{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:56:55Z","timestamp":1781672215300,"version":"3.54.5"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"\n Objective<\/jats:title>\n \n This study aimed to develop a hybrid model combining MRI-based radiomics, deep learning, and clinical variables for preoperative differentiation of\n Escherichia coli<\/jats:italic>\n from non-\n Escherichia coli<\/jats:italic>\n pathogens in perianal abscesses.\n <\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n A retrospective series of 215 patients with culture-confirmed perianal abscesses (119\n Escherichia coli<\/jats:italic>\n , 96 non-\n Escherichia coli<\/jats:italic>\n ) was analyzed. Preoperative MRI data were collected, with radiomic and deep learning features extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and fat-suppressed T2WI (FS-T2WI) sequences. Radiomic feature selection was performed using univariate\n t<\/jats:italic>\n -tests, Pearson correlation, and least absolute shrinkage and selection operator (LASSO) regression. Clinical and MRI data were screened through univariate and multivariable logistic regression. The MRI signature was derived by averaging the probabilities from a logistic regression model (radiomics) and a k-nearest neighbors classifier (deep learning). A hybrid logistic regression model integrated the MRI signature with clinical predictors to create a nomogram. Model performance was evaluated using receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis (DCA).\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Escherichia coli<\/jats:italic>\n accounted for 57.63% of all strains. Gender (odds ratio [OR]\u202f=\u202f0.456,\n p<\/jats:italic>\n \u202f=\u202f0.001) and diabetes (OR\u202f=\u202f9.207,\n p<\/jats:italic>\n \u202f&lt;\u202f0.001) were significant independent predictors. The nomogram achieved an area under the curve (AUC) of 0.885 in the testing set, outperforming the MRI signature alone (AUC\u202f=\u202f0.860), with accuracy of 0.815, sensitivity of 0.818, and specificity of 0.812. Calibration curves showed good agreement between predicted and observed outcomes, while DCA demonstrated superior clinical utility.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n \n The hybrid model, utilizing preoperative multi-sequence MRI, noninvasively identifies\n Escherichia coli<\/jats:italic>\n , the predominant pathogen in perianal abscesses, offering significant clinical potential to transition from empirical antibiotic regimens to microbiology-guided precision strategies.\n <\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fmed.2026.1865284","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:46:50Z","timestamp":1781671610000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MRI-based radiomics-deep learning model for preoperative pathogen prediction in perianal abscesses"],"prefix":"10.3389","volume":"13","author":[{"given":"Weiping","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Radiology, Third Affiliated Hospital of Soochow University","place":["Changzhou, Jiangsu, China"]},{"name":"Department of Radiology, Pudong Gongli Hospital, Shanghai University of Medicine and Health Sciences","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajia","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Gongli Hospital Medical Technology, University of Shanghai for Science and Technology","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Traditional Chinese Medicine Anorectal Surgery, Pudong Gongli Hospital, Shanghai University of Medicine and Health Sciences","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory Medicine, Pudong Gongli Hospital, Shanghai University of Medicine and Health Sciences","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Health Commission Key Lab of Artificial Intelligence (AI)-Based Management of Inflammation and Chronic Diseases, Sino-French Cooperative Central Lab, Pudong Gongli Hospital, Shanghai University of Medicine and Health Sciences","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingcang","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Pudong Gongli Hospital, Shanghai University of Medicine and Health Sciences","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xing","sequence":"additional","affiliation":[{"name":"Department of Radiology, Third Affiliated Hospital of Soochow University","place":["Changzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"j475","DOI":"10.1136\/bmj.j475","article-title":"Perianal abscess","volume":"356","author":"Sahnan","year":"2017","journal-title":"BMJ"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"014","DOI":"10.1055\/s-0031-1272819","article-title":"Anorectal infection: abscess-fistula","volume":"24","author":"Abcarian","year":"2011","journal-title":"Clin Colon Rectal Surg"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1007\/s00384-015-2500-7","article-title":"Prevalence and recurrence rate of perianal abscess--a population-based study, Sweden 1997-2009","volume":"31","author":"Adamo","year":"2016","journal-title":"Int J Color Dis"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1007\/s00384-020-03818-1","article-title":"Risk for developing perianal abscess in type 1 and type 2 diabetes and the impact of poor glycemic control","volume":"36","author":"Adamo","year":"2021","journal-title":"Int J Color Dis"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1093\/ecco-jcc\/jjy210","article-title":"The risk of inflammatory bowel disease in subjects presenting with perianal abscess: findings from the THIN database","volume":"13","author":"Thomas","year":"2019","journal-title":"J Crohns Colitis"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"7942","DOI":"10.12659\/MSM.917836","article-title":"Relationship between body mass index and recurrence\/anal fistula formation following initial operation for anorectal abscess","volume":"25","author":"Lu","year":"2019","journal-title":"Med Sci Monit"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.4103\/0366-6999.230738","article-title":"Impact of smoking on anal abscess and anal fistula diseases","volume":"131","author":"Zheng","year":"2018","journal-title":"Chin Med J"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1097\/DCR.0000000000002473","article-title":"The American society of colon and rectal surgeons clinical practice guidelines for