Researchers at the University of Jyväskylä in collaboration with the Biomedicine University Institute of Turku and Nova Central Finland have developed an artificial intelligence tool for automated colorectal cancer tissue analysis. The modified neural network outperforms all previous solutions to the task. Neural networks provide a faster, more precise method for classifying colorectal cancer tissue images from microscope slides. This can significantly reduce the workload of histopathologists, resulting in faster insight, prognosis and diagnosis.
Public accessibility for future advancements
In a remarkable desire to open up science and cooperative growth, researchers are making neural trained network tools available to the public. The gesture aims to further advance its capabilities by inviting scientists, researchers and developers from around the world to refine its capabilities and investigate new applications.
“By providing public access, the goal is to achieve rapid progress in colorectal cancer research,” added Fabi Prezza, who was responsible for the design of the method.
Rigorous clinical validation is required
While the results are promising, intelligent adoption of AI in clinical settings is critical. The caliber and diversity of medical data is central to the success of AI-driven approaches. As these AI solutions inch closer to routine clinical implementation, it is imperative that they consistently align with clinical standards with rigorous clinical validation for their results.