02

Colorectal Cancer

Colorectal cancer is considered a major health problem. It remains the third most commonly worldwide diagnosed cancer after lung and breast cancer and it ranks these condone in terms of mortality.


Diagnosing and staging colorectal cancer patients heavily relies on medical imaging. Imaging is also relevant for treatment follow up, identification of eventual resistance to chemotherapy and for surveillance after therapy. The regular examination should include CT of chest, abdomen and pelvis at least once a year, or every six months when higher risk of recurrence is suspected. Imaging analysis should be reported in conjunction with the patient’s clinical and biological data and previous imaging to prevent incorrect attribution of lesions as metastases.


Diagnosing and staging colorectal cancer patients heavily relies on medical imaging.


The challenges in colorectal cancer diagnoses and follow up that INCISIVE will attempt to address are associated with technical, economical and organizational issues.


The technical issues relate to improvement of:



  1. Region specific (low) specificity of CT which exhibits poor performance in rectal cancer staging;

  2. Efficient algorithms for fusion of clinical and biological data with diagnostic information from different imaging modalities, currently done by the panel of medical experts;

  3. Provision of robust evidence on importance of different features extracted from registered imaging modalities and integrated clinical data to fortify the standardized procedures and guidelines;

  4. Enhancing CT imaging analytics and visualization tools for improved performance in detection of liver metastases and follow-up examinations. Economical restrictions hamper the use of more sensitive modalities (e.g., MRI) for metastasis detection and treatment follow up.


INCISIVE aims at empowering computer-aided tools and introduction of powerful analytics for automated recommendations and prognostic modelling based on the fused patient data


The organizational issues relate to lack of adequate inhouse dedicated multi-disciplinary expertise, which is a guarantee of safe and adequate use of imaging technologies. Therefore, INCISIVE aims at empowering computer-aided tools and introduction of powerful analytics for automated recommendations and prognostic modelling based on the fused patient data, which could help to compensate for similar organisational issues related to the human based factor.


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

  • 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

  • Prostate Cancer

    MRI slices will be the input to the AI service of this pilot study. An initial classifier decides if the given image contains any kind of malignancy, while a segmentation algorithm extracts the corresponding Regions of Interest. The PIRADS score will be calculated from the extracted segments and an additional classifier will show the probability of recurrence, taking into consideration specific risk factors of the patient. We will also explore the possibilities of predicting the biopsy score directly from the initial MRI scan, allowing the patient to avoid an invasive screening procedure.

    + INFO