Subimage Cosegmentation in a Single White Blood Cell Image

2015 ◽  
Author(s):  
Rong Chu ◽  
Xiaoqin Zeng ◽  
Lixin Han ◽  
Min Wang
Keyword(s):  
Blood Cell ◽  
White Blood Cell ◽  
Cell Image

White Blood Cells Classification with Deep Convolutional Neural Networks

2018 ◽  
Vol 32 (09) ◽  
pp. 1857006 ◽  
Author(s):  
Ming Jiang ◽  
Liu Cheng ◽  
Feiwei Qin ◽  
Lian Du ◽  
Min Zhang
Keyword(s):  
Blood Cell ◽  
White Blood Cell ◽  
Blood Cells ◽  
Network Architecture ◽  
White Blood Cells ◽  
Activation Function ◽  
Training Set ◽  
Deep Convolutional Neural Networks ◽  
Cell Image ◽  
Attending Physician

The necessary step in the diagnosis of leukemia by the attending physician is to classify the white blood cells in the bone marrow, which requires the attending physician to have a wealth of clinical experience. Now the deep learning is very suitable for the study of image recognition classification, and the effect is not good enough to directly use some famous convolution neural network (CNN) models, such as AlexNet model, GoogleNet model, and VGGFace model. In this paper, we construct a new CNN model called WBCNet model that can fully extract features of the microscopic white blood cell image by combining batch normalization algorithm, residual convolution architecture, and improved activation function. WBCNet model has 33 layers of network architecture, whose speed has greatly been improved compared with the traditional CNN model in training period, and it can quickly identify the category of white blood cell images. The accuracy rate is 77.65% for Top-1 and 98.65% for Top-5 on the training set, while 83% for Top-1 on the test set. This study can help doctors diagnose leukemia, and reduce misdiagnosis rate.

Interest-Based Ordering for Fuzzy Morphology on White Blood Cell Image Segmentation

2012 ◽  
Vol 16 (1) ◽  
pp. 76-86 ◽  
Author(s):  
Chastine Fatichah ◽  
◽  
Martin Leonard Tangel ◽  
Muhammad Rahmat Widyanto ◽  
Fangyan Dong ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Blood Cell ◽  
White Blood Cell ◽  
Cancer Diagnosis ◽  
Fuzzy Clustering ◽  
High Accuracy ◽  
Low Density ◽  
Fuzzy Morphology ◽  
Cell Image ◽  
Improve Accuracy

An Interest-based Ordering Scheme (IOS) for fuzzy morphology on White-Blood-Cell (WBC) image segmentation is proposed to improve accuracy of segmentation. The proposed method shows a high accuracy in segmenting both high- and low-density nuclei. Further, its running time is low, so it can be used for real applications. To evaluate the performance of the proposed method, 100 WBC images and 10 leukemia images are used, and the experimental results show that the proposed IOS segments a nucleus in WBC images 3.99% more accurately on average than the Lexicographical Ordering Scheme (LOS) does and 5.29% more accurately on average than the combined Fuzzy Clustering and Binary Morphology (FCBM) method does. The proposal method segments a cytoplasm 20.72% more accurately on average than the FCBM method. The WBC image segmentation is a part of WBC classification in an automatic cancer-diagnosis application that is being developed. In addition, the proposed method can be used to segment any images that focus on the important color of an object of interest.

scholarly journals Global and Adaptive Thresholding Technique for White Blood Cell Image Segmentation

2020 ◽  
Vol 1569 ◽  
pp. 022054
Author(s):  
Eka Prakarsa Mandyartha ◽  
Fetty Tri Anggraeny ◽  
Faisal Muttaqin ◽  
Fawwaz Ali Akbar
Keyword(s):  
Image Segmentation ◽  
Blood Cell ◽  
White Blood Cell ◽  
Adaptive Thresholding ◽  
Cell Image
Sign in / Sign up

Export Citation Format

Share Document