Truace
Subscribe

Comparative evaluation of feature-selection strategies for machine learning-based histological grading of breast cancer using tumor and fibroglandular-tissue DCE-MRI features

Nottingham histological grading is central to breast cancer prognosis and treatment planning, but conventional pathological assessment is labor-intensive and subject to inter-observer variability. Radiomics and machine learning may support noninvasive preoperative grade prediction. To compare mutual-information, chi-squared, and LASSO feature-selection strategies for binary Nottingham grade classification using tumor- and fibroglandular-tissue (FGT)-derived DCE-MRI features. This retrospective secondary analysis…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-0858· cite & verify
Comparative evaluation of feature-selection strategies for machine learning-based histological grading of breast cancer using tumor and fibroglandular-tissue DCE-MRI features
A comparative study of commercial and Department of Defense strategies for developing software applications by Clancy, Gregory A.. Public domain

In brief

Nottingham histological grading is central to breast cancer prognosis and treatment planning, but conventional pathological assessment is labor-intensive and subject to inter-observer variability. Radiomics and machine learning may support noninvasive preoperative grade prediction.

This retrospective secondary analysis included 576 patients from the Duke-Breast-Cancer-MRI collection in The Cancer Imaging Archive, comprising 288 non-high-grade and 288 high-grade tumors. Chi-squared selection with a neural network achieved the highest mean accuracy (74.78%; AUC 0.77).

Main points

  1. Nottingham histological grading is central to breast cancer prognosis and treatment planning, but conventional pathological assessment is labor-intensive and subject to inter-observer variability.
  2. Radiomics and machine learning may support noninvasive preoperative grade prediction.
  3. To compare mutual-information, chi-squared, and LASSO feature-selection strategies for binary Nottingham grade classification using tumor- and fibroglandular-tissue (FGT)-derived DCE-MRI features.

The problem

Chi-squared selection with a neural network achieved the highest mean accuracy (74.78%; AUC 0.77).

The rundown

To compare mutual-information, chi-squared, and LASSO feature-selection strategies for binary Nottingham grade classification using tumor- and fibroglandular-tissue (FGT)-derived DCE-MRI features. This retrospective secondary analysis included 576 patients from the Duke-Breast-Cancer-MRI collection in The Cancer Imaging Archive, comprising 288 non-high-grade and 288 high-grade tumors.

Sources

  1. Peer-reviewedCancer Treatment and Research Communications2026-08-21

The debate