AI-based Chromatin Biomarkers enable early detection of cancer

by

Researchers at the Paul Scherrer Institute (PSI) have made a breakthrough in the early detection of cancer using artificial intelligence (AI)-based chromatin biomarkers. Led by G.V. Shivashankar, head of PSI’s Laboratory for Nanoscale Biology, the research team found that changes in the organization of the cell nucleus in certain blood cells can indicate the presence of a tumor in the body.

Using AI, the scientists were able to distinguish between healthy and sick individuals with an accuracy of approximately 85%. Furthermore, they successfully determined the type of tumor disease, including melanoma, glioma, and head and neck tumors. This achievement is a first in the field of oncology, according to Shivashankar. The results of the study were published in the journal npj Precision Oncology.

The conventional methods for detecting and monitoring cancer are often time-consuming and are typically carried out in the later stages when symptoms become apparent. Therefore, researchers are searching for techniques that are both reliable and sensitive, as well as easy to use in clinical practice. Shivashankar’s team focused on lymphocytes and monocytes, also known as mononuclear cells of peripheral blood, as these are easily obtained through a simple blood sample and have a round nucleus that can be easily observed under a microscope.

The researchers hypothesized that these blood cells act as tumor detectors, reacting to substances released by the tumor into the bloodstream, known as the secretome. This activation affects the chromatin in the nuclei of the blood cells, altering the organization of the genetic material and serving as a biomarker or indicator of tumor presence.

Using fluorescence microscopy, the researchers examined the chromatin of the blood cells, recording various characteristics such as texture, density, and contrast. These microscope images were then fed into an AI system for analysis. The supervised learning approach taught the AI system the known differences between healthy and sick cells, while the subsequent deep learning approach allowed the algorithm to identify differences that may not be discernible to the human eye.

The research group conducted three different approaches to validate their technique. Firstly, they compared the blood cells of ten cancer patients with those of ten healthy individuals. The AI system was able to accurately distinguish between healthy and cancer patients with 85% accuracy. Secondly, the researchers tested whether the AI system could differentiate between different types of tumors. By feeding the algorithm with chromatin data from patients with gliomas, meningiomas, and head and neck tumors, they achieved an accuracy of over 85%.

Finally, the research group collaborated with the Centre for Proton Therapy (CPT) at PSI to determine the success of radiation therapy. Blood samples were taken before, during, and after the treatment, and the AI system correctly identified the patterns with a high level of accuracy. As expected, the genetic material of the blood cells normalized, indicating a reduction in tumor signals due to the radiation therapy.

The researchers believe that their technique using blood cell chromatin biomarkers is applicable to various types of cancer and may be employed in different forms of therapy, including radiation therapy, chemotherapy, and surgery. However, further research is needed before the technique can be approved for clinical practice, including larger studies to determine false positive and false negative rates in real-world conditions. Despite the challenges, Shivashankar is confident that the method will ultimately benefit patients, with the potential to improve diagnosis and the monitoring of treatment success.

Ravina
+ posts

Ravina Pandya,  Content Writer, has a strong foothold in the market research industry. She specializes in writing well-researched articles from different industries, including food and beverages, information and technology, healthcare, chemical and materials, etc. With an MBA in E-commerce, she has an expertise in SEO-optimized content that resonates with industry professionals.