Improved Deep Learning for Disease Detection Using Blood Cells Classification from Microscopic Images

Blood cell classification and counting are vital for the diagnosis of various blood-related diseases, such as anemia, leukemia, lymphoma, and thrombocytopenia. The manual process of blood cell classification and counting is time-consuming, prone to errors, and labor-intensive. Therefore, we have proposed a deep learning (DL)-based automated system for blood cell classification and counting from microscopic blood smear images. We classify a total of nine types of blood cells, including Erythrocyte, Erythroblast, Neutrophil, Basophil, Eosinophil, Lymphocyte, Monocyte, Immature Granulocytes, and Platelet. Several preprocessing steps like image resizing, rescaling, contrast enhancement and augmentation are utilized. To segment the blood cells from the entire microscopic images, we employed the U-Net model. This segmentation technique aids in extracting the region of interest (ROI) by removing complex and noisy background elements. Both pixel-level metrics such as accuracy, precision, and sensitivity, and object-level evaluation metrics like Intersection over Union (IOU) and Dice coefficient are considered to comprehensively evaluate the performance of the U-Net model. The segmentation model achieved impressive performance metrics, including 98.23% accuracy, 98.40% precision, 98.26% sensitivity, 95.97% Intersection over Union (IOU), and 97.92% Dice coefficient. Subsequently, a watershed algorithm is applied to the segmented images to separate overlapped blood cells and extract individual cells. We have proposed a BloodCell-Net approach incorporated with custom light weight convolutional neural network (LWCNN) for classifying individual blood cells into nine types. Comprehensive evaluation of the classifier’s performance is conducted using metrics including accuracy, precision, recall, and F1 score. The classifier achieved an average accuracy of 97.10%, precision of 97.19%, recall of 97.01%, and F1 score of 97.10%. A 5-fold cross-validation technique is applied to split the data, which not only aids in reducing overfitting but also helps in generalizing the model.

Background/Objectives: Accurate detection and classification of blood cell types in microscopic images are crucial for diagnosing various hematological conditions. This study aims to develop and evaluate advanced architectures for automating blood cell detection and classification using the newly proposed YOLOv10 and YOLOv11 models, with a specific focus on identifying red blood cells (RBCs), white blood cells (WBCs), and platelets in microscopic images as a preliminary step of the complete blood count (CBC). Methods: The Blood Cell Count Detection (BCCD) dataset was enriched using data augmentation techniques to improve model robustness and diversity. Extensive experiments were performed, including complete weight initialization, advanced optimization strategies, and meticulous hyperparameter tuning for the YOLOv11 architecture. Results: The YOLOv11-l model achieved an overall mean Average Precision (mAP) of 93.8%, reflecting its robust accuracy across multiple blood cell types. Conclusions: The findings underscore the efficacy of the YOLOv11 architecture in automating blood cell classification with high precision, demonstrating its potential to enhance hematological analyses and support clinical diagnosis.

Leucocyte classification for leukaemia detection using image processing techniques.

Automated classification of white blood cells from microscope images is still challenging, particularly in terms of feature representations choice considering its complexity, compactness and efficiency. Particularly, in this scenario, the feature representations have to be invariant to non-uniform illumination, shape of the nuclei, stage of maturity, change in topology due to rotation, scale and shifting. This paper proposes a new white blood cell feature representation which aims at increasing robustness to those challenges. The proposed feature representation is designed based on L-moments (L-skewness, L-mean, L-scale and L-kurtosis) of the Radon projection of segmented nuclei shape. Coupled with Linear Discriminant Analysis, the proposed feature representation has been shown to be highly effective at encoding the discriminative properties of the white blood cells, and invariant to intra-class cell variations. Support Vector Machine (SVM) based (ones-vs-all) schema and a classification tree are applied to separate the multiple classes of cells. The proposed approach is evaluated for a 10-class problem. It achieves an average classification accuracy of 97.23% and outperforms all other feature representations, including bispectral invariant, local binary pattern, and histogram of oriented gradients using the same classifier on the same dataset. The proposed method is also compared and benchmarked with the other 12 existing techniques for classification of white blood cells into 10 classes over the same datasets and the results show that the proposed method achieves high accuracy in comparison with other approaches. The proposed method is also highly competitive in terms of computation and efficiency in comparison with other approaches.

