{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T10:11:44Z","timestamp":1784283104163,"version":"3.55.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T00:00:00Z","timestamp":1713830400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T00:00:00Z","timestamp":1713830400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National Institute for Health and Care Research Central London - Patient Safety Research Collaboration","award":["NIHR204297"],"award-info":[{"award-number":["NIHR204297"]}]},{"DOI":"10.13039\/501100020194","name":"Wellcome \/ EPSRC Centre for Interventional and Surgical Sciences","doi-asserted-by":"publisher","award":["203145Z\/16\/Z"],"award-info":[{"award-number":["203145Z\/16\/Z"]}],"id":[{"id":"10.13039\/501100020194","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020194","name":"Wellcome \/ EPSRC Centre for Interventional and Surgical Sciences","doi-asserted-by":"publisher","award":["NS\/A000050\/1"],"award-info":[{"award-number":["NS\/A000050\/1"]}],"id":[{"id":"10.13039\/501100020194","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EPSRC-funded UCL Centre for Doctoral Training in Intelligent, Integrated Imaging in Healthcare","award":["EP\/S021930\/1"],"award-info":[{"award-number":["EP\/S021930\/1"]}]},{"name":"Department of Science, Innovation and Technology"},{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering","doi-asserted-by":"crossref","award":["CiET1819\/2\/36"],"award-info":[{"award-number":["CiET1819\/2\/36"]}],"id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>Obtaining large volumes of medical images, required for deep learning development, can be challenging in rare pathologies. Image augmentation and preprocessing offer viable solutions. This work explores the case of necrotising enterocolitis (NEC), a rare but life-threatening condition affecting premature neonates, with challenging radiological diagnosis. We investigate data augmentation and preprocessing techniques and propose two optimised pipelines for developing reliable computer-aided diagnosis models on a limited NEC dataset.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We present a NEC dataset of 1090 Abdominal X-rays (AXRs) from 364 patients and investigate the effect of geometric augmentations, colour scheme augmentations and their combination for NEC classification based on the ResNet-50 backbone. We introduce two pipelines based on colour contrast and edge enhancement, to increase the visibility of subtle, difficult-to-identify, critical NEC findings on AXRs and achieve robust accuracy in a challenging three-class NEC classification task.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Our results show that geometric augmentations improve performance, with Translation achieving +6.2%, while Flipping and Occlusion decrease performance. Colour augmentations, like Equalisation, yield modest improvements. The proposed Pr-1 and Pr-2 pipelines enhance model accuracy by +2.4% and +1.7%, respectively. Combining Pr-1\/Pr-2 with geometric augmentation, we achieve a maximum performance increase of 7.1%, achieving robust NEC classification.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>Based on an extensive validation of preprocessing and augmentation techniques, our work showcases the previously unreported potential of image preprocessing in AXR classification tasks with limited datasets. Our findings can be extended to other medical tasks for designing reliable classifier models with limited X-ray datasets. Ultimately, we also provide a benchmark for automated NEC detection and classification from AXRs.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11548-024-03107-0","type":"journal-article","created":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T14:01:27Z","timestamp":1713880887000},"page":"1223-1231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An investigation into augmentation and preprocessing for optimising X-ray classification in limited datasets: a case study on necrotising enterocolitis"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4969-0139","authenticated-orcid":false,"given":"Franciszek","family":"Nowak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0048-3179","authenticated-orcid":false,"given":"Ka-Wai","family":"Yung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1008-6402","authenticated-orcid":false,"given":"Jayaram","family":"Sivaraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1659-0207","authenticated-orcid":false,"given":"Paolo","family":"De Coppi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0980-3227","authenticated-orcid":false,"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2960-5252","authenticated-orcid":false,"given":"Stavros","family":"Loukogeorgakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0357-5996","authenticated-orcid":false,"given":"Evangelos