Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

One Size Fits All Evaluation of the Transferability of a New “Learning” Histologic Image Analysis Application

One Size Fits All Evaluation of the Transferability of a New “Learning” Histologic... TECHNICAL ARTICLE One Size Fits All: Evaluation of the Transferability of a New “Learning” Histologic Image Analysis Application Janine Arlt, MSc,* Andre´ Homeyer, Dipl.-Inf.,w Constanze Sa¨nger, Dipl.-Biol.,* Uta Dahmen, MD, PhD,* and Olaf Dirsch, MD, PhDz he quantitative analysis of histologic sections is of Abstract: Quantitative analysis of histologic slides is of im- Tincreasing importance. In clinical practice, the fast portance for pathology and also to address surgical questions. and accurate quantitative analysis of histologic sections is Recently, a novel application was developed for the automated essential as a basis for therapeutic decisions, for example, quantification of whole-slide images. The aim of this study was for tumor grading. In addition to clinical pathology, to test and validate the underlying image analysis algorithm with quantitative analysis of histologic sections is important respect to user friendliness, accuracy, and transferability to dif- for scientific questions, for example, to quantify necrosis ferent histologic scenarios. The algorithm splits the images into in liver sections to assess the vital liver mass after focal tiles of a predetermined size and identifies the tissue class of each obstruction and studies regarding the proliferation index tile. In the training procedure, the user specifies example tiles of of defined http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Applied Immunohistochemistry & Molecular Morphology Wolters Kluwer Health

One Size Fits All Evaluation of the Transferability of a New “Learning” Histologic Image Analysis Application

Applied Immunohistochemistry & Molecular Morphology , Volume Publish Ahead of Print – Dec 1, 2014

Loading next page...
 
/lp/wolters-kluwer-health/one-size-fits-all-evaluation-of-the-transferability-of-a-new-ldquo-00czfL1pY1
Copyright
Copyright © 2014 by Lippincott Williams & Wilkins
ISSN
1541-2016
DOI
10.1097/PAI.0000000000000120
pmid
25517866
Publisher site
See Article on Publisher Site

Abstract

TECHNICAL ARTICLE One Size Fits All: Evaluation of the Transferability of a New “Learning” Histologic Image Analysis Application Janine Arlt, MSc,* Andre´ Homeyer, Dipl.-Inf.,w Constanze Sa¨nger, Dipl.-Biol.,* Uta Dahmen, MD, PhD,* and Olaf Dirsch, MD, PhDz he quantitative analysis of histologic sections is of Abstract: Quantitative analysis of histologic slides is of im- Tincreasing importance. In clinical practice, the fast portance for pathology and also to address surgical questions. and accurate quantitative analysis of histologic sections is Recently, a novel application was developed for the automated essential as a basis for therapeutic decisions, for example, quantification of whole-slide images. The aim of this study was for tumor grading. In addition to clinical pathology, to test and validate the underlying image analysis algorithm with quantitative analysis of histologic sections is important respect to user friendliness, accuracy, and transferability to dif- for scientific questions, for example, to quantify necrosis ferent histologic scenarios. The algorithm splits the images into in liver sections to assess the vital liver mass after focal tiles of a predetermined size and identifies the tissue class of each obstruction and studies regarding the proliferation index tile. In the training procedure, the user specifies example tiles of of defined

Journal

Applied Immunohistochemistry & Molecular MorphologyWolters Kluwer Health

Published: Dec 1, 2014

There are no references for this article.