28 March 2019
In the PROACTING project (funded by the Dutch Cancer Society (KWF)) we will develop deep learning algorithms that will leverage a large amount of data consisting of histopathology images and corresponding (weak) labels, with the aim of building computer systems that can assist pathologists and oncologists during cancer diagnostics and personalized (neoadjuvant) treatment procedures. This project will be performed in close collaboration with the Molecular Pathology research group of Jelle Wesseling at the Netherlands Cancer Institute.
Francesco Ciompi is member of theme Tumors of digestive tract.
Jeroen van der Laak is member of theme Women's cancers.
Francesco Ciompi and Jeroen van der Laak have been awarded a KWF grant of € 200K with € 150K for Radboudumc for the PROACTING project (PRedicting neOAdjuvant Chemotherapy Treatment response with deeplearnING).
Neoadjuvant Chemotherapy (NACT) is increasingly used for pre-operative treatment of breast cancer patients. Successful application of NACT, resulting in a substantial or complete reduction in tumor volume, enables breast-conserving surgery in a higher number of cases and allows assessment of tumor sensitivity to chemotherapy. Effective NACT gives a pathologic complete response (pCR), which was shown to be a strong indicator of long-term prognosis. pCR can be assessed by quantifying post-operative residual disease via histopathology. Although many patients benefit from neoadjuvant treatment, a large group of patients do not respond while still experiencing the toxic side effects. In addition, postponing surgery may have an adverse effect on long-time outcome for these patients. This scenario clearly shows the urgent need for personalized prediction to identify patients who are likely to achieve pCR, including the ones that are currently considered non-eligible, and patients who are not likely to respond to NACT, who could be precluded from getting it. To date, it is impossible to predict upfront whether a patient will respond to NACT.In the PROACTING project (funded by the Dutch Cancer Society (KWF)) we will develop deep learning algorithms that will leverage a large amount of data consisting of histopathology images and corresponding (weak) labels, with the aim of building computer systems that can assist pathologists and oncologists during cancer diagnostics and personalized (neoadjuvant) treatment procedures. This project will be performed in close collaboration with the Molecular Pathology research group of Jelle Wesseling at the Netherlands Cancer Institute.
Francesco Ciompi is member of theme Tumors of digestive tract.
Jeroen van der Laak is member of theme Women's cancers.
-
Want to know more about these subjects? Click on the buttons below for more news.