SlideShare a Scribd company logo
1 of 77
Tracking Colliding Cells  Nhat ‘Rich’ Nguyen Committee Members: Min Shin, PhD,  Richard Souvenir, PhD, and  Toan Huynh, MD
White Blood Cells “The little warriors of your body” ,[object Object]
Lookout for signs of diseaseMicroscopic scale: 7,000 to 25,000 in a drop of blood 2
Flowing Rolling Adhering  Motion Behaviors 3 Microscopy Video of white blood cells
Biologists learn cell behaviors by tracking a few cells 4
Manual Automatic Tedious Little Effort Expensive Inexpensive Subjective Objective 5
Previous Automatic Methods Ray et al. [2002] Active Contour Cui et al. [2005] Monte Carlo Mukherjee et al. [2004] Level Set Analysis 6
Previous Automatic Methods Eden et al. [2005] SmoothnessConstraints Li et al. [2005] Lineage Construction Smith et al. [2008] Probabilistic Formalization 7
Qualitative Comparison 8
Challenges As many cells move at  a wide range of speed Collisions! 9
Challenges In a collision, cell motion and appearance 1. could be different 2. change abruptly 10
Example  Eden et al. [2005] broken tracks robust tracks Our Method 11
Approach  To improve tracking accuracy of colliding cells by: having separate collision states to describe cells inside and outside of collisions testing multiple hypotheses of cell motion and appearance as transitions between abrupt motion patterns. 12
Cell Detection  Classify each pixel in the image as a Cell or Background 13
Detection Problems 14 Variation in cell appearances within an image time Varied appearance of a cell over time
AdaBoost 15 Idea: combine many “rules of thumb” to a highly accurate prediction rule. Input: visual features from training samples. Schema: maintain a strategy to determine “rules of thumb” using weight distribution. Output: a single strong classifier which is a linear combination of the set of weak classifiers.
Training 100 Cell Samples 100 Background Samples Features Mean Intensity Standard Dev. of Intensity Radial Mean  Decision Rules on feature scores 16
Detection Procedure  Scan each pixel p in the image Compute image feature vector V from a  window centered around p Classify p as a Cell pixel if the feature score in V  satisfies the learned decision rule; otherwise classify p as a Background pixel. Cluster groups of Cell pixels into cell observation. 17
Cell Tracking 1. Predict using multiple hypotheses 2. Correspond predictions and measurements 3. Update based on the current state 18
Kalman Filter 19 Extensively used for tracking. Estimator of the state that is optimal. Consist of two steps: ,[object Object]
Correct: incorporates a new measurement into a priori estimate to obtain an improved posteriori estimate.,[object Object]
Motion and Appearance Model 21 Collision States: State Transition: Hypotheses: to predict the state in the next frame control input vector State Vector*: Motion and Appearance Models:  (for        ) state transition matrix control input matrix process noise vector  ~N(0,Qs) Observation Vector:
22
23 Tracking Steps 3 1 2 4
24 Tracking Steps 3 1 2 4
25 Tracking Steps 3 1 2 4
26 Tracking Steps 3 1 2 4
27 Tracking Steps 3 1 2 4
28 Tracking Steps 3 1 correspond to H01 no measurement 2 4 correspond to H00 no prediction
29 Tracking Steps 3 1 colliding cells lost cell 2 4 5 non-colliding cell new cell
30 Tracking Steps 3 keep moving stay colliding 1 4 split away 2 5 keep moving start moving
31
Data 8 300 ~6k image sequences cells tracks  cell positions 32
Colliding vs. Non-colliding 33 112 188 colliding cells non-colliding cells
Evaluating Methods 34 Smoothness Constraints (SC) Single Hypothesis (SH) Multiple Hypotheses (MH)
Detection Performance 35 Recall :  TP / (TP + FN) 75% Precision: TP / (TP + FP) 77%
Tracking Performance 36 RMSE : Root mean squared errors of position (pixel) -0.03 -0.17 +0.36 -0.21 +0.33 -0.20 SH introduces additional error in positions. MH does not introduce any additional error. Estimating colliding cells’ positions is more difficult.
Tracking Performance 37 PTP: Percentage of Tracked Positions (%) +27 +9 +23 +3 +4 +24 +28 Large improvement in colliding positions. Improvement overall. Tracking colliding cells is more difficult.
Comparisons MH  SC  SH 38
Discussions  39  The effect of collision duration on tracking 6 112 Exclude SC from being considered for collision. Classify colliding positions into bins based on the number of frames of the collision. colliding cells bins  of collision duration
Discussions  40  The effect of collision duration on RMSE
Discussions  41  The effect of collision duration on PTP
