CORDIS - EU research results
CORDIS

Deep learning AI in cancer diagnostics

Periodic Reporting for period 2 - AiforCancerDX (Deep learning AI in cancer diagnostics)

Reporting period: 2020-11-01 to 2022-04-30

Pain point – Aging populations and increasing cancer rates are constantly increasing the number of samples in healthcare. Despite the growing trend of digitalisation, pathologists are still reviewing the samples manually, which is a subjective, time-consuming, expensive manual process that exposes patients to the risk of misdiagnosis. Thus, there is a clear need for an affordable tool that supports and streamlines the workflows of pathologists, complementing humans with automated and objective analysis.

Solution – Aiforia Technologies is revolutionising pathology. Our Aiforia® Cloud platform and the Aiforia Clinical AI models for specific diagnostic use cases augment the efficiency and consistency of pathologists’ clinical sample analysis. They remove the slow, manual, and inconsistent workflow by automatically performing a range of laborious image analysis tasks, in a fraction of time with unprecedented accuracy and consistency. This is enabled by our disruptive Deep Learning AI software, implemented on a cloud platform, and built specifically for pathology applications.

To achieve the overall objective of the project - to scale up the operations of Aiforia® Cloud and become the global leader in automated tissue sample analysis – several actions have been performed.
The project aimed at developing deep learning AI based image analysis algorithms for two major cancer types, lung cancer and prostate cancer. The objective was to overcome the challenges of the current pathologist’s manual sample review and scoring solutions and to develop and certify specific AI algorithms to support pathologist’s review and thus to make cancer diagnostics more efficient and accurate than before. The project also consisted of optimizing AIforia’s cloud-based software platform for clinical use cases. During the project, Aiforia has completed extensive preparatory work to implement a validation process and CE-IVD documentation process in house, and applied those to CE-IVD mark the AI algorithms for both lung cancer and prostate cancer diagnostic support.

During the project, Aiforia has strengthened its salesforce and increased its international presence and lead generation activities as planned. Aiforia project management activities have contributed to the overall progress of the project.
In the beginning of the project, Aiforia Technologies was offering software solutions for the medical research and pharmaceutical R&D, but did not have any software solutions or deep learning AI models validated and certified for diagnostic use. By the end of the project, Aiforia has developed the clinical version of the software platform, as well as the planned deep learning AI algorithms for lung and prostate cancer. The developed AI algorithms - PD-L1 biomarker for lung cancer and Gleason grading algorithm for prostate cancer - have been validated and certified for diagnostic use. In addition to the development related to this project, the company has launched three CE-IVD marked AI-models for breast cancer diagnostics, and the compatible, CE-IVD marked clinical viewer for reviewing digital samples and recording the AI results.

The project has had a major effect on Aiforia’s development path, as it has enabled the Company to expand its target market from research and pharmaceutical development to clinical diagnostics. The developed products and the technology which are now brought to the hands of pathologists can have a major impact on clinical diagnostics world-wide. The constantly increasing sample numbers are putting a lot of pressure currently for the pathology laboratories around the world, who oftentimes are lacking expert level pathologist resources. The use of digital pathology tools and AI to support experts in diagnostic tasks may have a major impact in reducing time to diagnosis and in democratising patient's access to expert level diagnosis and personalised treatment regardless of their country or location.

The project has also significantly supported Aiforia in its commercialization efforts and has helped Aiforia in maintaining its position as one of the global leaders in digital pathology & AI. The industry is developing at a fast pace and players in the digital pathology field are aiming to offer integrated AI analysis systems for clinical clients. This project has supported Aiforia in maintaining their leadership position in offering a wide variety of AI algorithms through a cloud-based software platform to support the tissue diagnostic workflows.
AIFORIA