LBP-TOP for Volume Lesion Classification in Breast DCE-MRI (original) (raw)
Related papers
Computerized Assessment of Breast Lesion Malignancy using DCE-MRI
Academic Radiology, 2010
Rationale and Objectives-To conduct a pre-clinical evaluation of the robustness of our computerized system for breast lesion characterization on two breast magnetic resonance imaging (MRI) databases that were acquired using scanners from two different manufacturers.
Integration of DCE-MRI and DW-MRI Quantitative Parameters for Breast Lesion Classification
BioMed Research International, 2015
Objective. The purpose of our study was to evaluate the diagnostic value of an imaging protocol combining dynamic contrast-enhanced MRI (DCE-MRI) and diffusion-weighted MRI (DW-MRI) in patients with suspicious breast lesions.Materials and Methods. A total of 31 breast lesions (15 malignant and 16 benign proved by histological examination) in 26 female patients were included in this study. For both DCE-MRI and DW-MRI model free and model based parameters were computed pixel by pixel on manually segmented ROIs. Statistical procedures included conventional linear analysis and more advanced techniques for classification of lesions in benign and malignant.Results. Our findings indicated no strong correlation between DCE-MRI and DW-MRI parameters. Results of classification analysis show that combining of DCE parameters or DW-MRI parameter, in comparison of single feature, does not yield a dramatic improvement of sensitivity and specificity of the two techniques alone. The best performance...
A novel threshold-independent computer-aided detection algorithm for breast MRI
Breast Cancer Research, 2010
Purpose To validate the predictive power for determining breast cancer risk of an automated breast density measurement system with full-fi eld digital mammography (FFDM). Materials and methods Two hundred cancers and 200 controls were imaged with FFDM. Density was measured separately on MLO and CC images using an integral automated volumetric breast density measurement system (Hologic, Quantra). For each cancer, the contralateral mammogram was used. Each cancer was matched to a control case by date of birth, age at examination and laterality of mammogram used for density determination. Breast density (percentage of fi broglandular tissue) was analyzed by Quantra. Data were analyzed by conditional logistic regression to determine the eff ect on breast cancer risk. Results The percentage of breast density ranged from 6% to 63%. Density declined signifi cantly with age (P <0.001). Overall, there was no signifi cant association of density with risk of breast cancer (P = 0.4). There was a suggestive increase in risk with dense volume higher than 35% (OR = 1.80, 95% CI = 0.96 to 3.39, P = 0.07). There was signifi cant heterogeneity by age in the eff ect of density on risk (P = 0.04). In women aged <50, density was signifi cantly associated with increased risk (P = 0.02), with odds ratios of 6.06, 3.98 and 10.59 for density volumes of 15 to 24%, 25 to 34% and ≥35% respectively, relative to those with <15%. In women aged ≥50 years there was no association of density with risk (P = 0.5). Conclusions Quantra automated volumetric breast density measurement is strongly associated with breast cancer risk in women aged under 50, but not in women aged ≥50 years or over.
aging, 2013
The aim of this work is to evaluate if a semi-quantitative assessment of uncertain TICs could improve overall diagnostic performance. Methods: In this study 49 lesions from 44 patients were retrospectively analysed. Per each lesion one region-of-interest (ROI)averaged TIC was qualitatively evaluated by two radiologists in consensus: all the ROIs resulted in type II (uncertain) TIC. The same TICs were semi-quantitatively re-classified on the basis of the difference between the signal intensities of the last-time-point and of the peak: this difference was classified according to two different cut-off ranges (±5% and ±3%). All patients were cytological or histological biopsy proven. Fisher test and McNemar test were performed to evaluate if results were statistically significant (p < 0.05). Results: Using ±5% cut-off 16 TICs were reclassified as type III and 12 as type I while 21 were reclassified again as type II. Using ±3% 22 TICs were reclassified as type III and 16 as type I while 11 were reclassified again as type II. The semi-quantitative classification was compared to the histologicalcytological results: the sensitivity, specificity, positive and negative predictive values obtained with ±3% were 77%, 91%, 91% and 78% respectively while using ±5% were 58%, 96%, 94% and 68% respectively. Using the ±5% cut-off 26/28 (93%) TICs were correctly reclassified while using the ±3% cut-off 34/38 (90%) TICs were correctly reclassified (p < 0.05). Conclusions: Semi-quantitative methods in ki-netic curve assessment on DCE-MRI could improve classification of qualitatively uncertain TICs, leading to a more accurate classification of suspicious breast lesions.
Selection of suspicious ROIs in breast DCE-MRI
2011
Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) could be helpful in screening high-risk women and in staging newly diagnosed breast cancer patients. Selection of suspicious regions of interest (ROIs) is a critical pre-processing step in DCE-MRI data evaluation. The aim of this work is to develop and evaluate a method for automatic selection of suspicious ROIs for breast DCE-MRI. The proposed algorithm includes three steps: (i) breast mask segmentation via intensity threshold estimation; (ii) morphological operations for hole-filling and leakage removal; (iii) suspicious ROIs extraction. The proposed approach has been evaluated, using adequate metrics, with respect to manual ROI selection performed, on ten patients, by an expert radiologist.
Computerized interpretation of breast MRI: Investigation of enhancement-variance dynamics
Medical Physics, 2004
The advantages of breast MRI using contrast agent Gd-DTPA in the diagnosis of breast cancer have been well established. The variation of interpretation criteria and absence of interpretation guidelines, however, is a major obstacle for applications of MRI in the routine clinical practice of breast imaging. Our study aims to increase the objectivity and reproducibility of breast MRI interpretation by developing an automated interpretation approach for ultimate use in computer-aided diagnosis. The database in this study contains 121 cases: 77 malignant and 44 benign masses as revealed by biopsy. Images were obtained using a T1-weighted 3D spoiled gradient echo sequence. After the acquisition of the precontrast series, Gd-DTPA contrast agent was injected intravenously by power injection with a dose of 0.2 mmol/kg. Five postcontrast series were then taken with a time interval of 60 s. Each series contained 64 coronal slices with a matrix of 128ϫ256 pixels and an in-plane resolution of 1.25ϫ1.25 mm 2 . Slice thickness ranged from 2 to 3 mm depending on breast size. The lesions were delineated by an experienced radiologist as well as independently by computer using an automatic volume-growing algorithm. Fourteen features that were extracted automatically from the lesions could be grouped into three categories based on ͑I͒ morphology, ͑II͒ enhancement kinetics, and ͑III͒ time course of enhancement-variation over the lesion. A stepwise feature selection procedure was employed to select an effective subset of features, which were then combined by linear discriminant analysis ͑LDA͒ into a discriminant score, related to the likelihood of malignancy. The classification performances of individual features and the combined discriminant score were evaluated with receiver operating characteristic ͑ROC͒ analysis. With the radiologistdelineated lesion contours, stepwise feature selection yielded four features and an A z value of 0.80 for the LDA in leave-one-out cross-validation testing. With the computer-segmented lesion volumes, it yielded six features and an A z value of 0.86 for the LDA in the leave-one-out testing.