Technology based on artificial intelligence can quickly and simply decipher genetic and molecular information about cancerous tumors. On the horizon: personalized medicine for cancer patients
The field of artificial intelligence is gaining momentum in the world of medicine, and also in the treatment of cancer. At the core of artificial intelligence is deep learning – a field of study in computer science that aims to create a computerized imitation of the operation of the human brain. These are algorithms that allow computer systems to learn from previous examples and experiences – and thus perform a variety of computational tasks.
Prof. Ron Kimmel and Dr. Gil Shamai from the Faculty of Computer Science at the Technion are engaged in the geometric processing and learning of signals and images. This is how they train computers to decipher visual information on their own. The goals: Cohen, director of the Department of Otolaryngology and Head and Neck Surgery at Rambam Medical Center, and a senior clinical lecturer in the Faculty of Medicine at the Technion. Dr. Irit Duak (specializes in ENT), Dr. Yoav Binnenbaum (specializes in pediatric oncology) and Prof. Ziv Gil (former head of the ENT department at Rambam Medical Center). Together, scientists and doctors have developed a technology based on artificial intelligence, dubbed the “computer pathologist.” This technology is used to decipher samples (tissues) of genetically and molecularly cancerous tumors. The system examines the samples and finds out what genetic mutations they have (which help the tumors develop) and identifies additional trait markers (such as proteins). That is, through it one can find out what is the unique signature of each tumor, and thus assist in deciding on the most appropriate oncology treatment for the patient, which is based on that signature.
https://youtube.com/watch?v=vZL7LfX4U0A%3Ff
As part of the diagnosis of cancer, tissue is taken from the suspected lump that is sent for biopsy in a pathological laboratory. The tissue is examined by pathologists under a microscope and stained with hemotoxin-eosin (H&E) staining – a quick and inexpensive method designed to distinguish between cells. From looking at the dyed tissue, pathologists can understand if it is cancerous, what type of cancer it is, how aggressive it is and more. However, they can not so characterize the tumor genetically and molecularly – information that is essential for physicians to decide on the most appropriate type of treatment. Therefore, there are more advanced technologies, such as NGS (which decodes the DNA sequences in the tumor and locates the mutations in it). These are expensive technologies that require additional manpower skilled in their implementation, and they do not yet exist in all undeveloped countries.
Using the technology they have developed, scientists and doctors have been able to show for the first time that artificial intelligence is able to extract genetic and molecular information from an analysis of the tissue structure as it is reflected in H&E images. Says Prof. Kimmel, “The computer pathologist can characterize genetically and molecularly cancerous cells according to the shape of the tumor tissue and its environment. That is, based on its morphology analysis. “.
Using the technology they have developed, scientists and doctors have been able to show for the first time that artificial intelligence is capable of extracting genetic and molecular information from tissue tissue analysis.
The technology built by the researchers “trained” on 20,000 H&E images taken from about 5,000 breast cancer patients. In about half of them, it was able to determine that there is a molecular expression of the sex hormone receptors estrogen, which contribute to the division and spread of the cancer cells, based on an analysis of the shape of the tissue. These receptors are present in most breast cancer tumors and are targeted for specific treatment, one that blocks them or prevents them from getting the hormone they need.
“Based on many experiments and examples of images, the computer found certain features in the cancerous tissue – for example the shape of the cells and the way they got along – and learned what the connection was between the tumor’s molecular and genetic profile. That is, in a simple artificial intelligence “We believe that it will make it possible to improve the diagnosis of cancerous tumors and the suitability for oncological treatments, and save complex and expensive tests for genetic mutations and molecular markers,” notes Dr. Shamai. Prof. Kimmel adds that “this technology may shorten. “Significantly reduce and reduce the time of diagnosis, allow pathologists to focus on more complex work, and advance the customized treatment of cancer.”
Researchers are currently examining the technology for additional cancerous tumors, and hope to be able to predict the effectiveness of oncological treatments and the chances of survival with its help. “We believe it will be a clinical tool that will help physicians make the right therapeutic decisions,” concludes Prof. Kimmel.
Life itself:
Prof. Ron Kimmel – 57 years old, married and a father of four (“14 to 26 years old”) and lives in Haifa. He used to be a dancer and now likes to ride mountain bikes, ski and paint. Among other things, he paints on the iPad and also on walls (“with my daughter. She is the real artist”). Eature = oembed
Dr. Gil Shamai – 36 years old, lives in Tel Aviv, graduated from the Technion Program for Excellence. As a child he loved mathematics and geometry (“I participated in many competitions in these fields”). His doctorate, which he recently completed in Prof. Kimmel’s laboratory, Three-dimensional, computational geometry and artificial intelligence in the medical field.Besides he loves to ride a bike and surf (“Every weekend I ride or ski”), plays piano and drums, and loves Iraqi food.
Dr. Yaki Cohen – 56 years old, married and the father of two daughters, lives alternately in Haifa and Tel Aviv. Has been involved in applied research and collaborations with industry for many years. Artificial intelligence In his spare time he engages in boxing and martial arts.
For an article on the website of the National Science Foundation
More on the subject on the Yadan website: