Special Feature
Part of a ZDNet Special Feature: Coronavirus: Business and technology in a pandemic

Fujitsu and Tokyo Shinagawa Hospital to develop AI for COVID-19 pneumonia diagnosis

In a bid to help automate the process of examining chest CT scans.

Fujitsu and Tokyo Shinagawa Hospital to develop AI for COVID-19 pneumonia diagnosis

Fujitsu and Tokyo Shinagawa Hospital have announced a partnership to jointly develop artificial intelligence (AI) technology that can be used to help with early detection of COVID-19 pneumonia, even in cases where the possibility of infection is determined as low during initial examinations.  

The AI technology will be designed specifically to help examine chest CT scans, which are considered as an effective method for diagnosing novel coronavirus pneumonia, even when COVID-19 test results are negative, Fujitsu said.

According to the Japanese tech giant, data collected from past CT scans of COVID-19 pneumonia patients from Tokyo Shinagawa Hospital will be used to train the AI technology to detect abnormal shadow patterns in the lungs.

"When diagnosing COVID-19 pneumonia, patterns of abnormal opacities in the lungs, as well as the spread of shadows across the entire lung is important information," the company said.

Applying AI to the analysis can help automate a process, according to Fujitsu, that normally requires doctors to visually check hundreds of chest CT images per patient to understand the characteristics of the lung. 

"A growing demand for technologies that reduce the burden on doctors and support speedy decision-making has accompanied the spread of the COVID-19 virus. It is also important to identify novel coronavirus pneumonia from a CT scan of the patient's chest if there is a low likelihood of a novel coronavirus infection during the examination and PCR testing is not performed," Fujitsu said. 

Fujitsu said the ultimate outcome for the R&D project is to commercialise the technology.

"By linking it with electronic medical record information, the goal is to support diagnosis by doctors based on chest CT images, while also expanding the application area of this technology," the company said.

Related Coverage

Drug development in a year? IBM bets on AI, robotics to ramp up molecule research

IBM's new platform could contribute to ongoing research efforts at a time when discovering new drugs is at the heart of many projects.

AI and the coronavirus fight: How artificial intelligence is taking on COVID-19

From moderating social media to unpicking the very essence of COVID-19, AI is helping tackle the coronavirus in all manner of ingenious ways.

'Fastest' AI supercomputer in academia to work on climate change, coronavirus projects

The University of Florida has revealed a partnership with Nvidia to upgrade its existing supercomputer to a next-level device that will support AI research.

New global coalition aims to help policymakers leverage AI against COVID-19

A collection of think tanks and UN-backed agencies are forming the Collective and Augmented Intelligence Against Covid-19 (CAIAC) to create a platform that relies on both AI and human expertise to guide COVID-19 decision-making.