MRI Radiomics of Breast Cancer: Machine Learning-Based Prediction of Lymphovascular Invasion Status

Academic Radiology, Journal Year: 2021, Volume and Issue: 29, P. S126 - S134

Published: Dec. 4, 2021

Language: Английский

---

Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions

Current Oncology, Journal Year: 2022, Volume and Issue: 29(3), P. 1947 - 1966

Published: March 13, 2022

Purpose:The purpose of this study was to discriminate between benign and malignant breast lesions through several classifiers using, as predictors, radiomic metrics extracted from CEM DCE-MRI images. In order optimize the analysis, balancing feature selection procedures were performed. Methods: Fifty-four patients with 79 histo-pathologically proven (48 31 lesions) underwent both DCE-MRI. The retrospectively analyzed artificial intelligence approaches. Forty-eight textural extracted, univariate multivariate analyses performed: non-parametric statistical test, receiver operating characteristic (ROC) machine learning classifiers. Results: Considering single CEM, best predictors KURTOSIS (area under ROC curve (AUC) = 0.71) SKEWNESS (AUC calculated on late MLO view. features DCE-MRI, RANGE 0.72), ENERGY ENTROPY 0.70) GLN (gray-level nonuniformity) gray-level run-length matrix 0.72). analysis an unbalanced dataset, no significant results obtained. After procedures, higher values accuracy, specificity AUC reached. performance obtained considering 18 robust among all derived using a linear discriminant (accuracy 0.84 0.88). Conclusions: Classifiers, adjusted adaptive synthetic sampling selection, allowed for increased diagnostic in differentiation lesions.

Language: Английский

---

Leveraging multimodal MRI-based radiomics analysis with diverse machine learning models to evaluate lymphovascular invasion in clinically node-negative breast cancer

Heliyon, Journal Year: 2023, Volume and Issue: 10(1), P. e23916 - e23916

Published: Dec. 19, 2023

Language: Английский

---

Distinguishing granulomas from adenocarcinomas by integrating stable and discriminating radiomic features on non-contrast computed tomography scans

European Journal of Cancer, Journal Year: 2021, Volume and Issue: 148, P. 146 - 158

Published: March 18, 2021

Language: Английский

---

Radiomics Analysis on Digital Breast Tomosynthesis: Preoperative Evaluation of Lymphovascular Invasion Status in Invasive Breast Cancer

Academic Radiology, Journal Year: 2022, Volume and Issue: 29(12), P. 1773 - 1782

Published: April 8, 2022

Language: Английский

---