Google+ Facebook Twitter Twitter

Precision pathology for cancer with new ai tool

A new AI tool interprets medical images with unprecedented clarity, according to the results of a new study.

A molecular biologist working with a microscope in a modern scientific Laboratory, we see a computer screen in the foreground- CREDIT - istock-1390303303

The tool, called iStar (Inferring Super-Resolution Tissue Architecture), was developed by researchers at the University of Pennsylvania.

They believe that it can help diagnose and better treat cancers that might otherwise go undetected.

The imaging technique provides highly detailed views of individual cells and a broader look at the full spectrum of how people’s genes operate to identify cancer cells that might otherwise have gone undetected.

This tool can be used to determine whether safe margins were achieved through cancer surgeries and automatically provide annotation for microscopic images, paving the way for molecular disease diagnosis at that level.

The team said the iStar has the ability to automatically detect critical anti-tumour immune formations called “tertiary lymphoid structures,” whose presence correlates with a patient’s likely survival and favourable response to immunotherapy.

They claim that iStar could be a powerful tool for determining which patients would benefit most from immunotherapy.

iStar was developed using spatial transcriptomics – a relatively new field used to map gene activities within the space of tissues.

To test the efficacy of the tool, iStar was evaluated on cancer tissue types, including breast, prostate, kidney, and colorectal cancers, mixed with healthy tissues.

Within these tests, iStar was able to automatically detect tumour and cancer cells that were hard to identify just by eye.

Image credit | iStock

Related Articles

Tech news: January 2024

This month's top tech news stories

My lab: digital pathology service

Rachael Nicholson gives a guided tour of the Medica MedPath Digital Pathology Hub in Runcorn.

AI grading the severity of a rare cancer

Professor Christina Messiou talks us through her study that shows AI is nearly twice as good at grading the aggressiveness of a rare form of cancer from scans as the current method.

Transforming histopathology

Following a complete overhaul, one lab is on track to hit the 98% target for 10-day turnaround times by 2025. Quality, Training and Transformation Manager Paul Chenery talks through the ambitious journey.