B.","family":"Mazomenos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,23]]},"reference":[{"key":"3107_CR1","unstructured":"Rajpurkar P, Irvin J, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz C, Shpanskaya K, Lungren MP, Ng AY (2017) CheXNet: radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv:1711.05225"},{"key":"3107_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2019.103345","volume":"111","author":"S Deepak","year":"2019","unstructured":"Deepak S, Ameer PM (2019) Brain tumor classification using deep cnn features via transfer learning. Comput Biol Med 111:103345. https:\/\/doi.org\/10.1016\/j.compbiomed.2019.103345","journal-title":"Comput Biol Med"},{"key":"3107_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797","volume":"66","author":"A Bustos","year":"2020","unstructured":"Bustos A, Pertusa A, Salinas J-M, Iglesia-Vay\u00e1 M (2020) Padchest: a large chest x-ray image dataset with multi-label annotated reports. Med Image Anal 66:101797 arXiv:1901.07441","journal-title":"Med Image Anal"},{"key":"3107_CR4","doi-asserted-by":"publisher","unstructured":"Sirazitdinov I, Kholiavchenko M, Kuleev R, Ibragimov B (2019) Data augmentation for chest pathologies classification. In: IEEE 16th international symposium on biomedical imaging (ISBI 2019), pp 1216\u20131219. https:\/\/doi.org\/10.1109\/ISBI.2019.8759573","DOI":"10.1109\/ISBI.2019.8759573"},{"key":"3107_CR5","doi-asserted-by":"publisher","first-page":"115","DOI":"10.2174\/1573396315666190312093119","volume":"38","author":"C Bazacliu","year":"2019","unstructured":"Bazacliu C, Neu J (2019) Necrotizing enterocolitis: long term complications. Curr Pediatr Rev 38:115\u2013124. https:\/\/doi.org\/10.2174\/1573396315666190312093119","journal-title":"Curr Pediatr Rev"},{"issue":"6","key":"3107_CR6","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1016\/j.siny.2018.08.004","volume":"23","author":"ME Mowitz","year":"2018","unstructured":"Mowitz ME, Dukhovny D, Zupancic JAF (2018) The cost of necrotizing enterocolitis in premature infants. Semin Fetal Neonatal Med 23(6):416\u2013419. https:\/\/doi.org\/10.1016\/j.siny.2018.08.004","journal-title":"Semin Fetal Neonatal Med"},{"key":"3107_CR7","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.earlhumdev.2016.03.002","volume":"97","author":"HS Thakkar","year":"2016","unstructured":"Thakkar HS, Lakhoo K (2016) The surgical management of necrotising enterocolitis (nec). Early Hum Dev 97:25\u201328. https:\/\/doi.org\/10.1016\/j.earlhumdev.2016.03.002","journal-title":"Early Hum Dev"},{"issue":"8","key":"3107_CR8","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1016\/j.jpedsurg.2014.01.052","volume":"49","author":"NJ Wright","year":"2014","unstructured":"Wright NJ, Thyoka M, Kiely EM, Pierro A, De Coppi P, Cross KMK, Drake DD, Peters MJ, Curry JI (2014) The outcome of critically ill neonates undergoing laparotomy for necrotising enterocolitis in the neonatal intensive care unit: a 10-year review. J Pediatr Surg 49(8):1210\u20131214. https:\/\/doi.org\/10.1016\/j.jpedsurg.2014.01.052","journal-title":"J Pediatr Surg"},{"key":"3107_CR9","unstructured":"Kenny S (2021) Paediatric general surgery and urology - GIRFT Programme National Specialty Report"},{"issue":"2","key":"3107_CR10","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1002\/cld.888","volume":"15","author":"K Nowak","year":"2020","unstructured":"Nowak K (2020) Parenteral nutrition-associated liver disease. Clin Liver Disease (Hoboken) 15(2):59\u201362. https:\/\/doi.org\/10.1002\/cld.888","journal-title":"Clin Liver Disease (Hoboken)"},{"key":"3107_CR11","doi-asserted-by":"publisher","DOI":"10.3389\/fped.2023.1182597","author":"SJ McElroy","year":"2023","unstructured":"McElroy SJ, Lueschow SR (2023) State of the art review on machine learning and artificial intelligence in the study of neonatal necrotizing enterocolitis. Front Pediatr. https:\/\/doi.org\/10.3389\/fped.2023.1182597","journal-title":"Front Pediatr"},{"issue":"2","key":"3107_CR12","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1038\/s41390-022-02322-2","volume":"93","author":"A Sitek","year":"2022","unstructured":"Sitek A, Seliga-Siwecka J, P\u0142otka S, Grzeszczyk MK, Seliga S, W\u0142odarczyk K, Bokiniec R (2022) Artificial intelligence in the diagnosis of necrotising enterocolitis in newborns. Pediatr Res 93(2):376\u2013381. https:\/\/doi.org\/10.1038\/s41390-022-02322-2","journal-title":"Pediatr Res"},{"key":"3107_CR13","doi-asserted-by":"publisher","first-page":"51050","DOI":"10.1109\/ACCESS.2021.3069191","volume":"9","author":"W Gao","year":"2021","unstructured":"Gao W, Pei Y, Liang H, Lv J, Chen J, Zhong W (2021) Multimodal AI system for the rapid diagnosis and surgical prediction of necrotizing enterocolitis. IEEE Access 