Morphological Granulometric Features of Nucleus in Automatic Bone Marrow White Blood Cell Classification

Digital Microscopy Augmented by Artificial Intelligence to Interpret Bone Marrow Samples for Hematological Diseases

Analysis of bone marrow aspirates (BMAs) is an essential step in the diagnosis of hematological disorders. This analysis is usually performed based on a visual examination of samples under a conventional optical microscope, which involves a labor-intensive process, limited by clinical experience and subject to high observer variability. In this work, we present a comprehensive digital microscopy system that enables BMA analysis for cell type counting and differentiation in an efficient and objective manner. This system not only provides an accessible and simple method to digitize, store, and analyze BMA samples remotely but is also supported by an Artificial Intelligence (AI) pipeline that accelerates the differential cell counting process and reduces interobserver variability. It has been designed to integrate AI algorithms with the daily clinical routine and can be used in any regular hospital workflow.

Using deep DenseNet with cyclical learning rate to classify leukocytes for leukemia identification

Background

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.

Materials and Methods

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.

Results

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.

Conclusion

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.

Artificial intelligence-assisted diagnosis of hematologic diseases based on bone marrow smears using deep neural networks

BACKGROUND AND OBJECTIVES

The morphological examination of bone marrow (BM) cells is essential in both diagnosing and treating various hematologic diseases. However, it is still done manually with a heavy workload. An artificial intelligence-assisted diagnosis support system of BM cells is highly required to reduce the workloads of examiners and improve the reproducibility of the results.

METHODS

In this paper, we proposed an artificial intelligence-assisted diagnosis support system of morphological examination based on bone marrow smears including cells detection, classification and prediction of leukemia types. For cell detection, we trained the novel YOLOX-s model to locate cells precisely and obtain single cell images. For cell classification, we regarded it as a fine- grained classification task and proposed a novel architecture called MLFL-Net utilizing multi-level features. Furthermore, we predicted the leukemia types on a dataset including 40 normal people (BM transplantation donors) and 40 patients of different kinds of acute leukemia according to the World Health Organization (WHO) standard.

RESULTS

We constructed a large-scale data set of 11,788 fully-annotated micrographs from 728 smears and 131,300 expert-annotated single cell images. With the data set, the detection model achieved 0.9797 AUC and 4.33% box placement error. For cell classification, the total accuracy of our proposed MLFL-Net reached 89.53% which outperformed all the other related models in identifying cell categories. In the meantime, we took acute leukemia as an example to explore the leukemia types prediction procedure of hematological disease. It generated the same diagnostic prediction as the experts gave for 92.5 percent of the cohort.

CONCLUSION

This Artificial Intelligence-assisted system can be implemented to aid in clinical decision making and accelerate diagnosis. The method will contribute to promote the intelligence and modernization of BM cytomorphology, which has vital significance of the development of the medical career.

Deep self-supervised transformation learning for leukocyte classification

The scarcity of training annotation is one of the major challenges for the application of deep learning technology in medical image analysis. Recently, self-supervised learning provides a powerful solution to alleviate this challenge by extracting useful features from a large number of unlabeled training data. In this article, we propose a simple and effective self-supervised learning method for leukocyte classification by identifying the different transformations of leukocyte images, without requiring a large batch of negative sampling or specialized architectures. Specifically, a convolutional neural network backbone takes different transformations of leukocyte image as input for feature extraction. Then, a pretext task of self-supervised transformation recognition on the extracted feature is conducted by a classifier, which helps the backbone learn useful representations that generalize well across different leukocyte types and datasets. In the experiment, we systematically study the effect of different transformation compositions on useful leukocyte feature extraction. Compared with five typical baselines of self-supervised image classification, experimental results demonstrate that our method performs better in different evaluation protocols including linear evaluation, domain transfer, and finetuning, which proves the effectiveness of the proposed method.

Fuzzy Model for the Automatic Recognition of Human Dendritic Cells

Background and objective: Nowadays, foodborne illness is considered one of the most outgrowing diseases in the world, and studies show that its rate increases sharply each year. Foodborne illness is considered a public health problem which is caused by numerous factors, such as food intoxications, allergies, intolerances, etc. Mycotoxin is one of the food contaminants which is caused by various species of molds (or fungi), which, in turn, causes intoxications that can be chronic or acute. Thus, even low concentrations of Mycotoxin have a severely harmful impact on human health. It is, therefore, necessary to develop an assessment tool for evaluating their impact on the immune response. Recently, researchers have approved a new method of investigation using human dendritic cells, yet the analysis of the geometric properties of these cells is still visual. Moreover, this type of analysis is subjective, time-consuming, and difficult to perform manually. In this paper, we address the automation of this evaluation using image-processing techniques. Methods: Automatic classification approaches of microscopic dendritic cell images are developed to provide a fast and objective evaluation. The first proposed classifier is based on support vector machines (SVM) and Fisher's linear discriminant analysis (FLD) method. The FLD-SVM classifier does not provide satisfactory results due to the significant confusion between the inhibited cells on one hand, and the other two cell types (mature and immature) on the other hand. Then, another strategy was suggested to enhance dendritic cell recognition results that are emitted from microscopic images. This strategy is mainly based on fuzzy logic which allows us to consider the uncertainties and inaccuracies of the given data. Results: These proposed methods are tested on a real dataset consisting of 421 images of microscopic dendritic cells, where the fuzzy classification scheme efficiently improved the classification results by successfully classifying 96.77% of the dendritic cells. Conclusions: The fuzzy classification-based tools provide cell maturity and inhibition rates which help biologists evaluate severe health impacts caused by food contaminants.

Evaluation of two semi-supervised learning methods and their combination for automatic classification of bone marrow cells

Differential bone marrow (BM) cell counting is an important test for the diagnosis of various hematological diseases. However, it is difficult to accurately classify BM cells due to non-uniformity and the lack of reproducibility of differential counting. Therefore, automatic classification systems have been developed in which deep learning is used. These systems requires large and accurately labeled datasets for training. To overcome this, we used semi-supervised learning (SSL), in which learning proceeds while labeling. We used three methods: self-training (ST), active learning (AL), and a combination of these methods, and attempted to automatically classify 16 types of BM cell images. ST involves data verification, as in AL, before adding them to the training dataset (confirmed self-training: CST). After 25 rounds of CST, AL, and CST + AL, the initial number of training data increased from 425 to 40,518; 3682; and 47,843, respectively. Accuracies for the test data of 50 images for each cell type were 0.944, 0.941, and 0.976, respectively. Data added with CST or AL showed some imbalances between classes, while CST + AL exhibited fewer imbalances. We suggest that CST + AL, when combined with two SSL methods, is efficient in increasing training data for the development of automatic BM cells classification systems.

White blood cell classification via a discriminative region detection assisted feature aggregation network

White blood cell (WBC) classification plays an important role in human pathological diagnosis since WBCs will show different appearance when they fight with various disease pathogens. Although many previous white blood cell classification have been proposed and earned great success, their classification accuracy is still significantly affected by some practical issues such as uneven staining, boundary blur and nuclear intra-class variability. In this paper, we propose a deep neural network for WBC classification via discriminative region detection assisted feature aggregation (DRFA-Net), which can accurately locate the WBC area to boost final classification performance. Specifically, DRFA-Net uses an adaptive feature enhancement module to refine multi-level deep features in a bilateral manner for efficiently capturing both high-level semantic information and low-level details of WBC images. Considering the fact that background areas could inevitably produce interference, we design a network branch to detect the WBC area with the supervision of segmented ground truth. The bilaterally refined features obtained from two directions are finally aggregated for final classification, and the detected WBC area is utilized to highlight the features of discriminative regions by an attention mechanism. Extensive experiments on several public datasets are conducted to validate that our proposed DRFA-Net can obtain higher accuracies when compared with other state-of-the-art WBC classification methods.

