News: “Personalizable AI platform for universal access to research and diagnosis in digital pathology”

In the context of the iPATH project, in partnership with pathologists from University of Coimbra and CCG/ZGDV we published  a new scientific article in Computer Methods and Programs in Biomedicine, entitled as “Personalizable AI platform for universal access to research and diagnosis in digital pathology”. The highlights of the work described are as follows:

  • Pure Web Platform for Digital Pathology: The work presents a web-based platform designed for digital pathology medical imaging. This platform relies on the DICOM standard for communication and data format, ensuring compatibility and interoperability with medical imaging systems.  The platform is equipped with features that facilitate collaboration in both production and research contexts. This suggests that it enables pathologists and researchers to work together effectively, potentially improving patient care and advancing medical research.
  • Vendor-Neutral Archive: The platform includes a multimodal vendor-neutral archive, which can store various types of medical imaging data. This archive supports metadata, pixel data, and both manual and automated annotations, making it a versatile solution for managing and analyzing pathology images.
  • API for AI Services: The platform provides an Application Programming Interface (API) that allows the integration of Artificial Intelligence (AI) services. This integration can enhance the quality of data and provide assistance in medical diagnosis, suggesting a focus on leveraging AI for pathology analysis.
  • Active Learning Framework: The work introduces an active learning framework specifically designed for the development and training of machine learning algorithms. This framework is likely intended to improve the accuracy and efficiency of AI algorithms for pathology analysis.
  • Validation with Mitosis Detection Algorithm: The platform was put to the test in a research project involving medical pathologists. During this project, a mitosis detection algorithm was successfully developed and integrated into the platform for case annotation and real-time inference. This implies that the platform’s capabilities were validated with data of practical medical context.


Overall, this work offers a comprehensive and advanced solution for digital pathology, integrating web-based technology, AI capabilities, collaborative features, and practical validation with medical professionals.

Do you want to test it out? Contact us:


Comments are closed.