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 describe the construction of a database with substantial amounts of detail-annotated oncology imaging data from pathology and radiology. A specific objective was to be proactive, that is, to support undefined subsequent AI training across a wide range of tasks, such as detection, quantification, segmentation, and classification, which puts particular focus on the quality and generality of the annotations. The main outcome of this project was the database as such, with a collection of labeled image data from breast, ovary, skin, colon, skeleton, and liver. In addition, this effort also served as an exploration of best practices for further scalability of high-quality image collections, and a main contribution of the study was generic lessons learned regarding how to successfully organize efforts to construct medical imaging databases for AI training, summarized as eight guiding principles covering team, process, and execution aspects.
Highlights
A constantly increasing workload and cost causes an extremely demanding situation for both the radiology and pathology disciplines
The project was run by a triple-helix consortium consisting of an academic institution (CMIV, Linköping University), the diagnostic division of one public care provider (Region Östergötland), and two companies working in artificial intelligence (AI) for medical imaging (Sectra and Context Vision)
The aim of the project was to establish a database with substantial amounts of detail-annotated oncology imaging data from pathology and radiology, as a first step towards developing high-quality collections on a large scale
Summary
A constantly increasing workload and cost causes an extremely demanding situation for both the radiology and pathology disciplines. A prerequisite for successful machine learning development in imaging diagnostics is the availability of large volumes of labeled (annotated) data. University, Campus Norrköping, SE-601 74 Norrköping, Sweden. 10 ContextVision AB, Klara Norra Kyrkogata 31, SE-111 22 Stockholm, Sweden. The demand for labeled data is immense, and lack of suitable annotated data is considered a major bottleneck for AI development in the field of medical imaging. The lack pertains to several aspects: amount of cases, coverage of relevant diagnostic areas, and quality/existence of annotations [7]. It is of utmost importance to develop sustainable processes and practices for generation of high-quality annotated imaging data. An important facet of high quality is representativeness for clinical tasks, both in terms of pixel data and annotated components
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
