common injury. The number and characteristics of these fractures influence whether a patient is treated nonoperatively or surgically. Rib fractures are typically diagnosed using CT scans, yet 19.2\u201326.8% of fractures are still missed during assessment. Another challenge in managing rib fractures is the interobserver variability in their classification. Purpose of this study was to develop and assess an automated method that detects rib fractures in CT scans, and classifies them according to the Chest Wall Injury Society (CWIS) classification.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>\n              <jats:bold>Methods<\/jats:bold>\n            <\/jats:title>\n            <jats:p>198 CT scans were collected, of which 170 were used for training and internal validation, and 28 for external validation. Fractures and their classifications were manually annotated in each of the scans. A detection and classification network was trained for each of the three components of the CWIS classifications. In addition, a rib number labeling network was trained for obtaining the rib number of a fracture. Experiments were performed to assess the method performance.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>\n              <jats:bold>Results<\/jats:bold>\n            <\/jats:title>\n            <jats:p>On the internal test set, the method achieved a detection sensitivity of 80%, at a precision of 87%, and an F1-score of 83%, with a mean number of FPPS (false positives per scan) of 1.11. Classification sensitivity varied, with the lowest being 25% for complex fractures and the highest being 97% for posterior fractures. The correct rib number was assigned to 94% of the detected fractures. The custom-trained nnU-Net correctly labeled 95.5% of all ribs and 98.4% of fractured ribs in 30 patients. The detection and classification performance on the external validation dataset was slightly better, with a fracture detection sensitivity of 84%, precision of 85%, F1-score of 84%, FPPS of 0.96 and 95% of the fractures were assigned the correct rib number.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>\n              <jats:bold>Conclusion<\/jats:bold>\n            <\/jats:title>\n            <jats:p>The method developed is able to accurately detect and classify rib fractures in CT scans, there is room for improvement in the (rare and) underrepresented classes in the training set.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s11548-025-03390-5","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T10:01:05Z","timestamp":1747389665000},"page":"1381-1389","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A deep learning-based approach to automated rib fracture detection and CWIS classification"],"prefix":"10.1007","volume":"20","author":[{"given":"Victoria","family":"Marting","sequence":"first","affiliation":[]},{"given":"Noor","family":"Borren","sequence":"additional","affiliation":[]},{"given":"Max R.","family":"van Diepen","sequence":"additional","affiliation":[]},{"given":"Esther M. M.","family":"van Lieshout","sequence":"additional","affiliation":[]},{"given":"Mathieu M. E.","family":"Wijffels","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8257-7759","authenticated-orcid":false,"given":"Theo","family":"van Walsum","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,16]]},"reference":[{"issue":"2","key":"3390_CR1","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/s10140-021-02000-6","volume":"29","author":"M Azuma","year":"2022","unstructured":"Azuma M, Nakada H, Takei M, Nakamura K, Katsuragawa S, Shinkawa N, Terada T, Masuda R, Hattori Y, Ide T, Kimura A, Shimomura M, Kawano M, Matsumura K, Meiri T, Ochiai H, Hirai T (2022) Detection of acute rib fractures on CT images with convolutional neural networks: effect of location and type of fracture and reader\u2019s experience. Emerg Radiol 29(2):317\u2013328","journal-title":"Emerg Radiol"},{"issue":"2","key":"3390_CR2","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1148\/radiol.2018180492","volume":"289","author":"N Banaste","year":"2018","unstructured":"Banaste N, Caurier B, Bratan F, Bergerot JF, Thomson V, Millet I (2018) Whole-body ct in patients with multiple traumas: factors leading to missed injury. Radiology 289(2):374\u2013383","journal-title":"Radiology"},{"key":"3390_CR3","doi-asserted-by":"crossref","unstructured":"Baumgartner M, Jaeger PF, Isensee F, Maier-Hein KH (2021) nndetection: a self-configuring method for medical object detection. In: Medical image computing and computer assisted intervention: MICCAI 2021. Springer","DOI":"10.1007\/978-3-030-87240-3_51"},{"key":"3390_CR4","doi-asserted-by":"crossref","unstructured":"Cho