Groundbreaking AI-based cancer treatment developed by Israeli researchers

The new technology allows AI to identify molecular features of cancer cells based on biopsy images.

By LEON SVERDLOV
September 11, 2019 17:55
2 minute read.
The original scan (left) and the areas where information was extracted (in red and green, right) usi

The original scan (left) and the areas where information was extracted (in red and green, right) using the technology developed at the Technion. (photo credit: TECHNION SPOKESPERSON'S OFFICE)

 Researchers at Technion-Israel Institute of Technology have developed a deep learning-based method for mapping critical receptors on cancer cells, which is expected to significantly improve personalized cancer treatment, the Office of the Technion Spokesperson reported on Wednesday.

According to the report, the new technology extracts molecular information from images of breast cancer biopsies that underwent hematoxylin and eosin (H&E) staining. The staining, made by a common dye used to test biopsy tissue, allows the pathologist to identify the type of cancer and its severity but does not allow the identification of biological characteristics that are crucial for personalized treatment.

The new technology allows for the identification of those crucial characteristics, enabling pathologists to match cancer patients with the treatment that will block the receptors on the cancer cell membrane, inhibiting the development of the tumor.

The research, published in the prestigious Journal of the American Medical Association, was created by doctoral students Gil Shamai and Ron Slossberg as well as Professor Ron Kimmel of the Technion Faculty of Computer Science, in collaboration with Dr. Yoav Binenbaum of Ichilov Hospital and Professor Ziv Gal of Rambam Medical Center, the office reported.

According to Shamai and Kimmel, pathologists have said that the researchers' conceptual innovation – extracting molecular information from the cell shape – was impossible. "A human pathologist cannot infer the tumor features from its shape because of the sheer number of variables," they said. "The good news is that artificial intelligence technologies, and especially deep learning, are capable of doing so."

"The computer, unlike even the most skilled pathologist, can characterize the cancer with a complex analysis of its morphology," the two said. "We succeeded in identifying the 'signature' that the cancer leaves in the tissue," Shamai explained, adding that "it's a morphological signature that, through our technology, we are able to glean essential information. It is important to note that deep learning systems require a huge amount information, and obtaining the kind of information required is not easy."

"To that end," Shamai added, "we have written software code to scan network sources and automatically download thousands of biopsy samples and the relevant medical information approved for research."

The research examined more than 20,000 scans from 5,356 breast cancer patients, and was supported by the Science and Technology Ministry, the National Science Foundation and the Lorry Lokey Interdisciplinary Center for Life Sciences and Engineering, as well as Schmidt Futures.

Using the new technology, the researchers were able to map the estrogen and progesterone receptors, among other molecular biomarkers, from the scans alone and based on cell morphology.

Although the study focused on breast cancer, the researchers make it clear that it is relevant to all cancers. "We have succeeded in showing that cancer has a unique signature in tissue morphology and that computerized mapping of this morphology can give us tremendously relevant information on tumor characteristics," Kimmel explained. "In the first phase, we believe it will be a tool to help doctors make decisions and will later be developed as a real clinical tool."



 


Related Content

A DOCTOR and a professor of rehabilitation help a man at a school of medicine
September 22, 2019
Israel launches pilot Hebrew terminology course for Arab medical students

By LEON SVERDLOV