Discussions  42  The impact of detection on tracking 38 596 Data with good detection results before and after collision (+/- 2 frames) cell positions treated colliding cells
Discussions  43  The impact of detection on RMSE -0.17 -0.13 -1.05 -1.09 Different improvement between dataset. Different improvement between methods.
Discussions  44  The impact of detection on PTP +9 +7 +16 +18 Large improvement between dataset. Large different between methods. MH achieves high performance in tracking.
Results Region B Our Method 45
Future Work 1. Add more features to improve detection. 46 5 7 6 8
Future Work 2. Incorporate a probabilistic approach to transition between collision states. 47 72 73 75 76
Future Work 3. Expand to track cells with more complex motions and behaviors. 48 49 50 51 52
Conclusion 49 A method for tracking colliding cells. Incorporate Kalman filter and multiple hypotheses for each collision state. Improve 28%in tracked position coverage compared to a previous work . Achieve 88% in tracked position coverage in tracking colliding cells.
Questions/Comments 50
S. J. Schmugge, S. Keller, N. Nguyen, R. Souvenir, T. H. Huynh, M. Clemens, M. C. Shin. "Segmentation of Vessels Cluttered with Cells using a Physics based Model". 11th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), New York, September 6-10 2008. N. Nguyen, S. Keller, T. Huynh, M. Shin. “Tracking Colliding Cells”. IEEE Workshop on Applications of Computer Vision (WACV), Snowbird, UT December 07-09 2009. to be submitted to IEEE Transactions on Medical Imaging N. Nguyen, S. Keller, Eric Norris, T. Huynh, M. Shin. “Tracking Colliding Cells in Intravital Microscopy Images”.  Related Publications 51
More Results 52 Eden et al. [2005] Our Method
53 Tracking Steps Predict motion Predict collision Get measurements Get errors in position & area  Match with minimal error
Collision States: Hypotheses: to predict the state in the next frame control input vector State Vector*: Motion and Appearance Models:  (for        ) state transition matrix control input matrix process noise vector  ~N(0,Qs) Observation Vector: Measurement Model: measurement noise vector ~N(0,R) measurement  transition matrix 54
State Vector of cell i : Predicted State Vector: Zero Matrix Zero Matrix Zero Vector Zero Vector Predicted Covariance: 55
z1 x’1a Calculate error between  all possible pairs  Sm & On Criteria: Position & Area. Assign pairs via Greedy Search HФ 2. Correspondence X1 x’1b HФ Cell Detector z2 x'2a HФ X2 HФ x’2b z3 x’3a HФ X3 HФ x’3b zn X1 x’ka HФ z1 x’1a Xk HФ x’kb X2 x’2b z3 Cell 3 is missing x’3a X3 New cell has entered z2 X4 Ck zn x’kb 56
Predicted State Vector: Hypothesized Measurement Vector: measurement  transition matrix Error of hypothesis       : observation from  the detector weight vector Rule 1: Rule 2: error threshold of  Unlikely (i, k) pair Stop corresponding condition: 57
Remaining Observation          : new cell leukocyte typical diameter area Remaining Cell       : Not corresponded for 3 frames: Updated State Vector : Kalman gain Updated Covariance: depends on the cell  current state s  ,[object Object],abrupt change in collision 58
59 II. AdaBoost1. Adaptive Boosting method Robert Schapire algorithm (1996). Idea: Combine many “rules of thumb”  a highly accurate prediction rule. Maintain a strategy to determine “rules of thumb”  weight. Terms: Learner = Hypothesis = Classifier. Weak Learner: <50% error rate. Strong Learner: linear combination of weak learner.
60 II. AdaBoost2. An Example of Boosting Plastic Apple Real Apple
61 II. AdaBoost3. Features Space Weight Color
62 II. AdaBoost4. 1st Iteration Wrong guess Wrong guess Weak Learner  Optimal Guessing line
63 II. AdaBoost5. 1st Reweight Wrong guess Gets larger Get smaller Right guess Gets smaller
64 II. AdaBoost6. 2nd Iteration More weighted ones get classify correctly Wrong guess Wrong guess
65 II. AdaBoost7. 2nd Reweight smaller Wrong guess Gets larger smaller Right guess Gets smaller
66 II. AdaBoost8. 3rd Iteration
67 II. AdaBoost9. 4th Iteration
68 II. AdaBoost10. Combination 3rd 2nd 1st 4th
69 II. AdaBoost11. Decision Plastic Apple Region Decision Boundary Real Apple Region
70 Tracking Steps
71 Tracking Steps
72
73
Tracking Performance 74 +.24 +.04 +.23 +.03 +.23 +.09 +.21 +.18
Discussions  75  The impact of detection on PTP +7 +16 +11 Large improvement between dataset. Large different between methods. MH achieves high performance in tracking.
Training 100 Cell Samples 100 Background Samples Features Mean Intensity Standard Dev. of Intensity Radial Mean  Decision Rules on feature scores 76

