15
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

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

Embed Size (px)

Citation preview

Page 1: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

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 PadoyProf. Nassir Navab

Supervisor:Advisor:

18 January 2007

Page 2: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 2

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

Page 3: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 3

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)

Page 4: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 4

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)

Page 5: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 5

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

EvaluationCode

Page 6: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 6

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 10.000 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)

Page 7: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 7

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?

Page 8: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 8

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)

Page 9: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 9

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 :

Page 10: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 10

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

Page 11: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 11

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)

Original MaxOriginal PushImage(With Parameters)

Gradient y(With Parameters)

Histogram(With Parameters)

Program 1

Program 2

New Program

Page 12: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 12

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

Page 13: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 13

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

Page 14: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 14

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

Page 15: Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided

CAMP | Department of Computer Science | Technische Universität München | 19 April 2023 15

Chair for Computer Aided Medical Procedures & Augmented Reality | wwwnavab.cs.tum.edu

Thank you for your attention!