Intelligyn's Commitment to Gynecological Care

Intelligyn is a spin-out of Karolinska Institutet and The Royal Institute of Technology (KTH) in Stockholm, Sweden, with the mission to drastically improve ovarian cancer diagnostics by bringing cutting-edge AI research into clinical use. Our research create solutions that prioritizes patient care and streamlines the efficiency of healthcare systems.

Publications

  • Screenshot of a scientific research article titled 'International multicenter validation of AI-driven ultrasound detection of ovarian cancer' from the journal 'Nature Medicine' with publication and acceptance dates, author affiliations, and a summary of the study.

    Multicenter Validation Study

    We developed and validated neural network models ability to differentiate between benign and malignant ovarian lesions, based on 17,000 ultrasound images from 3,652 patients across 20 hospitals in eight countries. The models’ diagnostic capacity was compared to a large group of examiners. The AI models outperformed both expert and non-expert examiners achieving an accuracy rate of 86.3%, compared to 82.6% and 77.7% for the expert and non-expert examiners respectively.

    Read article
  • Text-heavy scientific article explaining how the educational game SonoQz improves ultrasound diagnosis of ovarian tumors, including author information, abstract, and funding details.

    Educational Platform Study

    This study has scientifically proven to improve a clinician’s ability to characterise lesions as benign or malignant with greater specificity from 70% to 89% when used for a minimum of 200 cases or about 5 hours of use.

    Read article
  • Academic research paper titled "Ultrasound image analysis using deep neural networks for discriminating between benign and malignant ovarian tumors: comparison with expert subjective assessment" by multiple authors, including their institutional affiliations, keywords, and part of the contribution section discussing the use of deep neural networks and transfer learning for ovarian tumor classification.

    Proof of Concept Study

    To develop and test the performance of computerized ultrasound image analysis using deep neural networks in discriminating between benign and malignant ovarian tumors and to compare its diagnostic accuracy with that of subjective assessment by an ultrasound expert.

    Read article