Chaim Linhart, PhD is the CTO and Co-Founding father of Ibex Medical Analytics. He has greater than 25 years of experience in algorithm development, AI and machine learning from academia in addition to serving in an elite unit within the Israeli military and at several tech firms. Chaim has a PhD in Computer Science from Tel Aviv University and has won multiple Kaggle machine learning competitions.
Since 2016, Ibex has led the way in which in AI-powered diagnostics for pathology. The corporate set out to remodel pathology by ensuring that each patient can receive an accurate, timely, and personalized cancer diagnosis. Today, Ibex is probably the most widely deployed artificial intelligence platform in pathology. Developed by pathologists for pathologists, their solutions serve the world’s leading physicians, healthcare organizations, and diagnostic providers. Day by day, Ibex has the privilege of impacting the lives of patients worldwide. The platform raises physician confidence, streamlines diagnostic workflows, helps clinicians provide more personalized diagnoses, and, most significantly, enables higher clinical outcomes.
Are you able to share the journey and vision behind Ibex’s founding and its mission to remodel cancer diagnostics with AI?
In 2016, my co-founder, Joseph Mossel, and I learned concerning the direct impact a digital revolution in pathology could have on improving cancer diagnostics. Radiology had undergone the same transformation 20 years earlier, which had a distinguished impact on how the specialty was practiced. With pathology becoming digitized, we recognized it provided a possibility to develop recent advanced tools that utilize artificial intelligence (AI) to perform sophisticated image evaluation. We now have focused on developing AI-powered tools that help physicians in reaching more accurate, objective, reproducible diagnoses, and thereby helping each patient receive the fitting diagnosis, in a timely way, which ends up in one of the best possible treatment.
How has the landscape of cancer diagnostics modified since Ibex’s inception in 2016?
Labs have been adopting digitization at an increasing rate, even further accelerated by Covid-19. The digital revolution has enabled the labs to broaden their capabilities beyond the microscope in an impactful and meaningful way, leveraging AI that helps pathologists analyze and understand results efficiently.
The cancer diagnostics AI field has grown exponentially, as we’ve been seeing startups and other firms working on various points of AI for pathology within the cancer diagnosis realm. Precision medicine, for instance, is data-driven patient stratification enabled by an accurate diagnosis and various informatics approaches that result in optimal, personalized treatment. A rise in precision medicine comes with an enhanced need for more complex diagnostics to support the brand new targeted treatments.
We’ve also seen a rise in academic publications and industry associations specializing in the sphere. When Joseph and I attended our first conference on digital and computational pathology in 2016, AI was a small sliver of the conversation surrounding cancer diagnosis, because it wasn’t as mainstream. Now, when attending a big pathology conference, AI is the foremost event.
What differentiates Ibex from other firms in the sphere of AI-powered pathology?
Once we speak about AI-powered pathology, there are several subdomains. There are firms that prioritize research applications, like tools that analyze tissue images to assist understand disease processes on the morphological and cellular level, for instance. Secondly, there are firms that focus mainly on clinical applications, i.e., products which are utilized in labs to support routine diagnosis.
Ibex is targeted on clinical applications, and we have now the biggest and most widespread installation base with pathologists world wide using our tools every day for cancer diagnosis. We’re also partnering with Pharma to develop AI-powered clinical applications that support pathologists in quantifying biomarkers that enable targeted therapies.
Moreover, while some firms give attention to specific, limited indications per tumor type, like cancer detection, our approach is to coach the AI to research every part a pathologist would see in these tissues. It’s not only about cancer detection, but in addition the kind and subtype of cancer, the grade, its size, in addition to cancer-related morphologies and other clinical features. We all know pathology is greater than just determining if the patient has cancer or not. We would like to assist pathologists realize the vast advantages that AI brings to the table.
Are you able to explain the core technology behind Ibex’s solutions and the way it assists pathologists in cancer detection and grading?
Our approach is that pathologists essentially train the machine. We now have a big team of pathologists world wide annotating slides. This implies, they mark specific areas inside those slides and label them. They could mark a low-grade tumor, a blood vessel, a nerve, inflammation, and so forth. We then take that data and use it to coach the AI models. This ensures that the AI may be very accurate, even for rare and difficult cases, which is vitally essential. Our AI is taught by pathologists and is trained to discover many differing kinds of structures and morphologies of the tissue, which may be very helpful to pathologists and inevitably increases its accuracy. By accessing a breadth of information and knowledge, we’re in a position to improve our AI and implement learnings with the feedback obtained directly in the sphere.
How does Ibex ensure clinical-grade accuracy across different cancer types comparable to breast, prostate, and gastric cancers?