SH, Sung YM, Kim MS (2012) Missed rib fractures on evaluation of initial chest ct for trauma patients: pattern analysis and diagnostic value of coronal multiplanar reconstruction images with multidetector row ct. Br J Radiol 85(1018)","DOI":"10.1259\/bjr\/28575455"},{"key":"3390_CR5","doi-asserted-by":"crossref","unstructured":"de\u00a0Moya M, Nirula R, Biffl W (2017) Rib fixation: Who, what, when? Trauma Surg Acute Care Open 2(1)","DOI":"10.1136\/tsaco-2016-000059"},{"issue":"3","key":"3390_CR6","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1016\/j.injury.2018.01.004","volume":"49","author":"MB de Jong","year":"2018","unstructured":"de Jong MB, Houwert RM, van Heerde S, de Steenwinkel M, Hietbrink F, Leenen L (2018) Surgical treatment of rib fracture nonunion: a single center experience. Injury 49(3):599\u2013603","journal-title":"Injury"},{"issue":"2","key":"3390_CR7","doi-asserted-by":"publisher","first-page":"E40","DOI":"10.1097\/TA.0000000000002282","volume":"88","author":"JG Edwards","year":"2020","unstructured":"Edwards JG, Clarke P, Pieracci FM, Bemelman M, Black EA, Doben A, Gasparri M, Gross R, Wu J, Long WB, Lottenberg L, Majercik S, Marasco S, Mayberry J, Sarani B, Schulz-Drost S, Van Boerum D, Whitbeck SA, White T (2020) Taxonomy of multiple rib fractures: results of the chest wall injury society international consensus survey. J Trauma Acute Care Surg 88(2):E40\u2013E45","journal-title":"J Trauma Acute Care Surg"},{"issue":"4","key":"3390_CR8","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1016\/j.surg.2005.07.022","volume":"138","author":"BT Flagel","year":"2005","unstructured":"Flagel BT, Luchette FA, Reed RL, Esposito TJ, Davis KA, Santaniello JM, Gamelli RL (2005) Half-a-dozen ribs: the breakpoint for mortality. Surgery 138(4):717\u2013725","journal-title":"Surgery"},{"issue":"2","key":"3390_CR9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl S, Petersen J, Maier-Hein KH (2021) nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2):203\u2013211","journal-title":"Nat Methods"},{"key":"3390_CR10","unstructured":"Jaeger PF, Kohl SAA, Bickelhaupt S, Isensee F, Kuder TA, Schlemmer HP, Maier-Hein KH (2019) Retina u-net: embarrassingly simple exploitation of segmentation supervision for medical object detection. In: Dalca A, Mcdermott M, Alsentzer Eea (eds) Proceedings of machine learning research, pp 171\u2013183"},{"issue":"1146","key":"3390_CR11","doi-asserted-by":"publisher","first-page":"20221006","DOI":"10.1259\/bjr.20221006","volume":"96","author":"N Li","year":"2023","unstructured":"Li N, Wu Z, Jiang C, Sun L, Li B, Guo J, Liu F, Zhou Z, Qin H, Tan W, Tian L (2023) An automatic fresh rib fracture detection and positioning system using deep learning. Br J Radiol 96(1146):20221006","journal-title":"Br J Radiol"},{"issue":"9","key":"3390_CR12","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.1007\/s00256-021-03709-8","volume":"50","author":"XH Meng","year":"2021","unstructured":"Meng XH, Wu DJ, Wang Z, Ma XL, Dong XM, Liu AE, Chen L (2021) A fully automated rib fracture detection system on chest ct images and its impact on radiologist performance. Skelet Radiol 50(9):1821\u20131828","journal-title":"Skelet Radiol"},{"issue":"1","key":"3390_CR13","doi-asserted-by":"publisher","first-page":"8363","DOI":"10.1038\/s41598-022-12453-5","volume":"12","author":"A Niiya","year":"2022","unstructured":"Niiya A, Murakami K, Kobayashi R, Sekimoto A, Saeki M, Toyofuku K, Kato M, Shinjo H, Ito Y, Takei M, Murata C, Ohgiya Y (2022) Development of an artificial intelligence-assisted computed tomography diagnosis technology for rib fracture and evaluation of its clinical usefulness. Sci Rep 12(1):8363","journal-title":"Sci Rep"},{"issue":"4","key":"3390_CR14","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/s00068-018-0918-7","volume":"45","author":"J Peek","year":"2019","unstructured":"Peek J, Smeeing D, Hietbrink F, Houwert RM, Marsman M, de Jong MB (2019) Comparison of analgesic interventions for traumatic rib fractures: a systematic review and meta-analysis. Eur J Trauma Emerg Surg 45(4):597\u2013622","journal-title":"Eur J Trauma Emerg Surg"},{"key":"3390_CR15","doi-asserted-by":"crossref","unstructured":"Peek J, Ochen Y, Saillant N, Groenwold RHH, Leenen LPH, Uribe-Leitz T, Houwert RM, Heng M (2020) Traumatic rib fractures: a marker of severe injury. a nationwide study using the national trauma data bank. Trauma Surg Acute Care Open 5(1)","DOI":"10.1136\/tsaco-2020-000441"},{"issue":"2","key":"3390_CR16","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1007\/s00264-017-3612-1","volume":"42","author":"FM