TzanckNet: a convolutional neural network to identify cells in the cytology of erosive-vesiculobullous diseases.

Clicks: 183
ID: 261029
2020
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #1,331 of 1,628 articles by views in Scientific reports

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 1,628 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Tzanck smear test is a low-cost, rapid and reliable tool which can be used for the diagnosis of many erosive-vesiculobullous, tumoral and granulomatous diseases. Currently its use is limited mainly due to lack of experience in interpretation of the smears. We developed a deep learning model, TzanckNet, that can identify cells in Tzanck smear test findings. TzanckNet was trained on a retrospective development dataset of 2260 Tzanck smear images collected between December 2006 and December 2019. The finalized model was evaluated using a prospective validation dataset of 359 Tzanck smear images collected from 15 patients during January 2020. It is designed to recognize six cell types (acantholytic cells, eosinophils, hypha, multinucleated giant cells, normal keratinocytes and tadpole cells). For 359 images and 6 cell types, TzanckNet made 2154 predictions. The accuracy was 94.3% (95% CI 93.4-95.3), the sensitivity was 83.7% (95% CI 80.3-87.0) and the specificity was 97.3% (95% CI 96.5-98.1). The area under the receiver operating characteristic curve was 0.974. Our results show that TzanckNet has the potential to lower the experience barrier needed to use this test, broadening its user base, and hence improving patient well-being.
Reference Key
noyan2020tzancknetscientific Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Noyan, Mehmet Alican;Durdu, Murat;Eskiocak, Ali Haydar;
Journal Scientific reports
Year 2020
DOI
10.1038/s41598-020-75546-z
URL
Keywords
dermatology semantic segmentation in vivo segmentation melanocytic lesion reflectance confocal microscopy

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.