Artificial intelligence (AI) has emerged as a cutting-edge tool, simultaneously accelerating, securing, and enhancing the diagnosis and treatment of patients. An exemplification of this capability is evident in the analysis of peripheral blood smears (PBS). In university medical centers, hematologists routinely examine hundreds of PBS slides daily to validate or correct outcomes produced by advanced hematology analyzers assessing samples from potentially problematic patients. This process may logically lead to erroneous PBC readings, posing risks to patient health. AI functions as a transformative tool, significantly improving the accuracy and precision of readings and diagnoses. This study reshapes the parameters of blood cell classification, harnessing the capabilities of AI and broadening the scope from 5 to 11 specific blood cell categories with the challenging 11-class PBC dataset. This transformation facilitates a more profound exploration of blood cell diversity, surpassing prior constraints in medical image analysis. Our approach combines state-of-the-art deep learning techniques, including pre-trained ConvNets, ViTb16 models, and custom CNN architectures. We employ transfer learning, fine-tuning, and ensemble strategies, such as CBAM and Averaging ensembles, to achieve unprecedented accuracy and interpretability. Our fully fine-tuned EfficientNetV2 B0 model sets a new standard, with a macro-average precision, recall, and F1-score of 91%, 90%, and 90%, respectively, and an average accuracy of 93%. This breakthrough underscores the transformative potential of 11-class blood cell classification for more precise medical diagnoses. Moreover, our groundbreaking “Naturalize” augmentation technique produces remarkable results. The 2K-PBC dataset generated with “Naturalize” boasts a macro-average precision, recall, and F1-score of 97%, along with an average accuracy of 96% when leveraging the fully fine-tuned EfficientNetV2 B0 model. This innovation not only elevates classification performance but also addresses data scarcity and bias in medical deep learning. Our research marks a paradigm shift in blood cell classification, enabling more nuanced and insightful medical analyses. The “Naturalize” technique’s impact extends beyond blood cell classification, emphasizing the vital role of diverse and comprehensive datasets in advancing healthcare applications through deep learning.

Deep learning based Non-Local k-best renyi entropy for classification of white blood cell subtypes

Blood cell classification is widely used in the biomedical research. Appropriate separation between touching and overlapping blood cells is of great importance for the successful classification. In this paper, a novel algorithm based on shape information is proposed for the separation of partially overlapping blood cells. It is motivated by the problem of finding the borders between adjacent blood cells in microscopy images. The algorithm can not only separate the simple touching blood cells, but also large clusters of overlapping blood cells. In addition, this algorithm can be adopted for other applications, where separation between touching and overlapping particles is required.

Blood cell detection considers a gold standard key in diagnosing blood disease and producing automatic reports to hematologists and doctors. Blood cell detection is a challenging task due to non-illumination level, high number of overlapped cells per image, variations in cell densities among platelets, white blood cells and red blood cells, and the variety of staining process. Traditional procedure of blood cell detection requires pathologist effort and time. In computer aided diagnosis, machine learning and deep learning techniques become the practical way to automate the procedure of diagnosing, classify microscopic blood cells, and increase the accuracy and speed of the procedure. This paper provides a review of the detection and classification of blood cell, including red blood cells, white blood cells and platelets and their characteristics using machine learning techniques. We also have detailed the dataset of microscope blood cell. We have divided the previous works into four categories based on the output of the models, including pre-processing, segmentation, feature extraction and classification. Then, we discuss the challenges that face these methods and suggest the potential future techniques.

Adaptive blood cell segmentation and hybrid Learning-based blood cell classification: A Meta-heuristic-based model

The problem of identifying and counting blood cells within the blood smear is of both theoretical and practical interest. The differential counting of blood cells provides invaluable information to pathologist for diagnosis and treatment of many diseases. In this paper we propose an efficient hierarchical blood cell image identification and classification method based on multi-class support vector machine. In this automated process, segmentation and classification of blood cells are the most important stages. We segment the stained blood cells in digital microscopic images and extract the geometric features for each segment to identify and classify the different types of blood cells. The experimental results are compared with the manual results obtained by the pathologist, and demonstrate the effectiveness of the proposed method.

There are three major types of blood cells, red blood cells (erythrocytes), white blood cells (leukocytes), and platelets (thrombocytes). Together, these three kinds of blood cells add up to a total of 45% of the blood tissue by volume, with the remaining 55% of the volume composed of plasma, the liquid component of blood. These three types play an important role in the human body by increasing immunity by fighting against infectious diseases. The classification and count of blood cells play an important role in the detection of a disease in an individual. It can also assist with the identification of diseases like infections, anemia, leukemia, cancer, etc. This classification will assist the hematologist to distinguish between the types of white blood cells, red blood cells, and platelets present in the human body and find the root cause of diseases. Currently, there is a large amount of research going on in this field. Considering a huge potential in the significance of the classification of different blood cells, a deep learning technique called Convolution Neural Networks will be used which can classify the images of human blood cells into their subtypes namely Neutrophils, Eosinophils, Basophils, Lymphocytes, Monocytes, Immature Granulocytes (Promyelocytes, Myelocytes, and Metamyelocytes), Red blood cells or Erythroblasts and Platelets or Thrombocytes. In this paper, the discussion have been done on a dataset that was acquired in the Core Laboratory at the Hospital Clinic of Barcelona using Convolution Neural Networks.

Large number of diseases can be diagnosed by the counting and classification of blood cells. One type of the most common blood diseases is Acute Lymphoblastic Leukemia (ALL). Rapid and uncontrolled growth of immature leukemic cells (also named as blast cells) is used to characterize ALL. The morphological analysis of the bone marrow and blood smear is the primary step of diagnosis. Valuable information is provided by the features extracted from the blood cells for the confirmation of the diagnosis. As the process have numerous drawbacks, a computerized system will be helpful for the analysis of stained microscopic images of the blood cells for quantitative examination. This paper demonstrates a new and simple segmentation approach using watershed transform and two simpler classification models to diagnose the presence of ALL in blood smear accurately.