9:51050\u201351064. https:\/\/doi.org\/10.1109\/ACCESS.2021.3069191","journal-title":"IEEE Access"},{"key":"3107_CR14","unstructured":"Geiping J, Goldblum M, Somepalli G, Shwartz-Ziv R, Goldstein T, Wilson AG (2023) How much data are augmentations worth? An investigation into scaling laws, invariance, and implicit regularization arXiv:2210.06441"},{"key":"3107_CR15","doi-asserted-by":"publisher","first-page":"132144","DOI":"10.1109\/ACCESS.2022.3229591","volume":"10","author":"W Chokchaithanakul","year":"2022","unstructured":"Chokchaithanakul W, Punyabukkana P, Chuangsuwanich E (2022) Adaptive image preprocessing and augmentation for tuberculosis screening on out-of-domain chest x-ray dataset. IEEE Access 10:132144\u2013132152. https:\/\/doi.org\/10.1109\/ACCESS.2022.3229591","journal-title":"IEEE Access"},{"key":"3107_CR16","doi-asserted-by":"publisher","unstructured":"Av\u015far E (2021) Effects of image preprocessing on the performance of convolutional neural networks for pneumonia detection. In: INISTA 2021, pp 1\u20135. https:\/\/doi.org\/10.1109\/INISTA52262.2021.9548351","DOI":"10.1109\/INISTA52262.2021.9548351"},{"key":"3107_CR17","doi-asserted-by":"publisher","unstructured":"Heidari M, Mirniaharikandehei S, Khuzani AZ, Danala G, Qiu Y, Zheng B (2020) Improving the performance of cnn to predict the likelihood of covid-19 using chest x-ray images with preprocessing algorithms. Int J Med Inform 144:104284\u2013104284. https:\/\/doi.org\/10.1016\/j.ijmedinf.2020.104284","DOI":"10.1016\/j.ijmedinf.2020.104284"},{"issue":"1","key":"3107_CR18","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.cpet.2021.09.009","volume":"17","author":"N Hasani","year":"2022","unstructured":"Hasani N, Farhadi F, Morris MA, Nikpanah M, Rhamim A, Xu Y, Pariser A, Collins MT, Summers RM, Jones E, Siegel E, Saboury B (2022) Artificial intelligence in medical imaging and its impact on the rare disease community: threats, challenges and opportunities. PET Clin. 17(1):13\u201329. https:\/\/doi.org\/10.1016\/j.cpet.2021.09.009","journal-title":"PET Clin."},{"key":"3107_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770\u2013778. arXiv:1512.03385","DOI":"10.1109\/CVPR.2016.90"},{"key":"3107_CR20","doi-asserted-by":"publisher","unstructured":"Yousef R, Gupta G, Yousef N, Khari M (2022) A holistic overview of deep learning approach in medical imaging. Multimed Syst 28:881\u2013914. https:\/\/doi.org\/10.1007\/s00530-021-00884-5","DOI":"10.1007\/s00530-021-00884-5"},{"key":"3107_CR21","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3107_CR22","doi-asserted-by":"publisher","unstructured":"Bai Q, Gui Z, Yi L, Zhang P, Hou H (2022) X-ray image enhancement based on gradient domain and illumination image estimation for complex castings. Signal Image Video P (preprint) , https:\/\/doi.org\/10.21203\/rs.3.rs-1586915\/v1","DOI":"10.21203\/rs.3.rs-1586915\/v1"},{"key":"3107_CR23","doi-asserted-by":"crossref","unstructured":"Guo X (2016) LIME: a method for low-light IMage enhancement. arXiv:1605.05034","DOI":"10.1145\/2964284.2967188"},{"key":"3107_CR24","unstructured":"Xu K, Hu W, Leskovec J, Jegelka S (2019) How powerful are graph neural networks?. arXiv:1810.00826"},{"key":"3107_CR25","doi-asserted-by":"publisher","unstructured":"Faker O, Dogdu E (2019) Intrusion detection using big data and deep learning techniques. In: ACMSE , pp 86\u201393. https:\/\/doi.org\/10.1145\/3299815.3314439","DOI":"10.1145\/3299815.3314439"},{"key":"3107_CR26","doi-asserted-by":"crossref","unstructured":"Kazeminia S, Sadafi A, Makhro A, Bogdanova A, Albarqouni S, Marr C Anomaly-aware multiple instance learning for rare anemia disorder classification. In: Medical image computing and computer assisted intervention \u2013 MICCAI 2022, pp 341\u2013350. arXiv:2207.01742","DOI":"10.1007\/978-3-031-16452-1_33"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03107-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-024-03107-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03107-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T11:26:39Z","timestamp":1718364399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-024-03107-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,23]]},"references-count":26,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["3107"],"URL":"https:\/\/doi.org\/10.1007\/s11548-024-03107-0","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,23]]},"assertion":[{"value":"5 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Ethics was obtained from the Great Ormond Street Hospital, Clinical Research Adoptions Committee (CRAC) for retrospective collection of fully anonymised AXRs. The study is registered under IRAS: 21DS17.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"This article does not contain patient data.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}