Applications of Computational Intelligence to Medicine and Health - - PowerPoint PPT Presentation

▶
applications of computational intelligence to medicine
SMART_READER_LITE
LIVE PREVIEW

Applications of Computational Intelligence to Medicine and Health - - PowerPoint PPT Presentation

Aug 26, 2023 153 likes •655 views

Applications of Computational Intelligence to Medicine and Health Manuel Graa Computational Intelligence Group UPV/EHU InMed 2013, Piraeus, Greece, 19 July 1 Contents Motivation and main lines Brain Image biomarkers Vessel Image

slide-1
SLIDE 1

Applications of Computational Intelligence to Medicine and Health Manuel Graña Computational Intelligence Group UPV/EHU

1 InMed 2013, Piraeus, Greece, 19 July

slide-2
SLIDE 2

Contents

  • Motivation and main lines
  • Brain Image biomarkers
  • Vessel Image segmentation
  • Clinical Decision Systems
  • Future directions

InMed 2013, Piraeus, Greece, 19 July 2

slide-3
SLIDE 3

Motivation

  • Computational Intelligence

– Classification – Optimization – Reasoning (fuzzy, etc)

  • Main application

– Computer Assisted Diagnosis – Signal/Image processing

  • Interactive/assisted segmentation
  • Biomarkers

InMed 2013, Piraeus, Greece, 19 July 3

slide-4
SLIDE 4

Motivation

  • Biomarkers

– Signal features – Locations in image/anatomical space – Biomedical meaning

  • Agreement with medical expertise

– Classification accuracy

  • Predictive validation

InMed 2013, Piraeus, Greece, 19 July 4

slide-5
SLIDE 5

Motivation

  • Computer Assisted Diagnosis

– Classification/regression

  • Based on signal/image

– Speeding processing of huge amounts of data – Auxiliary tool – Multiple type evidences

  • Ontology based Reasoning

InMed 2013, Piraeus, Greece, 19 July 5

slide-6
SLIDE 6

Motivation

  • Interactive segmentation

– High variability

  • Data imaging
  • Biological structures

– Aids to manual segmentation

  • Active learning

– Automated segmentation

  • Filtering + classification

InMed 2013, Piraeus, Greece, 19 July 6

slide-7
SLIDE 7

Main work lines

  • Brain image processing (MRI) CAD

– Alzheimer disease

  • Public data: OASIS
  • Private data: Hospital Santiago, Vitoria

– Bipolar disorder

  • Private data: Hospital Santiago, Vitoria

– Schizophrenia

  • Private data

– Cocaine addiction

  • (UJI group Neuroimage)

InMed 2013, Piraeus, Greece, 19 July 7

slide-8
SLIDE 8

Main work lines

  • Vessel image segmentation

– Abdominal Aortic Aneuryms

  • Private data (Biodonostia, Vicomtech-IK4)

– Retinal image segmentation

  • Public data

InMed 2013, Piraeus, Greece, 19 July 8

slide-9
SLIDE 9

Main Lines

  • Breast-cancer

– Ontology-based clinical decision systems – Multi-source modality information – Vicomtech-IK4, projects MIND, LIFE

InMed 2013, Piraeus, Greece, 19 July 9

slide-10
SLIDE 10

Contents

  • Motivation and main lines
  • Brain Image biomarkers
  • Vessel Image segmentation
  • Clinical Decision Systems
  • Future directions

InMed 2013, Piraeus, Greece, 19 July 10

slide-11
SLIDE 11

Brain image biomarkers

  • MRI imaging modalities

– Anatomical, diffusion, functional

  • Classification approach

– Feature selection

  • Significant voxel sites

– Classification validation experiments

  • Discriminant / predictive value of features

– Visualization and biomedical interpretation

  • Atlas localization

InMed 2013, Piraeus, Greece, 19 July 11

slide-12
SLIDE 12

InMed 2013, Piraeus, Greece, 19 July 12

slide-13
SLIDE 13

InMed 2013, Piraeus, Greece, 19 July 13

slide-14
SLIDE 14

InMed 2013, Piraeus, Greece, 19 July 14

slide-15
SLIDE 15
  • OASIS reduced database

InMed 2013, Piraeus, Greece, 19 July 15

slide-16
SLIDE 16

InMed 2013, Piraeus, Greece, 19 July 16

VBM cluster localizations for feature extraction

A Savio; MT Garcia-Sebastian; D Chyzhyk; C Hernandez; M Graña; A Sistiaga; A Lopez de Munain; J Villanua Neurocognitive disorder detection based on Feature Vectors extracted from VBM analysis of structural MRI Computers in Biology and Medicine 41 (2011), pp. 600-610

slide-17
SLIDE 17

InMed 2013, Piraeus, Greece, 19 July 17 Maite Termenon, Manuel Graña A two stage sequential ensemble applied to the classification of Alzheimer's Disease based on MRI features Neural Processing Letters (2012) 35(1): 1-12 Darya Chyzhyk, Manuel Graña, Alexandre Savio, Josu Maiora Hybrid Dendritic Computing with Kernel-LICA applied to Alzheimer’s Disease detection in MRI. Neurocomputing, 2012, 75(1), pp. 72-77

slide-18
SLIDE 18

InMed 2013, Piraeus, Greece, 19 July 18

Deformation Based Feature Selection for Computer Aided Diagnosis of Alzheimer's Disease

