04

Prostate Cancer

Prostate cancer is recognized as one of the major medical problems faced by the male population. In Europe, an estimated 2.6 million new cases of cancer are diagnosed each year. Prostate cancer survivors face serious long-term side effects, thus improved treatment pathways enabled by AI, such as those targeted by INCISIVE, are urgently required.


The enormous progress in survival rates, and the fact that long-term prostate cancer survivors are at increased risk for comorbidities, suggests the time is right for a stronger focus on patient outcomes, optimized care pathways and precision medicine to accelerate personalized medicine approvals, reduce long-term care requirements and address influences on patient outcomes.


Multiparametric magnetic resonance imaging (mpMRI) is the technique of choice in the diagnosis of prostate cancer, allowing the location and staging of prostate cancer. Several studies have demonstrated that mpMRI can improve the sensitivity and specificity of prostate cancer detection and its use have increased the detection of higher-grade cancer, however, around 10-15% of clinically significant tumors cannot be detected. Relapsing level of prostate-specific antigen (PSA) after surgery treatment is often the first sign of recurrence. However, PSA level recurrence does not enable accurate differentiation of locally recurrent tumor from metastatic disease.


Several studies have demonstrated that mpMRI can improve the sensitivity and specificity of prostate cancer detection and its use have increased the detection of higher-grade cancer, however, around 10-15% of clinically significant tumors cannot be detected.


Conventional imaging, including CT and bone scan, has long been the standard of care but have limited sensitivity in depicting early local recurrence or metastatic disease. Currently, the use of MRI after surgical treatment to detect recurrences and progression is increasing since it has shown to be more sensitive in detecting locally recurrent tumor in the prostatectomy bed, as well as in recurrence in a prostate gland that has been treated with radiation therapy or thermal ablation.


The challenges addressed in INCISIVE are the following:



  1. Optimize diagnostic and therapeutic management of Prostate cancer patients by improving Prostate cancer patients stratification; distinguish patients who will benefit from entering an active surveillance program from those who should undergo local treatment with intention to cure, through AI enabled fusion of mpMRI, histology and genomic profiles;

  2. Improve the accuracy of mpMRI using AI tools;

  3. Identify improved biomarkers and diagnostic and surveillance approaches to inform more patient-centered clinical practice for initial diagnosis and/or screening by analyzing patient outcomes from different diagnostic and follow up technologies such as imaging, machine learning capabilities applied to genomics data and grading/ staging data;

  4. Comparison of outcomes between data on new diagnostics and follow-up approaches and patient records to better assess the opportunities for adopting novel technologies in clinical practice to benefit Prostate cancer patient and healthcare system outcomes.


Take a look to the other pilots

  • Lung Cancer

    Accurate classification and segmentation of non-small lung cancer (NSCLC) lesions by utilizing X-ray images aiming to retrieve initial but still essential diagnostic information, as well as CT scans and PET/CT scans for further diagnostic analysis. Explainable AI (XAI) tools will be adopted in an effort to understand which areas of the image contributed to the final classification decision.

    + INFO

  • Colorectal Cancer

    Binary classification healthy/non-healthy of the input MRI scans constitutes the initial stage of the Colorectal cancer diagnostic pipeline. Accordingly, the accurate segmentation of ROIs (Regions Of Interest) and the classification as malignant or benign is another major aspect of this pilot study. Additionally, the prediction of metastatic risk and the evaluation of treatment response would be of great interest for the purposes of this AI service. XAI features will be part of this study as well.

    + INFO

  • Breast Cancer

    Utilization of low-cost imaging modalities like mammographies, aiming to provide reliable and accurate diagnostic services that focus on identification of lesions and calcifications, as well as prediction of BIRADS score and ACR density. MRI scans will also be evaluated as a secondary step and the findings will be combined with clinical data to address elaborate clinical questions. The diagnostic models will also be enriched with explainability features.

    + INFO