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

Membranous nephropathy (MN) is a frequent type of adult nephrotic syndrome,which has a high clinical incidence and can cause various complications. In thebiopsy microscope slide of membranous nephropathy, spikelike projections on theglomerular basement membrane is a prominent feature of the MN. However, due tothe whole biopsy slide contains large number of glomeruli, and each glomerulusincludes many spike lesions, the pathological feature of the spikes is notobvious. It thus is time-consuming for doctors to diagnose glomerulus one byone and is difficult for pathologists with less experience to diagnose. In thispaper, we establish a visualized classification model based on the multi-scaleannotation multi-instance learning (MSA-MIL) to achieve glomerularclassification and spikes visualization. The MSA-MIL model mainly involvesthree parts. Firstly, U-Net is used to extract the region of the glomeruli toensure that the features learned by the succeeding algorithm are focused insidethe glomeruli itself. Secondly, we use MIL to train an instance-levelclassifier combined with MSA method to enhance the learning ability of thenetwork by adding a location-level labeled reinforced dataset, therebyobtaining an example-level feature representation with rich semantics. Lastly,the predicted scores of each tile in the image are summarized to obtainglomerular classification and visualization of the classification results ofthe spikes via the usage of sliding window method. The experimental resultsconfirm that the proposed MSA-MIL model can effectively and accurately classifynormal glomeruli and spiked glomerulus and visualize the position of spikes inthe glomerulus. Therefore, the proposed model can provide a good foundation forassisting the clinical doctors to diagnose the glomerular membranousnephropathy.

MSA-MIL: A deep residual multiple instance learning model based on multi-scale annotation for classification and visualization of glomerular spikes