제주대학교 Repository

Few-Shot Image Generation and Novel Deep Learning Model for Enhancing Classification of Microscopic Single-Cell Images Obtained from Peripheral Blood Smears

Metadata Downloads
Abstract
The human body is composed of 1.2 to 1.5 gallons of blood which is approximately 7%-10%
of the weight of an adult. The blood constitutes of plasma and blood cells, and the ratio is 55% and
45%. The plasma in the blood is responsible for carrying proteins, hormones and nutrients that help
the blood clot and remove waste components from the human body. The blood cells in the body
carry oxygen to the tissues, fight infections and also helps blood to clot. An excessive amount of
blood cells or deficiency of blood cells can indicate various health problems like anaemia,
leukaemia, thalassemia, etc. The most common form of malignancy in kids is leukaemia which
represents 30% of all pediatric cancers. Classification of cells procured from bone marrow aspirate
smears and cell differential count is important for hematologic disease diagnosis. But the process
of classification and cell counting requires thorough manual intervention and is error-prone and
tedious. Machine learning and deep learning have successfully generated accurate and excellent
results in the medical domain, especially for automating the medical field's diagnosis proc ess. The
only drawback is the requirement of ample data and a balanced dataset to develop an efficient model.
The structure and pattern of data also play an important role in enhancing the performance of a
model.
In our research work, we take advantage of generative adversarial networks (GAN) and deep
learning models to enhance the classification of microscopic single-cell images obtained from
peripheral blood smears. To enhance classification, our primary goal was to balance and normalize
the dataset. We use GAN for three reason in our proposed work. First, we utilize GAN for stain
normalization. Second, we use GAN to generate synthetic images of blood cells that contained
more than thousand images but less than six thousand images, per cell type in the dataset. Third,
for cell types having less than hundred images we propose few-shot image generation based on
GAN architecture and meta-learning framework. We combine the original and the synthetic data
to form a balanced dataset. After stain normalization and image generation, we obtain a balanced
and normalized dataset which is used by the classification model. For classification, we proposed
a novel deep learning model, SENet-154-GE which uses the original data and the balanced dataset
individually to demonstrate how normalizing and balancing a dataset through proper models and
algorithms can enhance the performance of a classification model and improve the classification
accuracy.
For stain normalization, we have proposed a modified version of cycle consistency GAN
(CycleGAN). We have incorporated Wasserstein GAN with gradient penalty (WGAN-GP) for the
CycleGAN training and concentrated on the adversarial loss, cycle consistency loss and identity
loss for building our model. Also, for the generator, instead of an encoder, transformer, and
decoder network, we have used a U-Net architecture. For generating images of cell types with a
moderate number of images, we have built a three-network GAN architecture consisting of a
classifier, generator and discriminator. We named the model C-WGAN-GP since it’s a classifierbased GAN architecture which incorporates the loss function of WGAN-GP. For cell types with
very less images, we have proposed a meta learning based GAN framework that is trained on a
larger dataset and, through learning the parameters, can generate images with fewer examples. We
have incorporated the squeeze-and-excitation networks (SE) into the aggregated residual
transformations (ResNeXt) architecture. We have implemented SENet-154 model and combined
the gather excite model with SENet-154 for crucial and detailed feature extraction. We named the
novel deep learning classification model SENet-154-GE.
For evaluation, we have used various evaluation metrics such as structural similarity index
measurement (SSIM), Frechet inception distance (FID), and inception score (IS) for stain
normalization. FID, precision, recall, F1-score, SSIM, L1 and L2 error, IS and learned perceptual
image patch similarity (LPIPS) were used for evaluating C-WGAN-GP. We used FID, LPIPS and
IS for evaluating few-shot image generation. We assessed the performance of the SENet-154-GE
classification model through accuracy, specificity and sensitivity. We performed an ablation study
to demonstrate the importance of each module in our proposed work, and the results show that our
proposed approach can significantly enhance the performance of classifying microscopic singlecell images obtained from peripheral blood smears.|The human body is composed of 1.2 to 1.5 gallons of blood which is approximately 7%-10%
of the weight of an adult. The blood constitutes of plasma and blood cells, and the ratio is 55% and
45%. The plasma in the blood is responsible for carrying proteins, hormones and nutrients that help
the blood clot and remove waste components from the human body. The blood cells in the body
carry oxygen to the tissues, fight infections and also helps blood to clot. An excessive amount of
blood cells or deficiency of blood cells can indicate various health problems like anaemia,
leukaemia, thalassemia, etc. The most common form of malignancy in kids is leukaemia which
represents 30% of all pediatric cancers. Classification of cells procured from bone marrow aspirate
