Detection and Classification of Leukocytes in Leukemia using YOLOv2 with CNN

Abas, Shakir M.; Abdulazeez, Adnan Mohsin

doi:10.9734/ajrcos/2021/v8i330204

Cited by 11 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DarkNet53 is the backbone feature extraction network used by the target detection network YOLOv3 for extracting features with 8, 16, and 32-fold downsampling, respectively [25]. The network structure of DarkNet53 is shown in Figure 1, and this network model combines the deep residual network with DarkNet19, the feature extraction network used by YOLOv2 [26]. This network partly makes extensive use of 1 × 1 convolution and 3 × 3 convolution, where 1 × 1 is mainly applied to the expansion and reduction of channels.…”

Section: Darknet53 Convolutional Neural Networkmentioning

confidence: 99%

Hybrid Encrypted Watermarking Algorithm for Medical Images Based on DCT and Improved DarkNet53

Liu

Bhatti

et al. 2023

Electronics

View full text Add to dashboard Cite

To solve the problem of robustness of encrypted medical image watermarking algorithms, a zero watermarking algorithm based on the discrete cosine transform (DCT) and an improved DarkNet53 convolutional neural network is proposed. The algorithm targets medical images in the encrypted domain. In this algorithm, DCT is performed on the encrypted medical image to extract 32-bit features as feature 1. DarkNet53, a pre-trained network, was chosen for migration learning for the network model. The network uses a fully connected layer and a regression layer instead of the original Softmax layer and classification layer, changing the original classification network into a regression network with an output of 128. With these transformations, 128-bit features can be extracted from encrypted medical images by this network, and then DCT is performed to extract 32-bit features as feature 2. The fusion of features 1 and 2 can effectively improve the robustness of the algorithm. The experimental results show that the algorithm can accurately distinguish different encrypted medical images and can effectively restore the original information from the encrypted watermarked information under traditional and geometric attacks. Compared with other algorithms, the proposed method demonstrates better robustness and invisibility.

show abstract

Section: Darknet53 Convolutional Neural Networkmentioning

confidence: 99%

Hybrid Encrypted Watermarking Algorithm for Medical Images Based on DCT and Improved DarkNet53

Liu

Bhatti

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…The shape and the number of WBCs indicate that human has disease related to the blood such as Leukemia. One of the must importance studies is using deep learning algorithms to localize and classify blood cells [14]. However, the fast RCNN is used to object detection and classification.…”

Section: Related Workmentioning

confidence: 99%

Diagnosing the Leukemia using Faster Region based Convolutional Neural Network

ABAS¹

2022

JASTT

View full text Add to dashboard Cite

It is difficult to building deep learning algorithms for identifying chronic diseases. One of the must difficulties facing the system of diagnosing leukemia is the irregular shape and twisted nucleus in white blood cells (WBCs) without cleaning and segmentation of cells by Appling filters. Moreover, it is challenge to identify and classify the WBC at once time which is considered the essential step of leukemia diagnosing. This paper proposed system only based on deep learning algorithms. The modified Faster R-CNN (Faster Region based-Convolutional Neural Networks) algorithm is used to detect and classify WBCs. The system is achieved a high accuracy training on the database tacked directly from microscope which used in [4].

show abstract

“…It's the most common cancer in children, and it's caused by an overabundance of premature white blood cells in the bone marrow [29], as well as a long-term overabundance. It's difficult to tell the difference between flu and other common illnesses because they share symptoms like bone and joint fatigue, stiffness, and discomfort [5].…”

Section: Acute Lymphocytic Leukemia (All)mentioning

confidence: 99%

Leukemia Diagnosis using Machine Learning Classifiers Based on Correlation Attribute Eval Feature Selection

Armya

Abdulazeez

Sallow

et al. 2021

AJRCoS

View full text Add to dashboard Cite

Leukemia refers to a disease that affects the white blood cells (WBC) in the bone marrow and/or blood. Blood cell disorders are often detected in advanced stages as the number of cancer cells is much higher than the number of normal blood cells. Identifying malignant cells is critical for diagnosing leukemia and determining its progression. This paper used machine learning with classifiers to detect leukemia types as a result, it can save both patients and physicians time and money. The primary objective of this paper is to determine the most effective methods for leukemia detection. The WEKA application was used to evaluate and analyze five classifiers (J48, KNN, SVM, Random Forest, and Naïve Bayes classifiers). The results were respectively as follows: 83.33%, 87.5%, 95.83%, 88.88%, and 98.61%, with the Naïve Bayes classifier achieving the highest accuracy; however, accuracy varies according to the shape and size of the sample and the algorithm used to classify the leukemia types.

show abstract

Detection and Classification of Leukocytes in Leukemia using YOLOv2 with CNN

Cited by 11 publications

References 29 publications

Hybrid Encrypted Watermarking Algorithm for Medical Images Based on DCT and Improved DarkNet53

Hybrid Encrypted Watermarking Algorithm for Medical Images Based on DCT and Improved DarkNet53

Diagnosing the Leukemia using Faster Region based Convolutional Neural Network

Leukemia Diagnosis using Machine Learning Classifiers Based on Correlation Attribute Eval Feature Selection

Contact Info

Product

Resources

About