Non-invasive and label-free identification of human natural killer cell subclasses by biophysical single-cell features in microfluidic flow

Natural killer (NK) cells are indicated as favorite candidates for innovative therapeutic treatment and are divided into two subclasses: immature regulatory NK CD56^bright and mature cytotoxic NK CD56^dim. Therefore, the ability to discriminate CD56^dim from CD56^bright could be very useful because of their higher cytotoxicity. Nowadays, NK cell classification is routinely performed by cytometric analysis based on surface receptor expression. Here, we present an in-flow, label-free and non-invasive biophysical analysis of NK cells through a combination of light scattering and machine learning (ML) for NK cell subclass classification. In this respect, to identify relevant biophysical cell features, we stimulated NK cells with interleukine-15 inducing a subclass transition from CD56^bright to CD56^dim. We trained our ML algorithm with sorted NK cell subclasses (≥86% accuracy). Next, we applied our NK cell classification algorithm to cells stimulated over time, to investigate the transition of CD56^bright to CD56^dim and their biophysical feature changes. Finally, we tested our approach on several proband samples, highlighting the potential of our measurement approach. We show a label-free way for the robust identification of NK cell subclasses based on biophysical features, which can be applied in both cell biology and cell therapy.

Morphological, fractal, and textural features for the blood cell classification: the case of acute myeloid leukemia

Microscopic examination of stained peripheral blood smears is, nowadays, an indispensable tool in the evaluation of patients with hematological and non-hematological diseases. While a rapid automated quantification of the regular blood cells is available, recognition and counting of immature white blood cells (WBC) still relies mostly on the microscopic examination of blood smears by an experienced observer. Recently, there are efforts to improve the prediction by various machine learning approaches. An open dataset collection including the recently digitalized single-cell images for 200 patients, from peripheral blood smears at 100 × magnification, was used. We studied different morphological, fractal, and textural descriptors for WBC classification, with an aim to indicate the most reliable parameters for the recognition of certain cell types. Structural properties of both the mature and non-mature leukocytes obtained from (i) acute myeloid leukemia patients, or (ii) non-malignant controls, were studied in depth, with a sample size of about 25 WBC per group. We quantified structural and textural differences and, based on the statistical ranges of parameters for different WBC types, selected eight features for classification: Cell area, Nucleus-to-cell ratio, Nucleus solidity, Fractal dimension, Correlation, Contrast, Homogeneity, and Energy. Classification Precision of up to 100% (80% on average) was achieved.

Regulation of diverse nuclear shapes: pathways working independently, together

Membrane-bound organelles provide physical and functional compartmentalization of biological processes in eukaryotic cells. The characteristic shape and internal organization of these organelles is determined by a combination of multiple internal and external factors. The maintenance of the shape of nucleus, which houses the genetic material within a double membrane bilayer, is crucial for a seamless spatio-temporal control over nuclear and cellular functions. Dynamic morphological changes in the shape of nucleus facilitate various biological processes. Chromatin packaging, nuclear and cytosolic protein organization, and nuclear membrane lipid homeostasis are critical determinants of overall nuclear morphology. As such, a multitude of molecular players and pathways act together to regulate the nuclear shape. Here, we review the known mechanisms governing nuclear shape in various unicellular and multicellular organisms, including the non-spherical nuclei and non-lamin-related structural determinants. The review also touches upon cellular consequences of aberrant nuclear morphologies.