3D microscopy imaging is important for understanding complex biological assemblies. Computers and digital image acquisition systems have made possible the 3D visualization of images obtained from optical microscopes. This paper discussed a morphological approach for 3D blood cell visualization. The 3D plotted image is obtained from 2D image by combining 2D image space with the intensity value presented as third axis. 2D image detection techniques are commonly apply for blood cell analysis on image taken from microscopy or scanner sample which normally could be affected by noise. In order to enhance the detection of blood cell for 2D image and to obtain the clearest view of the blood cell, 3D image detection, which is more flexible and accurate, is proposed. This approach helps to obtain a clear image for disease analysis. A color image taken from microscopy or scanner has to gone through such image analysis using intensity, and edge operator to detect the blood cell disease, before 3D visualization can be done. INTRODUCTION In blood analysis component of the blood are distinguished by their dimensions and color. Blood cell classification and analysis is an important diagnostic technique in the detection of many illnesses [1]. The importance of traceability in the medical diagnostics is a technique that can be determined from a microscope slide or from a set of images. An accurate diagnosis could aid in diagnoses treatment disease, therefore the accurate details of the cells has to be analytical. In malarial blood, the red corpuscles of vertebrates are infected by malarial parasites [2]. The morphological blood cell image analysis includes calculation of geometrical features for recognition of pathology [3]. The goal of this paper is to enhance the detection by using or viewing blood cells visualization to provide a clear view to pathologies in order to reduce noise of the image for more accuracy diagnoses. BLOOD IMAGE DETECTION TECHNIQUES There are automated technologies for cell analysis, such as impendence analysis and flow cytometry, these method lack the ability to visualize each of the cell used in there determinations, and visually inspect them to ensure that they were classified appropriately [4]. In edge image detection acquired from stained blood, smears are suitable for measuring and characterizing properties of individual cells [5]. Edge detection is essentially the operation of detection significantly local changes in image. In one dimension, a step edge is associated with local peak in the first derivative. The gradient is a measure of change in function, and an image can be considered to be an array of sample of some continues function of image intensity. The gradient is the two-dimensional equivalent of the first derivative and is defined as the vector. 3D Visualization For Blood Cells Analysis Versus Edge Detection

The examination, counting, and classification of white blood cells (WBCs), also known as leukocytes, are essential processes in the diagnosis of many disorders, including leukemia, a kind of blood cancer characterized by the uncontrolled proliferation of carcinogenic leukocytes in the marrow of the bone. Blood smears can be chemically or microscopically studied to better understand hematological diseases and blood disorders. Detecting, identifying, and categorizing the many blood cell types are essential for disease diagnosis and therapy planning. A theoretical and practical issue. However, methods based on deep learning (DL) have greatly helped blood cell classification. Images of blood cells in a microscopic smear were collected from GitHub, a public source that uses the MIT license. An end-to-end computer-aided diagnosis (CAD) system for leukocytes has been created and implemented as part of this study. The introduced system comprises image preprocessing and enhancement, image segmentation, feature extraction and selection, and WBC classification. By combining the DenseNet-161 and the cyclical learning rate (CLR), we contribute an approach that speeds up hyperparameter optimization. We also offer the one-cycle technique to rapidly optimize all hyperparameters of DL models to boost training performance. The dataset has been split into two sets: approximately 80% of the data (9,966 images) for the training set and 20% (2,487 images) for the validation set. The validation set has 623, 620, 620, and 624 eosinophil, lymphocyte, monocyte, and neutrophil images, whereas the training set has 2,497, 2,483, 2,487, and 2,499, respectively. The suggested method has 100% accuracy on the training set of images and 99.8% accuracy on the testing set. Using a combination of the recently developed pretrained convolutional neural network (CNN), DenseNet, and the one fit cycle policy, this study describes a technique of training for the classification of WBCs for leukemia detection. The proposed method is more accurate compared to the state of the art.

Among the blood cells, white blood cells (WBC), which play a crucial role in forming our body's defense system, are essential components. Originating in the bone marrow, these cells serve as the fundamental components of the immune system, shouldering the responsibility of safeguarding the body against foreign microbes and diseases. Insufficient WBC counts may compromise the body's skill to resist infections, a status known as leukopenia. White blood cell counting is a specialty procedure that is usually carried out by qualified physicians and radiologists. Thanks to recent advances, image processing techniques are frequently used in biological systems to identify a wide spectrum of illnesses. In this work, image processing techniques were applied to enhance the white blood cell deep learning models' classification accuracy. To expedite the classification process, Convolutional Neural Network (CNN) models were combined with Ridge feature selection and Maximal Information Coefficient techniques. These tactics successfully determined the most important characteristics. The selected feature set was then applied to the classification procedure. ResNet-50, VGG19, and our suggested model were used as feature extractors in this study. The categorizing of white blood cells was completed with an amazing 98.27% success rate. Results from the experiments demonstrated a considerable improvement in classification accuracy using the proposed CNN model.