Computer monitors the assessment of radiology images 24/7

Computer monitors the assessment of radiology images 24/7
Computer monitors the assessment of radiology images 24/7

How does AI . work

For the past three years, medical imaging in Isala has been working closely with AIDOC, a company specializing in AI. Rogier: ‘They mainly focus on prioritizing imaging in acute radiology. In large hospitals, for example in America, there are often long lists of CT scans that have yet to be viewed. Then it is important that the radiologists are the first to see the images of patients in the emergency room (ED) with abnormalities that cannot wait too long. We do use this application, but it is less important for Isala because we usually assess all CT scans made in the emergency department within an hour. Still, we were interested in working together when that question came up.’

The system works as follows. For example, when someone with a head injury comes to the emergency room, a CT scan is often made to rule out bleeding or fractures. Martijn: ‘The images are immediately visible to us, so that we can assess them. In addition, they are sent directly (anonymised) to AIDOC. Within 10 minutes after I have received all the images, I also receive a message from AIDOC on my screen. If the AI ​​module has detected a bleeding, I see on the screen where that bleeding is and I know where to look. We also receive a notification when the computer has not seen any abnormalities. Of course you always check it yourself again. You want to be one hundred percent sure.’

Faster

It takes a lot of time and research to run an AI program “perfectly” within your own hospital. Martijn: ‘One of the problems in the beginning was that it took too long before we received the AI ​​images again, sometimes more than 30 minutes after the scan was made. That had to be faster. We were also not notified at first if no abnormalities were found. But how can you be sure that the computer has looked? So that too has been adjusted.’

Deviations

Radiology is now using AI for possible brain haemorrhages, cervical vertebral fractures and pulmonary embolisms. Rogier: ‘Everyone sees major bleeding in the brain or fractures in the neck vertebrae. The computer picks out the small bleeding or tears that patients may suffer from. That is certainly a real added value during the assessment of the CT images in the night hours. AI keeps us on our toes. During our research into the use of AI, we had the computer assessed 2500 neck scans, among other things. Some of those scans showed fractures. The computer pulled almost all of them out, but also eventually saw fractures that the doctors reviewing the scan at the time hadn’t seen. This almost always involved very small tears that the patient most likely never had any problems with. The abnormalities that the computer had not found turned out not to be fractures but displacements of the vertebrae.’

pulmonary embolism

The program also often removes the small pulmonary embolisms, says Martijn. ‘We will therefore also be using AI for all contrast scans of the lungs. Oncology patients, for example, have a greater risk of developing pulmonary embolisms. When you do a lung scan to assess how the tumors are doing, that’s your focus. If the computer then shows a possible pulmonary embolism, that is only a gain and even better care.’

Priority

AI also helps the radiologists with busy shifts. Martijn: ‘When the service is busy and we receive several scans from different locations at the same time, that requires one hundred percent attention. AI helps us to respond faster and adequately.’

Final responsibility

But will it be computers that will completely take over healthcare? ‘No, that’s not going to happen’, Martijn and Rogier answer. ‘A computer cannot take ultimate responsibility, the doctor will always do that. AI helps us do our job better. All studies show that radiologists and AI do better together than either alone. Now that it is getting busier in healthcare, including in the emergency room, that extra pair of eyes is a must. AI is one of the solutions to responsibly deal with the increasing demand for care.’

The article is in Dutch

Tags: Computer monitors assessment radiology images

NEXT Why is your sense of direction better if you come from the countryside?