The BrainScan system has a chance to revolutionize the work of radiologists not only in Poland but also in the world. By analyzing the records of several hundred thousand unique tests, it helps to detect over a dozen pathological changes in the brain. We asked the creators – Szymon Korzekwa (CEO BrainScan) and Marek Trojanowicz (Co-Founder BrainScan) about the operation and effectiveness of the tool, as well as about plans for the future.
1. Where did the idea to deal with computed tomography come from?
Szymon Korzekwa, CEO of BrainScan: One of the founders of the company – Marek Trojanowicz, graduating 28 years ago at the Gdańsk University of Technology, dealt with the theory of artificial intelligence. Even then, he dreamed about the times that have come now – when the theory developed three decades ago will meet the computing power that allows its verification – verification of the theory in practice. Five years ago, on our way, we met Adam Brzeski, then one of the best graduates of the Gdańsk University of Technology, who was starting his doctorate. It was he who came to us with the idea of using machine learning methods to recognize images from imaging diagnostics of the gastrointestinal tract – exactly from images recorded using capsule endoscopy.
This is how it all started. We invested our own money, built a team of six Artificial Intelligence engineers, and obtained image data – this is how our five-year-long adventure began. The project related to capsule endoscopy showed how far is the path between the idea and the implementation of production software, between the results of tests carried out in our offices and the results coming from the solution implemented at the client’s.
2. If they could explain in a few sentences what BrainScan is and how it can help both patients and doctors and medical institutions.
SK: BrainScan is a commercial company, its foundation – like any other company – is generating profits. Obviously, setting up a company in which the source of income largely depends on research and development is a doubly difficult task to achieve it. Why? Because before the stage – as it is nicely called – commercialization, you need to provide resources, time, and the team to prepare a startup solution, a product in its first commercial version.
In the case of BrainScan, it took over three years to get to this product. We started with the analysis of images from capsule endoscopy, and today’s company and its successfully implemented product deals with the analysis of imaging examinations from computed tomography of the brain. We recognize over a dozen pathological changes using machine learning methods – creating a tool that significantly supports the work of a radiologist.
Referring to your question, if we provide radiologists, tele-radiology companies, hospitals – a tool that makes their work more effective, we help patients in a natural way. In the first two cases, if the doctor can describe more tests at the same time, and with greater certainty that no lesions will be missed, the patient gains. In the second case, if the hospital receives a tool from us that allows for an effective trio of patients awaiting surgery – we are talking directly about helping to save human lives. Such immediate, accurate medical segregation of patients in the emergency department in the event of a stroke is crucial for the patient’s life and further therapy.
3. It is no secret that imaging tests in Poland, especially at the National Health Fund, often have to be waited for a long time. Is there a chance that BrainScan will really change it?
SK: As I mentioned before – there are two areas where our solution helps to improve patient diagnostics. While in the aforementioned implementation of our solution in hospitals, we facilitate trioscopy, in teleradiology companies we increase the effectiveness of the work of the radiologist who describes the imaging examination. With the use of our software, he can describe more tests, which directly reduces the time from the moment the test is performed to the receipt of the description by the patient. Briefly answering – yes, we shorten this time, what’s more, the system is able to detect very small changes that are easy to overlook by a human, especially in the sixth – seventh hour of his work. The system, detecting all pathologies, will give the radiologist a second opinion with a list of detected changes, which gives greater certainty and precision.
The BrainScan system should be treated as the next generation tool provided to the doctor. After all, some of us still remember how the X-ray machine was the basis of imaging diagnostics, and the picture taken on the film attached to the negatoscope was viewed by a radiologist. Then came the era of computed tomographs and magnetic resonances. Digitally saved images gave room for software development, which enables image processing to extract as much diagnostic information as possible from the examination. It offers the doctor many options to change display parameters, image reconstruction, filtering and many more – that was the second step. Now it’s time for the next step, introducing further improvements that are possible thanks to knowledge and technology, and which always help the patient at the end.
4. When will the average patient in Poland be able to benefit from your solution? Is there a chance that its use in our country will become widespread in the next five years?
