Virtum - treating cancer with AI-powered imaging healthcare
- Cloud processing
- Digital histopathology
AI is a powerful force disrupting the medical industry and its many workflows. So powerful in fact, that it brings us a step closer to beating one of the world’s ultimate challenges – Cancer. To aid this race, Tooploox brings Virtum, the AI-ready digital pathology workflow platform.
Virtum is a comprehensive platform for automated image analysis and an enabler for clinical AI solutions. It emerged from the need to support, enhance and automate the histopathology and medical imaging workflows.
Medical imaging and histopathology today
The WHO data shows that the leading causes of global deaths are non-transitional diseases, with cancer being one of the most common. Also, up to 50% of cancer cases can be avoided with relative ease, by avoiding the risk factors. The next most effective way to reduce the number of cancer-related deaths is early detection.
The early diagnosis can be provided by regular check-ups and access to modern healthcare advanced imaging devices like CT scanners or MRI as well as by skilled teams of medical imaging specialists and histopathologists alike.
What is a medical imaging?
Medical Imaging is an umbrella term describing the process of taking images of the internal human body as well as analyzing the functions and flow of particular organs and tissues. It is done using devices like ultrasound scanners, Magnetic Resonance Imaging (MRI), computer tomography (CT) or X-ray scanners among others, producing various types of medical scans.
Medical imaging is a way to spot suspicious changes in the body. If the organ or tissue is removed, it is further analyzed within the pathology workflows, usually histopathology.
What is histopathology?
Histopathology focuses on examining the tissue on a microscopic level. While medical imaging can determine if there is some suspicious change in the body, histopathologists deliver a detailed diagnosis on the type of the detected change.
IBM researchers estimate, that up to 90% of modern healthcare data consist of images with medical imaging and histopathology heavily contributing to the upbuild. While specialists from both areas save lives on a daily basis using their sophisticated equipment, there are several challenges to overcome.
Challenges in medical imaging and histopathology
While the new diagnostic tools bring new possibilities to modern healthcare, there are also multiple challenges to overcome to get the full out of them.
An increasing number of samples to analyze – Aging society
According to the World Bank data, life expectancy is rising globally, from 58.58 years in 1970 to 72.74 in 2020. The advancing age is one of the leading risk factors for cancer with the risks rising exponentially for the 50+yo kohorts. Hence, the rising life expectancy is increasing the demand for healthcare for elderly people, with medical imaging and healthcare histopathology services being one of the easiest ways to prevent or control many illnesses, including cancer.
Developing countries demanding access to high-quality diagnostic imaging
The problem is in the access to the trained staff and the costly equipment that is required to deliver reliable diagnostic outcomes. The additional challenge comes from the shrinking number of pathology specialists worldwide. According to the US National Library of Medicine the percentage of total US physicians, pathologists have decreased from 2.03% in 2007 to 1.43% in 2017.
Antiquated and hard to automate the approach
It is the role of the specialist to deliver the medical image analysis. This can be done in hard-to-automate, traditional ways, with the imaging specialist looking at the screen of the computer and the pathologist using the microscope. In fact, it is a lot of manual and complicated work to do, without the easy way to shoft from the qualitative to quantitative approach in tissue assessment.
Troublesome access to the knowledge due to the manual workflows
The manual way of processing the images results in a limited way to share the knowledge and reach out for second opinions a common practice in the field The machines are using exotic formats of data, images are heavy and hard to collaborate on using the telepathology approach.
Virtum is an outcome of a collaboration between histopathologists, scientists and software engineers. With histopathology as the top-of-mind use case, Virtum is a universal work-flow collaboration and storage system aimed at healthcare professionals with the goal to build the environment for machine learning in medical imaging.
To make the solution as flexible and reliable as possible, the team decided to deliver a solution accelerator rather than the solution itself. Virtum itself comes with multiple features that together enable the technology to tackle the challenges:
As the effect, a full artificial intelligence pathology diagnosis system was delivered, with multiple ways to merge the medical image processing with ai diagnostics.
