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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Purpose: To develop a deep network architecture that would achieve fullyautomated radiologist-level segmentation of cancers at breast MRI. Materialsand Methods: In this retrospective study, 38229 examinations (composed of 64063individual breast scans from 14475 patients) were performed in female patients(age range, 12-94 years; mean age, 52 years +/- 10 [standard deviation]) whopresented between 2002 and 2014 at a single clinical site. A total of 2555breast cancers were selected that had been segmented on two-dimensional (2D)images by radiologists, as well as 60108 benign breasts that served as examplesof noncancerous tissue; all these were used for model training. For testing, anadditional 250 breast cancers were segmented independently on 2D images by fourradiologists. Authors selected among several three-dimensional (3D) deepconvolutional neural network architectures, input modalities, and harmonizationmethods. The outcome measure was the Dice score for 2D segmentation, which wascompared between the network and radiologists by using the Wilcoxon signed ranktest and the two one-sided test procedure. Results: The highest-performingnetwork on the training set was a 3D U-Net with dynamic contrast-enhanced MRIas input and with intensity normalized for each examination. In the test set,the median Dice score of this network was 0.77 (interquartile range, 0.26). Theperformance of the network was equivalent to that of the radiologists (twoone-sided test procedures with radiologist performance of 0.69-0.84 asequivalence bounds, P <= .001 for both; n = 250). Conclusion: When trained on asufficiently large dataset, the developed 3D U-Net performed as well asfellowship-trained radiologists in detailed 2D segmentation of breast cancersat routine clinical MRI.

Radiologist-level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans