Researchers at Ruhr University Bochum have developed new infrared imaging technology which can improve colon cancer diagnostics.
Artificial Intelligence (AI)-based technology can help tailor colon cancer therapy to individual patients. Significant progress has been made in therapy options for cancer over recent years and patient prognosis for colon cancer has vastly improved. However, approaches, such as immunotherapies, require precise cancer diagnostics so that they can be specifically tailored to individual patients.
Using so-called label-free infrared (IR) imaging, the researchers have been able to measure the genomic and proteomic composition of potentially cancerous tissue. This provides molecular information on the infrared spectra. This information can be decoded using AI and displayed as false-colour images. The researchers used image analysis methods from the field of deep learning to do this.
The full study, titled ‘Fast and label-free automated detection of microsatellite status in early colon cancer using artificial intelligence integrated infrared imaging‘ has been published in The European Journal of Cancer.
IR imaging works faster than traditional cancer diagnostics
The team worked with clinical partners to show that deep neural networks can reliably determine the microsatellite status of colon cancer. The microsatellite status of cancer is a useful parameter for prognoses and determining therapeutic approaches.
During IR imaging, the tissue sample goes through a standardised, user-independent, automated process. Within an hour, medical professionals can determine a spatially resolved differential classification of the tumour. In classical cancer diagnostics, microsatellite status is determined by complex immunostaining of various proteins or via DNA analysis.
“15%-20% of colon cancer patients show microsatellite instability in the tumour tissue. This instability is a positive biomarker indicating that immunotherapy will be effective,” said Professor Andrea Tannapfel, head of the Institute of Pathology at Ruhr University.
As therapy options have improved, the need for fast and uncomplicated cancer diagnostics has become more important.
AI enables more accurate diagnoses
During the study, the researchers used IR microscopic data to modify neuronal networks and establish optimised label-free cancer diagnostics. This approach does not require dyes like immunostaining and is significantly faster than DNA analysis.
“We were able to show that the accuracy of IR imaging for determining microsatellite status comes close to the most common method used in the clinic, immunostaining,” said PhD student Stephanie Schörner.
“Through constant further development and optimisation of the method, we expect a further increase in accuracy,” added Dr Frederik Großerüschkamp.
The research team used the ColoPredict Plus 2.0 molecular registry, a non-interventional, multi-centre registry study for patients with early-stage colorectal cancer, to develop this approach to cancer diagnostics.
“The ColoPredict registry also enables a more targeted therapy for patients through the targeted analysis of biomarkers. Thus, the registry recently serves as a study platform for precision oncology approaches,” said Reinacher-Schick.
As well as providing tissue samples, the registry offered a database of prognostically and therapeutically relevant baseline characteristics.
“In such a project, it was of immense importance to be able to draw on an excellent cohort and pathological expertise,” explained Gerwert.
“Our work on the classification of microsatellite status in colon cancer patients was based on one of the largest cohorts we have published to date and clearly demonstrates the potential for use in translational cancer research,” concluded Tannapfel.
