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

Breast cancer is one of the most prevalent cancers worldwide and pathologistsare closely involved in establishing a diagnosis. Tools to assist in making adiagnosis are required to manage the increasing workload. In this context,artificial intelligence (AI) and deep-learning based tools may be used in dailypathology practice. However, it is challenging to develop fast and reliablealgorithms that can be trusted by practitioners, whatever the medical center.We describe a patch-based algorithm that incorporates a convolutional neuralnetwork to detect and locate invasive carcinoma on breast whole-slide images.The network was trained on a dataset extracted from a reference acquisitioncenter. We then performed a calibration step based on transfer learning tomaintain the performance when translating on a new target acquisition center byusing a limited amount of additional training data. Performance was evaluatedusing classical binary measures (accuracy, recall, precision) for both centers(referred to as test reference dataset and test target dataset) and at twolevels: patch and slide level. At patch level, accuracy, recall, and precisionof the model on the reference and target test sets were 92.1\% and 96.3\%, 95\%and 87.8\%, and 73.9\% and 70.6\%, respectively. At slide level, accuracy,recall, and precision were 97.6\% and 92.0\%, 90.9\% and 100\%, and 100\% and70.8\% for test sets 1 and 2, respectively. The high performance of thealgorithm at both centers shows that the calibration process is efficient. Thisis performed using limited training data from the new target acquisition centerand requires that the model is trained beforehand on a large database from areference center. This methodology allows the implementation of AI diagnostictools to help in routine pathology practice.

Multicenter automatic detection of invasive carcinoma on breast whole slide images