More Related Content

Similar to Wbc master thesisdefense

interconnected powersystem
interconnected powersysteminterconnected powersystem
interconnected powersystemDivyang soni
 
Dependency patterns for latent variable discovery
Dependency patterns for latent variable discovery Dependency patterns for latent variable discovery
Dependency patterns for latent variable discovery Bayesian Intelligence
 
IFAC2008art
IFAC2008artIFAC2008art
IFAC2008artYuri Kim
 
Wcdma rno parameters optimization
Wcdma rno parameters optimization Wcdma rno parameters optimization
Wcdma rno parameters optimization Akaninyene Uko III
 
Prediction Of Bioactivity From Chemical Structure
Prediction Of Bioactivity From Chemical StructurePrediction Of Bioactivity From Chemical Structure
Prediction Of Bioactivity From Chemical StructureJeremy Besnard
 
A temporal classifier system using spiking neural networks
A temporal classifier system using spiking neural networksA temporal classifier system using spiking neural networks
A temporal classifier system using spiking neural networksDaniele Loiacono
 
Dr. Thomas Yankeelov: Integrating Advanced Imaging and Biophysical Models to...
Dr. Thomas Yankeelov:  Integrating Advanced Imaging and Biophysical Models to...Dr. Thomas Yankeelov:  Integrating Advanced Imaging and Biophysical Models to...
Dr. Thomas Yankeelov: Integrating Advanced Imaging and Biophysical Models to...Dawn Yankeelov
 
clustering tendency
clustering tendencyclustering tendency
clustering tendencyAmir Shokri
 
Experimental one-way
Experimental one-wayExperimental one-way
Experimental one-wayCAA Sudan
 
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...ijccmsjournal
 
Computational Complexity Comparison Of Multi-Sensor Single Target Data Fusion...
Computational Complexity Comparison Of Multi-Sensor Single Target Data Fusion...Computational Complexity Comparison Of Multi-Sensor Single Target Data Fusion...
Computational Complexity Comparison Of Multi-Sensor Single Target Data Fusion...ijccmsjournal
 
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...ijccmsjournal
 
Measuring of migration of a fully automated imaging based approach
Measuring of migration of a fully automated imaging based approachMeasuring of migration of a fully automated imaging based approach
Measuring of migration of a fully automated imaging based approachPerkinElmer, Inc.
 
Regression vs Neural Net
Regression vs Neural NetRegression vs Neural Net
Regression vs Neural NetRatul Alahy
 
Breaking the 49 qubit barrier in the simulation of quantum circuits
Breaking the 49 qubit barrier in the simulation of quantum circuitsBreaking the 49 qubit barrier in the simulation of quantum circuits
Breaking the 49 qubit barrier in the simulation of quantum circuitshquynh
 

Similar to Wbc master thesisdefense (20)

interconnected powersystem
interconnected powersysteminterconnected powersystem
interconnected powersystem
 
Dependency patterns for latent variable discovery
Dependency patterns for latent variable discovery Dependency patterns for latent variable discovery
Dependency patterns for latent variable discovery
 
IFAC2008art
IFAC2008artIFAC2008art
IFAC2008art
 
Wcdma rno parameters optimization
Wcdma rno parameters optimization Wcdma rno parameters optimization
Wcdma rno parameters optimization
 