Deep Multi-Instance Learning Using Multi-Modal Data for Diagnosis of Lymphocytosis

We investigate the use of recent advances in deep learning and propose an end-to-end trainable multi-instance convolutional neural network within a mixture-of-experts formulation that combines information from two types of data-images and clinical attributes-for the diagnosis of lymphocytosis. The convolutional network learns to extract meaningful features from images of blood cells using an embedding level approach and aggregates them. Moreover, the mixture-of-experts model combines information from these images as well as clinical attributes to form an end-to-end trainable pipeline for diagnosis of lymphocytosis. Our results demonstrate that even the convolutional network by itself is able to discover meaningful associations between the images and the diagnosis, indicating the presence of important unexploited information in the images. The mixture-of-experts formulation is shown to be more robust while maintaining performance via. a repeatability study to assess the effect of variability in data acquisition on the predictions. The proposed methods are compared with different methods from literature based both on conventional handcrafted features and machine learning, and on recent deep learning models based on attention mechanisms. Our method reports a balanced accuracy of [Formula: see text] and outperfroms the handcrafted feature-based and attention-based approaches as well that of biologists which scored [Formula: see text], [Formula: see text] and [Formula: see text] respectively. These results give insights on the potentials of the applicability of the proposed method in clinical practice. Our code and datasets can be found at https://github.com/msahasrabudhe/lymphoMIL.

Recent Advances in Medical Image Processing

BACKGROUND

Application and development of the artificial intelligence technology have generated a profound impact in the field of medical imaging. It helps medical personnel to make an early and more accurate diagnosis. Recently, the deep convolution neural network is emerging as a principal machine learning method in computer vision and has received significant attention in medical imaging. Key Message: In this paper, we will review recent advances in artificial intelligence, machine learning, and deep convolution neural network, focusing on their applications in medical image processing. To illustrate with a concrete example, we discuss in detail the architecture of a convolution neural network through visualization to help understand its internal working mechanism.

SUMMARY

This review discusses several open questions, current trends, and critical challenges faced by medical image processing and artificial intelligence technology.

Automated Semantic Segmentation of Red Blood Cells for Sickle Cell Disease

Red blood cell (RBC) segmentation and classification from microscopic images is a crucial step for the diagnosis of sickle cell disease (SCD). In this work, we adopt a deep learning based semantic segmentation framework to solve the RBC classification task. A major challenge for robust segmentation and classification is the large variations on the size, shape and viewpoint of the cells, combining with the low image quality caused by noise and artifacts. To address these challenges, we apply deformable convolution layers to the classic U-Net structure and implement the deformable U-Net (dU-Net). U-Net architecture has been shown to offer accurate localization for image semantic segmentation. Moreover, deformable convolution enables free-form deformation of the feature learning process, thus making the network more robust to various cell morphologies and image settings. dU-Net is tested on microscopic red blood cell images from patients with sickle cell disease. Results show that dU-Net can achieve highest accuracy for both binary segmentation and multi-class semantic segmentation tasks, comparing with both unsupervised and state-of-the-art deep learning based supervised segmentation methods. Through detailed investigation of the segmentation results, we further conclude that the performance improvement is mainly caused by the deformable convolution layer, which has better ability to separate the touching cells, discriminate the background noise and predict correct cell shapes without any shape priors.

Accurate automatic detection of acute lymphatic leukemia using a refined simple classification

An improved classification technique is presented to identify automatically the acute lymphatic leukemia (ALL) subtypes. An adaptive segmentation procedure is performed on peripheral blood smear images to extract the main features (10 geometric features) from the segmented images of white blood cell (WBC), nucleus, and cytoplasm. To show the importance of the different extracted features for the diagnostic accuracy, a comprehensive study is made on all the possible permutation cases of the features using powerful classifiers which are K-nearest neighbor (KNN) at different metric functions, support vector machine (SVM) with different kernels, and artificial neural network (ANN). This procedure enables us to construct a feature map depending only on least number of features which lead to the highest diagnostic accuracy. It is found that the features map regarding the vacuoles in the cytoplasm and the regularity of the nucleus membrane gives the highest accurate results. The automatic classification for ALL subtypes based only on these two effective features is assessed using the receiver operating characteristic (ROC) curve and F₁ -score measures. It is confirmed that the present technique is highly accurate, and saves the effort and time of training.

