Mahmudul Hasan . Asstt . Teacher East Senhati Govt primary School. Digholia , Khulna.
SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad...
Transcript of SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad...
![Page 1: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/1.jpg)
SVM Model for Blood Cell Classification usingInterpretable Features Outperforms CNN Based
Approaches
William Franz Lamberti 1
George Mason University
June 4, 2020
1MS Statistical SciencePhD Candidate Computational Sciences and Informatics
William Franz Lamberti 1
![Page 2: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/2.jpg)
Outline
IntroductionBlood Cell ClassificationCNNs
Goal
Data
ModelMetricsAlgorithmModel: Algorithm
ResultsConfusion TableClassification Rates
Conclusion
Acknowledgements
William Franz Lamberti 2
![Page 3: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/3.jpg)
Introduction: Blood Cell Classification
▸ Important task inHealth Sciences
▸ Counts are used tomeasure overallhealth of patient
▸ Often done by hand,which is tedious
William Franz Lamberti 3
![Page 4: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/4.jpg)
Introduction: CNNs
▸ Convolution NeuralNetworks (CNNs)very popular methodin Computer Vision
▸ Lots of differentapplications and verypowerful
▸ Difficult to interpretand explain
▸ Require a largeamount of data
Image from: Redmon, Joseph et al. “You Only Look Once: Unified, Real-TimeObject Detection.” arXiv.org (2016): n. pag. Web.
William Franz Lamberti 4
![Page 5: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/5.jpg)
Goal
▸ Build model that outperforms state of the art in classifyingobjects
▸ Use interpretable metrics
William Franz Lamberti 5
![Page 6: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/6.jpg)
Data
▸ Publicly available BBCDdataset:https://github.com/
Shenggan/BCCD_Dataset
▸ Classes▸ Red Blood Cells (RBCs):
4153▸ White Blood Cells
(WBCs): 372▸ Platelets:361
▸ Objects are extracted withgiven annotation file anduniversal segmentationoperators are applied
William Franz Lamberti 6
![Page 7: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/7.jpg)
Model: Metrics
m⃗q,i Metric
1 White EI2 Black EI3 SP value
4 1st Eigenvalue
5 2nd Eigenvalue6 Eccentricity
7 White Bounding Box Count8 Black Bounding Box Count
9 Circularity10 Number of Corners
William Franz Lamberti 7
![Page 8: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/8.jpg)
Model: Algorithm
▸ Split data into training(70%) and validation data(30%)▸ Training data = data
used to build the model▸ Validation data = data
never used to build themodel
▸ Perform 5-folds CV ontraining data to determineSVM Polynomial parameters
▸ Using learned parameters,build model on all oftraining data
▸ Evaluate model onvalidation data
Image from: An Introduction to Statistical Learning with Applications in R
William Franz Lamberti 8
![Page 9: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/9.jpg)
Results: Confusion Table
Predicted/Truth Platelet WBC RBC
Platelet 249 (106) 1 (1) 1 (6)WBC 0 (0) 93 (93) 6 (3)RBC 4 (2) 17 (17) 2901 (1236)
William Franz Lamberti 9
![Page 10: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/10.jpg)
Results: Classification Rates
Approach Platelet WBC RBC
SVM (Lamberti) 98.1% 83.8% 99.3%
Tiny YOLO 96.1% 86.9% 96.4%VGG-16 73.0% 100% 90.9%
ResNet50 79.8% 95.1% 87.3%
InceptionV3 87.8% 100% 96.4%MobileNet 74.2% 93.4% 83.6%
CNN approaches from: Mohammad Mahmudul Alam, and Mohammad TariqulIslam. “Machine Learning Approach of Automatic Identification and Countingof Blood Cells.” Healthcare Technology Letters 6.4 (2019)
William Franz Lamberti 10
![Page 11: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/11.jpg)
Conclusion
▸ SVM outperforms all other approaches▸ Overall Mean Outperformance: 5%▸ Underperforms for WBC
▸ Future Work▸ Develop segmentation technique without need for annotations▸ Improve classification▸ Develop for other applications such as COVID-19
▸ Code and Manuscript available▸ Code: https://github.com/billyl320/bccd_svm▸ Manuscript: https://github.com/billyl320/bccd_svm/
