Machine learning models based on magnetic resonance imaging for predicting Lymphovascular Invasion in Invasive Breast Cancer

Hong Li, Jieling Huang, Jianning Hou, Xinxin Chen, Cheng Zhi, Zhiming Li · 2026

Read Machine learning models based on magnetic resonance imaging for predicting Lymphovascular Invasion in Invasive Breast Cancer by Hong Li, Jieling Huang, Jianning Hou, Xinxin Chen, Cheng Zhi, Zhiming Li (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-0350085.txt.

Description

Hong Li, Zhiming Li, and co-authors tested whether patterns hidden in breast MRI scans can predict if a cancer has invaded nearby vessels, a sign that guides treatment choices. Checking for this invasion normally requires tissue after surgery. Their 2026 study used scans from one hundred sixty-six women with operable invasive breast cancer, extracting hundreds of image features from different scan types.

Four prediction signatures were built and compared. The winner used change features, calculated as the difference between scans before and after contrast dye was given, and it clearly beat two of the other signatures. A signature from a standard anatomical scan also performed respectably. The authors propose the change-based signature as a possible non-invasive marker to flag vessel invasion before surgery.

Catalog record

CREATORHong Li, Jieling Huang, Jianning Hou, Xinxin Chen, Cheng Zhi, Zhiming Li
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE39870
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0350085

Browse the full library · About the Tower of Babel