Observer Variability in the Application of Morphologic and Dynamic Criteria According to the BI-RADS for MRI

Moraes, Paula; Chala, Luciano Fernandes; Chang, Yoon Seoung; Kim, Su Jin; Endo, Erica; Barros, Nestor de; Spinola, Flavio

doi:10.1111/j.1524-4741.2010.00968.x

Cited by 5 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in the present study, the agreement rates for the BI-RADS category and descriptors between the three radiologists with various levels of experience were also poor ( κ = 0.18–0.34). As demonstrated in a previous study, the diagnostic performance of BI-RADS MRI reading was affected by reader experience [ 9 , 10 ]; less experienced readers showed the poorest diagnostic outcomes in the interpretation of NME assessments [ 10 ], which is consistent with our results. In addition, subcategorization of BI-RADS category 4 lesions has not yet been adopted in MRI because of a lack of data on the accuracy of subdivision.…”

Section: Discussionsupporting

confidence: 92%

“…In the present study, the agreement rates between the three radiologists who had different levels of experience in general and breast radiology were poor for all BI-RADS MRI descriptors of NME ( κ = 0.15–0.39). Previous reports have shown that there is significant variability among radiologists in choosing the optimal BI-RADS lesion description, especially when reporting non-mass lesions [ 8 , 9 ]. The reported agreement rates were 0.25–0.27 in the distribution and 0.25–0.34 in the internal enhancement pattern [ 8 , 9 ], which is consistent with the present study.…”

Section: Discussionmentioning

confidence: 99%

“…Previous reports have shown that there is significant variability among radiologists in choosing the optimal BI-RADS lesion description, especially when reporting non-mass lesions [ 8 , 9 ]. The reported agreement rates were 0.25–0.27 in the distribution and 0.25–0.34 in the internal enhancement pattern [ 8 , 9 ], which is consistent with the present study.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists’ interpretations at various levels

et al. 2023

View full text Add to dashboard Cite

Purpose To evaluate the diagnostic performance of deep learning using the Residual Networks 50 (ResNet50) neural network constructed from different segmentations for distinguishing malignant and benign non-mass enhancement (NME) on breast magnetic resonance imaging (MRI) and conduct a comparison with radiologists with various levels of experience. Materials and methods A total of 84 consecutive patients with 86 lesions (51 malignant, 35 benign) presenting NME on breast MRI were analyzed. Three radiologists with different levels of experience evaluated all examinations, based on the Breast Imaging-Reporting and Data System (BI-RADS) lexicon and categorization. For the deep learning method, one expert radiologist performed lesion annotation manually using the early phase of dynamic contrast-enhanced (DCE) MRI. Two segmentation methods were applied: a precise segmentation was carefully set to include only the enhancing area, and a rough segmentation covered the whole enhancing region, including the intervenient non-enhancing area. ResNet50 was implemented using the DCE MRI input. The diagnostic performance of the radiologists’ readings and deep learning were then compared using receiver operating curve analysis. Results The ResNet50 model from precise segmentation achieved diagnostic accuracy equivalent [area under the curve (AUC) = 0.91, 95% confidence interval (CI) 0.90, 0.93] to that of a highly experienced radiologist (AUC = 0.89, 95% CI 0.81, 0.96; p = 0.45). Even the model from rough segmentation showed diagnostic performance equivalent to a board-certified radiologist (AUC = 0.80, 95% CI 0.78, 0.82 vs. AUC = 0.79, 95% CI 0.70, 0.89, respectively). Both ResNet50 models from the precise and rough segmentation exceeded the diagnostic accuracy of a radiology resident (AUC = 0.64, 95% CI 0.52, 0.76). Conclusion These findings suggest that the deep learning model from ResNet50 has the potential to ensure accuracy in the diagnosis of NME on breast MRI.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists’ interpretations at various levels

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Imaging takes the entire in situ tumor into consideration. Since visual assessment of MR images by human readers may suffer from inter-observer variability due to the subjective nature of image interpretation (Wedegartner et al 2001, Stoutjesdijk et al 2005, de Camargo Moraes et al 2010, automated computerized image analysis may be preferable.…”

Section: Introductionmentioning

confidence: 99%

Eigentumors for prediction of treatment failure in patients with early-stage breast cancer using dynamic contrast-enhanced MRI: a feasibility study

et al. 2017

View full text Add to dashboard Cite

We present a radiomics model to discriminate between patients at low risk and those at high risk of treatment failure at long-term follow-up based on eigentumors: principal components computed from volumes encompassing tumors in washin and washout images of pre-treatment dynamic contrast-enhanced (DCE-) MR images. Eigentumors were computed from the images of 563 patients from the MARGINS study. Subsequently, a least absolute shrinkage selection operator (LASSO) selected candidates from the components that contained 90% of the variance of the data. The model for prediction of survival after treatment (median follow-up time 86 months) was based on logistic regression. Receiver operating characteristic (ROC) analysis was applied and area-under-the-curve (AUC) values were computed as measures of training and cross-validated performances. The discriminating potential of the model was confirmed using Kaplan-Meier survival curves and log-rank tests. From the 322 principal components that explained 90% of the variance of the data, the LASSO selected 28 components. The ROC curves of the model yielded AUC values of 0.88, 0.77 and 0.73, for the training, leave-one-out cross-validated and bootstrapped performances, respectively. The bootstrapped Kaplan-Meier survival curves confirmed significant separation for all tumors (P < 0.0001). Survival analysis on immunohistochemical subgroups shows significant separation for the estrogen-receptor subtype tumors (P < 0.0001) and the triple-negative subtype tumors (P = 0.0039), but not for tumors of the HER2 subtype (P = 0.41). The results of this retrospective study show the potential of early-stage pre-treatment eigentumors for use in prediction of treatment failure of breast cancer.

show abstract

Characterization of the enhancing lesions on dynamic contrast enhanced magnetic resonance imaging in patients with interstitial mammoplasty

Kim

Kang

et al. 2013

European Journal of Radiology

View full text Add to dashboard Cite

Observer Variability in the Application of Morphologic and Dynamic Criteria According to the BI-RADS for MRI

Cited by 5 publications

References 6 publications

Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists’ interpretations at various levels

Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists’ interpretations at various levels

Eigentumors for prediction of treatment failure in patients with early-stage breast cancer using dynamic contrast-enhanced MRI: a feasibility study

Characterization of the enhancing lesions on dynamic contrast enhanced magnetic resonance imaging in patients with interstitial mammoplasty

Contact Info

Product

Resources

About