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/

Zendy Plus

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

Zendy Tools

Zendy Open

Prostate cancer is the most prevalent cancer among men in Western countries,with 1.1 million new diagnoses every year. The gold standard for the diagnosisof prostate cancer is a pathologists' evaluation of prostate tissue.  To potentially assist pathologists deep-learning-based cancer detectionsystems have been developed. Many of the state-of-the-art models arepatch-based convolutional neural networks, as the use of entire scanned slidesis hampered by memory limitations on accelerator cards. Patch-based systemstypically require detailed, pixel-level annotations for effective training.However, such annotations are seldom readily available, in contrast to theclinical reports of pathologists, which contain slide-level labels. As such,developing algorithms which do not require manual pixel-wise annotations, butcan learn using only the clinical report would be a significant advancement forthe field.  In this paper, we propose to use a streaming implementation of convolutionallayers, to train a modern CNN (ResNet-34) with 21 million parameters end-to-endon 4712 prostate biopsies. The method enables the use of entire biopsy imagesat high-resolution directly by reducing the GPU memory requirements by 2.4 TB.We show that modern CNNs, trained using our streaming approach, can extractmeaningful features from high-resolution images without additional heuristics,reaching similar performance as state-of-the-art patch-based andmultiple-instance learning methods. By circumventing the need for manualannotations, this approach can function as a blueprint for other tasks inhistopathological diagnosis.  The source code to reproduce the streaming models is available athttps://github.com/DIAGNijmegen/pathology-streaming-pipeline .

Detection of prostate cancer in whole-slide images through end-to-end training with image-level labels