the management of anorectal abscess, fistula-in-ano, and rectovaginal fistula","volume":"65","author":"Gaertner","year":"2022","journal-title":"Dis Colon Rectum"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"33","DOI":"10.26689\/par.v5i5.2591","article-title":"Meta-analysis of the bacterial detection rate in perianal abscess","volume":"5","author":"Han","year":"2021","journal-title":"Proc Anticancer Res"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s00384-006-0121-x","article-title":"Microbiological analysis and endoanal ultrasonography for diagnosis of anal fistula in acute anorectal sepsis","volume":"22","author":"Toyonaga","year":"2007","journal-title":"Int J Color Dis"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1016\/j.surg.2017.07.001","article-title":"Antibiotic therapy for prevention of fistula in-ano after incision and drainage of simple perianal abscess: a randomized single blind clinical trial","volume":"162","author":"Ghahramani","year":"2017","journal-title":"Surgery"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1016\/j.amjsurg.2019.01.015","article-title":"Antibiotic use in prevention of anal fistulas following incision and drainage of anorectal abscesses: a systematic review and meta-analysis","volume":"217","author":"Mocanu","year":"2019","journal-title":"Am J Surg"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s00423-017-1563-z","article-title":"German S3 guidelines: anal abscess and fistula (second revised version)","volume":"402","author":"Ommer","year":"2017","journal-title":"Langenbeck's Arch Surg"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1557","DOI":"10.1007\/s00384-014-2028-2","article-title":"Management of cryptoglandular supralevator abscesses in the magnetic resonance imaging era: a case series","volume":"29","author":"Garcia-Granero","year":"2014","journal-title":"Int J Color Dis"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s00234-014-1411-6","article-title":"Differentiation of pyogenic and fungal brain abscesses with susceptibility-weighted MR sequences","volume":"56","author":"Antulov","year":"2014","journal-title":"Neuroradiology"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1007\/s00234-007-0242-0","article-title":"Fungal versus bacterial brain abscesses: is diffusion-weighted MR imaging a useful tool in the differential diagnosis?","volume":"49","author":"Mueller-Mang","year":"2007","journal-title":"Neuroradiology"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.3174\/ajnr.A0548","article-title":"Comparative evaluation of fungal, tubercular, and pyogenic brain abscesses with conventional and diffusion MR imaging and proton MR spectroscopy","volume":"28","author":"Luthra","year":"2007","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e222729","DOI":"10.1148\/radiol.222729","article-title":"Predicting microvascular invasion in hepatocellular carcinoma using CT-based radiomics model","volume":"307","author":"Xia","year":"2023","journal-title":"Radiology"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1007\/s00330-024-11275-5","article-title":"Deep learning-based intratumoral and peritumoral features for differentiating ocular adnexal lymphoma and idiopathic orbital inflammation","volume":"35","author":"Zhang","year":"2025","journal-title":"Eur Radiol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1097\/DCR.0000000000000733","article-title":"Clinical practice guideline for the management of anorectal abscess, fistula-in-ano, and rectovaginal fistula","volume":"59","author":"Vogel","year":"2016","journal-title":"Dis Colon Rectum"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/s00383-023-05556-1","article-title":"Perianal abscess in children: an evaluation of microbiological etiology and the effectiveness of antibiotics","volume":"39","author":"Guner Ozenen","year":"2023","journal-title":"Pediatr Surg Int"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1437849","DOI":"10.3389\/fmed.2024.1437849","article-title":"Causal relationship between obesity and anorectal abscess: a Mendelian randomization study","volume":"11","author":"Zeng","year":"2024","journal-title":"Front Med (Lausanne)"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"18473","DOI":"10.1038\/s41598-024-66892-3","article-title":"The analysis of different types of anorectal abscesses was conducted using the MRI 3D reconstruction technique","volume":"14","author":"Ma","year":"2024","journal-title":"Sci Rep"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1186\/s12880-024-01257-w","article-title":"Dynamic contrast-enhanced MR imaging in identifying active anal fistula after surgery","volume":"24","author":"Lu","year":"2024","journal-title":"BMC Med Imaging"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1186\/s13244-025-01988-6","article-title":"Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images","volume":"16","author":"Xiao","year":"2025","journal-title":"Insights Imaging"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1016\/j.acra.2023.10.004","article-title":"Development of MRI-based deep learning signature for prediction of axillary response after NAC in breast cancer","volume":"31","author":"Zhang","year":"2024","journal-title":"Acad Radiol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"102940","DOI":"10.1016\/j.eclinm.2024.102940","article-title":"Development and validation of the MRI-based deep learning classifier for distinguishing perianal fistulizing Crohn's disease from cryptoglandular fistula: a multicenter cohort study","volume":"78","author":"Zhang","year":"2024","journal-title":"EClinicalMedicine"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"9066128","DOI":"10.1155\/2021\/9066128","article-title":"Deep learning-based magnetic resonance imaging features in diagnosis of perianal abscess and fistula formation","volume":"2021","author":"Yang","year":"2021","journal-title":"Contrast Media Mol Imaging"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1865284\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:46:54Z","timestamp":1781671614000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1865284\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":29,"alternative-id":["10.3389\/fmed.2026.1865284"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1865284","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"article-number":"1865284"}}