Prediction Of Bioactivity From Chemical Structure
Prediction Of Bioactivity From Chemical StructurePrediction Of Bioactivity From Chemical Structure
Prediction Of Bioactivity From Chemical Structure
 
A temporal classifier system using spiking neural networks
A temporal classifier system using spiking neural networksA temporal classifier system using spiking neural networks
A temporal classifier system using spiking neural networks
 
Nanotechnology in Cancer - Dr. Cote
Nanotechnology in Cancer - Dr. CoteNanotechnology in Cancer - Dr. Cote
Nanotechnology in Cancer - Dr. Cote
 
Dr. Thomas Yankeelov: Integrating Advanced Imaging and Biophysical Models to...
Dr. Thomas Yankeelov:  Integrating Advanced Imaging and Biophysical Models to...Dr. Thomas Yankeelov:  Integrating Advanced Imaging and Biophysical Models to...
Dr. Thomas Yankeelov: Integrating Advanced Imaging and Biophysical Models to...
 
Doutorado.Slides v5 - Rubens
Doutorado.Slides v5 - RubensDoutorado.Slides v5 - Rubens
Doutorado.Slides v5 - Rubens
 
Quantum computing meghaditya
Quantum computing meghadityaQuantum computing meghaditya
Quantum computing meghaditya
 
clustering tendency
clustering tendencyclustering tendency
clustering tendency
 
Chi square test
Chi square testChi square test
Chi square test
 
Chapter 15
Chapter 15 Chapter 15
Chapter 15
 
Experimental one-way
Experimental one-wayExperimental one-way
Experimental one-way
 
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
 
Computational Complexity Comparison Of Multi-Sensor Single Target Data Fusion...
Computational Complexity Comparison Of Multi-Sensor Single Target Data Fusion...Computational Complexity Comparison Of Multi-Sensor Single Target Data Fusion...
Computational Complexity Comparison Of Multi-Sensor Single Target Data Fusion...
 
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
COMPUTATIONAL COMPLEXITY COMPARISON OF MULTI-SENSOR SINGLE TARGET DATA FUSION...
 
Measuring of migration of a fully automated imaging based approach
Measuring of migration of a fully automated imaging based approachMeasuring of migration of a fully automated imaging based approach
Measuring of migration of a fully automated imaging based approach
 
Regression vs Neural Net
Regression vs Neural NetRegression vs Neural Net
Regression vs Neural Net
 
Breaking the 49 qubit barrier in the simulation of quantum circuits
Breaking the 49 qubit barrier in the simulation of quantum circuitsBreaking the 49 qubit barrier in the simulation of quantum circuits
Breaking the 49 qubit barrier in the simulation of quantum circuits
 

Recently uploaded

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesBoston Institute of Analytics
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfhans926745
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessPixlogix Infotech
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 

Recently uploaded (20)