  • A. Savio, M. Graña, Expert Systems with Applications, 2012
slide-19
SLIDE 19

InMed 2013, Piraeus, Greece, 19 July 19

Displacement norm Modulated GM Geodesic anysotropy Jacobian map

slide-20
SLIDE 20

Oasis database

InMed 2013, Piraeus, Greece, 19 July 20

slide-21
SLIDE 21

InMed 2013, Piraeus, Greece, 19 July 21

slide-22
SLIDE 22

InMed 2013, Piraeus, Greece, 19 July 22

Voxel sites 95% Pearson correlation on Jacobian maps Voxel sites 95% Pearson correlation on modulated GM

slide-23
SLIDE 23

Critical issues

  • Circularity

– Strict separation of feature selection and training from test in validation

  • Sample

– Imbalance – Small size

  • Leave one out
  • Biomedical meaning of findings

InMed 2013, Piraeus, Greece, 19 July 23

slide-24
SLIDE 24

Contents

  • Motivation and main lines
  • Brain Image biomarkers
  • Vessel Image segmentation
  • Clinical Decision Systems
  • Conclusions

InMed 2013, Piraeus, Greece, 19 July 24

slide-25
SLIDE 25

Vessel image segmentation

  • Wide variety of applications and image

modalities

  • Focus on Abdominal Aortic Aneurysm

– Monitoring of evolution of EVAR – Segmentation of thrombus

  • Filtering + machine learning
  • Interactive segmentation -- Active Learning

InMed 2013, Piraeus, Greece, 19 July 25

slide-26
SLIDE 26

InMed 2013, Piraeus, Greece, 19 July 26

Computerized Tomography Angiography (CTA) Magnetic Resonance Angiography (MRA)

slide-27
SLIDE 27

InMed 2013, Piraeus, Greece, 19 July 27

Angiographic Images Vascular Detection Vascular Extraction Vascular Model Vascular Quantification Clinical Applications Vascular image processing pipeline, from Ivan Macia’s PhD slides

slide-28
SLIDE 28

InMed 2013, Piraeus, Greece, 19 July 28 I Macia, M Graña; C Paloc,Knowledge Management in Image-based Analysis of Blood Vessel Structures Knowledge and Information Systems 30(2) (2012):457-491

Vessel Rep. Model Vessel Symb. Model (Disconnected) Angiographic Images Projected Symbolic Viz Vessel Segmented Volume Vessel Surface Model Symbolic Vessel Rendering File Branch Labelled Volume Measurements

Direct Extraction Lumen Segmentation Contour Sweeping Quantificatio n 2D Projection Vessel- Image Registration Tree Connection Accumulation Voxelization Storage Voxelization

slide-29
SLIDE 29

InMed 2013, Piraeus, Greece, 19 July 29

Abdominal Aortic Aneurysm

slide-30
SLIDE 30

InMed 2013, Piraeus, Greece, 19 July 30

RADIAL MODEL

AORTA LUMEN THROMBUS STENT GRAFT DIFFUSE BORDER CALCIFICATION (MIND YOUR DIET!)

θ r

I Macia; M Graña; J Maiora; C Paloc; M de Blas Detection of Type II Endoleaks in Abdominal Aortic Aneurysms After Endovascular Repair Computers in Biology and Medicine 41(10): 871-880

slide-31
SLIDE 31

InMed 2013, Piraeus, Greece, 19 July 31

!"#$%&''%()%*'+,-.% /012#,1%3-#142-%5-,1"2.%6"2%&''%*'+,-.%% &,1+7-%!-#28+89% :+1;%*+89'-%*'+,-% </0=-2+>-81?@%% &''%*'+,-.%('#..+6+,#1+"8% &,1+7-%!-#28+89% :+1;%&''%*'+,-.%% </0=-2+>-81A@%% (">=41-%3-#142-%B>="21#8,-% ()%5"'4>-%%C-8$-2+89%

Active learning experiments J Maiora’s PhD slides

slide-32
SLIDE 32

InMed 2013, Piraeus, Greece, 19 July 32

Active learning to build interactively classifiers for thrombus segmentation

slide-33
SLIDE 33

InMed 2013, Piraeus, Greece, 19 July 33

Josu Maiora; Borja Ayerdi; Manuel Graña Random Forest Active Learning for Computed Tomography Angiography Image Segmentation, Neurocomputing (in press)

