MR-based radiomics of mesorectal fat for improved prediction of perirectal lymph node metastasis and extramural venous invasion in locally advanced rectal cancer
Yaniga Swaengdee, Sararas Khongwirotphan, Jaravee Lasode, Phakakarn Kuecharoen, Phathayphout Phetvilay, Thitithep Limvorapitak, Anapat Sanpavat, Sira Sriswasdi · 2026
Read MR-based radiomics of mesorectal fat for improved prediction of perirectal lymph node metastasis and extramural venous invasion in locally advanced rectal cancer by Yaniga Swaengdee, Sararas Khongwirotphan, Jaravee Lasode, Phakakarn Kuecharoen, Phathayphout Phetvilay, Thitithep Limvorapitak, Anapat Sanpavat, Sira Sriswasdi (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/plos-pone-0357268.txt.
Description
Yaniga Swaengdee and colleagues teach computer models to read MRI scans of rectal cancer after chemotherapy and radiation, hunting signs doctors struggle to see. Two bad signs, cancer in nearby lymph nodes and cancer growing into small veins, often hide in treatment-changed tissue. The team extracted texture numbers from the tumor and the fatty tissue around it in more than two hundred restaging scans, then trained three model types against surgical results.
Models that combined tumor and surrounding fat beat models using either region alone for both bad signs. A simple regression model led on the vein measure, and the combined model also led on node spread. Swaengdee and colleagues argue the fat around the tumor carries real signal, and including it should sharpen pre-surgery planning.
Catalog record
| CREATOR | Yaniga Swaengdee, Sararas Khongwirotphan, Jaravee Lasode, Phakakarn Kuecharoen, Phathayphout Phetvilay, Thitithep Limvorapitak, Anapat Sanpavat, Sira Sriswasdi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33900 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |