Clinicial researchers at Imperial College London and the University of Edinburgh have developed an artificial intelligence software for identifying and quantifying small vessel disease, a frequent cause of dementia and stroke in older people, from CT scans.
The investigators have already tested the software at Imperial’s Charing Cross Hospital, demonstrating that the technology rivals that of MRI scans coupled with specialized clinicians in spotting and measuring small vessel disease.
Because CT scans are used, which are considerably faster to perform than MRI scans, and that the assessment may not need any human input, the technology can help speed up triage of patients presenting at emergency rooms with signs of stroke or dementia.
Some study details according to Imperial College London:
The study used historical data of 1082 CT scans of stroke patients across 70 hospitals in the UK between 2000-2014, including cases from the Third International Stroke Trial. The software identified and measured a marker of SVD, and then gave a score indicating how severe the disease was ranging from mild to severe. The researchers then compared the results to a panel of expert doctors who estimated SVD severity from the same scans. The level of agreement of the software with the experts was as good as agreements between one expert with another.
Additionally, in 60 cases they obtained MRI and CT in the same subjects, and used the MRI to estimate the exact amount of SVD. This showed that the software is 85 per cent accurate at predicting how severe SVD is.
Study in RSNA’s journal Radiology: Rapid Automated Quantification of Cerebral Leukoaraiosis on CT Images: A Multicenter Validation Study…