Siamese Network-Based Few-Shot Learning for Classification of Human Peripheral Blood Leukocyte

Guo, Zijian; Liu, Li; Sun, Sanshan; Feng, Botao; Zhao, Xiaolan

doi:10.1109/iceict53123.2021.9531084

Cited by 3 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, there have been research teams using the Siamese network-based learning method for disease diagnosis. Guo et al [12] proposed a Siamese network model containing two identical CNN subnetworks for the classification of human peripheral blood leukocytes. The developed model classified eosinophil samples and basophil samples with an average accuracy of 89.66% on the Munich Morphology dataset of acute myelocytic leukemia.…”

Section: Literature Reviewmentioning

confidence: 99%

Convolutional Siamese network-based few-shot learning for monkeypox detection under data scarcity

Liu¹

2023

Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022)

View full text Add to dashboard Cite

Monkeypox is a rare zoonosis and has been recognized as a public health emergency of international concern by the World Health Organization (WHO). Clinically, monkeypox shares many similarities with smallpox and varicella. How to accurately diagnose monkeypox is a problem faced by medical staff. Since the discovery of monkeypox, related studies have been few and ignored for a long time. Research on monkeypox is limited by the lack of available data. In order to overcome the problem of sample scarcity, we propose a few-shot learning method based on the VGG16 Siamese network model, which aims to classify monkeypox and similar skin disease images with a small number of samples. The model contains two identical VGG16 subnetworks with shared weights for extracting feature vectors of input image pairs. The distance between feature vectors is measured to determine whether the input pair belongs to the same category. We validate our model on the Monkeypox Skin Lesions dataset (MSLD). The accuracy of monkeypox image classification reaches 90.32%, and the AUC reaches 90.60%. Our proposed model has the best performance among similar studies. This confirms the effectiveness of the few-shot learning method based on convolutional Siamese networks for image classification tasks when data is scarce. This method can be used to solve the problem of monkeypox detection and is expected to be extended to the diagnosis of other rare diseases.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Convolutional Siamese network-based few-shot learning for monkeypox detection under data scarcity

Liu¹

2023

Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022)

View full text Add to dashboard Cite

show abstract

“…Cross-validation was further used in each trial. Researchers from [26] suggested using the Siamese network to categorize WBC. Implementing the Siamese network framework, basophils and eosinophil cells were classified with an estimated accuracy of about 89.66%.…”

Section: Literature Reviewmentioning

confidence: 99%

An Intelligent Attention-Based Transfer Learning Model for Accurate Differentiation of Bone Marrow Stains to Diagnose Hematological Disorder

Alshahrani,

Sharma,

Anand

et al. 2023

Life

View full text Add to dashboard Cite

Bone marrow (BM) is an essential part of the hematopoietic system, which generates all of the body’s blood cells and maintains the body’s overall health and immune system. The classification of bone marrow cells is pivotal in both clinical and research settings because many hematological diseases, such as leukemia, myelodysplastic syndromes, and anemias, are diagnosed based on specific abnormalities in the number, type, or morphology of bone marrow cells. There is a requirement for developing a robust deep-learning algorithm to diagnose bone marrow cells to keep a close check on them. This study proposes a framework for categorizing bone marrow cells into seven classes. In the proposed framework, five transfer learning models—DenseNet121, EfficientNetB5, ResNet50, Xception, and MobileNetV2—are implemented into the bone marrow dataset to classify them into seven classes. The best-performing DenseNet121 model was fine-tuned by adding one batch-normalization layer, one dropout layer, and two dense layers. The proposed fine-tuned DenseNet121 model was optimized using several optimizers, such as AdaGrad, AdaDelta, Adamax, RMSprop, and SGD, along with different batch sizes of 16, 32, 64, and 128. The fine-tuned DenseNet121 model was integrated with an attention mechanism to improve its performance by allowing the model to focus on the most relevant features or regions of the image, which can be particularly beneficial in medical imaging, where certain regions might have critical diagnostic information. The proposed fine-tuned and integrated DenseNet121 achieved the highest accuracy, with a training success rate of 99.97% and a testing success rate of 97.01%. The key hyperparameters, such as batch size, number of epochs, and different optimizers, were all considered for optimizing these pre-trained models to select the best model. This study will help in medical research to effectively classify the BM cells to prevent diseases like leukemia.

show abstract

“…The subject of leukemia classification was researched thoroughly using deep learning methods. The authors of [ 20 , 21 , 22 , 23 , 24 ] applied various types of convolutional neural networks (CNNs) [ 25 ]. In [ 20 ], Rehman et al applied the AlexNet [ 26 ] architecture of CNN networks for leukemia classification, achieving 97.78% accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…They achieved classification with 81% accuracy. The authors of [ 23 ] (Guo et al) used Siamese networks [ 29 ] to achieve few-shot learning [ 30 ] with 89.96% accuracy. Similar research was conducted by Abhishek et al [ 24 ].…”

Section: Introductionmentioning

confidence: 99%

“…The results of leukemia classification using deep learning in [ 20 , 21 , 22 , 23 ] (Rehman et al, Prellberg et al, Ahmed et al, Guo et al, Abhishek et al, and Rodrigues et al) provided substantial accuracy for healthy vs. sick discrimination. However, due to the black box nature of deep learning methods, it is unclear what pattern was extracted by neural networks to achieve such efficiency.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Entropy Measurements for Leukocytes’ Surrounding Informativeness Evaluation for Acute Lymphoblastic Leukemia Classification

Pałczyński

Ledziński

Andrysiak

2022

Entropy

View full text Add to dashboard Cite

The study of leukemia classification using deep learning techniques has been conducted by multiple research teams worldwide. Although deep convolutional neural networks achieved high quality of sick vs. healthy patient discrimination, their inherent lack of human interpretability of the decision-making process hinders the adoption of deep learning techniques in medicine. Research involving deep learning proved that distinguishing between healthy and sick patients using microscopic images of lymphocytes is possible. However, it could not provide information on the intermediate steps in the diagnosis process. As a result, despite numerous examinations, it is still unclear whether the lymphocyte is the only object in the microscopic picture containing leukemia-related information or if the leukocyte’s surroundings also contain the desired information. In this work, entropy measures and machine learning models were applied to study the informativeness of both whole images and lymphocytes’ surroundings alone for Leukemia classification. This work aims to provide human-interpretable features marking the probability of sickness occurrence. The research stated that the hue distribution of images with lymphocytes obfuscated alone is informative enough to facilitate 93.0% accuracy in healthy vs. sick classification. The research was conducted on the ALL-IDB2 dataset.

show abstract

Siamese Network-Based Few-Shot Learning for Classification of Human Peripheral Blood Leukocyte

Cited by 3 publications

References 9 publications

Convolutional Siamese network-based few-shot learning for monkeypox detection under data scarcity

Convolutional Siamese network-based few-shot learning for monkeypox detection under data scarcity

An Intelligent Attention-Based Transfer Learning Model for Accurate Differentiation of Bone Marrow Stains to Diagnose Hematological Disorder

Entropy Measurements for Leukocytes’ Surrounding Informativeness Evaluation for Acute Lymphoblastic Leukemia Classification

Contact Info

Product

Resources

About