SK: Some of our patients can use our solution for a year. We work on a commercial basis with several companies, such as PZU Zdrowie. At the same time, we are conducting further talks with other clients in Poland. These are private entities – commercial networks of medical facilities offering diagnostic imaging. But we are also talking to many state actors.
Of course, I am not able to say to you whether in five years everyone in Poland will benefit from our solution – although it is a very nice prospect for me, I would very much like that to happen. However, I am convinced that systems such as BrainScan will become tools commonly used in diagnostic imaging in the next few years. Just like more than ten years ago, the fluorescent lamp illuminating the X-ray examination was replaced by the monitor and more and more perfect software allowing the manipulation of imaging examinations, obtained with more and more modern methods of imaging diagnostics, such as CT, MRI, PET-CT, PET-MR, etc.
5. BrainScan, using machine learning solutions, is constantly being developed. How effective is the tool now? How has this changed over time?
Marek Trojanowicz, Co-Founder BrainScan: The collection of imaging examinations from brain computed tomography collected by the company includes several hundred thousand unique examinations. Currently, as we mentioned earlier, we recognize several pathological changes, but approximately every six months we update both the number of recognized lesions and the effectiveness of their detection and, importantly, of identifying the areas of the brain in which they occur. This number of examinations is a huge amount of information to be processed, it must be remembered that each CT scan consists of successive sections, and the number of unique images that we process is the product of the number of examinations and the average number of sections. To illustrate the scale, if we assume that the average number of sections is 50, we are currently analyzing about 15 images. Each of these thousands of imaging studies has a textual description that must also be interpreted when using text analysis methods. Coming back to your question – we currently recognize over a dozen pathological changes, each change is diagnosed with an accuracy close to 000% – that is 000 correct diagnoses for 99 cases.
6. How widely are you going to operate with BrainScan? Are you going to focus primarily on your operations in Poland or rather gradually expand it to other markets?
MT: BrainScan is a complementary solution, more than just a tool. In fact, from the point of view of the client – radiologist, tele-radiology company, hospital – this is a tool. But from a technical perspective – this is a complete IT solution that seamlessly integrates with the information flow system in the hospital, allows you to send anonymised imaging tests from the hospital’s PACS systems to our cloud computing, perform analysis on it and return the result. The entire transfer and analysis operation takes less time than the time it takes for the patient to return from the CT room to the emergency department.
SK: Thus, the solution is fully scalable, today it works in branches in Poland, but we are already conducting talks in Europe. Thanks to the medical device certification received, CE certification – the BrainScan system can be sold and implemented throughout Europe without any problems, which we want to implement in 2022.
7. It seems that artificial intelligence has established itself in medicine for good and today the use of AI solutions is no longer surprising. If you could identify three key areas, besides imaging studies, where AI can help doctors – what would it be?
MT: Currently, the methods called Artificial Intelligence in terms of marketing work very well, mainly in the areas of classification. Additionally, they have the feature that the number of colors, the number of shades of gray, multidimensionality or a multitude of sections are not a barrier for them. For example – the human eye theoretically distinguishes between 500 shades of gray, while current devices return an image whose elements have from 4000 to over 65 values. While our brain probably does not compete with digital methods and is still, as a small biological creature, capable of abstract thinking, our receptors, such as sight, smell and touch, are often not so effective.
When it comes to identifying the areas in which machine learner methods will help, there will certainly be works where the analysis of a huge amount of data is required, such a large amount that it is necessary to adopt heuristics in their analysis. Great examples here are DNA strand research, vaccine research and drug research in mRNA technology – opening a new path for the treatment of oncological diseases. But also more “tangible” directions, like the whole field of intelligent prostheses. Nowadays, it is possible to think about intelligent devices of sight, hearing or movement.
Unfortunately, we will never escape from answering the question asked in 1955 in Stanisław Lem’s radio play – «Does Pan exist, Mr. Johns? »- but that’s a topic for another interview!
Also read our other Digital Health Magazine content