Red Blood Cell Detection by the Improved Two-Layer Watershed Segmentation Method with a Full Convolutional Neural Network

BACKGROUND: Measurement of abnormal Red Blood Cell (RBC) deformability is a main indicator of Sickle Cell Anemia (SCA) and requires standardized quantification methods. Ektacytometry is commonly used to estimate the fraction of Sickled Cells (SCs) by measuring the deformability of RBCs from laser diffraction patterns under varying shear stress. In addition to estimations from model comparisons, use of maximum Elongation Index differences (ΔEImax) at different laser intensity levels was recently proposed for the estimation of SC fractions. OBJECTIVE: Implement a convolutional neural network to accurately estimate rigid-cell fraction and RBC concentration from laser diffraction patterns without using a theoretical model and eliminating the ektacytometer dependency for deformability measurements. METHODS: RBCs were collected from control patients. Rigid-cell fraction experiments were performed using varying concentrations of glutaraldehyde. Serial dilutions were used for varying the concentration of RBC. A convolutional neural network was constructed using Python and TensorFlow. RESULTS: Our measurements and model predictions show that a linear relationship between ΔEImax and rigid-cell fraction exists only for rigid-cell fractions less than 0.2. Our proposed neural network architecture can be used successfully for both RBC concentration and rigid-cell fraction estimations without a need for a theoretical model.

Download Full-text

Fused Convolutional Neural Network for White Blood Cell Detection

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2020.5334 ◽

2020 ◽

Vol 8 (5) ◽

pp. 2040-2043

Author(s):

J. Karthiyayini

Keyword(s):

Neural Network ◽

Blood Cell ◽

Convolutional Neural Network ◽

White Blood Cell ◽

Cell Detection

Download Full-text

Implementation of Convolutional Neural Network in the classification of red blood cells have affected of malaria

SinkrOn ◽

10.33395/sinkron.v5i2.10713 ◽

2020 ◽

Vol 5 (2) ◽

pp. 199-207

Author(s):

Mawaddah Harahap ◽

Jefferson Jefferson ◽

Surya Barti ◽

Suprianto Samosir ◽

Christi Andika Turnip

Keyword(s):

Neural Network ◽

Blood Cell ◽

Convolutional Neural Network ◽

Red Blood Cells ◽

Red Blood Cell ◽

Blood Cells ◽

Training Data ◽

Test Accuracy ◽

Number Of Layers

Malaria is a disease caused by plasmodium which attacks red blood cells. Diagnosis of malaria can be made by examining the patient's red blood cells using a microscope. Convolutional Neural Network (CNN) is a deep learning method that is growing rapidly. CNN is often used in image classification. The CNN process usually requires considerable resources. This is one of the weaknesses of CNN. In this study, the CNN architecture used in the classification of red blood cell images is LeNet-5 and DRNet. The data used is a segmented image of red blood cells and is secondary data. Before conducting the data training, data pre-processing and data augmentation from the dataset was carried out. The number of layers of the LeNet-5 and DRNet models were 4 and 7. The test accuracy of the LeNet-5 and DrNet models was 95% and 97.3%, respectively. From the test results, it was found that the LeNet-5 model was more suitable in terms of red blood cell classification. By using the LeNet-5 architecture, the resources used to perform classification can be reduced compared to previous studies where the accuracy obtained is also the same because the number of layers is less, which is only 4 layers

Download Full-text

Active Learning with Bayesian UNet for Efficient Semantic Image Segmentation

Journal of Imaging ◽

10.3390/jimaging7020037 ◽

2021 ◽

Vol 7 (2) ◽

pp. 37

Author(s):

Isah Charles Saidu ◽

Lehel Csató

Keyword(s):

Neural Network ◽

Image Segmentation ◽

Active Learning ◽

Convolutional Neural Network ◽

Medical Image ◽

Segmentation Method ◽

Semantic Image Segmentation ◽

Batch Normalization ◽

Set Up ◽

Image Datasets

We present a sample-efficient image segmentation method using active learning, we call it Active Bayesian UNet, or AB-UNet. This is a convolutional neural network using batch normalization and max-pool dropout. The Bayesian setup is achieved by exploiting the probabilistic extension of the dropout mechanism, leading to the possibility to use the uncertainty inherently present in the system. We set up our experiments on various medical image datasets and highlight that with a smaller annotation effort our AB-UNet leads to stable training and better generalization. Added to this, we can efficiently choose from an unlabelled dataset.

Download Full-text

Stereo Vision-Based Object Recognition and Manipulation by Regions with Convolutional Neural Network

Electronics ◽

10.3390/electronics9020210 ◽

2020 ◽

Vol 9 (2) ◽

pp. 210 ◽

Cited By ~ 5

Author(s):

Yi-Chun Du ◽

Muslikhin Muslikhin ◽

Tsung-Han Hsieh ◽

Ming-Shyan Wang

Keyword(s):

Neural Network ◽

Object Recognition ◽

Convolutional Neural Network ◽

Stereo Vision ◽

Fuzzy Inference ◽

Target Object ◽

Robot Arm ◽

Segmentation Method ◽

Inference System ◽

Six Degree Of Freedom

This paper develops a hybrid algorithm of adaptive network-based fuzzy inference system (ANFIS) and regions with convolutional neural network (R-CNN) for stereo vision-based object recognition and manipulation. The stereo camera at an eye-to-hand configuration firstly captures the image of the target object. Then, the shape, features, and centroid of the object are estimated. Similar pixels are segmented by the image segmentation method, and similar regions are merged through selective search. The eye-to-hand calibration is based on ANFIS to reduce computing burden. A six-degree-of-freedom (6-DOF) robot arm with a gripper will conduct experiments to demonstrate the effectiveness of the proposed system.

Download Full-text