Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided.

Slides:

Advertisements

Similar presentations

Real-Time Template Tracking

Advertisements

Efficient Program Compilation through Machine Learning Techniques Gennady Pekhimenko IBM Canada Angela Demke Brown University of Toronto.

Relevant characteristics extraction from semantically unstructured data PhD title : Data mining in unstructured data Daniel I. MORARIU, MSc PhD Supervisor:

Optimizing single thread performance Dependence Loop transformations.

Technische Universität München Face Model Fitting based on Machine Learning from Multi-band Images of Facial Components Institute for Informatics Technische.

Matthias Wimmer, Ursula Zucker and Bernd Radig Chair for Image Understanding Computer Science Technische Universität München { wimmerm, zucker, radig

Automatic determination of skeletal age from hand radiographs of children Image Science Institute Utrecht University C.A.Maas.

Carolina Galleguillos, Brian McFee, Serge Belongie, Gert Lanckriet Computer Science and Engineering Department Electrical and Computer Engineering Department.

CMSC 345, Version 11/07 SD Vick from S. Mitchell Software Testing.

Face Recognition & Biometric Systems, 2005/2006 Face recognition process.

This presentation will probably involve audience discussion, which will create action items. Use PowerPoint to keep track of these action items during.

Content Based Image Clustering and Image Retrieval Using Multiple Instance Learning Using Multiple Instance Learning Xin Chen Advisor: Chengcui Zhang Department.

Study of a Paper about Genetic Algorithm For CS8995 Parallel Programming Yanhua Li.

LYU 0602 Automatic PhotoHunt Generation1 Automatic PhotoHunt Generation Shum Hei Lung To Wan Chi Supervisor: Prof. Michael R. Lyu.

1 Integrating User Feedback Log into Relevance Feedback by Coupled SVM for Content-Based Image Retrieval 9-April, 2005 Steven C. H. Hoi *, Michael R. Lyu.

Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.

1.3 Executing Programs. How is Computer Code Transformed into an Executable? Interpreters Compilers Hybrid systems.

12 August 2015 Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for.

Matthias Wimmer, Bernd Radig, Michael Beetz Chair for Image Understanding Computer Science Technische Universität München Adaptive.

Matthias Wimmer, Sylvia Pietzsch, Freek Stulp and Bernd Radig Chair for Image Understanding Institute for Computer Science Technische Universität München.

Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.

Your Project Title Here Lab Course / Praktikum: Winter Semester 2012/2013 Project Management and Software Development for Medical Applications Your Name.

Transformation of Input Space using Statistical Moments: EA-Based Approach Ahmed Kattan: Um Al Qura University, Saudi Arabia Michael Kampouridis: University.

Topic #10: Optimization EE 456 – Compiling Techniques Prof. Carl Sable Fall 2003.

© Janice Regan, CMPT 128, Jan CMPT 128 Introduction to Computing Science for Engineering Students Creating a program.

Comparing the Parallel Automatic Composition of Inductive Applications with Stacking Methods Hidenao Abe & Takahira Yamaguchi Shizuoka University, JAPAN.

Universal Concepts of Programming Creating and Initializing local variables on the stack Variable Scope and Lifetime Stack Parameters Stack Frames Passing.

INTRODUCTION TO COMPUTING CHAPTER NO. 06. Compilers and Language Translation Introduction The Compilation Process Phase 1 – Lexical Analysis Phase 2 –

Face Model Fitting with Generic, Group-specific, and Person- specific Objective Functions Chair for Image Understanding and Knowledge-based Systems Institute.

Chapter 10: Compilers and Language Translation Invitation to Computer Science, Java Version, Third Edition.

1 COMP 3438 – Part II-Lecture 1: Overview of Compiler Design Dr. Zili Shao Department of Computing The Hong Kong Polytechnic Univ.

Boltzmann Machine (BM) (§6.4) Hopfield model + hidden nodes + simulated annealing BM Architecture –a set of visible nodes: nodes can be accessed from outside.

Computational Biology 2008 Advisor: Dr. Alon Korngreen Eitan Hasid Assaf Ben-Zaken.

Applying Genetic Algorithm to the Knapsack Problem Qi Su ECE 539 Spring 2001 Course Project.

Derivatives In modern structural analysis we calculate response using fairly complex equations. We often need to solve many thousands of simultaneous equations.

1 Multiple Classifier Based on Fuzzy C-Means for a Flower Image Retrieval Keita Fukuda, Tetsuya Takiguchi, Yasuo Ariki Graduate School of Engineering,

G.Corti, P.Robbe LHCb Software Week - 19 June 2009 FSR in Gauss: Generator’s statistics - What type of object is going in the FSR ? - How are the objects.

Exploiting Context Analysis for Combining Multiple Entity Resolution Systems -Ramu Bandaru Zhaoqi Chen Dmitri V.kalashnikov Sharad Mehrotra.

Lab Course / Praktikum: S ummer Semester 2012 Project Management and Software Development for Medical Applications Computer Aided Medical Procedures (CAMP),

Blue Brain Project Carlos Osuna, Carlos Aguado, Fabien Delalondre.

Mining Binary Constraints in Feature Models: A Classification-based Approach Yi Li.

SECURITY IMAGING Prof. Charles A. Bouman Vertical Integrated Projects (VIP) Spring 2011, Call-Out.

6. Program Translation CS100: The World of Computing John Dougherty Haverford College.

Program Design. The design process How do you go about writing a program? –It’s like many other things in life Understand the problem to be solved Develop.

M Machine Learning F# and Accord.net.

