It's well-known that detecting cancers at earlier stages can significantly improve outcomes and save lives. Hence, there has been a constant focus on using technology to improve screening. Now, a team of researchers have developed an artificial intelligence (AI) tool that can quickly analyse medical images to provide information about diseases in tissues and tissue microenvironments.
The new AI tool, iStar (Inferring Super-Resolution Tissue Architecture), was developed by researchers at the Perelman School of Medicine at the University of Pennsylvania to help clinicians diagnose and better treat cancers that might otherwise go undetected.
The tool’s imaging technique provides highly detailed views of individual cells and a look at the full spectrum of how people’s genes work. This can help doctors and researchers focus on cancer cells that might otherwise have been virtually invisible, the university’s press statement explains.
The tool can be used to determine whether safe margins were achieved through cancer surgeries and automatically provide annotation for microscopic images, which can enable molecular disease diagnosis at that level. The findings were published in the journal Nature Biotechnology.
The researchers also said that iStar can automatically identify critical anti-tumour immune formations called tertiary lymphoid structures, whose presence correlates with a patient’s likely survival and favourable response to immunotherapy, which requires high precision in patient selection, the statement elaborates. This indicates that iStar could have the ability to determine which patients would benefit most from immunotherapy.
“The power of iStar stems from its advanced techniques, which mirror, in reverse, how a pathologist would study a tissue sample,” study author Mingyao Li explained in the statement. “Just as a pathologist identifies broader regions and then zooms in on detailed cellular structures, iStar can capture the overarching tissue structures and also focus on the minutiae in a tissue image,” Li added.
The researchers tested iStar’s efficacy on several types of cancer tissue, including breast, prostate, kidney, and colorectal cancers, mixed with healthy tissues. The tool could automatically detect tumour and cancer cells that were difficult to identify just by eye. According to the statement, the speed of iStar makes it possible to reconstruct a huge amount of spatial data within a short period.
With the rapid integration of AI in different fields, researchers have been using it to improve the diagnosis and treatment of different diseases. For instance, in October 2023, Harvard Medical School researchers developed a new tool that could make predictions about new viruses before they emerge. In the study, published in Nature, researchers show that if the tool, EVEscape, had been used during the covid-19 pandemic, it could have predicted the most detected variants the world should focus on.