Cell Image Classification: A Comparative Overview

Cell image classification methods are currently being used in numerous applications in cell biology and medicine. Applications include understanding the effects of genes and drugs in screening experiments, understanding the role and subcellular localization of different proteins, as well as diagnosis and prognosis of cancer from images acquired using cytological and histological techniques. The article also reviews three main approaches for cell image classification most often used: numerical feature extraction, end-to-end classification with neural networks (NNs), and transport-based morphometry (TBM). In addition, we provide comparisons on four different cell imaging datasets to highlight the relative strength of each method. The results computed using four publicly available datasets show that numerical features tend to carry the best discriminative information for most of the classification tasks. Results also show that NN-based methods produce state-of-the-art results in the dataset that contains a relatively large number of training samples. Data augmentation or the choice of a more recently reported architecture does not necessarily improve the classification performance of NNs in the datasets with limited number of training samples. If understanding and visualization are desired aspects, TBM methods can offer the ability to invert classification functions, and thus can aid in the interpretation of results. These and other comparison outcomes are discussed with the aim of clarifying the advantages and disadvantages of each method. © 2020 International Society for Advancement of Cytometry.

Classification of chronic myeloid leukemia cell subtypes based on microscopic image analysis

This paper presents a simple and efficient computer-aided diagnosis method to classify Chronic Myeloid Leukemia (CML) cells based on microscopic image processing. In the proposed method, a novel combination of both typical and new features is introduced for classification of CML cells. Next, an effective decision tree classifier is proposed to classify CML cells into eight groups. The proposed method was evaluated on 1730 CML cell images containing 714 cells of non-cancerous bone marrow aspiration and 1016 cells of cancerous peripheral blood smears. The performance of the proposed classification method was compared to manual labels made by two experts. The average values of accuracy, specificity and sensitivity were 99.0 %, 99.4 % and 98.3 %, respectively for all groups of CML. In addition, Cohen's kappa coefficient demonstrated high conformity, 0.99, between joint diagnostic results of two experts and the obtained results of the proposed approach. According to the obtained results, the suggested method has a high capability to classify effective cells of CML and can be applied as a simple, affordable and reliable computer-aided diagnosis tool to help pathologists to diagnose CML.

Pixel-to-Pixel Learning With Weak Supervision for Single-Stage Nucleus Recognition in Ki67 Images

OBJECTIVE

Nucleus recognition is a critical yet challenging step in histopathology image analysis, for example, in Ki67 immunohistochemistry stained images. Although many automated methods have been proposed, most use a multi-stage processing pipeline to categorize nuclei, leading to cumbersome, low-throughput, and error-prone assessments. To address this issue, we propose a novel deep fully convolutional network for single-stage nucleus recognition.

METHODS

Instead of conducting direct pixel-wise classification, we formulate nucleus identification as a deep structured regression model. For each input image, it produces multiple proximity maps, each of which corresponds to one nucleus category and exhibits strong responses in central regions of the nuclei. In addition, by taking into consideration the nucleus distribution in histopathology images, we further introduce an auxiliary task, region of interest (ROI) extraction, to assist and boost the nucleus quantification with weak ROI annotation. The proposed network can be learned in an end-to-end, pixel-to-pixel manner for simultaneous nucleus detection and classification.

RESULTS

We have evaluated this network on a pancreatic neuroendocrine tumor Ki67 image dataset, and the experiments demonstrate that our method outperforms recent state-of-the-art approaches.

CONCLUSION

We present a new, pixel-to-pixel deep neural network with two sibling branches for effective nucleus recognition and observe that learning with another relevant task, ROI extraction, can further boost individual nucleus localization and classification.

SIGNIFICANCE

Our method provides a clean, single-stage nucleus recognition pipeline for histopathology image analysis, especially a new perspective for Ki67 image quantification, which would potentially benefit individual object quantification in whole-slide images.

