{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T18:05:28Z","timestamp":1784657128187,"version":"3.55.0"},"reference-count":37,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Magnetic resonance imaging (MRI) is widely considered the gold standard for evaluating Crohn\u2019s disease anoperineal lesions. However, despite its central role in clinical evaluation, automated methods specifically dedicated to the analysis of these lesions remain rare. This is particularly challenging in the context of anoperineal lesions due to (i) the diversity of MRI sequences, (ii) the small size of cohorts available to train complex models, and (iii) the absence of a standard shape for lesions. In this context, we explore an alternative strategy based on interpretable asymmetry features in axial MRIs, explicitly capturing morphological and intensity differences between the left and right sides of the perineal region. These features were used to either classify images as containing or not anoperineal lesions, or to precisely locate a lesion on an MRI slice. We apply this method on a small cohort of 44 patients affected by Crohn\u2019s disease, including 134 sequences of MRI of various types (38 T1 sequences, 74 T2 sequences, etc). First, a proof-of-concept dataset was constructed, including images either clearly presenting lesions or not (thus excluding symmetrical lesions), to prove that the asymmetry features we compute are sensitive to the presence of asymmetric lesions on MRI images. Importantly, we were able to show that the asymmetry features are not particularly sensitive to MRI sequences\u2019 type, or patients\u2019 effect, even with limited annotated datasets. The classification model demonstrates promising diagnostic performance, achieving an Area Under Curve (AUC) greater than 0.85 on the proof-of-concept dataset. However, when making predictions on the validation and test dataset, the AUCs drop to 0.667 and 0.647 respectively. The model struggles to generalize to all kinds of lesions, particularly to classify lesions slices when symmetrical (horseshoe) lesions are observed. Additionally, the method designed to locate a lesion in an image exhibited good precision, with a median distance of 1 centimeter between the detected area and the actual lesion position on our proof-of-concept dataset and 1.2 centimeter on the complete dataset, indicating its potential usefulness in future studies focused on standardized assessment of anoperineal lesions.<\/jats:p>","DOI":"10.1371\/journal.pone.0340243","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T17:40:57Z","timestamp":1784655657000},"page":"e0340243","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sequence-robust MRI asymmetry measures for the detection of anoperineal lesions in Crohn\u2019s disease on axial pelvic MRI scans"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5243-2931","authenticated-orcid":true,"given":"Corentin","family":"Lucas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myriam","family":"Bontonou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Aubry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Ogier-Denis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Bouguen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuelle","family":"Becker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3068-5675","authenticated-orcid":true,"given":"Yann","family":"Le Cunff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"issue":"3","key":"pone.0340243.ref001","article-title":"The Impact of Crohn\u2019s Perianal Fistula on Quality of Life: Results of an International Patient Survey","volume":"5","author":"A Spinelli","year":"2023","journal-title":"Crohns Colitis 360"},{"issue":"5","key":"pone.0340243.ref002","first-page":"3674","article-title":"Precise and comprehensive evaluation of perianal fistulas, classification and related complications using magnetic resonance imaging","volume":"15","author":"W-W Zhao","year":"2023","journal-title":"Am J Transl Res"},{"issue":"10","key":"pone.0340243.ref003","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1016\/j.dld.2007.07.154","article-title":"The natural history of perianal Crohn\u2019s disease","volume":"39","author":"SB Ingle","year":"2007","journal-title":"Dig Liver Dis"},{"issue":"37","key":"pone.0340243.ref004","doi-asserted-by":"crossref","first-page":"13205","DOI":"10.3748\/wjg.v20.i37.13205","article-title":"Treatment of peri-anal fistula in Crohn\u2019s disease","volume":"20","author":"GS Sica","year":"2014","journal-title":"World J Gastroenterol"},{"issue":"24","key":"pone.0340243.ref005","doi-asserted-by":"crossref","first-page":"3866","DOI":"10.3748\/wjg.v19.i24.3866","article-title":"Clinical prognostic factors for disabling Crohn\u2019s disease: a systematic review and meta-analysis","volume":"19","author":"CC