English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Objective. To use habitat analysis (also termed habitat imaging) for classifying untreated breast cancer-enhanced magnetic resonance imaging (MRI) in women. Moreover, we intended to obtain clustering parameters to predict the BReast CAncer gene 1 (BRCA1) gene mutation and to determine the use of MRI as a noninvasive examination tool. Methods. We obtained enhanced MRI data of patients with breast cancer before treatment and selected some sequences as the source of habitat imaging. We used the  k -means clustering to classify these images. According to the formed subregions, we calculated several parameters to evaluate the clustering. We used immunohistochemistry to detect BRCA1 mutations. Moreover, we separately determined the ability of these parameters through independent modeling or multiple parameter joint modeling to predict these mutations. Results. Of all extracted values, separation (SP) demonstrated the best prediction performance for a single parameter (area under the receiver operating characteristic curve (AUC), 0.647; 95% confidence interval (CI), 0.557–0.731). Simultaneously, models based on the Calinski-Harabasz Index and sum of square error performed better in the training (AUC, 0.903; 95% CI, 0.831–0.96) and verification (AUC, 0.845; 95% CI, 0.723–0.942) sets for multiparameter joint modeling. Conclusion. Based on the enhanced MRI of breast tumors and the subregions generated according to the habitat imaging theory, the parameters extracted to describe the clustering effect could reflect the BRCA1 status. Differences between clusters, including the general differences of cluster centers and clusters and the similarity of samples within clusters, were the embodiment of this mutation. We propose an algorithm to predict the BRCA1 mutation of a patient according to the enhanced MRI of the breast tumor.

Habitat Analysis of Breast Cancer-Enhanced MRI Reflects BRCA1 Mutation Determined by Immunohistochemistry