Brain tumor diagnosis takes only 30 seconds in Taiwan

New AI-based system makes brain tumor treatment more efficient

  1644
CyberKnife robotic radiosurgery system at NTUH (CNA photo)

CyberKnife robotic radiosurgery system at NTUH (CNA photo)

TAIPEI (Taiwan News) – National Taiwan University Hospital (NTUH) announced on Wednesday (Aug. 14) that it now takes less than 30 seconds for the hospital to locate a brain tumor, a major breakthrough made with the assistance of artificial intelligence (AI) technologies.

The collaboration between the leading hospital of Taiwan and the healthcare startup Vysioneer led to a reduction of the amount of time required for a brain tumor diagnosis, which could otherwise take hours. In less than a minute, the AI system is capable of spotting the three most common types of brain tumor, namely brain metastasis, meningioma, and acoustic neuroma, said NTUH.

In traditional medical practices, the diagnosis of brain tumors usually involves the use of electroencephalography, magnetic resonance imaging (MRI), and computed tomography (CT) scans. The new technology, an automated tumor detection and imaging system developed through machine learning, helps deliver a quick brain examination, diagnosing tumors with a 90 percent rate of accuracy.

The medical advance will bring about shorter surgery preparation for neurosurgeons and radiation oncologists. It is also touted to increase the success rate of operations and allow for more efficient treatment, according to NTUH.

The hospital has treated over 20 patients with the new system since July. The achievement will be presented in a thesis at the American Society for Radiation Oncology's annual meeting, which will take place in Chicago in September, reported the Central News Agency.