What type of study is this?

September 10, 2025Applied SciencesOpen Access

Radiomics and Machine Learning Approaches for the Preoperative Classification of In Situ vs. Invasive Breast Cancer Using Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE–MRI)

View Full Paper

Ask AI

Bookmark

Authors

LCLuana ConteIstituto Nazionale di Fisica Nucleare RRRocco RizzoUniversity of Pisa ASAlessandra SallustioOspedale A. Perrino

Discussion

Member takes

Implication

This study evaluates machine learning classifiers for differentiating in situ from invasive breast cancer, suggesting radiomics can enhance diagnostic accuracy.

Key Points

Machine learning classifiers can successfully distinguish between in situ and invasive breast cancer.
The best models achieved an area under the curve (AUC) of 0.77 to 0.81, with KNN showing optimal sensitivity and specificity.
Analysis included 71 DCE–MRI scans with radiomic feature extraction using the PyRadiomics library and minimum redundancy maximum relevance for feature selection.
Such approaches may improve preoperative planning, but further validation with larger datasets is needed.

Cite This Study

Conte et al. (2025) studied this question.

synapsesocial.com/papers/68c1bd4854b1d3bfb60eeda9 https://doi.org/10.3390/app15147999

View Full Paper

Ask AI

Bookmark

Implication

This study evaluates machine learning classifiers for differentiating in situ from invasive breast cancer, suggesting radiomics can enhance diagnostic accuracy.

Radiomics and Machine Learning Approaches for the Preoperative Classification of In Situ vs. Invasive Breast Cancer Using Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE–MRI)

Discussion

Member takes

Implication

Key Points

Cite This Study

Radiomics and Machine Learning Approaches for the Preoperative Classification of In Situ vs. Invasive Breast Cancer Using Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE–MRI)

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider