Diagnosing cancer through biopsies in minutes, not weeks

When Dean Bitan’s mother was diagnosed with stage 4 breast cancer, the Israeli entrepreneur felt paralyzed.

“But then my best friend told me, ‘Put your feelings aside and act like this is another project of yours,'” Petain told ISRAEL21c.

“Standing on the front lines with my mother, I learned a lot about the loopholes in regards to treatment. I knew we could and should do better. So this is what I decided to do.”

Petain’s mother, unfortunately, passed away two years ago. But the result of Petain’s persistence would make any Jewish mother proud.

to imagineThe 2020 startup Bitan, along with Jonathan Zallach and Shahar Porat, developed a technology that can perform a complete molecular analysis on a digital biopsy image in real time and return the result within minutes, rather than the current situation for a few weeks.

How do you imagine doing that? Artificial intelligence of course.

Imagene’s AI aims to “democratize” personalized medicine, Petain explains, by allowing oncologists to obtain an accurate diagnosis and then initiate a precisely targeted treatment plan much sooner than ever before.

Oracle founder Larry Ellison led a $21.5 million Series A investment in the company earlier this year.

Ellison’s involvement is not out of character – he and Dr. David Agus founded the Institute for Transformational Medicine in 2016 with the goal of leading patient-centered, multidisciplinary research. Agus is so impressed with Imagene’s technology that he is a member of the company’s board of directors.

Pathologists help

Imagene’s AI looks for biomarkers in the form of a digital biopsy to help pathologists classify a tumor as precancerous or not, and if so, what type.

It’s a big step forward from placing a tissue slice under a microscope and examining it manually.

Imagene can be integrated into your existing pathologist workflow. “We are neutral in their situations,” says Petain. “We don’t want to add any effort to these doctors.”

The workflow with Imagene inside looks like this:

Image courtesy of Imagene

Imagene’s report summarizes the findings and indicates actionable biomarkers, “including those that match targeted therapies and relevant clinical trials,” says Betain.

Imagene has developed models that can check 28 biomarkers in eight organs including the lungs, thyroid, breast and ovaries, with more on the way. “On average, our privacy and sensitivity are more than 95%,” Petain notes.

“Today, only about 15% of patients will be diagnosed with a biomarker that can lead to precision medical treatment. The goal is to push the boundaries of precision medicine, to make it more accessible and available,” Petain told ISRAEL21c.

“Even in the United States, there is a huge gap between the quality of diagnosis in the academic center and the community setting,” Betan says. “By identifying actionable biomarkers, between 40 and 50 percent of lung cancer patients should be able to be diagnosed.”

Agus calls Imagene’s approach “Theragnostics” – a combination of diagnosis and treatment.

from all angles

The first step in Imagene analysis is to determine what you are looking for.

“If you show me a glass, that’s what the glass looks like,” Petain explains. “But what if I flip it? Now I’m changing the look. AI changed the whole approach by teaching the computer by example.”

Accordingly, Imagene is training its AI to recognize the mutation in the digital biopsy image by showing several images of the biopsy tissue at different angles.

Imagene also addresses another challenge in diagnosing cancer: It can be difficult to collect enough tissue for a conventional microscopic biopsy. This is the case with 20% of lung biopsies, Petain says. Even worse, many lung cancer patients do not live long enough to benefit from genetic screening, which takes between 14 and 28 days.

These challenges make it difficult for drug companies to identify patients and include them in precision medicine tests. This is especially true for patients with rare cases, where 26% of trials are terminated due to low accrual rates.

“We can help these companies with a super cost-effective solution that can see dozens of patients per day without wasting tissue,” says Petain.

within 5 years

Petain stresses that Imagine does not yet have regulatory clearances. In anticipation of entering the US market, Imagene has set up a small office in the Philadelphia area.

Betaine hopes that within five years, patients will be able to have a “comprehensive diagnosis at the point of care and then immediately discuss personalized treatment options or clinical trials. Just imagine what patients deal with when they have to wait for results a month later — that is if precision medicine is and NGS [next generation screening] They are served even in their area.”

Imagene founders, left, CDS Jonathan Zalach, CEO Dean Bitan and CTO Shahar Porat, with CSO Dr. Nurit Paz-Yaacov. Kafr Ziv’s photo

The Tel Aviv-based company, with 25 full-time workers, has collaborated with Sheba Medical Center and Tel Aviv Sourasky Medical Center in Israel and with several medical facilities and pharmaceutical companies outside of Israel whose identities remain confidential.

Imagene and Sheba recently published research on modern pathology Describes the accuracy of artificial intelligence models In the detection of cancer biomarkers in non-small cell lung cancer.

“Imagene’s deep learning algorithms are radically simplifying cancer diagnosis and targeted therapy, and we are committed to continuing and expanding this collaboration to include more cancer types and biomarkers,” said Professor Iris Barshak, Head of the Institute of Pathology in Chiba.

biological affinity

Petain, a computer scientist by training, earned his college degree at the age of 15 and was a computer programmer during his military service. He points out that rapid cancer diagnosis is more about engineering than biology.

“When you need a lot of data to process and answer the question of whether or not this is cancer, that’s an engineering problem,” he says.

“It’s about the way you collect data and generate different insights from it. Of course, you also need biologists and clinicians in the picture, but at the end of the day, you need engineering and data science.”

It turns out that Israel has a real advantage in this kind of biological affinity. It is a small country where everyone knows everyone and where there is regular collaboration between universities and startups.

“Add some Israeli insolence — in a positive sense — and that leads many entrepreneurs to believe that they can do things differently,” says Petain.

He tries not to lose sight of the end user.

“Behind all the conferences, publications and numbers are real patients, and it’s very easy to forget that when you look at the millions of slides. When we hire new employees, the most important thing is that they have a strong desire to do good, to make a better future. That’s why we created Imagene.”

“When I was once asked if I would have a chance to sit down with anyone, who it would be, I said, ‘With the first patient where Imagene saved his or her life. “That’s why we do what we do.”

For more information about Imagene, click here.