dc.creator | Tsarouchi M.I., Vlachopoulos G.F., Karahaliou A.N., Vassiou K.G., Costaridou L.I. | en |
dc.date.accessioned | 2023-01-31T10:11:59Z | |
dc.date.available | 2023-01-31T10:11:59Z | |
dc.date.issued | 2020 | |
dc.identifier | 10.1016/j.ejmp.2020.10.007 | |
dc.identifier.issn | 11201797 | |
dc.identifier.uri | http://hdl.handle.net/11615/79867 | |
dc.description.abstract | Purpose: To identify intra-lesion imaging heterogeneity biomarkers in multi-parametric Magnetic Resonance Imaging (mpMRI) for breast lesion diagnosis. Methods: Dynamic Contrast Enhanced (DCE) and Diffusion Weighted Imaging (DWI) of 73 female patients, with 85 histologically verified breast lesions were acquired. Non-rigid multi-resolution registration was utilized to spatially align sequences. Four (4) DCE (2nd post-contrast frame, Initial-Enhancement, Post-Initial-Enhancement and Signal-Enhancement-Ratio) and one (1) DWI (Apparent-Diffusion-Coefficient) representations were analyzed, considering a representative lesion slice. 11 1st-order-statistics and 16 texture features (Gray-Level-Co-occurrence-Matrix (GLCM) and Gray-Level-Run-Length-Matrix (GLRLM) based) were derived from lesion segments, provided by Fuzzy C-Means segmentation, across the 5 representations, resulting in 135 features. Least-Absolute-Shrinkage and Selection-Operator (LASSO) regression was utilized to select optimal feature subsets, subsequently fed into 3 classification schemes: Logistic-Regression (LR), Random-Forest (RF), Support-Vector-Machine-Sequential-Minimal-Optimization (SVM-SMO), assessed with Receiver-Operating-Characteristic (ROC) analysis. Results: LASSO regression resulted in 7, 6 and 7 features subsets from DCE, DWI and mpMRI, respectively. Best classification performance was obtained by the RF multi-parametric scheme (Area-Under-ROC-Curve, (AUC) ± Standard-Error (SE), AUC ± SE = 0.984 ± 0.025), as compared to DCE (AUC ± SE = 0.961 ± 0.030) and DWI (AUC ± SE = 0.938 ± 0.032) and statistically significantly higher as compared to DWI. The selected mpMRI feature subset highlights the significance of entropy (1st-order-statistics and 2nd-order-statistics (GLCM)) and percentile features extracted from 2nd post-contrast frame, PIE, SER maps and ADC map. Conclusion: Capturing breast intra-lesion heterogeneity, across mpMRI lesion segments with 1st-order-statistics and texture features (GLCM and GLRLM based), offers a valuable diagnostic tool for breast cancer. © 2020 | en |
dc.language.iso | en | en |
dc.source | Physica Medica | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094606684&doi=10.1016%2fj.ejmp.2020.10.007&partnerID=40&md5=3202f9ee1c59a5608bae54f2b78e83d2 | |
dc.subject | adult | en |
dc.subject | aged | en |
dc.subject | apparent diffusion coefficient | en |
dc.subject | Article | en |
dc.subject | breast cancer | en |
dc.subject | breast tumor | en |
dc.subject | cancer diagnosis | en |
dc.subject | cancer patient | en |
dc.subject | cohort analysis | en |
dc.subject | contrast enhancement | en |
dc.subject | controlled study | en |
dc.subject | diagnostic imaging | en |
dc.subject | differential diagnosis | en |
dc.subject | diffusion weighted imaging | en |
dc.subject | entropy | en |
dc.subject | feature extraction | en |
dc.subject | female | en |
dc.subject | first order statistics | en |
dc.subject | fuzzy c means clustering | en |
dc.subject | Gray Level Cooccurrence Matrix | en |
dc.subject | Gray Level Run Length Matrix | en |
dc.subject | human | en |
dc.subject | image analysis | en |
dc.subject | image segmentation | en |
dc.subject | initial enhancement | en |
dc.subject | Least Absolute Shrinkage and Selection Operator | en |
dc.subject | logistic regression analysis | en |
dc.subject | major clinical study | en |
dc.subject | multiparametric magnetic resonance imaging | en |
dc.subject | oncological parameters | en |
dc.subject | post contrast frame | en |
dc.subject | post initial enhancement | en |
dc.subject | radiological parameters | en |
dc.subject | random forest | en |
dc.subject | receiver operating characteristic | en |
dc.subject | retrospective study | en |
dc.subject | signal enhancement ratio | en |
dc.subject | statistical analysis | en |
dc.subject | statistical parameters | en |
dc.subject | support vector machine | en |
dc.subject | Support Vector Machine Sequential Minimal Optimization | en |
dc.subject | breast tumor | en |
dc.subject | nuclear magnetic resonance imaging | en |
dc.subject | biological marker | en |
dc.subject | contrast medium | en |
dc.subject | Biomarkers | en |
dc.subject | Breast Neoplasms | en |
dc.subject | Contrast Media | en |
dc.subject | Female | en |
dc.subject | Humans | en |
dc.subject | Magnetic Resonance Imaging | en |
dc.subject | Multiparametric Magnetic Resonance Imaging | en |
dc.subject | Associazione Italiana di Fisica Medica | en |
dc.title | Multi-parametric MRI lesion heterogeneity biomarkers for breast cancer diagnosis | en |
dc.type | journalArticle | en |