Tech we used
Virtum prototype was initially delivered by MicroscopeIT company that was later acquired by Tooploox to enhance the portfolio of medtech solutions as well as support the development of the technology.
Our goal was to deliver the solution using the most flexible and popular technologies to ensure easy modification and development.
What is a medical imaging
Virtum is the cloud-based platform for acquisition, annotation, management, processing and analysis of large volumes of multi-dimensional and multi-modal images.
Originally, the tool has been developed to support histopathologists. Adaptation of Virtum contributed to more efficient data modeling and helped enhance medical processes. It uses image classification AI algorithms to link textual and visual content. The goal is to prototype novel methods, engineering schema for analytics & data management of medical data.
Virtum has also found its applications in non-medical industries, including manufacturing, renewable energy, life science, biotech, space, mining or chemical. The experiments involved microscope equipment manufacturers and medical R&D units to analyze images from remotely controlled microscopes, process super-resolution images, and take the full advantage of the virtual microscopy toolbox.
The deep understanding of the context as well as the technical proficiency resulted in delivering the tool that has tackled the main challenges in the medical imaging and histopathology fields.
Searchable and legible sample archive – quick access to any image
Virtum is a cloud-based suite that can be used to store and catalogue samples with an easy access to each of them. Also, contrary to more traditional ways of storing samples, these are fully searchable, can be tagged or marked in other ways to be easy to find in the upcoming future. Over the course of many projects, Virtum had been adopted for work on High Performance Computing (HPC) clusters, for instance, Fortissimo.
All-in-one workflow platform – tool-juggling no more
Virtum provides the tools to store, manage, analyze and work on microscopic images. There is no need for the image to leave the secure environment of Virtum for any reason given, bringing to hospitals and healthcare institutions the level of security they require.
Easy collaboration on any image given – consult with peers from all around the world
Virtum learns on the experiences of Google Workspace and similar collaboration tools, bringing the ease of sharing, commenting and editing to digital oncology and digital pathology systems. The users can check the version history, reply comments in threads, share the image and withdraw the access at will.
This comes as a great opportunity for healthcare professionals willing to consult their cases with peers from all over the world. The user whom the image was shared with needs only a browser to access the full benefits of using Virtum and can support his or her colleagues in providing better care for the patients.
Cloud or on-prem infrastructure to better address the compliance
Following the GDPR regulations, sometimes it is more desired for the institution to keep all data in-house. The technologies used to build Virtum support the on-prem infrastructure, leaving no uncertainty regarding compliance.
AI-ready for both labelling and operations – boost your microscopic workflows with AI
Virtum is accessible with API, making the tool perfect for the Artificial Intelligence application. Virtum itself can be used for data labeling to build an AI-ready dataset that can be used to train the algorithm to support the workflow.
The algorithm can be further implemented within the Virtum workflow by letting it work as a separate component that connects with the rest of the suite via API. There is also no obstacle to using Virtum as a platform to run the AI algorithm and send the effects to other tools or workflows.
Virtum is also powerful enough to combine artificial intelligence and radiology. Being the format-agnostic tool it can deliver AI image diagnostics for radiology and serve as a platform for ai in pathology solutions.
AI tackling cancer
In the traditional workflow, the user had to manually check the research papers on histopathology to compare the encountered anomaly with the base of existing ones. Virtum, powered by the AI algorithms, enables the user to run the auto-search through the database of research papers. It looks for comparable case, enhancing significantly the accuracy of diagnosis, even if the case is rare to the extreme.
While not being an AI diagnosis per se, it is a clear example of how machine learning and medical diagnosis can go along. It is huge support the life-saving and improving human lives in the way it is delivered in the Tooploox mission.
High UX standards
Last but not least, Virtum was designed by Tooploox design team, skilled and experienced with working for world-class companies and startups. By that, we provide healthcare and microscopic specialists working with Virtum the world-class UX levels unseen in other tools.
Use cases and other features
The AI-readiness of the software comes with interesting ways of development. One of the recent features enables the user to automatically scan through the digital histopathology literature in search of similar cases.