AI Tool for Automatic Colorectal Cancer Tissue Analysis Outperforms Prior Methods

Colorectal Cancer (CRC) ranks as the third most prevalent and the second most lethal cancer. Catching it early and treating it promptly are extremely important. While machine vision technologies have seen remarkable improvements in automatically classifying types of cancer, they largely rely on deep neural networks with millions of parameters fine-tuned for diagnostic and prognostic tasks. Even though deep learning has shown extraordinary capabilities, healthcare professionals still have to inspect biopsied tissue samples to verify the diagnosis and assess the stage of the tumor. To advance this field further, scientists have now introduced an artificial intelligence (AI) solution specifically designed for automated analysis of colorectal cancer tissue that outperforms previous techniques.

The refined neural network developed by researchers from the University of Jyväskylä (Jyväskylä, Finland) has set new performance benchmarks in colorectal cancer tissue analysis. The AI-based system offers a more accurate and quicker way to categorize tissue samples of colorectal cancer from microscope slides. This advancement could significantly ease the work burden on histopathologists, thus enabling faster and more precise prognoses and diagnoses. Despite the promising results, it is important to be cautious while incorporating AI into medical practice.

Image: A new AI tool outperforms prior methods in colorectal cancer analysis (Photo courtesy of 123RF)

As AI technologies move closer to becoming a standard part of clinical procedures, it becomes increasingly vital that they go through rigorous clinical validation. This is to ensure that the results they produce are consistently in line with established clinical norms. In a move encouraging collaborative development, the researchers are making this trained neural network publicly available. Their aim is to accelerate progress in the field by allowing scientists, researchers, and developers from around the world to further refine the tool and explore its various potential applications.

“By granting universal access, the aim is to fast-track breakthroughs in colorectal cancer research,” said Fabi Prezja, who was responsible for the design of the method.

Related Links:
University of Jyväskylä