A professor from the Perelman School of Medicine has shed light on a new artificial intelligence device that holds promise for enhancing cancer treatments. The device, named iStar, utilizes advanced techniques to study tissue samples, potentially revolutionizing the field of oncology.
Mingyao Li, Ph.D., at Penn Medicine explains the working of iStar: "The power of iStar stems from its advanced techniques, which mirror, in reverse, how a pathologist would study a tissue sample." She further adds, "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."
Developed by researchers at the Perelman School of Medicine, iStar stands for Inferring Super-Resolution Tissue Architecture. This AI tool is capable of processing images at an unprecedented speed. In comparison with another similar AI tool, iStar processed a sample 213 times faster. What took only nine minutes for iStar to analyze required thirty-two hours for the other machine. Li emphasizes the importance of this speed: "Its speed is also important for its current extensions in 3D and biobank sample prediction. In the 3D context, a tissue block may involve hundreds to thousands of serially cut tissue slices. The speed of iStar makes it possible to reconstruct this huge amount of spatial data within a short period of time," according to a news release from Penn Medicine.
Li and her team put iStar through rigorous testing on various types of cancer tissues including prostate, kidney, and breast cancer along with healthy tissues. They found that iStar could accurately detect cancer cells that would otherwise be challenging to identify without such technology. Moreover, it efficiently located anti-tumor immune formations - crucial in determining whether a cancer patient will respond positively to immunotherapy. According to Penn Medicine's news release: "The tool’s precision and accuracy make it a promising option to improve cancer treatment."
The creation of iStar was part of a project in the field of special transcriptomics, which is centered on monitoring gene activities in tissues. Utilizing data from a tool known as the Hierarchical Vision Transformer, iStar predicts gene activity. Li explains: "The implication is that iStar can be applied to a large number of samples, which is critical in large-scale biomedical studies." The team aims to continue their research using this new AI device to explore storage solutions for samples and apply the technology to other areas of medicine, according to a news release from Penn Medicine.
