Health AI Central
Share:
Peer-Reviewed Publication
J Digit Imaging2021;34(1):105-115.February 1, 2021Journal Article

Proactive Construction of an Annotated Imaging Database for Artificial Intelligence Training.

Caroline Bivik Stadler1,2, Martin Lindvall3,4, Claes Lundström5,3,4, Anna Bodén5,6,7, Karin Lindman5,6,7, Jeronimo Rose5, Darren Treanor5,6,7,8,9, Johan Blomma10, Karin Stacke3,4, Nicolas Pinchaud11, Martin Hedlund11, Filip Landgren10, Mischa Woisetschläger5,10, Daniel Forsberg3
1Center for Medical Image Science and Visualization (CMIV), Linköping University Hospital, Linköping University, SE-581 85, Linköping, Sweden. caroline.bivik.stadler@liu.se.
2Department of Health, Medicine and Caring Sciences (HMV), Linköping University, SE-581 85, Linköping, Sweden. caroline.bivik.stadler@liu.se.
3Sectra AB, Teknikringen 20, SE-583 30, Linköping, Sweden.
4Department of Science and Technology (ITN), Linköping University, Campus Norrköping, SE-601 74, Norrköping, Sweden.
5Center for Medical Image Science and Visualization (CMIV), Linköping University Hospital, Linköping University, SE-581 85, Linköping, Sweden.
6Department of Clinical Pathology, Region Östergötland, Linköping University Hospital, SE-581 85, Linköping, Sweden.
7Department of Biomedical and Clinical Sciences (BKV), Linköping University, SE-581 85, Linköping, Sweden.
8Department of Cellular Pathology, Leeds Teaching Hospital NHS Trust, Beckett St, Leeds, LS9 7TF, UK.
9University of Leeds, Leeds, LS2 9JT, UK.
10Department of Radiology, Region Östergötland, Linköping University Hospital, SE-581 85, Linköping, Sweden.
11ContextVision AB, Klara Norra Kyrkogata 31, SE-111 22, Stockholm, Sweden.
PubMed PMC DOI PDF

Abstract

Artificial intelligence (AI) holds much promise for enabling highly desired imaging diagnostics improvements. One of the most limiting bottlenecks for the development of useful clinical-grade AI models is the lack of training data. One aspect is the large amount of cases needed and another is the necessity of high-quality ground truth annotation. The aim of the project was to establish and describ…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.