Accurate label-free 3-part leukocyte recognition with single cell lens-free imaging flow cytometry

Three-part white blood cell differentials which are key to routine blood workups are typically performed in centralized laboratories on conventional hematology analyzers operated by highly trained staff. With the trend of developing miniaturized blood analysis tool for point-of-need in order to accelerate turnaround times and move routine blood testing away from centralized facilities on the rise, our group has developed a highly miniaturized holographic imaging system for generating lens-free images of white blood cells in suspension. Analysis and classification of its output data, constitutes the final crucial step ensuring appropriate accuracy of the system. In this work, we implement reference holographic images of single white blood cells in suspension, in order to establish an accurate ground truth to increase classification accuracy. We also automate the entire workflow for analyzing the output and demonstrate clear improvement in the accuracy of the 3-part classification. High-dimensional optical and morphological features are extracted from reconstructed digital holograms of single cells using the ground-truth images and advanced machine learning algorithms are investigated and implemented to obtain 99% classification accuracy. Representative features of the three white blood cell subtypes are selected and give comparable results, with a focus on rapid cell recognition and decreased computational cost.

White blood cell differential count of maturation stages in bone marrow smear using dual-stage convolutional neural networks

The white blood cell differential count of the bone marrow provides information concerning the distribution of immature and mature cells within maturation stages. The results of such examinations are important for the diagnosis of various diseases and for follow-up care after chemotherapy. However, manual, labor-intensive methods to determine the differential count lead to inter- and intra-variations among the results obtained by hematologists. Therefore, an automated system to conduct the white blood cell differential count is highly desirable, but several difficulties hinder progress. There are variations in the white blood cells of each maturation stage, small inter-class differences within each stage, and variations in images because of the different acquisition and staining processes. Moreover, a large number of classes need to be classified for bone marrow smear analysis, and the high density of touching cells in bone marrow smears renders difficult the segmentation of single cells, which is crucial to traditional image processing and machine learning. Few studies have attempted to discriminate bone marrow cells, and even these have either discriminated only a few classes or yielded insufficient performance. In this study, we propose an automated white blood cell differential counting system from bone marrow smear images using a dual-stage convolutional neural network (CNN). A total of 2,174 patch images were collected for training and testing. The dual-stage CNN classified images into 10 classes of the myeloid and erythroid maturation series, and achieved an accuracy of 97.06%, a precision of 97.13%, a recall of 97.06%, and an F-1 score of 97.1%. The proposed method not only showed high classification performance, but also successfully classified raw images without single cell segmentation and manual feature extraction by implementing CNN. Moreover, it demonstrated rotation and location invariance. These results highlight the promise of the proposed method as an automated white blood cell differential count system.

Statistical performance of image cytometry for DNA, lipids, cytokeratin, & CD45 in a model system for circulation tumor cell detection

Detection of circulating tumor cells (CTCs) in a blood sample is limited by the sensitivity and specificity of the biomarker panel used to identify CTCs over other blood cells. In this work, we present Bayesian theory that shows how test sensitivity and specificity set the rarity of cell that a test can detect. We perform our calculation of sensitivity and specificity on our image cytometry biomarker panel by testing on pure disease positive (D⁺ ) populations (MCF7 cells) and pure disease negative populations (D^- ) (leukocytes). In this system, we performed multi-channel confocal fluorescence microscopy to image biomarkers of DNA, lipids, CD45, and Cytokeratin. Using custom software, we segmented our confocal images into regions of interest consisting of individual cells and computed the image metrics of total signal, second spatial moment, spatial frequency second moment, and the product of the spatial-spatial frequency moments. We present our analysis of these 16 features. The best performing of the 16 features produced an average separation of three standard deviations between D⁺ and D^- and an average detectable rarity of ∼1 in 200. We performed multivariable regression and feature selection to combine multiple features for increased performance and showed an average separation of seven standard deviations between the D⁺ and D^- populations making our average detectable rarity of ∼1 in 480. Histograms and receiver operating characteristics (ROC) curves for these features and regressions are presented. We conclude that simple regression analysis holds promise to further improve the separation of rare cells in cytometry applications. © 2017 International Society for Advancement of Cytometry.

