Courses

Back

A8 - Front-End Vision and Multi-Scale Image Analysis

From: November 19 to 23, 2017 and from: December 4 to 4, 2017 Registration is Closed

 

 

A PhD / MSc course given at the Department of Biomedical Engineering of Eindhoven University of Technology.


 

Deep learning, self-organization and plasticity, convolutional neural networks, geometry engine, contextual Gestalt processing: the field known as 'brain-inspired computing' is one of the most promising avenues in medical image computing today.
To make new breakthroughs in this spectacular arena, the interplay between the fields of brain imaging and physiology, neural network informatics and fundamental mathematics is essential. However, these fields speak different languages, and interaction is nontrivial.
This course focuses on exactly that: we will discuss in detail modern findings in the neurophysiology, connectivity and functionality of the visual system, the best studied brain function today. The goal is to develop highly effective and efficient computer-aided diagnosis systems.

This is an intensive course of two full weeks (with a break in between), where each half day of theory is followed by a computer lab (all software code is supplied). We exercise with the developed notions, exploiting the high-level 'play and design' functionality of Mathematica 11.

The lecturers have extensive experience in the field, and are known for their excellent teaching.

Tutors: Prof. Bart M. ter Haar Romeny, Eindhoven University of Technology / Northeastern University (Shenyang, China)
Prof. Nicolai Petkov, University of Groningen
Dates: 2 fulltime weeks: Lectures (each half day) from Monday 20 November 2017 till Friday 24 November 2017, and from Tuesday 5 December 2017 till Friday 8 December 2017. Computer laboratories (other each half day) using Mathematica 11.

Registration:

Register through the ASCI website: here.
TU/e BME students: Register through the regular TU/e OASIS page for 8DM00.
Registration for course and exam is free for TU/e, ASCI, NFBIA, ImagO students, and employees of industries officially collaborating with TU/e BME.
For registration as 'contractant' with TU/e to do an official exam for 3 ECTS as non-TU/e student: see STU registration form. Costs: € 500 per course.
Costs for industrial participants: € 1200 (invoice will be sent by ASCI after registration).
Venue Campus of Eindhoven University of Technology, Eindhoven, the Netherlands.  Google Maps, TU/e campus map.
Hotel Suggestions (Booking.com)

 

Total duration: 27 oral lectures of 45 minutes each, and 27 hours hands-on training.

Code ASCI:
a8 (4 ECTS study points).
Code TUE-BME:
8D010 (2.5 ECTS study points).
Code MANET:
Training
(4 ECTS study points).
 

Description:

We give insight in modern approaches to deep convolutional neural nets, and we will teach a number of well-established mathematical modeling techniques in detail, in particular multi-scale and multi-orientation differential geometry, models for self-organization and plasticity, and geometric neural feedback, leading to effective adaptive operations. We present the theory in an axiomatic, intuitive and fundamentally understood way.

This interactive course is interspersed with working and powerful applications in medical image analysis, such as computer-aided detection of breast tumors, invariant feature detection, development of retinal vessel biomarkers, and contextual Gestalt-based operators to deal with missing data.

You will learn how geometric reasoning works and can be applied. We design image analysis algorithms by carefully studying the requirements, physical analogies, and in particular by looking how our visual system does it. After all, this is still the best performing recognition computer we know, even for noisy, partly missing (occluded) data, low contrast etc. Modern (often optical) brain imaging methods will be discussed (voltage sensitive dyes, opto-genetics, fMRI, DTI/HARDI) and recent discoveries of functional brain mechanisms in visual perception.

The majority of the examples discussed are from 2D, 3D and 4D (3D-time) medical imaging. We devote some time to the efficient numerical implementation of the different techniques. Hands-on experience is acquired in a computer lab. We use Mathematica 11 as this software suite is eminently suited for this design process. We experiment hands-on with virtually all aspects discussed in the course.

Some applications discussed:

  •  detection of stellate tumors in mammography,
  •  counting follicles for fertility related diagnosis with 3D ultrasound,
  •  detecting polyps in 3D virtual colonoscopy,
  •  detecting pulmonary emboli (narrowed vessels in the lung),
  •  retinal vessel analysis,
  •  vesselness for vessel enhancement.

 

For the detailed program and content click here: bmia.bmt.tue.nl/Education/Courses/FEV/course/index2017-BME.html

 

 

Back

 ASCI Tweets 
 Headlines