MRI phenotypes associated with breast cancer predisposing genetic variants, a multisite review

Maimone, Santo; Harper, Laura; Mantia, Sarah K.; Advani, Pooja; Hochwald, Alexander P.; Li, Zhuo; Hines, Stephanie L.; Patel, Bhavika

doi:10.1016/j.ejrad.2023.110788

Cited by 2 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, the number of breast biopsies has skyrocketed, with some estimates suggesting that the annual rate of these procedures in the United States alone may be as high as 1,000,000 per year [ 7 ]. This places a high economic burden on society, estimated to be USD 2 billion annually [ 8 ], and is emotionally burdensome to patients [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

Feasibility of Diffusion Tensor Imaging for Decreasing Biopsy Rates in Breast Imaging: Interim Analysis of a Prospective Study

Ecanow

Hack

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Because of the limited specificity of diagnostic imaging, many breast lesions referred for biopsy turn out to be benign. The objective of this study was to evaluate whether diffusion tensor MRI (DTI) parametric maps can be used to safely avoid biopsy of breast lesions. Individuals referred for breast biopsy based on mammogram (MG), ultrasound (US), and/or contrast enhanced (CE)-MRI were recruited. Scans consisting of T2-weighted and DTI sequences were performed. Multiple DTI-derived parametric color maps were evaluated semi-quantitatively to characterize lesions as “definitely benign,” “not definitely benign,” or “suspicious.” All patients subsequently underwent biopsy. In this moderately-sized prospective study, 21 out of 47 pathologically proven benign lesions were characterized by both readers as “definitely benign,” which would have precluded the need for biopsy. Biopsy was recommended for 11 out of 13 cancers that were characterized as “suspicious.” In the remaining two cancers and 26 of 47 benign lesions, the scans were characterized as “not definitely benign” and hence required biopsy. The main causes for “not definitely benign” scans were small lesion sizes and noise. The results suggest that in appropriately selected patients, DTI may be used to safely reduce the number of unnecessary breast biopsies.

show abstract

Section: Introductionmentioning

confidence: 99%

Feasibility of Diffusion Tensor Imaging for Decreasing Biopsy Rates in Breast Imaging: Interim Analysis of a Prospective Study

Ecanow

Hack

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

Identifying radiogenomic associations of breast cancer based on DCE‐MRI by using Siamese Neural Network with manufacturer bias normalization

Chen,

Zeng,

Cheng

et al. 2024

Medical Physics

View full text Add to dashboard Cite

Background and PurposeThe immunohistochemical test (IHC) for Human Epidermal Growth Factor Receptor 2 (HER2) and hormone receptors (HR) provides prognostic information and guides treatment for patients with invasive breast cancer. The objective of this paper is to establish a non‐invasive system for identifying HER2 and HR in breast cancer using dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI).MethodsIn light of the absence of high‐performance algorithms and external validation in previously published methods, this study utilizes 3D deep features and radiomics features to represent the information of the Region of Interest (ROI). A Siamese Neural Network was employed as the classifier, with 3D deep features and radiomics features serving as the network input. To neutralize manufacturer bias, a batch effect normalization method, ComBat, was introduced. To enhance the reliability of the study, two datasets, Predict Your Therapeutic Response with Imaging and moLecular Analysis (I‐SPY 1) and I‐SPY 2, were incorporated. I‐SPY 2 was utilized for model training and validation, while I‐SPY 1 was exclusively employed for external validation. Additionally, a breast tumor segmentation network was trained to improve radiomic feature extraction.ResultsThe results indicate that our approach achieved an average Area Under the Curve (AUC) of 0.632, with a Standard Error of the Mean (SEM) of 0.042 for HER2 prediction in the I‐SPY 2 dataset. For HR prediction, our method attained an AUC of 0.635 (SEM 0.041), surpassing other published methods in the AUC metric. Moreover, the proposed method yielded competitive results in other metrics. In external validation using the I‐SPY 1 dataset, our approach achieved an AUC of 0.567 (SEM 0.032) for HR prediction and 0.563 (SEM 0.033) for HER2 prediction.ConclusionThis study proposes a non‐invasive system for identifying HER2 and HR in breast cancer. Although the results do not conclusively demonstrate superiority in both tasks, they indicate that the proposed method achieved good performance and is a competitive classifier compared to other reference methods. Ablation studies demonstrate that both radiomics features and deep features for the Siamese Neural Network are beneficial for the model. The introduced manufacturer bias normalization method has been shown to enhance the method's performance. Furthermore, the external validation of the method enhances the reliability of this research. Source code, pre‐trained segmentation network, Radiomics and deep features, data for statistical analysis, and Supporting Information of this article are online at: https://github.com/FORRESTHUACHEN/Siamese_Neural_Network_based_Brest_cancer_Radiogenomic.

show abstract

MRI phenotypes associated with breast cancer predisposing genetic variants, a multisite review

Cited by 2 publications

References 30 publications

Feasibility of Diffusion Tensor Imaging for Decreasing Biopsy Rates in Breast Imaging: Interim Analysis of a Prospective Study

Feasibility of Diffusion Tensor Imaging for Decreasing Biopsy Rates in Breast Imaging: Interim Analysis of a Prospective Study

Identifying radiogenomic associations of breast cancer based on DCE‐MRI by using Siamese Neural Network with manufacturer bias normalization

Contact Info

Product

Resources

About