blob/master/Lamberti_SDSS_short_paper.pdf
William Franz Lamberti 11
![Page 12: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/12.jpg)
Acknowledgements
▸ Committee▸ Jason Kinser▸ William Kennedy▸ Michael Eagle▸ David Holmes
▸ Sounding Board▸ John Schuler
William Franz Lamberti 12
![Page 13: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/13.jpg)
Acknowledgements
▸ GMU, Office of the Provost
▸ 2020 SDSS Student and Early-Career Award
William Franz Lamberti 13
![Page 15: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/15.jpg)
Extra
William Franz Lamberti 15
![Page 16: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/16.jpg)
Metrics: SPEI
▸ Shape Proportion (SP)▸ Describe shape as a proportion
▸ Encircled Image-Histogram (EI)▸ Black and White pixel counts▸ Realization of SP
William Franz Lamberti 16
![Page 17: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/17.jpg)
Metrics: Eccentricity and Eigenvalues
▸ First Eigenvalue = Relativemeasure of major axis
▸ Second Eigenvalue = Relativemeasure of minor axis
▸ Eccentricity = ratio of first oversecond
▸ Ch. 18 of ”Image Operators:Image Processing in Python”,Kinser for more details
Image from: https://bit.ly/35FH8h5
William Franz Lamberti 17
![Page 18: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/18.jpg)
Metrics: Rectangularity
▸ Minimum bounding box (MBB)counts▸ Black and White picel counts▸ Jointly measure how similar
object is to a rectangle
Image from: ”Minimum Bounding Rectangle.” Encyclopedia of GeographicInformation Science, edited by Karen K. Kemp, SAGE Publications, 2008, pp.
286-287. Gale eBooks
William Franz Lamberti 18
![Page 19: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/19.jpg)
Metrics: Circularity
▸ Circularity = measure of how circular a shape is
▸ Has unique values for regular polygons and circles
▸ Based on area and perimeter
William Franz Lamberti 19
![Page 20: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/20.jpg)
Metrics: Number of Corners
▸ Finds the edges in the x and y direction
▸ Takes Gaussian smoothing kernel of both
▸ Create tensor image: A
▸ Obtain final image by: H = det(A) − k ∗ trace(A)2
William Franz Lamberti 20
![Page 21: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/21.jpg)
CNN Architecture
▸ Convolution Layers: ReLU Activation and l2-normregularization
▸ Pooling Layers: Batch size of 2 × 2 and max pooling
▸ Output Layer: Softmax operation
▸ Dropout Layer: 0.20
▸ Early stopping: Max of 100 epochs
J. Gu et al., “Recent advances in convolutional neural networks,” PatternRecognition, vol. 77, pp. 354–377, May 2018.
William Franz Lamberti 21
![Page 22: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/22.jpg)
CNN Results
William Franz Lamberti 22
![Page 23: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/23.jpg)
CNN Results
William Franz Lamberti 23
![Page 24: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/24.jpg)
CNN Results
William Franz Lamberti 24
![Page 25: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/25.jpg)
Pill Shapes - Examples
Class Counts
Triangle 12Quadrilateral 8
Pentagon 12Hexagon 8
Total 40
William Franz Lamberti 25
![Page 26: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/26.jpg)
Experiments: Pill Shapes - Results
William Franz Lamberti 26
![Page 27: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/27.jpg)
Experiments: Galaxy Shape - Examples
▸ Counts▸ Edge: 75▸ Spiral: 223▸ Ellipse: 225
William Franz Lamberti 27
![Page 28: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/28.jpg)
Experiments: Galaxy Shapes - Results
William Franz Lamberti 28
![Page 29: SVM Model for Blood Cell Classification using Interpretable ......CNN approaches from: Mohammad Mahmudul Alam, and Mohammad Tariqul Islam. \Machine Learning Approach of Automatic Identi](https://reader035.fdocuments.us/reader035/viewer/2022071117/6000ab31811bb903a7139a6d/html5/thumbnails/29.jpg)
Experiments: Galaxy Shapes - Results
William Franz Lamberti 29