Accuracy of segmentation and its uncertainty in the interactive enrichment of the training data set for

  • ne volume, per slice.
slide-34
SLIDE 34

InMed 2013, Piraeus, Greece, 19 July 34

slide-35
SLIDE 35

Contents

  • Motivation and main lines
  • Brain Image biomarkers
  • Vessel Image segmentation
  • Clinical Decision Systems
  • Future directions

InMed 2013, Piraeus, Greece, 19 July 35

slide-36
SLIDE 36

Clinical decision support

InMed 2013, Piraeus, Greece, 19 July 36

Bridging challenges of Clinical Decision Support Systems with a semantic approach. A case study on breast cancer. Eider Sanchez, Carlos Toro, Arkaitz Artetxe, Manuel Graña, Cesar Sanin, Edward Szczerbicki, Eduardo Carrasco and Frank Guijarro Pattern Recognition Letters, 2013, in press online first

slide-37
SLIDE 37

Clinical decision support

InMed 2013, Piraeus, Greece, 19 July 37

slide-38
SLIDE 38

InMed 2013, Piraeus, Greece, 19 July 38

Eider Sanchez, Carlos Toro, Arkaitz Artetxe, Manuel Graña, Cesar Sanin, Edward Szczerbicki, Eduardo Carrasco and Frank Guijarro Bridging challenges of Clinical Decision Support Systems with a semantic approach . A case study on breast cancer. Pattern Recognition Letters (in press,

  • nline)
slide-39
SLIDE 39

InMed 2013, Piraeus, Greece, 19 July 39

Breast cancer clinical process treatment ontology

slide-40
SLIDE 40

Reflexive ontologies

InMed 2013, Piraeus, Greece, 19 July 40

Toro, C., Sanín, C., Szczerbicki, E., Posada, J.: Reflexive Ontologies: Enhancing Ontologies with self-contained queries. In: Cybernetics and Systems: An International Journal 39, 171-189 (2008)

slide-41
SLIDE 41

Reflexive ontologies

InMed 2013, Piraeus, Greece, 19 July 41

827 1899 2539 2741 4150 6263 RuleSet 1 RuleSet 2 RuleSet 3 RO no-RO

Speed up obtained with Reflexive

  • ntologies
slide-42
SLIDE 42

Reflexive ontologies

InMed 2013, Piraeus, Greece, 19 July 42

Distribution of frequency of rule invocation per domain in MIND project,

Impact of Reflexive Ontologies in Semantic Clinical Decision Support Systems Arkaitz Artetxe, Eider Sanchez, Carlos Toro, Cesar Sanin, Edward Szczerbicki, Manuel Graña, Jorge Posada Cybernetics and Systems, 44(2-3), pp 187-203 , 2012

slide-43
SLIDE 43

Contents

  • Motivation and main lines
  • Brain Image biomarkers
  • Vessel Image segmentation
  • Clinical Decision Systems
  • Future directions

InMed 2013, Piraeus, Greece, 19 July 43

slide-44
SLIDE 44
  • ICT to the service of the health care

– Social Networks + Comp. Int.

  • Exchanging information
  • Creating/maintaining social intelligence

– (Serious) Games

  • Education
  • Training
  • Diffusion (viral)

InMed 2013, Piraeus, Greece, 19 July 44

slide-45
SLIDE 45

Social Networks

  • An unrelated instance: Social and Smart

– Household Appliance users – Exchange of appliance recipes – Underlying intelligent layer – Involvement of appliance manufacturers

InMed 2013, Piraeus, Greece, 19 July 45

slide-46
SLIDE 46

InMed 2013, Piraeus, Greece, 19 July 46

slide-47
SLIDE 47

InMed 2013, Piraeus, Greece, 19 July 47

slide-48
SLIDE 48

GIC team 2013

  • Alexandre Savio
  • Carlos Toro*
  • Maite Termenon
  • Eider Sanchez*
  • Borja Ayerdi
  • Ivan Macia*
  • Josu Maiora
  • Xabier Albizuri
  • Eloy Iriondo
  • Iñigo Barandiaran*
  • Darya Chyzhyk
  • Rosalia Dacosta
  • Ion Marques
  • David Nuñez
  • Borja Fernandez
  • Jose M. Lopez Guede
  • Ana I Gonzalez
  • Ekaitz Zulueta
  • Alicia d’Anjou
  • Israel Rebollo+

InMed 2013, Piraeus, Greece, 19 July 48

* Vicomtech-IK4,

+Informatica68, Unidad I+D+i

http://www.ehu.es/ccwintco/index.php/Miembros