Pieracci","year":"2018","unstructured":"Pieracci FM, Agarwal S, Doben A, Shiroff A, Lottenberg L, Whitbeck SA, White TW (2018) Indications for surgical stabilization of rib fractures in patients without flail chest: surveyed opinions of members of the chest wall injury society. Int Orthop 42(2):401\u2013408","journal-title":"Int Orthop"},{"issue":"4","key":"3390_CR17","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/s00068-018-0969-9","volume":"45","author":"MG Van Vledder","year":"2019","unstructured":"Van Vledder MG, Kwakernaak V, Hagenaars T, Van Lieshout E, Verhofstad M (2019) Patterns of injury and outcomes in the elderly patient with rib fractures: a multi-center observational study. Eur J Trauma Emerg Surg 45(4):575\u2013583","journal-title":"Eur J Trauma Emerg Surg"},{"issue":"6","key":"3390_CR18","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1097\/TA.0000000000003766","volume":"93","author":"S Van Wijck","year":"2022","unstructured":"Van Wijck S, Curran C, Sauaia A, Van Lieshout E, Whitbeck S, Edwards JG, Pieracci FM, Wijffels M (2022) Interobserver agreement for the chest wall injury society taxonomy of rib fractures using computed tomography images. J Trauma Acute Care Surg 93(6):736\u2013742","journal-title":"J Trauma Acute Care Surg"},{"issue":"3","key":"3390_CR19","doi-asserted-by":"publisher","first-page":"1824","DOI":"10.1007\/s00330-022-09156-w","volume":"33","author":"S Wang","year":"2023","unstructured":"Wang S, Wu D, Ye L, Chen Z, Zhan Y, Li Y (2023) Assessment of automatic rib fracture detection on chest CT using a deep learning algorithm. Eur Radiol 33(3):1824\u20131834","journal-title":"Eur Radiol"},{"key":"3390_CR20","doi-asserted-by":"crossref","unstructured":"Wasserthal J, Breit HC, Meyer MT, Pradella M, Hinck D, Sauter AW, Heye T, Boll DT, Cyriac J, Yang S, Bach M, Segeroth M (2023) TotalSegmentator: robust segmentation of 104 anatomic structures in CT images. Radiol Artif Intell 5(5):e230024","DOI":"10.1148\/ryai.230024"},{"key":"3390_CR21","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1186\/s13017-019-0258-x","volume":"14","author":"M Wijffels","year":"2019","unstructured":"Wijffels M, Prins J, Polinder S, Blokhuis TJ, De Loos ER, Den Boer RH, Flikweert ER, Pull Ter Gunne AF, Ringburg AN, Spanjersberg WR, Van Huijstee PJ, Montfort G, Vermeulen J, Vos DI, Verhofstad M, Van Lieshout E (2019) Early fixation versus conservative therapy of multiple, simple rib fractures (fixcon): protocol for a multicenter randomized controlled trial. World J Emerg Surg 14:38","journal-title":"World J Emerg Surg"},{"key":"3390_CR22","doi-asserted-by":"crossref","unstructured":"Yao L, Guan X, Song X, Tan Y, Wang C, Jin C, Chen M, Wang H (2021) Rib fracture detection system based on deep learning. Sci Rep 11(1)","DOI":"10.1038\/s41598-021-03002-7"},{"key":"3390_CR23","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.clinimag.2021.09.010","volume":"81","author":"QQ Zhou","year":"2022","unstructured":"Zhou QQ, Hu ZC, Tang W, Xia ZY, Wang JS, Zhang RG, Li XY, Chen CY, Zhang B, Lu LQ, Zhang H (2022) Precise anatomical localization and classification of rib fractures on ct using a convolutional neural network. Clin Imaging 81:24\u201332","journal-title":"Clin Imaging"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03390-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03390-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03390-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T14:51:52Z","timestamp":1751554312000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03390-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,16]]},"references-count":23,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["3390"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03390-5","relation":{},"ISSN":["1861-6429"],"issn-type":[{"type":"electronic","value":"1861-6429"}],"subject":[],"published":{"date-parts":[[2025,5,16]]},"assertion":[{"value":"14 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Mathieu M.E. Wijffels is a clinical consultant for KLS Martin and Johnson & Johnson. The other authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The study was performed in accordance with the ethical standards as laid down in the 1964 Declaration of Helsinki. The Erasmus MC data were retrospectively collected and anonymized CT scans. An ethical approval waiver was granted by the Medical Research Ethics Committee under the reference number MEC-2023-0039. The FixCon trial was approved by the Medical Research Ethics Committee Erasmus MC (MEC-2018-067). Patients signed informed consent to participate in the FixCon study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}