Enhanced differentiation of breast lesions through integration of microvascular flow imaging and machine learning algorithms

Fangfang Zhou, Wanling Lin, Jiqin Yao, Xiaoxi Lu, Lifang Yu · 2026

Read Enhanced differentiation of breast lesions through integration of microvascular flow imaging and machine learning algorithms by Fangfang Zhou, Wanling Lin, Jiqin Yao, Xiaoxi Lu, Lifang Yu (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/PMC13318774.txt.

Description

Fangfang Zhou and colleagues present a 2026 prospective study of a new ultrasound method for breast lesions. Microvascular flow imaging shows tiny tumour vessels better than standard colour Doppler. The team also built machine learning models using the new measures. Their goal was sharper separation of benign and malignant lumps.

The sample held 101 lesions from 79 patients. Flow imaging found blood flow in 16 lesions that Doppler had missed. Reader agreement was also higher with the new method. A vascular index ran much higher in cancers, at a median of 20.25 against 3.10 for benign lesions in their data. Among eight models, a nearest-neighbour model scored best, with 0.927 accuracy on test data. Age and imaging category were the top predictors.

Catalog record

CREATORFangfang Zhou, Wanling Lin, Jiqin Yao, Xiaoxi Lu, Lifang Yu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE45615
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13318774

Browse the full library · About the Tower of Babel