Xê-mi-na khoa học
03/02/2021: TS. Pierre Ambrosini (Erasmus MC, Netherlands), Automatic Detection of Cribriform Growth Pattern in Prostate Histology Images
Cribriform growth patterns in prostate carcinoma are associated with poor prognosis. We aimed to introduce a method to detect such patterns automatically. To do so, convolutional neural network was trained to detect cribriform growth patterns. To benchmark method performance, intra- and inter-observer variability has been evaluated. In the presentation we will discuss the method, the experiments and the results of our detection algorithm.
Speaker: TS. Pierre Ambrosini, Erasmus MC
Time: 15:30, Wednesday, February 03, 2021
Venue: G2-315, 144 Xuan Thuy, Cau Giay, Hanoi
Pierre Ambrosini received a Master in Computer Science from the University of Lyon (France). He worked as a research engineer at the Biomedical Imaging Group Rotterdam (BIGR) in Erasmus MC. With his group, he prototyped a workstation that aims at improving image guidance during medical interventions. Afterward, he continued his research in the same group as a Ph.D. candidate on image guidance for the Transcatheter Arterial ChemoEmbolization procedure. The research was a collaboration with Philips Healthcare. His research mainly revolved around real-time registration, tracking, and segmentation with X-ray images. After his Ph.D. project, he has been in a postdoctoral position at the Imaging Physics department of the Delft University of Technology working on automatic detection of tumor growth patterns in prostate histopathology images. Since September 2020, he is now back in Erasmus MC at the BIGR and the surgery department working on augmented reality in surgical oncology.