MR Prepare is an application in the field of medical diagnostics, which allows students and medical doctors to annotate medical cases, ie. mark items of interest (lesions, pathologies and similar) and provide related medical data. In this way, a specific pool of annotated (processed) medical images are created and stored in a database together with the original medical imagery files. MR Prepare will enable students to recognize pathology through their annotations. The goal is to collect high-quality data which will be used to teach an artificial intelligence system to individually make diagnoses. This will further help medical doctors to make a faster, better and more accurate diagnosis which will improve patients’ medical treatment in a timely manner and save patients’ lives.
Since this platform is in the complex field of medicine, there were certain challenges to overcome - including the customization of the pre-selected DICOM (OHIF) viewer and the industry-specific Orthanc database itself. We have successfully integrated the internal (Postgres) database with Orthanc and enabled the system functioning as a whole. Additionally, translating medical domain language into technical specifications and vice versa helped great understanding and developing synergy between our two domains.
Next to this, the 3-month timeline required a specific approach to the project management itself. To be able to meet the MVP goal in a timely manner, we defined and prioritized the requirements for the entire project at the very onset of the project. We jointly cut out the first viable solution (MVP) and agreed on the steps to follow shortly after. The defined scope, however, did not prevent the agile process of learning, changing the existing and creating new requirements during the product development. To the contrary, we jointly discovered the advantages of diverging ideas and managed them effectively to achieve the maximum benefit for our product.
The greatest challenge was the integration with the third-party solutions and their adaptation to the Partner's needs. In addition, we did mathematical modelling and metrics to find needed deviations using the medicine-specific systems. At this point, our two domains got completely intertwined. Working closely together with our Partner, we managed to effectively find and implement the solution.
We started working on this project in August 2020, with the timeline of 3 months for the initial (MVP) version. Our Partner needed the product to be developed swiftly and efficiently. During the first few weeks, we thoroughly investigated the project domain of medical imagery and the selected services - DICOM files, OHIF viewer and Orthanc database. Additionally, we agreed to maximize the benefit of the given time frame by identifying the highest-impact features and cutting out the MVP version accordingly. We then started the investigation, proving the concept and adjusting the approach early on.
After several sprints of intensive work, we had the first version of the complete flow at our hands. Together with the Partner, we took time to thoroughly test it, mutually share our feedback/suggestions and agree on the priorities. We are still actively developing, and the first release is planned for December 1st. In parallel, we are planning the next steps to take for Version 1 and are looking forward to enhancing our solution.
Reliable solution for aggregating medical data for AI.
Scalable and reliable application for processing large data volumes.
Delivery of a complex application in the medical field, during which we acquired knowledge using previously unknown libraries and systems.