This takes a variety of exertions. We collect data from many partners world wide. We ensure the info may be very diverse, with representation from different labs and various tissue preparation techniques, scanners, and clinical findings. We enrich the training data with rare kinds of cancer. This ensures the AI is trained with a wide selection of features. In the course of the training process, we measure what the AI does well, and we also determine where improvements have to be made. The team, with vast experience in machine learning, tests the AI on 1000’s of slides that we collected from different labs. We run studies and clinical trials and compare two fundamental points of the system. First, we review its standalone performance in comparison with the bottom truth. Second, we determine how accurately the pathologist works with and without AI. In doing so, we make sure the AI is accurate, robust, unbiased, and secure. We measure its impact on the pathologists using the AI. Across our applications, we see that the pathologist, with the help of AI, reaches higher results (meaning more accurate, higher agreement with the bottom truth) than in standard of care (i.e., once they should not supported by the AI). We also measure the efficiency of their work and other essential advantages of the AI platform, comparable to optimizing the workflow within the lab and decreasing the turnaround time (how quickly the patient receives the outcomes).
What are some unique features of Ibex’s solutions that enhance diagnostic workflows and improve patient outcomes?
Our integrated system features a slide viewer, the AI results, and built-in reporting tools. This holistic system was designed to boost accuracy and productivity. It walks pathologists through the diagnostic process, showing them the foremost findings in every case and slide. As a substitute of trying to find features, which might be small and hard to detect, the AI highlights every part very clearly. From there, the pathologist can confirm or modify. The AI shows measurements and quantifications; it also scores every part. With built-in reports, the pathologist doesn’t have to take a look at the slide, make the diagnosis of their mind, after which go to a different system and report every part; as an alternative, reporting is finished while the AI is driving the integrated workflow. Even the variety of mouse clicks was optimized. All the things was built with pathologists in mind to boost diagnostic accuracy and efficiency, thereby making a higher work environment for these physicians with higher outcomes for his or her patients.
How does Ibex’s solutions integrate with existing digital pathology software solutions and laboratory information systems?
We work with several vendors in the sphere that sell image management solutions or offer lab information systems. For every partner, there are several types of integration opportunities. In some cases, we embed our AI into their tools so the pathologist can use their platform with our AI inside it. In other cases, we integrate with these tools in a way that permits pathologists to launch Ibex from the opposite system. No matter the mixing, we at all times wish to make certain the users have probably the most optimal way of using the AI. Moreover, we have now developed an open application programming interface (API) that permits third parties, including other firms or customers’ IT departments, to retrieve information from our AI and integrate it into their environment.
What challenges did Ibex face in achieving widespread adoption of its AI-powered solutions in pathology?
Upon reflection, I’d say the foremost challenge Ibex faced was across the sheer complexity and the quantity of labor, effort, and time required to bring diagnostics products to market. This includes multidisciplinary approaches: collecting data, working with pathologists, training the AI and testing it rigorously, running clinical trials, and, in some geographies, gaining regulatory clearance – and doing all of this under strict quality assurance measures. Within the medical field, additionally it is extremely essential to generate scientific evidence and publish results with multiple labs to exhibit the performance and advantages of the AI platform.
One other notable challenge is integration. We’d like to make certain that pathologists can use the AI in a way that’s efficient and natural. There are multiple systems within the lab: digital pathology scanners, the lab information system and workflow, and reporting tools. Put simply, we make certain every part comes together in probably the most efficient way possible, despite the challenges.
Are you able to share some success stories or case studies from healthcare organizations which have implemented Ibex’s solutions?
We’re very happy with our partnerships and global reach. For instance, we have now the primary nationwide deployment of AI in Wales – all the Health Boards in Wales are using Ibex’s AI solution. One other example is CorePlus Laboratories in Puerto Rico – they have been using Ibex for several years and published a paper, which shows the impact the platform has had on their clinical practice. For instance, using the AI algorithm, the pathologists were in a position to discover 160 men that otherwise would have been misdiagnosed. Those patients got the fitting treatment due to the AI’s support. That’s really the impact that we’re making. It’s something we are able to’t forget – we’re here to affect people’s lives.
What role do you see AI playing in the longer term of pathology and cancer diagnostics over the subsequent decade?
Throughout the subsequent decade, we’ll proceed to see pathologists use AI to support them of their primary diagnostic efforts. I envision pathologists will use AI on most of their workloads to make certain that the standard is high, and every part is objective, reproducible, and timely. Moreover, AI will help physicians do things they don’t currently do. It could help them determine which additional tests have to be performed on a selected case, in addition to provide a more accurate prognosis and streamlined treatment selection.
AI will probably be integral throughout all the patient journey, not only the cancer diagnostic part within the pathology lab, but in addition, for instance, the oncologist who decides on the course of treatment. Also, I believe AI will help mix disciplines. With time, the various modalities (pathology, radiology, genomics, clinical records) will probably be fed to numerous AI modules to support recent and improved precision medicine. From a health equity perspective, patients that don’t have access to one of the best doctors on this planet will experience an enormous leap in the standard of their diagnosis and their treatment. AI will bring everyone to the extent of near expert. Everyone deserves access to quality care, and AI will help bring us in the fitting direction to democratized health access.