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 

Wbc master thesisdefense

  • 1. Tracking Colliding Cells Nhat ‘Rich’ Nguyen Committee Members: Min Shin, PhD, Richard Souvenir, PhD, and Toan Huynh, MD
  • 2.
  • 3. Lookout for signs of diseaseMicroscopic scale: 7,000 to 25,000 in a drop of blood 2
  • 4. Flowing Rolling Adhering Motion Behaviors 3 Microscopy Video of white blood cells
  • 5. Biologists learn cell behaviors by tracking a few cells 4
  • 6. Manual Automatic Tedious Little Effort Expensive Inexpensive Subjective Objective 5
  • 7. Previous Automatic Methods Ray et al. [2002] Active Contour Cui et al. [2005] Monte Carlo Mukherjee et al. [2004] Level Set Analysis 6
  • 8. Previous Automatic Methods Eden et al. [2005] SmoothnessConstraints Li et al. [2005] Lineage Construction Smith et al. [2008] Probabilistic Formalization 7
  • 10. Challenges As many cells move at a wide range of speed Collisions! 9
  • 11. Challenges In a collision, cell motion and appearance 1. could be different 2. change abruptly 10
  • 12. Example Eden et al. [2005] broken tracks robust tracks Our Method 11
  • 13. Approach To improve tracking accuracy of colliding cells by: having separate collision states to describe cells inside and outside of collisions testing multiple hypotheses of cell motion and appearance as transitions between abrupt motion patterns. 12
  • 14. Cell Detection Classify each pixel in the image as a Cell or Background 13
  • 15. Detection Problems 14 Variation in cell appearances within an image time Varied appearance of a cell over time
  • 16. AdaBoost 15 Idea: combine many “rules of thumb” to a highly accurate prediction rule. Input: visual features from training samples. Schema: maintain a strategy to determine “rules of thumb” using weight distribution. Output: a single strong classifier which is a linear combination of the set of weak classifiers.
  • 17. Training 100 Cell Samples 100 Background Samples Features Mean Intensity Standard Dev. of Intensity Radial Mean  Decision Rules on feature scores 16
  • 18. Detection Procedure Scan each pixel p in the image Compute image feature vector V from a window centered around p Classify p as a Cell pixel if the feature score in V satisfies the learned decision rule; otherwise classify p as a Background pixel. Cluster groups of Cell pixels into cell observation. 17
  • 19. Cell Tracking 1. Predict using multiple hypotheses 2. Correspond predictions and measurements 3. Update based on the current state 18
  • 20.
  • 21.
  • 22. Motion and Appearance Model 21 Collision States: State Transition: Hypotheses: to predict the state in the next frame control input vector State Vector*: Motion and Appearance Models: (for ) state transition matrix control input matrix process noise vector ~N(0,Qs) Observation Vector:
  • 23. 22
  • 24. 23 Tracking Steps 3 1 2 4
  • 25. 24 Tracking Steps 3 1 2 4
  • 26. 25 Tracking Steps 3 1 2 4
  • 27. 26 Tracking Steps 3 1 2 4
  • 28. 27 Tracking Steps 3 1 2 4
  • 29. 28 Tracking Steps 3 1 correspond to H01 no measurement 2 4 correspond to H00 no prediction
  • 30. 29 Tracking Steps 3 1 colliding cells lost cell 2 4 5 non-colliding cell new cell
  • 31. 30 Tracking Steps 3 keep moving stay colliding 1 4 split away 2 5 keep moving start moving
  • 32. 31
  • 33. Data 8 300 ~6k image sequences cells tracks cell positions 32
  • 34. Colliding vs. Non-colliding 33 112 188 colliding cells non-colliding cells
  • 35. Evaluating Methods 34 Smoothness Constraints (SC) Single Hypothesis (SH) Multiple Hypotheses (MH)
  • 36. Detection Performance 35 Recall : TP / (TP + FN) 75% Precision: TP / (TP + FP) 77%
  • 37. Tracking Performance 36 RMSE : Root mean squared errors of position (pixel) -0.03 -0.17 +0.36 -0.21 +0.33 -0.20 SH introduces additional error in positions. MH does not introduce any additional error. Estimating colliding cells’ positions is more difficult.
  • 38. Tracking Performance 37 PTP: Percentage of Tracked Positions (%) +27 +9 +23 +3 +4 +24 +28 Large improvement in colliding positions. Improvement overall. Tracking colliding cells is more difficult.
  • 39. Comparisons MH SC SH 38
  • 40. Discussions 39 The effect of collision duration on tracking 6 112 Exclude SC from being considered for collision. Classify colliding positions into bins based on the number of frames of the collision. colliding cells bins of collision duration
  • 41. Discussions 40 The effect of collision duration on RMSE
  • 42. Discussions 41 The effect of collision duration on PTP
