If the technology passes muster, it will relieve radiologists from the daily tedium of manually examining hundreds of abnormal CT scans.
A joint research-and-development project has been launched in Japan to support effective diagnoses of pneumonia via artificial intelligence.
The newly-proposed AI technology assists doctors who are performing imaging diagnosis on patients suspected of having COVID 19 pneumonia. This assistance involves presenting the likelihood of infection through a numerical, three-dimensional visualization of the spread of shadows in the lungs using chest CT imaging.
Applying AI to this analysis could significantly reduce the burden on doctors by automating a process that normally demands the visual confirmation of hundreds of chest CT images per patient.
The two research partners, Fujitsu and Tokyo Shinagawa Hospital, anticipate that the system will deliver early detection of cases of COVID-19 pneumonia based on chest CT image findings, even in cases in which the possibility of infection is determined to be low upon initial examination.
Training the AI
To feed the AI engine, past CT images to facilitate diagnosis of COVID-19 pneumonia patients from Tokyo Shinagawa Hospital will be used. The AI can then be trained to detect abnormal shadow patterns in the lungs. Its learning progress will be evaluated for effectiveness by the two research groups.
The AI should ideally shorten the amount of time doctors spend visually confirming the three-dimensional spread of the lesions’ shadows from hundreds of chest CT images and to allow even non-specialists to efficiently diagnose COVID-19 pneumonia.
This joint research could be invaluable when applied globally. Tokyo Shinagawa Hospital aims to contribute to society by integrating various studies conducted in the hospital and using them for diagnosis and treatment of novel coronavirus pneumonia. Fujitsu ultimately aims to commercialize the technology as a healthcare solution for frontline medical professionals.