Precision Cancer Control Group – Martin Eklund's research group

The overarching aim of my research group is to develop personalized, high-precision control systems to reduce prostate- and breast cancer mortality as well as the negative side effects of today’s imprecise diagnostics and treatment selection. By combining biomarkers, genomics and medical imaging using statistical methods and artificial intelligence, we develop new methods for individualised diagnosis and treatment, which we translate to patients via clinical trials.

Part of the:

Our research

Our research aims to reduce breast- and prostate cancer mortality through the use of individualized prevention, diagnostics, and treatment.

Publications

All publications from group members

Funding

Grants

  • Swedish Research Council
    1 January 2023 - 31 December 2025
  • Swedish Cancer Society
    1 January 2022
    Prostate cancer is the most common form of cancer and the leading cause of cancer death among men in Sweden. In 2018, over 10,000 men were diagnosed with prostate cancer and 2,350 died from the disease. A bottleneck in the effort to reduce prostate cancer mortality is the difficulty in making objective and reproducible pathological assessments of tissue samples (biopsies) from the prostate. Histopathological evaluation of prostate biopsies is used to diagnose the disease and grade its severity, and is of crucial importance for the clinical management and treatment of men diagnosed with prostate cancer. Despite the importance of histopathological assessment of prostate biopsies, there are major challenges. The so-called Gleason grade is crucial for treatment decisions for men diagnosed with prostate cancer. As the Gleason grade often differs between different pathologists' assessments, treatment decisions can be made on incorrect information about the severity of the disease. This can lead to the man not receiving sufficiently aggressive treatment or receiving unnecessarily aggressive treatment. My research group has developed a system based on artificial intelligence (AI) to assist the pathologists, with the overall goal of solving these challenges. In the proposed research, we will continue the development of the AI system, link it to genomic information from the tissue samples, and conduct rigorous clinical validation of the system through a network of international collaborators and through a randomized clinical trial. The overall aim of the research is to make prostate cancer diagnosis more accurate, in order to provide better information to make correct treatment decisions for men diagnosed with prostate cancer and thus achieve better treatment results and fewer side effects of the treatment.
  • Swedish Research Council
    1 January 2021 - 31 December 2026
    Histopathological evaluation of prostate biopsies is critical to the clinical management of men suspected of having prostate cancer. Despite this importance, the histopathological diagnosis of prostate cancer is associated with a number of challenges: The large number of prostate biopsies being performed worldwide together with the shortage of well-trained uro-pathologists and the high inter- pathologist variability leads to suboptimal prostate cancer diagnostics and prognostication, with risks for under- and overtreatment.My research group has over the last years developed an artificial intelligence (AI) system to assist the pathologists in the evaluation of prostate biopsies, with the overarching aim of solving these problems. In a recent article in the Lancet Oncology, we demonstrate that the system performs on par with internationally leading uro-pathologist for grading prostate needle biopsies.In this research proposal, we aim to:Perform retrospective international multisite validation of the AI system to assess the AI’s performance across different labs, technical platforms (scanners), and disease subtypesDevelop methods to go beyond today’s grading to improve prognosticationLink the AI system with genomic profiling of tumor tissue to improve treatment selectionPerform prospective validation of the AI system in a randomized diagnostic histopathology trial
  • Improved active monitoring of patients with diagnosed low-risk prostate cancer
    Swedish Cancer Society
    1 January 2018
    More than 2,500 men die each year from prostate cancer in Sweden. Although PSA sampling every two years between ages 50 and 70 has been shown to nearly halve mortality, PSA has significant diagnostic limitations leading to many unnecessary biopsies, over-diagnosis, and over-treatment, which is why prostate cancer screening is not recommended by healthcare. The need for improved methods for early detection of prostate cancer is thus great. In recent years, we have conducted the SHLM3 studies, where we show that we can significantly improve prostate cancer diagnosis using the STHLM3 test and the use of magnetic camera studies. Active monitoring of men with diagnosed low-risk prostate cancer is a method for reducing over-treatment, which involves following up the patient with repeated PSA tests and biopsies to be able to subsequently distinguish those who need to be treated. One disadvantage of active monitoring is the many biopsies that men are exposed to, which can lead to serious infections and impaired opportunities for effective surgery if active treatment is needed. We want to develop methods for monitoring low-risk patients who are safe and less invasive using the STHLM3 test and magnetic camera surveys. The research aims to improve the methods for active monitoring in order to reduce the negative consequences of early diagnostics for prostate cancer. Considering that over-diagnosis and over-treatment were the main reason why prostate cancer screening was not recommended, improved methods of managing mites that are diagnosed with low-risk prostate cancers are required so that we can move towards effective organized screening for prostate cancer to reduce morbidity and mortality in Sweden's most deadly cancer.
  • Swedish Research Council
    1 January 2016 - 31 December 2019
  • Swedish Research Council for Health Working Life and Welfare
    1 November 2012 - 31 October 2015

Staff and contact

Group leader

All members of the group

Visiting address

Karolinska Institutet, Department of Medical Epidemiology and Biostatistics, Nobels väg 12A, Stockholm, 17177, Sverige

Postal address

Karolinska Institutet, Department of Medical Epidemiology and Biostatistics, PO Box 281, Stockholm, 17177, Sverige