“Our results were very promising, as both trained models performed remarkably well and achieved an absolute percentage error of less than 5%. This indicated that the models could identify the object inserted in the phantom with similar accuracy and confidence as a human professional, for almost all reconstruction configurations and abnormalities sizes and contrasts,” wrote lead researcher Dr. Sandra Doria, from the University of Florence’s physics department, in her study, which will be part of the JMI Special Issue on Medical Image Perception and Observer Performance.

Additionally, reviewing, creating and adapting guidelines and integrating them into the technological process may not only reduce exposure without affecting outcomes, but also cut expenses for providers.


Clinicians at the Pediatric Trauma Center at UR Medicine Golisano Children’s Hospital in New York did just this by adapting existing guidelines for head, neck and abdomen/pelvis, and developing new ones for the chest area that cut unnecessary imaging in half, according to their study published in the Journal of Pediatric Surgery.

These insights demonstrate that in order to reduce repetitive CT imaging and associated risks of developing cancer, it is essential to enforce these standard guidelines for appropriate imaging, and ensure providers have access to the necessary technologies, resources and funding to automate the processes for reducing unnecessary radiation exposure so that clinicians are more motivated to integrate them into their practices.

The findings of the Taiwanese study were published in CMAJ (Canadian Medical Association Journal).

Back to HCB News

CT Homepage