Researchers from Porto test the use of Artificial Intelligence in the early diagnosis of gastric cancer
13th September 2021
A team of researchers from Porto, led by the Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), has been developing technologies for the early diagnosis of gastric cancer based on Artificial Intelligence. This team brings together experts in the field of Artificial Intelligence and computer vision from INESC TEC and the Faculty of Sciences of the University of Porto (FCUP), as well as specialists in the field of gastroenterology and digestive endoscopy in oncology from the Portuguese Institute of Oncology (IPO Porto).
Gastric cancer is the third deadliest in the world and minimally invasive screening and gastrointestinal endoscopy play a key role in early diagnosis, crucial to improve survival rates. However, due to technical and cognitive factors, the risk of a misdiagnosis caused by human error is likely.
“Our main objective is to create technologies based on computer vision to automatically analyse videos and images obtained through non-invasive gastrointestinal endoscopies”, explained Miguel Coimbra, researcher at INESC TEC and professor at FCUP, who is leading the project together with Mário Dinis-Ribeiro, director of the Gastroenterology Unit of the IPO Porto and visiting Full Professor at the Faculty of Medicine of the University of Porto (FMUP).
“Artificial Intelligence, more specifically Computer Vision, has the potential to mitigate current limitations by providing automated endoscopy assessment tools that not only can support physicians in detecting and characterising gastric cancer lesions, but can also monitor the quality of the endoscopy performed”, he added.
“Endoscopic observation can and will certainly improve with the support of Artificial Intelligence. The quality of endoscopy in Portugal is very good, but the search for improvement in teaching and practice is also being done through Artificial Intelligence worldwide”, explained Mário Dinis-Ribeiro.
In order to achieve these goals, the researchers are developing a set of new Artificial Intelligence algorithms that will integrate a prototype to be tested in a hospital environment at the Gastroenterology Unit of the IPO Porto.
The first phase focuses on the definition of the protocol for the collection of a set of data, which will then lead to the development of the prototype. The CAGED project (Computer Assisted Gastric Cancer Diagnosis) received €240K from the Foundation for Science and Technology (FCT) and has a duration of three years.