Dias","year":"2013","journal-title":"World J Gastroenterol"},{"issue":"3","key":"pone.0340243.ref006","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1148\/radiol.2016151491","article-title":"MR Imaging of Perianal Crohn Disease","volume":"282","author":"SP Sheedy","year":"2017","journal-title":"Radiology"},{"issue":"12","key":"pone.0340243.ref007","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.1016\/j.dld.2014.08.003","article-title":"Magnetic resonance imaging and clinical assessments for perianal Crohn\u2019s disease: gain and limits","volume":"46","author":"A Garros","year":"2014","journal-title":"Dig Liver Dis"},{"key":"pone.0340243.ref008","first-page":"27","article-title":"MRI of perianal fistulas in Crohn\u2019s disease","volume":"91","author":"A Reginelli","year":"2020","journal-title":"Acta Biomed"},{"key":"pone.0340243.ref009","doi-asserted-by":"crossref","first-page":"128487","DOI":"10.1016\/j.eswa.2025.128487","article-title":"Deep learning framework for enhanced MRI analysis in healthcare diagnosis","volume":"292","author":"X Wen","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"7","key":"pone.0340243.ref010","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0304757","article-title":"Deep learning empowered breast cancer diagnosis: Advancements in detection and classification","volume":"19","author":"J Ahmad","year":"2024","journal-title":"PLoS One"},{"key":"pone.0340243.ref011","doi-asserted-by":"crossref","first-page":"107624","DOI":"10.1016\/j.cmpb.2023.107624","article-title":"Automatic detection of prostate cancer grades and chronic prostatitis in biparametric MRI","volume":"239","author":"O Bashkanov","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"issue":"1","key":"pone.0340243.ref012","article-title":"Development and Validation of a Deep Learning-Based Synthetic Bone-Suppressed Model for Pulmonary Nodule Detection in Chest Radiographs","volume":"6","author":"H Kim","year":"2023","journal-title":"JAMA Netw Open"},{"key":"pone.0340243.ref013","doi-asserted-by":"crossref","first-page":"106796","DOI":"10.1016\/j.oraloncology.2024.106796","article-title":"Deep learning for the automatic detection and segmentation of parotid gland tumors on MRI","volume":"152","author":"R Zhang","year":"2024","journal-title":"Oral Oncol"},{"issue":"3","key":"pone.0340243.ref014","doi-asserted-by":"crossref","first-page":"778","DOI":"10.3390\/s21030778","article-title":"Brain asymmetry detection and machine learning classification for diagnosis of early dementia","volume":"21","author":"NJ Herzog","year":"2021","journal-title":"Sensors"},{"key":"pone.0340243.ref015","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s12859-020-03936-1","article-title":"MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction","volume":"22","author":"C Han","year":"2021","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"pone.0340243.ref016","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/s12911-023-02114-6","article-title":"MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques","volume":"23","author":"S Saeedi","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"issue":"23","key":"pone.0340243.ref017","doi-asserted-by":"crossref","first-page":"4285","DOI":"10.3748\/wjg.v23.i23.4285","article-title":"Magnetic resonance imaging may predict deep remission in patients with perianal fistulizing Crohn\u2019s disease","volume":"23","author":"L Thomassin","year":"2017","journal-title":"World J Gastroenterol"},{"issue":"5","key":"pone.0340243.ref018","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1093\/ecco-jcc\/jjab168","article-title":"Fibrosis and MAGNIFI-CD Activity Index at Magnetic Resonance Imaging to Predict Treatment Outcome in Perianal Fistulizing Crohn\u2019s Disease Patients","volume":"16","author":"KL van Rijn","year":"2022","journal-title":"J Crohns Colitis"},{"issue":"11","key":"pone.0340243.ref019","doi-asserted-by":"crossref","first-page":"2135","DOI":"10.3390\/diagnostics11112135","article-title":"Quantitative Magnetic Resonance Imaging in Perianal Crohn\u2019s Disease at 1.5 and 3.0 T: A Feasibility Study","volume":"11","author":"A Alyami","year":"2021","journal-title":"Diagnostics"},{"issue":"4","key":"pone.0340243.ref020","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1016\/0305-0483(96)00010-2","article-title":"Effect of data standardization on neural network training","volume":"24","author":"M Shanker","year":"1996","journal-title":"Omega"},{"issue":"1","key":"pone.0340243.ref021","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-023-00727-2","article-title":"A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications","volume":"10","author":"L Alzubaidi","year":"2023","journal-title":"J Big Data"},{"key":"pone.0340243.ref022","doi-asserted-by":"crossref","first-page":"786802","DOI":"10.1155\/2015\/786802","article-title":"MRI