On February 27, Finland's University of Jyvaskyla said its researchers had developed a new tool, using Artificial Intelligence (AI) technology, to automatically identify colon cancer from histopathological sample analysis.
According to the University of Jyvaskyla, the neural network model developed in this study outperformed all previous analysis methods in tissue sample classification.
The researcher responsible for developing the method, Fabi Prezja, said the new tool can identify all tissue types relevant to identifying colon cancer, with an accuracy of 96.74%.
Typically, tissue analysis requires a pathologist to look through scanned tissue slides and mark each spot where cancerous and related tissue can be seen.
However, the AI-powered tool analyzes a sample and automatically highlights areas containing different tissue types. The accuracy of this tool has the potential to significantly reduce the workload of pathologists, potentially leading to faster diagnosis, prognosis, and clinical understanding.
Notably, the University of Jyvaskyla research team has made the tool freely available to encourage research collaboration.
“Making the tool freely available is intended to accelerate future advances by encouraging scientists, developers, and researchers around the world to continue developing the tool and finding new applications for it,” said researcher Prezja.
However, the research team from the University of Jyvaskyla also pointed out that despite the promising results, the introduction of AI tools into clinical practice needs to be done gradually and cautiously.
The tool was developed by researchers at the University of Jyvaskyla, in collaboration with the Institute of Biomedical Sciences at the University of Turku, the University of Helsinki and Nova Hospital in Finland./.
Source: https://www.vietnamplus.vn/ung-dung-ai-xac-dinh-ung-thu-dai-trang-tu-phan-tich-mau-mo-benh-hoc-post1014882.vnp
Comment (0)