Multiparametric MRI model with dynamic contrast‐enhanced and diffusion‐weighted imaging enables breast cancer diagnosis with high accuracy

Zhang, Michelle; Horvat, João V.; Bernard‐Davila, Blanca; Marino, Maria Adele; Leithner, Doris; Ochoa‐Albiztegui, R. Elena; Helbich, Thomas H.; Morris, Elizabeth A.; Thakur, Sunitha B.; Pinker, Katja

doi:10.1002/jmri.26285

Cited by 50 publications

(51 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with Ha et al [21] who concluded that any T2 hypointense enhancing focus representing an interval change should be biopsied rather than undergo short-term follow-up, we found no significant difference in T2 signal intensity between benign and malignant lesions. This is in agreement with Zhang et al who also showed that T2-weighted imaging does not significantly contribute to differentiating benign from malignant lesions [22]. In addition, we found that DWI signal analysis did not contribute to the accuracy of assessing these lesions, which can in part be explained by its limited spatial resolution which makes it challenging to accurately evaluate sub-centimeter masses.…”

Section: Discussionsupporting

confidence: 92%

Improved characterization of sub-centimeter enhancing breast masses on MRI with radiomics and machine learning in BRCA mutation carriers

et al. 2020

Self Cite

View full text Add to dashboard Cite

Objectives To investigate whether radiomics features extracted from MRI of BRCA-positive patients with sub-centimeter breast masses can be coupled with machine learning to differentiate benign from malignant lesions using model-free parameter maps. Methods In this retrospective study, BRCA-positive patients who had an MRI from November 2013 to February 2019 that led to a biopsy (BI-RADS 4) or imaging follow-up (BI-RADS 3) for sub-centimeter lesions were included. Two radiologists assessed all lesions independently and in consensus according to BI-RADS. Radiomics features were calculated using open-source CERR software. Univariate analysis and multivariate modeling were performed to identify significant radiomics features and clinical factors to be included in a machine learning model to differentiate malignant from benign lesions. Results Ninety-six BRCA mutation carriers (mean age at biopsy = 45.5 ± 13.5 years) were included. Consensus BI-RADS classification assessment achieved a diagnostic accuracy of 53.4%, sensitivity of 75% (30/40), specificity of 42.1% (32/76), PPV of 40.5% (30/74), and NPV of 76.2% (32/42). The machine learning model combining five parameters (age, lesion location, GLCM-based correlation from the pre-contrast phase, first-order coefficient of variation from the 1st post-contrast phase, and SZM-based gray level variance from the 1st post-contrast phase) achieved a diagnostic accuracy of 81.5%, sensitivity of 63.2% (24/38), specificity of 91.4% (64/70), PPV of 80.0% (24/30), and NPV of 82.1% (64/78). Conclusions Radiomics analysis coupled with machine learning improves the diagnostic accuracy of MRI in characterizing sub-centimeter breast masses as benign or malignant compared with qualitative morphological assessment with BI-RADS classification alone in BRCA mutation carriers. Key Points • Radiomics and machine learning can help differentiate benign from malignant breast masses even if the masses are small and morphological features are benign. • Radiomics and machine learning analysis showed improved diagnostic accuracy, specificity, PPV, and NPV compared with qualitative morphological assessment alone.

show abstract

Section: Discussionsupporting

confidence: 92%

Improved characterization of sub-centimeter enhancing breast masses on MRI with radiomics and machine learning in BRCA mutation carriers

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…X-ray mammography screening is characterized by a high level of sensitivity in detecting abnormal breast masses, but relatively low specificity in assessing malignancies 1 . This has triggered an increasing interest in additional methods for clarifying ambiguous findings, especially using magnetic resonance imaging (MRI) to avoid the large number of unnecessary biopsies [2][3][4][5][6][7] . A recent and successful trend has been the use of abbreviated, contrastagent free protocols based on diffusion-weighted imaging (DWI) and T2-weighted acquisitions, especially in the light of the required short examination times and the possible side effects of Gadolinium containing contrast agents 8 , which is especially relevant when aiming to apply these techniques during the clarification process of routine screening 3,[9][10][11] .…”

Section: Influence Of Residual Fat Signal On Diffusion Kurtosis Mri Omentioning

confidence: 99%

Influence of residual fat signal on diffusion kurtosis MRI of suspicious mammography findings

