A complete blood cell count is an important test in medical diagnosis to evaluate overall health condition. Traditionally blood cells are counted manually using haemocytometer along with other laboratory equipment's and chemical compounds, which is a time-consuming and tedious task. In this work, the authors present a machine learning approach for automatic identification and counting of three types of blood cells using ‘you only look once’ (YOLO) object detection and classification algorithm. YOLO framework has been trained with a modified configuration BCCD Dataset of blood smear images to automatically identify and count red blood cells, white blood cells, and platelets. Moreover, this study with other convolutional neural network architectures considering architecture complexity, reported accuracy, and running time with this framework and compare the accuracy of the models for blood cells detection. They also tested the trained model on smear images from a different dataset and found that the learned models are generalised. Overall the computer-aided system of detection and counting enables us to count blood cells from smear images in less than a second, which is useful for practical applications.

Machine learning approach of automatic identification and counting of blood cells

The performance of Differential Evolution is significantly affected by the mutation scheme, which attracts many researchers to develop and enhance the mutation scheme in DE. In this article, the authors introduce an enhanced DE algorithm (EDDE) that utilizes the information given by good individuals and bad individuals in the population. The new mutation scheme maintains effectively the exploration/exploitation balance. Numerical experiments are conducted on 24 test problems presented in CEC'2006, and five constrained engineering problems from the literature for verifying and analyzing the performance of EDDE. The presented algorithm showed competitiveness in some cases and superiority in other cases in terms of robustness, efficiency and quality the of the results.

Enhanced Directed Differential Evolution Algorithm for Solving Constrained Engineering Optimization Problems

An Automated Method for Counting Red Blood Cells using Image Processing

Thalassemia is viewed as a prevalent inherited blood disease that has gotten exorbitant consideration in the field of medical research around the world. Inherited diseases have a high risk that children will get these diseases from their parents. If both the parents are $\beta $ -Thalassemia carriers then there are 25% chances that each child will have $\beta $ -Thalassemia intermediate or $\beta $ -Thalassemia major, which in most of its cases leads to death. Prenatal screening after counseling of couples is an effective way to control $\beta $ -Thalassemia. Generally, identification of the Thalassemia carriers is performed by some quantifiable blood traits determined effectively by high-performance-liquid-chromatography (HPLC) test, which is costly, time-consuming, and requires specialized equipment. However, cost-effective and rapid screening techniques need to be devised for this problem. This study aims to detect $\beta $ -Thalassemia carriers by evaluating red blood cell indices from the complete-blood-count test. The present study included Punjab Thalassemia Prevention Project Lab Reports dataset. The proposed SGR-VC is an ensemble of three machine learning algorithms: Support Vector Machine, Gradient Boosting Machine, and Random Forest. Comparative analysis proved that the proposed ensemble model using all indices of red blood cells is very effective in $\beta $ -Thalassemia carrier screening with 93% accuracy.

/pdf/classification-of-b-thalassemia-carriers-from-red-blood-cell-21n1c5hktz.pdf

Classification of β -Thalassemia Carriers From Red Blood Cell Indices Using Ensemble Classifier

Complete blood cell (CBC) counting has played a vital role in general medical examination. Common approaches, such as traditional manual counting and automated analyzers, were heavily influenced by the operation of medical professionals. In recent years, computer-aided object detection using deep learning algorithms has been successfully applied in many different visual tasks. In this paper, we propose a deep neural network-based architecture to accurately detect and count blood cells on blood smear images. A public BCCD (Blood Cell Count and Detection) dataset is used for the performance evaluation of our architecture. It is not uncommon that blood smear images are in low resolution, and blood cells on them are blurry and overlapping. The original images were preprocessed, including image augmentation, enlargement, sharpening, and blurring. With different settings in the proposed architecture, five models are constructed herein. We compare their performance on red blood cells (RBC), white blood cells (WBC), and platelet detection and deeply investigate the factors related to their performance. The experiment results show that our models can recognize blood cells accurately when blood cells are not heavily overlapping.

/pdf/complete-blood-cell-detection-and-counting-based-on-deep-174peftv.pdf

Complete Blood Cell Detection and Counting Based on Deep Neural Networks

Counting of Red Blood cell (RBC) is a significant measure that helps to diagnose specific diseases. Manual pathological RBCs counting process by experienced specialist is extremely tedious, time consuming, and imprecise which may be prone to high chance of error. Due to recent advancement, automated detection of red blood cell using image processing techniques is gaining popularity. In order to increase the accuracy of the results, it is preferred to accommodate experienced specialist in the RBC counting. In this paper, a new approach is presented for semi-automatically count of the RBCs. The user can specify the dimension of RBC by dragging two points over the image and then apply the Hough transform to detect the oval and biconcave shape of RBC with the specified diameter. The proposed semi-automatic system outperformed the automated system in terms of the executing time. In addition, the proposed system is supported by a GUI to facilitate the pathologist interaction with the proposed system.

Mohd. Iqbal Alam

Papers

A semiautomated approach using GUI for the detection of red blood cells