AI Tissue Imaging Helps Guide Targeted Therapy for Lung Cancer

Lung cancer is the leading cause of cancer-related death, and many patients require rapid genotyping to guide targeted therapy selection. Current workflows often rely on molecular tests that are costly, time-consuming, and can exhaust limited biopsy material. These delays can slow treatment decisions and strain diagnostic services as screening expands. To help address this challenge, researchers have developed an imaging and artificial intelligence approach that predicts actionable gene mutations directly from routine tissue samples.

The technology, fluorescence lifetime imaging microscopy (FLIM), was developed by the University of Edinburgh with NHS Lothian. FLIM captures the natural light signals emitted by untreated tissue. Those signals are then analyzed by AI to detect patterns associated with specific genetic alterations without staining or sequencing.

In the study, the method accurately predicted epidermal growth factor receptor (EGFR) mutations and distinguished between the two most common EGFR variants that guide therapy choice. Investigators report high accuracy while preserving biopsy material, because the scan leaves the specimen intact for downstream analyses. The findings were published in Cancer Research on July 13, 2026.

The work comes as expanded screening programs detect suspected cancers earlier, increasing pressure on diagnostic pathways to deliver fast and reliable results from small samples. The approach builds on earlier results from the same team showing that FLIM can differentiate major types of non-small cell lung cancer from non-cancerous tissue. The group is now pursuing clinical validation, exploring additional targetable mutations and other tumor types, and planning integration into routine workflows.

“This is a significant step towards a future where a single, non-destructive fluorescence scan of a biopsy could quickly inform clinicians whether a patient has cancer, what type of cancer they have and now, with this work, if it is likely to respond to targeted treatment, helping to ensure the right treatment reaches the right patient more quickly,” said Professor Ahsan Akram, co-lead of the study from the Institute for Regeneration and Repair.

“Clinicians are increasingly seeing more patients with earlier-stage disease and dealing with a growing number of biopsy samples, placing significant pressure on diagnostic services. Technologies like this, which can deliver more information from smaller tissue samples at speed, will be essential for developing clinically effective diagnostic pathways,” stated Dr. David Dorward, Consultant Thoracic Pathologist at NHS Lothian.

Related Links
Institute for Regeneration and Repair, University of Edinburgh
NHS Lothian