Mlynarska-Bujny

Bickelhaupt

Laun

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Using the accompanying information about the index lesion localization from the X-ray screening report and T2-weighted imaging, ROIs were manually defined on the b = 1500 s/mm 2 images or-if not clearly visible for this highest diffusion weighting-on b = 750 s/mm 2 , while trying to minimize partial volume effects by using the inner border of the lesion. Additionally, for each patient, a second ROI was drawn on the DWI dataset in an area containing fatty tissue as determined in concordance with the T2-weighted imaging. The oval-shaped fatty tissue area was usually drawn on the contralateral breast, in a mirrored position of the lesion to provide comparable distance to the surface of the coil. Calculation of quantitative parameters. The following diffusion and kurtosis evaluation approaches were evaluated to investigate the influence of fat contamination. D i (i = 1. .. 5) and K i (i = 2. .. 5) denote the apparent diffusion coefficient and the apparent kurtosis coefficient obtained by the respective methods. Method 1. The standard apparent diffusion coefficient, termed D 1 here, was obtained using the mono-exponential fit function with the two fitting parameters D 1 and S 0 , which corresponds to the signal without diffusion weighting. S(b) is the mean signal intensity in the respective lesion ROI. Method 2. For the standard kurtosis fitting approach, the following equation was used: with the modified apparent diffusion coefficient D 2 , the apparent kurtosis coefficient K 2 , and S 0 as free parameters in the fit. Method 3. This method accounts for possible fat signal contamination due to chemical shift in phase encoding direction, which may transfer unsuppressed fat signal to the lesion ROI. Therefore, a constant signal level was added to Eq. (2), which was determined in fatty tissue:

show abstract

“…The apparent diffusion coefficient (ADC) from diffusion‐weighted imaging (DWI) has been reported to improve the differentiation between benign and malignant breast lesions, 9–11 the latter typically showing restricted water molecule diffusivity. However, previous studies have reported variable results in sensitivity and specificity between malignant and benign lesions 12–15 …”

mentioning

confidence: 99%

Investigation of Synthetic Relaxometry and Diffusion Measures in the Differentiation of Benign and Malignant Breast Lesions as Compared to BI‐RADS

Gao

Zhang

Guo³

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Breast cancer is the most common malignant tumor in women and a quantitative contrast‐free method is highly desirable for its diagnosis. Purpose To investigate the performance of quantitative MRI in differentiating malignant from benign breast lesions and to compare with the Breast Imaging Reporting and Data System (BI‐RADS). Study Type Retrospective. Subjects Eighty patients (56 with malignant lesions and 24 with benign lesions). Field Strength/Sequence Diffusion‐weighted imaging (DWI) with a single‐shot echo planar sequence and synthetic MRI with magnetic resonance image compilation (MAGiC) were performed at 3T. Assessment T1 relaxation time (T1), T2 relaxation time (T2), and proton density (PD) from synthetic MRI and apparent diffusion coefficient (ADC) from DWI were analyzed by two radiologists (Reader A, Reader B). Univariable and multivariable models were developed to optimize differentiation between malignant and benign lesions and their performances compared to BI‐RADS. Statistical Tests The diagnostic performance was evaluated using multivariate logistic regression analysis and area under the receiver operating characteristic (ROC) curves (AUC). Results T2, PD, and ADC values for malignant lesions were significantly lower than those in benign breast lesions for both radiologists (all P < 0.05). The combined T2, PD, and ADC model had the best performance for differentiating malignant and benign lesions with AUC, sensitivity, specificity, positive predictive value, and negative predictive values of 0.904, 94.6%, 87.5%, 94.6%, and 87.5%, respectively. The corresponding results for BI‐RADS were no AUC, 94.6%, 75.0%, 89.8%, and 85.7%, respectively. Data Conclusion The approach that combined synthetic MRI and DWI outperformed BI‐RADS in the differential diagnosis of malignant and benign breast lesions and was achieved without contrast agents. This approach may serve as an alternative and effective strategy for the improvement of breast lesion differentiation. Level of Evidence 3. Technical Efficacy Stage 3.

show abstract

Multiparametric MRI model with dynamic contrast‐enhanced and diffusion‐weighted imaging enables breast cancer diagnosis with high accuracy

Cited by 50 publications

References 40 publications

Improved characterization of sub-centimeter enhancing breast masses on MRI with radiomics and machine learning in BRCA mutation carriers

Improved characterization of sub-centimeter enhancing breast masses on MRI with radiomics and machine learning in BRCA mutation carriers

Influence of residual fat signal on diffusion kurtosis MRI of suspicious mammography findings

Investigation of Synthetic Relaxometry and Diffusion Measures in the Differentiation of Benign and Malignant Breast Lesions as Compared to BI‐RADS

Contact Info

Product

Resources

About