Artificial intelligence-based algorithms Decision-making support for computed tomography of the chest
Manava P, Galster M, Heinen H, Stebner A, Lell M (2020)
Publication Type: Journal article
Publication year: 2020
Journal
DOI: 10.1007/s00117-020-00714-1
Abstract
Artificial intelligence (AI) algorithms are increasingly used in radiology. The main areas of application are, for example, the detection of lung lesions and the diagnosis of chronic obstructive and interstitial lung diseases. The aim of our study was to train and evaluate a package of algorithms that analyze data from computed tomographic (CT) images of the chest and provide quantitative measurements to the radiologist. The following algorithms were trained: lung lesion detection and measurement, lung lobe segmentation, vessel segmentation and measurement, coronary calcium scoring, measurement and density analysis of vertebral bodies. AI-supported algorithms will become part of daily routine of the radiologist in the future. Tasks that do not require medical expertise can be performed by AI. However, our results show that, based on the current accuracy, verification by an experienced radiologist is necessary.
Authors with CRIS profile
Additional Organisation(s)
Involved external institutions
Germany (DE)How to cite
APA:
Manava, P., Galster, M., Heinen, H., Stebner, A., & Lell, M. (2020). Artificial intelligence-based algorithms Decision-making support for computed tomography of the chest. Radiologe. https://dx.doi.org/10.1007/s00117-020-00714-1
MLA:
Manava, Panagiota, et al. "Artificial intelligence-based algorithms Decision-making support for computed tomography of the chest." Radiologe (2020).
BibTeX: Download