1235 GMT November 12, 2019
The private Showa University in Tokyo together with Nagoya University and Cybernet Systems Co. jointly developed a software that analyzes colon polyps shown in images taken during endoscopic examinations, japantimes.co.jp reported.
Using a vast amount of past diagnostic data, the software can determine whether such polyps are malignant. It has been proven reliable — with an assessment determining that it can identify a potentially cancerous polyp with the same accuracy as a leading specialist — and approved for commercialization by the government.
LPixel Inc., an image analysis service venture, produced a program that spots cell degeneration in the cerebrum by examining images taken during a magnetic resonance imaging (MRI) scan.
The company used a deep learning approach, having the system process large amounts of diagnostic data. When a progression in a cerebral disease is suspected, the system will recommend that the patient undergo a closer check by a doctor. LPixel’s software has also been approved for sale.
The types of cell degeneration detected are often caused by arteriosclerosis or age-related deterioration in blood circulation, and are associated with the prevalence of dementia and stroke.
Software-aided medical devices are expected to lessen the burden on doctors during diagnosis, while reducing human error.
Expecting increased reliance on AI technologies in the medical field, the Ministry of Health, Labor and Welfare has compiled guidelines that put the onus on doctors to ultimately ensure diagnostic results are correct.