smears and cell differential count is important for hematologic disease diagnosis. But the process
of classification and cell counting requires thorough manual intervention and is error-prone and
tedious. Machine learning and deep learning have successfully generated accurate and excellent
results in the medical domain, especially for automating the medical field's diagnosis proc ess. The
only drawback is the requirement of ample data and a balanced dataset to develop an efficient model.
The structure and pattern of data also play an important role in enhancing the performance of a
model.
In our research work, we take advantage of generative adversarial networks (GAN) and deep
learning models to enhance the classification of microscopic single-cell images obtained from
peripheral blood smears. To enhance classification, our primary goal was to balance and normalize
the dataset. We use GAN for three reason in our proposed work. First, we utilize GAN for stain
normalization. Second, we use GAN to generate synthetic images of blood cells that contained
more than thousand images but less than six thousand images, per cell type in the dataset. Third,
for cell types having less than hundred images we propose few-shot image generation based on
GAN architecture and meta-learning framework. We combine the original and the synthetic data
to form a balanced dataset. After stain normalization and image generation, we obtain a balanced
and normalized dataset which is used by the classification model. For classification, we proposed
a novel deep learning model, SENet-154-GE which uses the original data and the balanced dataset
individually to demonstrate how normalizing and balancing a dataset through proper models and
algorithms can enhance the performance of a classification model and improve the classification
accuracy.
For stain normalization, we have proposed a modified version of cycle consistency GAN
(CycleGAN). We have incorporated Wasserstein GAN with gradient penalty (WGAN-GP) for the
CycleGAN training and concentrated on the adversarial loss, cycle consistency loss and identity
loss for building our model. Also, for the generator, instead of an encoder, transformer, and
decoder network, we have used a U-Net architecture. For generating images of cell types with a
moderate number of images, we have built a three-network GAN architecture consisting of a
classifier, generator and discriminator. We named the model C-WGAN-GP since it’s a classifierbased GAN architecture which incorporates the loss function of WGAN-GP. For cell types with
very less images, we have proposed a meta learning based GAN framework that is trained on a
larger dataset and, through learning the parameters, can generate images with fewer examples. We
have incorporated the squeeze-and-excitation networks (SE) into the aggregated residual
transformations (ResNeXt) architecture. We have implemented SENet-154 model and combined
the gather excite model with SENet-154 for crucial and detailed feature extraction. We named the
novel deep learning classification model SENet-154-GE.
For evaluation, we have used various evaluation metrics such as structural similarity index
measurement (SSIM), Frechet inception distance (FID), and inception score (IS) for stain
normalization. FID, precision, recall, F1-score, SSIM, L1 and L2 error, IS and learned perceptual
image patch similarity (LPIPS) were used for evaluating C-WGAN-GP. We used FID, LPIPS and
IS for evaluating few-shot image generation. We assessed the performance of the SENet-154-GE
classification model through accuracy, specificity and sensitivity. We performed an ablation study
to demonstrate the importance of each module in our proposed work, and the results show that our
proposed approach can significantly enhance the performance of classifying microscopic singlecell images obtained from peripheral blood smears.
Author(s)
Debapriya Hazra
Issued Date
2022
Awarded Date
2022-08
Type
Dissertation
URI
https://dcoll.jejunu.ac.kr/common/orgView/000000010901
Alternative Author(s)
하즈라 데바프리야
Affiliation
제주대학교 대학원
Department
대학원 컴퓨터공학과
Advisor
Byun, Yung-cheol
Table Of Contents
Abstract 1
Chapter 1: Introduction 4
Chapter 2: Literature Review 10
2.1 Generative Adversarial Networks (GAN) . 11
2.2 Stain Normalization 13
2.3 Few-Shot Learning 18
2.4 Few-Shot Image Generation 21
2.5 Medical Image Analysis and Classification 23
Chapter 3: Proposed Methodology for Enhancing Classification of Microscopic Single-Cell
Images. 26
3.1 Overview of the Proposed Methodology 27
3.2 Overview of the Datasets and Data Preprocessing Techniques 29
3.2.1 Data Preprocessing Techniques . 32
3.3 Foundations of the Proposed Methodology 36
3.3.1 Generative Adversarial Networks (GAN) 36
3.3.2 Few-Shot Learning and Meta Learning 42
3.4 Stain Normalization 48
3.5 Classifier Based Generative Adversarial Networks. 59
3.6 Few-Shot Image Generation 63
3.7 Novel Deep Learning Model for Classification. 70
Chapter 4: Experiments and Performance Analysis 77
4.1 Performance Analysis of Stain Normalization 77
4.2 Performance Analysis of Classifier-Based Generative Adversarial Networks 89
4.3 Evaluation of Few-Shot Image Generation. 93
4.4 Evaluation of SENet-154-GE Classification Model 98
Chapter 5: Conclusion and Discussion 105
References. 112
Degree
Doctor
Publisher
제주대학교 대학원
Appears in Collections:
General Graduate School > Computer Engineering
Authorize & License
  • AuthorizeOpen
  • Embargo2022-08-18
Files in This Item:

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.