Potential MRI Interpretation Model: Differentiation of Benign from Malignant Breast Masses

Purpose: To evaluate a fully automatic computer-assisted diagnosis (CAD) method for breast magnetic resonance imaging (MRI), which considered dynamic as well as morphologic parameters and linked those to descriptions laid down in the Breast Imaging Reporting and Data System (BI-RADS) MRI atlas.Materials and Methods: MR images of 108 patients with 141 histologically proven mass-like lesions (88 malignant, 53 benign) were included. The CAD system automatically performed the following processing steps: 3D nonrigid motion correction, detection of lesions by a segmentation algorithm, extraction of multiple dynamic and morphologic parameters, and classification of lesions. As one final result, the lesions were categorized by defining their probability of malignancy; this so-called morpho-dynamic index (MDI) ranged from 0%-100%. The results of the CAD system were correlated with histopathologic findings. Results:The CAD system had a high detection rate of the histologically proven lesions, missing only two malignancies of invasive multifocal carcinomas and four benign lesions (three fibroadenomas, one atypical ductal hyperplasia). The 86 detected malignant lesions showed a mean MDI of 86.1% (615.4%); the mean MDI of the 49 coded benign lesions was 41.8% (622.0%; P < 0.001). Based on receiver-operating characteristic analysis, the diagnostic accuracy of the CAD system was 93.5%. Using an appropriate cutoff value (MDI 50%), sensitivity was 96.5% combined with specificity of 75.5%. Conclusion:The fully automatic CAD technique seems to reliably distinguish between benign and malignant masslike breast tumors. Observer-independent CAD may be a promising additional tool for the interpretation of breast MRI in the clinical routine.

Section: Cad Evaluation Of Morphologic Mri Parameterssupporting

confidence: 74%

Section: Morphologic and Dynamic Mri Parametersmentioning

confidence: 99%

Section: Morphologic and Dynamic Mri Parametersmentioning

confidence: 99%

Section: Morphologic and Dynamic Mri Parametersmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Detection and classification of contrast‐enhancing masses by a fully automatic computer‐assisted diagnosis system for breast MRI

Renz

Böttcher

Diekmann

et al. 2012

Pilot study of improved lesion characterization in breast MRI using a 3D radial balanced SSFP technique with isotropic resolution and efficient fat‐water separation

Moran

Kelcz

Jung

et al. 2009

Purpose To assess a 3D radial balanced steady state free precession technique that provides sub-millimeter isotropic resolution and inherently registered fat and water image volumes in comparison to conventional T2-weighted RARE imaging for lesion characterization in breast MRI. Materials and Methods 3D PRojection SSFP (3DPR-SSFP) combines a dual half-echo radial k-space trajectory with a linear combination fat/water separation technique (Linear Combination SSFP). A pilot study was performed in 20 patients to assess fat suppression and depiction of lesion morphology using 3DPR-SSFP. For all patients fat suppression was measured for the 3DPR-SSFP image volumes and depiction of lesion morphology was compared against corresponding T2-weighted Fast Spin Echo (FSE) datasets for 15 lesions in 11 patients. Results The isotropic 0.63 mm resolution of the 3DPR-SSFP sequence demonstrated improved depiction of lesion morphology in comparison to FSE. The 3DPR-SSFP fat and water datasets were available in a 5 minute scan time while average fat suppression with 3DPR-SSFP was 71% across all twenty patients. Conclusion 3DPR-SSFP has the potential to improve the lesion characterization information available in breast MRI, particularly in comparison to conventional FSE. A larger study is warranted to quantify the effect of 3DPR-SSFP on specificity.

Potential of computer‐aided diagnosis of high spectral and spatial resolution (HiSS) MRI in the classification of breast lesions

Bhooshan

Giger

Medved

et al. 2013

Purpose: To compare the performance of CADx analysis of pre-contrast HiSS MRI to that of clinical DCE-MRI in the diagnostic classification of breast lesions. Materials and Methods: Thirty-four malignant and seven benign lesions were scanned using 2D HiSS and clinical 4D DCE-MRI protocols. Lesions were automatically segmented. Morphological features were calculated for HiSS whereas both morphological and kinetic features were calculated for DCE-MRI. After stepwise feature selection, Bayesian artificial neural networks merged selected features, and ROC analysis evaluated the performance with leave-one-lesion-out validation. Results: AUC values of 0.92 ± 0.06 and 0.90 ± 0.05 were obtained using CADx on HiSS and DCE-MRI, respectively, in the task of classifying benign and malignant lesions. While we failed to show that the higher HiSS performance was significantly better than DCE-MRI, non-inferiority testing confirmed that HiSS was not worse than DCE-MRI. Conclusion: CADx of HiSS (without contrast) performed similarly to CADx on clinical DCE-MRI; thus, computerized analysis of HiSS may provide sufficient information for diagnostic classification. The results are clinically important for patients in whom contrast agent is contra-indicated. Even in the limited acquisition mode of 2D single slice HiSS, by using quantitative image analysis to extract characteristics from the HiSS images, similar performance levels were obtained as compared to those from current clinical 4D DCE-MRI. As HiSS acquisitions become possible in 3D, CADx methods can also be applied. Since HiSS and DCE-MRI are based on different contrast mechanisms, the use of the two protocols in combination may increase diagnostic accuracy.