  • 43. Discussions 42 The impact of detection on tracking 38 596 Data with good detection results before and after collision (+/- 2 frames) cell positions treated colliding cells
  • 44. Discussions 43 The impact of detection on RMSE -0.17 -0.13 -1.05 -1.09 Different improvement between dataset. Different improvement between methods.
  • 45. Discussions 44 The impact of detection on PTP +9 +7 +16 +18 Large improvement between dataset. Large different between methods. MH achieves high performance in tracking.
  • 46. Results Region B Our Method 45
  • 47. Future Work 1. Add more features to improve detection. 46 5 7 6 8
  • 48. Future Work 2. Incorporate a probabilistic approach to transition between collision states. 47 72 73 75 76
  • 49. Future Work 3. Expand to track cells with more complex motions and behaviors. 48 49 50 51 52
  • 50. Conclusion 49 A method for tracking colliding cells. Incorporate Kalman filter and multiple hypotheses for each collision state. Improve 28%in tracked position coverage compared to a previous work . Achieve 88% in tracked position coverage in tracking colliding cells.
  • 52. S. J. Schmugge, S. Keller, N. Nguyen, R. Souvenir, T. H. Huynh, M. Clemens, M. C. Shin. "Segmentation of Vessels Cluttered with Cells using a Physics based Model". 11th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), New York, September 6-10 2008. N. Nguyen, S. Keller, T. Huynh, M. Shin. “Tracking Colliding Cells”. IEEE Workshop on Applications of Computer Vision (WACV), Snowbird, UT December 07-09 2009. to be submitted to IEEE Transactions on Medical Imaging N. Nguyen, S. Keller, Eric Norris, T. Huynh, M. Shin. “Tracking Colliding Cells in Intravital Microscopy Images”. Related Publications 51
  • 53. More Results 52 Eden et al. [2005] Our Method
  • 54. 53 Tracking Steps Predict motion Predict collision Get measurements Get errors in position & area Match with minimal error
  • 55. Collision States: Hypotheses: to predict the state in the next frame control input vector State Vector*: Motion and Appearance Models: (for ) state transition matrix control input matrix process noise vector ~N(0,Qs) Observation Vector: Measurement Model: measurement noise vector ~N(0,R) measurement transition matrix 54
  • 56. State Vector of cell i : Predicted State Vector: Zero Matrix Zero Matrix Zero Vector Zero Vector Predicted Covariance: 55
  • 57. z1 x’1a Calculate error between all possible pairs Sm & On Criteria: Position & Area. Assign pairs via Greedy Search HФ 2. Correspondence X1 x’1b HФ Cell Detector z2 x'2a HФ X2 HФ x’2b z3 x’3a HФ X3 HФ x’3b zn X1 x’ka HФ z1 x’1a Xk HФ x’kb X2 x’2b z3 Cell 3 is missing x’3a X3 New cell has entered z2 X4 Ck zn x’kb 56
  • 58. Predicted State Vector: Hypothesized Measurement Vector: measurement transition matrix Error of hypothesis : observation from the detector weight vector Rule 1: Rule 2: error threshold of Unlikely (i, k) pair Stop corresponding condition: 57
  • 59.
  • 60. 59 II. AdaBoost1. Adaptive Boosting method Robert Schapire algorithm (1996). Idea: Combine many “rules of thumb”  a highly accurate prediction rule. Maintain a strategy to determine “rules of thumb”  weight. Terms: Learner = Hypothesis = Classifier. Weak Learner: <50% error rate. Strong Learner: linear combination of weak learner.
  • 61. 60 II. AdaBoost2. An Example of Boosting Plastic Apple Real Apple
  • 62. 61 II. AdaBoost3. Features Space Weight Color
  • 63. 62 II. AdaBoost4. 1st Iteration Wrong guess Wrong guess Weak Learner Optimal Guessing line
  • 64. 63 II. AdaBoost5. 1st Reweight Wrong guess Gets larger Get smaller Right guess Gets smaller
  • 65. 64 II. AdaBoost6. 2nd Iteration More weighted ones get classify correctly Wrong guess Wrong guess
  • 66. 65 II. AdaBoost7. 2nd Reweight smaller Wrong guess Gets larger smaller Right guess Gets smaller
  • 67. 66 II. AdaBoost8. 3rd Iteration
  • 68. 67 II. AdaBoost9. 4th Iteration
  • 69. 68 II. AdaBoost10. Combination 3rd 2nd 1st 4th
  • 70. 69 II. AdaBoost11. Decision Plastic Apple Region Decision Boundary Real Apple Region
  • 73. 72
  • 74. 73
  • 75. Tracking Performance 74 +.24 +.04 +.23 +.03 +.23 +.09 +.21 +.18
  • 76. Discussions 75 The impact of detection on PTP +7 +16 +11 Large improvement between dataset. Large different between methods. MH achieves high performance in tracking.
  • 77. Training 100 Cell Samples 100 Background Samples Features Mean Intensity Standard Dev. of Intensity Radial Mean  Decision Rules on feature scores 76
  • 78. 77

Editor's Notes

  1. Asjfl;ogp;ernjvlsdmawrkl;fgjndflefopghw.l/vgiowejgiopwer;’kbmjkserlfmk