Monthly Computer Vision Meetup Roundup #3

Project Description

Monthly Computer Vision Meetup Roundup #3

New year, new meetups!

We started into the new year with a new edition of our Computer Vision Get-togethers! We’re very excited about all the talks, discussions and try-out workshops in 2016 and we’ll do our best do keep improving our meetups so you’ll get the best out of it. Hopefully many of you will join us along the ride and be part of our community!

An Introduction on Medical Computer Vision

At our Second Computer Vision Meetup in December, Rene from the CIR (Computational Imaging Research) Lab at the Medical University of Vienna gave a very interesting introduction on Deep Learning. For our recent edition, Rene’s colleague Markus Holzer volunteered to present his thoughts and ideas to Medical Computer Vision.

presentation

After everyone had arrived and grabbed a drink, Markus started his talk by giving an overview of the different types of medical images like X-Ray, MRI, functional MRI and CT.

overview

He then continued with three examples of medical image detection. The first example was a detection method for bones in X-Ray images. The approach he explained, is based on a combination of Active Shape Models (ASM) and a Random Forest classifier. This method takes an annotated set of shapes and grayscale X-Ray images as input, and learns the variations of the shapes of the bones, as well as selects the most discriminating features computed on these images.  Using these learnt features, the system is able to predict the position of the bone on a new unseen X-Ray image, and fit the shape. The practical application of this method can be seen in the automatic quantification of bone diseases, such as osteoporosis, or automatic detection of caries and other dental problems on X-Ray images.

The second example was about MR images of Fetal Brain Development and how this is used to identify the different fetal brain regions and see how they develop.

header

With the third example, the 3d image search with CT examples, Markus introduced the crowd to his own project: The Radiology-Explorer. This 3d image and text search engine makes it possible for radiologists to find similar 3d images in the blink of an eye. The radiologist simply has to select the area of his interest on the image and the engine finds similar cases with a record of treatment.

radiologyexplorer

Markus showed pictures of the interface of the engine and then ended his talk with a quick summary to move on to answering questions from the audience.

highres_446333888

The third Computer Vision Meetup was a great kick-off into the new year and we hope to see many of you on our following get togethers!

Hold a Talk Yourself!

You have a project or topic you would like to talk about or you know someone, who would like to share his/her experiences and knowledge? Please contact us!
Oh – and don’t forget to join our meetup group ! 😉

 

QUESTIONS? LET US KNOW!

If you have questions, suggestions or feedback on this, please don’t hesitate to reach out to us via FacebookTwitter or simply via [email protected]! Cheers!