Projects to advance AI use in abdominal radiology are booming, according to Prof. Luis Martí-Bonmatí, head of the medical imaging department and chairman of radiology at La Fe Hospital in Valencia, Spain, who tackled the topic at ESGAR 2023, the annual meeting of the European Society of Gastrointestinal and Abdominal Radiology that unfolded last week in the same city.
‘Radiologists use AI on all imaging modalities – MR, CT and ultrasound – first and foremost to reconstruct images (… and the obtained) images are beautiful, clear, well defined and without noise,’ he told Mélisande Rouger, publisher and executive editor of Diagnostic Imaging Europe. ‘Once we have the images, we use AI to help with these processes that take time and are tedious such as organ segmentation, tumor detection and segmentation.’
For example in neuroblastoma, researchers are now developing AI-fed software that can detect 1,000 cases in just a few seconds, and provide information on tumor location, volume and shape on T2-weighted images, he added.
‘We also use AI to provide information on the properties of the tumor, for example are they aggressive, will they respond to a specific treatment, not just in neuroblastoma, but also colorectal cancer, hepatocellular carcinoma, liver metastasis and pancreatic tumors,’ he said.
AI tools are increasingly used not just in research but also innovative clinical practice, according to Martí-Bonmatí, who is scientific director of the European Cancer Imaging Initiative (EUCAIM), an infrastructure deployment project that feeds on federated AI to tackle all issues related to data privacy and security.
The project will ‘help radiologists and medical teams perform AI research to improve reproducibility,’ he concluded.