A research team from the Prodi Centre for Protein Diagnostics at the Ruhr-Universität Bochum (RUB) has used infrared (IR) microscopes based on quantum cascade lasers (QCLs) to classify tissue samples of colo-rectal cancer from everyday clinical practice in a marker-free and automated way. With the help of artificial intelligence, it was possible to differentiate between different tumor types with great accuracy within about 30 minutes. The classification is the basis for a prognosis of the course of the disease and the choice of a therapy. The team reported in the journal Scientific Reports of 23 June 2020.
In colon and other cancers, a distinction is made between microsatellite stable (MSS) and microsatellite unstable (MSU) tumors. Microsatellites are usually functionless, short DNA sequences that are frequently repeated. Patients with MSU tumors have a significantly higher survival rate. This is due to a mutation rate of cancer cells that is about 1,000 times higher, which makes their growth less successful. Furthermore, innovative immunotherapy is more successful in patients with MSU tumors. "It is therefore important for the prognosis and the decision for a therapy to know what kind of tumor it is", says Prof. Dr. Anke Reinacher-Schick, Head of the Department of Hematology and Oncology at the RUB Saint Josef University Hospital. Until now, differential diagnosis has been carried out by immunohistochemical staining of tissue samples with subsequent complex genetic analysis.
The potential of IR imaging as a diagnostic tool for the classification of tissue, label-free digital pathology, had already been demonstrated in earlier studies by the group led by Prof. Dr. Klaus Gerwert from the RUB Chair of Biophysics. The method recognizes cancer tissue without prior staining or other labeling and therefore also functions automatically with the help of artificial intelligence. In contrast to the conventional differential diagnosis of microsatellite status, which takes about one day, the new method requires only about half an hour.
The decisive improvement of the method is that the protein research team has extended it to the detection of a molecular change in the tissue. Previously, only morphological visualizations of the tissue were possible. "This is a big step that shows that IR imaging can become a promising method in future diagnostics and therapy prediction," said Dr. Gerwert.
In cooperation with the Institute of Pathology at the RUB under the direction of Prof. Dr. Andrea Tannapfel and the Department of Hematology and Oncology at the RUB St. Josef Hospital, the research team carried out a feasibility study with 100 patients. It showed a sensitivity of 100 percent and a specificity of 93 percent: All MSU tumors were correctly classified with the new method, only a few were falsely identified as MSU tumors. An expanded clinical trial is now starting, which will be carried out on samples from the Colopredict Plus 2.0 registry study. The registry study was initiated by Andrea Tannapfel and Anke Reinacher-Schick and allows the validation of results of the published work. "The methodology is also interesting because very little sample material is used, which can be a decisive advantage in today's diagnostics with more and more applicable techniques," says Andrea Tannapfel.
In the future, the method is to be introduced into the clinical workflow to find out how great its potential for precision oncology is. "Rapid and precise diagnostics is of great importance due to the increasingly targeted therapy of oncological diseases," explains Anke Reinacher-Schick.
Source:
Angela Kallenbach-Thieltges, Frederik Großerueschkamp, Hendrik Jütte, Claus Kuepper, Anke Reinacher-Schick, Andrea Tannapfel, Klaus Gerwert: Label-free, automated classification of microsatellite status in colorectal cancer by infrared imaging, in: Scientific Reports, 2020, DOI: 10.1038/s41598-020-67052-z