Koło Naukowe Uczenia Maszynowego Wydziału Matematyki, Informatyki i Mechaniki Uniwersytetu Warszawskiego i Konferencja ML in PL zapraszają na pierwszy ML in PL pre-meeting, podczas którego Krzysztof Geras - assistant professor w New York University School of Medicine wygłosi wykład pt. "Towards solving breast cancer screening diagnosis with deep learning", dotyczący wykorzystywania sztucznej inteligencji w wykrywaniu raka piersi.
Abstract:
Although deep learning has made a stunning progress in the last few years, both in terms of engineering and theory, its real-life applications remain rather limited. One of the fields that has been anticipated to be revolutionized by deep learning for some time, yet proved to be much harder that many expected, is medical diagnosis. In this talk I will shed some light on my 2.5-year long journey in developing deep learning methods for medical imaging, in particular, for breast cancer screening. I will explain how we created a deep learning model that can perform a diagnosis with an accuracy comparable to experienced radiologists. To achieve this goal we needed a lot of perseverance, novel neural network architectures and training methods specific to medical imaging. I will also discuss the limitations of our work and what can be likely achieved in the next few years.
Wykład odbędzie się w czwartek 18 lipca 2019 o godzinie 18:00 w sali 3180 budynku MIM UW (ul. Banacha 2, 02-097 Warszawa). Udział w wydarzeniu jest bezpłatny.
Szczegółowe informacje: https://www.facebook.com/events/347213515912633/