MRI-based radiomics-deep learning model for preoperative pathogen prediction in perianal abscesses
Weiping Lu, Jiajia Wang, Yan Li, Na Jiang, Ying Wang, Bingcang Huang, Wei Xing · 2026
Read MRI-based radiomics-deep learning model for preoperative pathogen prediction in perianal abscesses by Weiping Lu, Jiajia Wang, Yan Li, Na Jiang, Ying Wang, Bingcang Huang, Wei Xing (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13318606.txt.
Description
Weiping Lu and co-workers present a 2026 modelling study using MRI scans. The scans were taken before surgery for perianal abscess. The model predicts whether Escherichia coli or another germ is the cause. That distinction guides antibiotic choice. Records came from 215 patients with confirmed abscess cultures.
Image features came from three scan types. Clinical details such as sex and diabetes joined them. Both details were strong predictors in the analysis. A combined score was drawn as a nomogram for bedside use. It reached an AUC of 0.885 in the testing set. Imaging alone scored 0.860 on that measure in the same testing. Calibration and decision checks also looked good. The authors propose a noninvasive step toward matching antibiotics to the likely germ.
Catalog record
| CREATOR | Weiping Lu, Jiajia Wang, Yan Li, Na Jiang, Ying Wang, Bingcang Huang, Wei Xing |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33492 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |