The application, known as iStar, was created by Perelman School of Medicine researchers to give clinicians more insights into gene activities in medical images and, potentially, help them diagnose cancers that might have otherwise been undetected.
Researchers at Penn Medicine have developed a new artificial intelligence application that offers a new way to examine and interpret medical images and could help clinicians diagnose cancers that might not have been found before.
WHY IT MATTERS
Called iStar – it stands for Inferring Super-Resolution Tissue Architecture – the new tool was created at U Penn’s Perelman School of Medicine. Its computing power enables detailed views of individual cells in images, and thus could help oncologists and researchers see cancer cells that might have gone unnoticed otherwise.
As explained in a recent Nature paper, the AI tool can help determine whether safe margins were achieved after cancer surgeries, according to Penn Medicine, and can also provide automatic annotation for microscopic images – thus enabling new advancements in molecular disease diagnosis.
The iStar technology was developed from National Institutes of Health-funded research spearheaded by Mingyao Li, professor of biostatistics and digital pathology at the Perelman School, and Penn Medicine research associate David Zhang.
The application can automatically detect critical anti-tumor immune formations known as tertiary lymphoid structures. The presence of those formations correlates with a patient’s likely survival and favorable response to immunotherapy, said Li, indicating that iStar could be hugely helpful determining whether a given patient would benefit from specific immunotherapy interventions.
Penn Medicine notes that iStar’s research and development stems from the emerging field of spatial transcriptomics, in which gene activities are mapped within the space of tissues. By adapting machine learning tool called the Hierarchical Vision Transformer, Li and her colleagues trained it on standard tissue images.
Starting by segmenting images into different stages – starting by seeking fine details, then moving up and “grasping broader tissue patterns,” as Li explained – the iStar AI uses that data in context with other clinical information, applying it to predict gene activities, often at near-single-cell resolution.
Li and her colleagues tested the tool by evaluated iStar on different types of cancer tissue, alongside with healthy tissues. In those tests, the technology was able to “automatically detect tumor and cancer cells that were hard to identify just by eye,” according to Penn Medicine, which noted that “clinicians in the future may be able to pick up and diagnose more hard-to-see or hard-to-identify cancers with iStar acting as a layer of support.”
THE LARGER TREND
Artificial intelligence is enabling big advancement in more personalized and patient-focused care – just as innovative policies and more powerful computers are paving the way for further innovation in precision medicine and genomic programs and other AI-enabled oncology treatments.
ON THE RECORD
“The power of iStar stems from its advanced techniques, which mirror, in reverse, how a pathologist would study a tissue sample,” said Li in a 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.
Moreover, she noted, iStar can be applied to a sizable volume of samples – a key need for large-scale biomedical studies.
“Its speed is also important for its current extensions in 3D and biobank sample prediction,” said Li. “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.”
Mike Miliard is executive editor of Healthcare IT News
Email the writer: mike.miliard@himssmedia.com
Healthcare IT News is a HIMSS publication.