MoT Berlin #15 @ MX Healthcare

We are happy to announce our next meetup!

Agenda
19:00 Doors Open, Food & Drinks
19:30 Dr. Oliver Eidel (Software Engineer, Medical Doctor, Regulatory Affairs @ MX Healthcare) - Applying Deep Learning to Breast Cancer Screening - in the Browser
19:50 Dr. Thijs Kooi (Machine Intelligence Engineer @ MX Healthcare) - Why melanomas are peanuts and breast tumors are a harder nut
20:10 Break
20:25 Valeriy Shevchenko (QA Engineer @ Delivery Hero) - Fantastic bugs and where to find them (Security testing for fun and profit)

After the talks, there will be time for discussion, networking, drinks etc.

Food & Drinks are sponsored by MX Healthcare (https://www.merantix.com).

Meetup organisation: eBay Tech Berlin (https://ebaytech.berlin/) and GameOn Berlin (http://gameon.berlin/)

More details on the talks:

Applying Deep Learning to Breast Cancer Screening - in the Browser

Breast cancer screening with x-ray images (mammograms) is one of the most common imaging procedures in the world. However, assessing these images correctly is hard and requires years of experience.

To improve both efficiency and confidence of mammography screening, we developed a deep learning model which assists radiologists in reading mammograms. In contrast to traditional medical image (DICOM) viewers which are installed as stand-alone software, our application runs in the browser which itself poses new challenges - it has to be able to process large files, hold the 14 megapixel images in memory and re-render them at 30 frames per second.

Oliver, a doctor and software engineer, will give a brief introduction into deep learning and our tech stack (Clojure). He’ll talk about the technical challenges we faced and the QA challenges which lie before us.

Why melanomas are peanuts and breast tumors are a harder nut

Thijs Kooi is a Machine Intelligence Engineer at MX Healthcare and did his PhD on deep learning for breast cancer screening. He explains the challenges we face in applying deep learning to mammographies and outlines why some medical image problems are harder than others for machine learning.

Fantastic bugs and where to find them (Security testing for fun and profit)

Not many people pay attention to the security of the application and infrastructure. In that speech, I will try to talk about testing from a security point of view. It's all about fantastic bugs and where to find them. Also, share some tips about bugs that you will find yourself.