for Crohn\u2019s Disease: Present and Future","volume":"2015","author":"K Yoon","year":"2015","journal-title":"BioMed Research International"},{"issue":"5","key":"pone.0340243.ref023","doi-asserted-by":"crossref","first-page":"1508","DOI":"10.1016\/j.gastro.2003.08.025","article-title":"AGA technical review on perianal Crohn\u2019s disease","volume":"125","author":"WJ Sandborn","year":"2003","journal-title":"Gastroenterology"},{"issue":"9","key":"pone.0340243.ref024","doi-asserted-by":"crossref","first-page":"3183","DOI":"10.1007\/s00261-024-04326-4","article-title":"Deep learning in magnetic resonance enterography for Crohn\u2019s disease assessment: a systematic review","volume":"49","author":"O Brem","year":"2024","journal-title":"Abdom Radiol (NY)"},{"issue":"1","key":"pone.0340243.ref025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10044-023-01206-3","article-title":"Distinguishing between Crohn\u2019s disease and ulcerative colitis using deep learning models with interpretability","volume":"27","author":"J Maur\u00edcio","year":"2024","journal-title":"Pattern Analysis and Applications"},{"issue":"6","key":"pone.0340243.ref026","article-title":"Automatic lesion detection, segmentation and characterization via 3D multiscale morphological sifting in breast MRI","volume":"6","author":"H Min","year":"2020","journal-title":"Biomed Phys Eng Express"},{"key":"pone.0340243.ref027","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/B978-0-12-824349-7.00032-3","article-title":"Validation and evaluation metrics for medical and biomedical image synthesis","volume-title":"Biomedical Image Synthesis and Simulation","author":"T Ne\u010dasov\u00e1","year":"2022"},{"key":"pone.0340243.ref028","doi-asserted-by":"crossref","first-page":"93","DOI":"10.12659\/PJR.892628","article-title":"Artifacts in magnetic resonance imaging","volume":"80","author":"K Krupa","year":"2015","journal-title":"Pol J Radiol"},{"key":"pone.0340243.ref029","unstructured":"Weerakkody Y. MRI artifacts. Radiology Reference Article. https:\/\/radiopaedia.org\/articles\/mri-artifacts-1?lang=us. 2026."},{"issue":"2","key":"pone.0340243.ref030","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.21595\/jve.2018.19756","article-title":"Artifacts in magnetic resonance imaging: how it can really affect diagnostic image quality and confuse clinical diagnosis?","volume":"20","author":"T Budrys","year":"2018","journal-title":"J vibroeng"},{"key":"pone.0340243.ref031","doi-asserted-by":"crossref","DOI":"10.1088\/978-0-7503-1284-4","volume-title":"MRI: Connecting the Dots: A Start to Concepts","author":"D Wu","year":"2023"},{"issue":"2","key":"pone.0340243.ref032","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1002\/jmri.24288","article-title":"Body MRI artifacts in clinical practice: a physicist\u2019s and radiologist\u2019s perspective","volume":"38","author":"MJ Graves","year":"2013","journal-title":"J Magn Reson Imaging"},{"issue":"2","key":"pone.0340243.ref033","doi-asserted-by":"crossref","first-page":"13","DOI":"10.4102\/sajr.v8i2.127","volume":"8","author":"LJ Erasmus","year":"2004","journal-title":"South African Journal of Radiology"},{"issue":"4","key":"pone.0340243.ref034","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.2214\/AJR.07.3657","article-title":"MRI artifact reduction and quality improvement in the upper abdomen with PROPELLER and prospective acquisition correction (PACE) technique","volume":"191","author":"Y Hirokawa","year":"2008","journal-title":"AJR Am J Roentgenol"},{"issue":"3","key":"pone.0340243.ref035","doi-asserted-by":"crossref","DOI":"10.1148\/rg.210021","article-title":"Primer on commonly occurring MRI artifacts and how to overcome them","volume":"42","author":"C Noda","year":"2022","journal-title":"Radiographics"},{"issue":"2","key":"pone.0340243.ref036","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/S0002-9270(02)05909-9","article-title":"Magnetic resonance imaging of the effects of infliximab on perianal fistulizing Crohn\u2019s disease","volume":"98","author":"G Van Assche","year":"2003","journal-title":"Am J Gastroenterol"},{"issue":"5","key":"pone.0340243.ref037","doi-asserted-by":"crossref","DOI":"10.1053\/j.gastro.2019.07.027","article-title":"Development and Validation of a Magnetic Resonance Index for Assessing Fistulas in Patients With Crohn\u2019s Disease","volume":"157","author":"P Hindryckx","year":"2019","journal-title":"Gastroenterology"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T17:41:06Z","timestamp":1784655666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340243"}},"subtitle":[],"editor":[{"given":"Khan Bahadar","family":"Khan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":37,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0340243","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]}}}