Lab Course / Praktikum: S ummer Semester 2012 Project Management and Software Development for Medical Applications Computer Aided Medical Procedures (CAMP),

Coevolutionary Automated Software Correction Josh Wilkerson PhD Candidate in Computer Science Missouri S&T.

10th of June 2005 Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair.

Programming and Languages Dept. of Computer and Information Science IUPUI.

Geometry Synthesis Ares Lagae Olivier Dumont Philip Dutré Department of Computer Science Katholieke Universiteit Leuven 10 August, 2004.

Data Mining for Surveillance Applications Suspicious Event Detection Dr. Bhavani Thuraisingham.

Higher Computing Science 2016 Prelim Revision. Topics to revise Computational Constructs parameter passing (value and reference, formal and actual) sub-programs/routines,

The Functions and Purposes of Translators Translators, Interpreters and Compilers - High Level Languages.

Stephan Tschechne Chair for Image Understanding Computer Science Technische Universität München Designing vs. Learning the Objective.

The Functions and Purposes of Translators Translators, Interpreters and Compilers - High Level Languages.

Prof. Amr Goneid, AUC1 Analysis & Design of Algorithms (CSCE 321) Prof. Amr Goneid Department of Computer Science, AUC Part 3. Time Complexity Calculations.

PROGRAMMING FUNDAMENTALS INTRODUCTION TO PROGRAMMING. Computer Programming Concepts. Flowchart. Structured Programming Design. Implementation Documentation.

Lab Course / Praktikum: Winter Semester 2011/2012 Project Management and Software Development for Medical Applications Computer Aided Medical Procedures.

Deep Learning Overview Sources: workshop-tutorial-final.pdf

Introduction to Computer Programming Concepts M. Uyguroğlu R. Uyguroğlu.

Software Engineering Algorithms, Compilers, & Lifecycle.

Dept of ECE, Concordia University, Montreal, Canada

Semi-supervised Machine Learning Gergana Lazarova

OVERVIEW Impact of Modelling and simulation in Mechatronics system

R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.

Project Implementation for ITCS4122

Students: Meiling He Advisor: Prof. Brain Armstrong

Introduction to Computer Programming

Type Topic in here! Created by Educational Technology Network

1.3.7 High- and low-level languages and their translators

Presentation transcript:

Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Automatic Feature Generation for Endoscopic Image Classification Ulrich Klank Nicolas Padoy Prof. Nassir Navab Supervisor: Advisor: 18 January 2007

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Overview  Endoscopic images  Differences  Similarities  Image feature generation using Genetic Programming  A low level approach  A high level approach  An example

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Endoscopic Images of two Surgical Phases: OP3 Images from the cutting and clipping phase (OP3) Images from the bag retraction phase (OP3)

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu …: OP1 Images from the bag retraction phase (OP1)Images from the cutting and clipping phase (OP1)

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Low-level Approach - Short Reminder Genetic Programming: combination of low-level operators PIXEL (With Parameters) PUSH… FOR (With Parameters) MUL LOAD (With Parameters) ADD Mutation Evaluation Code

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Low-level Approach - Results  Distributed evaluation of programs on several computers (up to 7)  Nearly programs evaluated (~300 generations)  First results:  Characteristics of the best programs:  returning a short vector in a short time  Classification rate with a linear classifier is 62%  (64 images of 2 phases of 4 videos)

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Problems with the low-level Approach  ~40% of the programs contain major errors like  Infinite running time, stack overflow  No reference to the input image  Resulting programs still has structural similarity to the initial program. More generations needed  Evaluation of a programs is very slow due to the simulation of basic instructions on images How to improve this method?

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Existing Software: GENIE  GENIE Software published by:  Los Alamos National Laboratories  First publication ’97,  Commercial version in development  Genetic Programming for segmentation of images  Application example:  Segmentation of Medical Images Using a Genetic Algorithm by Payel Ghosh, Melanie Mitchell (’06)

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu The Step to a higher level approach Erode (With Parameters) Histogram (With Parameters) MinLocOriginal CannyEdge (With Parameters) Gradient x (With Parameters) Dilate (With Parameters) PIXEL (With Parameters) PUSH… FOR (With Parameters) MUL LOAD (With Parameters) ADD Replace the basic commands in a program by higher level operators: Examples for low-level operator : Examples for high-level operator :

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Evaluation of a Program  Semantic checks  Input referred?  No infinite loops?  Execution with several inputs  16 images per phase  2 phases per video at the moment  4 videos used for evaluation  A fitness function with 2 components:  A classification of the phases by the output vectors  The average execution time per input

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Genetic Concept – Cross Over Erode (With Parameters) Histogram (With Parameters) MinLocOriginal CannyEdge (With Parameters) Gradient x (With Parameters) Dilate (With Parameters) Gauss (With Parameters) OriginalMaxOriginal PushImage (With Parameters) Gradient y (With Parameters) Histogram (With Parameters) Program 1 Program 2 New Program

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu High-level Approach Benefits  Faster evaluation  Reduced number of commands  Optimized basic image operations (OpenCV)  Resulting programs easier to understand

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Current Results:  Running time: 480 ms (in simulation)  Output length: a vector of 48 signed integer  Classification rate: 67%  Rate based on 512 testing images out of 4 videos and 2 phases  Number of generations needed: ~80

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Future Work  Completion of the available image operators  Extension to multi-phases classification  Comparison of the fitness function with a standard classifier  Comparison with several standard features  Features evaluation within the workflow segmentation system

CAMP | Department of Computer Science | Technische Universität München | 12 August Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu Thank you for your attention!