Dictionary-enhanced imaging cytometry

State-of-the-art high-throughput microscopes are now capable of recording image data at a phenomenal rate, imaging entire microscope slides in minutes. In this paper we investigate how a large image set can be used to perform automated cell classification and denoising. To this end, we acquire an image library consisting of over one quarter-million white blood cell (WBC) nuclei together with CD15/CD16 protein expression for each cell. We show that the WBC nucleus images alone can be used to replicate CD expression-based gating, even in the presence of significant imaging noise. We also demonstrate that accurate estimates of white blood cell images can be recovered from extremely noisy images by comparing with a reference dictionary. This has implications for dose-limited imaging when samples belong to a highly restricted class such as a well-studied cell type. Furthermore, large image libraries may endow microscopes with capabilities beyond their hardware specifications in terms of sensitivity and resolution. We call for researchers to crowd source large image libraries of common cell lines to explore this possibility.

A new thresholding technique based on fuzzy set as an application to leukocyte nucleus segmentation

BACKGROUND AND OBJECTIVES

The main aim of this paper is to segment leukocytes in blood smear images using interval-valued intuitionistic fuzzy sets (IVIFSs). Generally, uncertainties occur in terms of vagueness through brightness levels of image. Processing of such uncertain images can be efficiently handled by using fuzzy sets, particularly IVIFSs.

METHODS

Logarithmic membership function is utilized for computing membership values corresponding to intensities of the pixel. Non-membership function of IVIFS is constructed by using Yager generating function. By varying parameters, 256 IVIFSs are generated. An IVIFS is selected from 256 IVIFSs having maximizing ultrafuzziness along with varying threshold. Threshold is determined by finding an IVIFS with maximum similarity between ideal segmented and segmented results obtained from the proposed method.

RESULTS

Quantitatively, the segmented images are evaluated using precision-recall, receiver operator characteristic curves, Jaccard coefficient and measure for structural similarity index along with the time taken for segmenting nucleus, and their results are compared with results of existing methods. Performance measures reveal that the proposed method seems to segment leukocytes better than other comparable methods.

CONCLUSIONS

Segmentation of leukocytes using the proposed method helps the analyst in differentiating various types of leukocytes and in the determination of leukocyte count, and the counting is essential in finding out diseases related to reduction or surplus quantity of these cells.

Training echo state networks for rotation-invariant bone marrow cell classification

The main principle of diagnostic pathology is the reliable interpretation of individual cells in context of the tissue architecture. Especially a confident examination of bone marrow specimen is dependent on a valid classification of myeloid cells. In this work, we propose a novel rotation-invariant learning scheme for multi-class echo state networks (ESNs), which achieves very high performance in automated bone marrow cell classification. Based on representing static images as temporal sequence of rotations, we show how ESNs robustly recognize cells of arbitrary rotations by taking advantage of their short-term memory capacity. The performance of our approach is compared to a classification random forest that learns rotation-invariance in a conventional way by exhaustively training on multiple rotations of individual samples. The methods were evaluated on a human bone marrow image database consisting of granulopoietic and erythropoietic cells in different maturation stages. Our ESN approach to cell classification does not rely on segmentation of cells or manual feature extraction and can therefore directly be applied to image data.

Computer aided detection and classification of acute lymphoblastic leukemia cell subtypes based on microscopic image analysis

Acute lymphoblastic leukemia (ALL) is a cancer that starts from the early version of white blood cells called lymphocytes in the bone marrow. It can spread to different parts of the body rapidly and if not treated, would probably be deadly within a couple of months. Leukemia cells are categorized into three types of L1, L2, and L3. The cancer is detected through screening of blood and bone marrow smears by pathologists. But manual examination of blood samples is a time-consuming and boring procedure as well as limited by human error risks. So to overcome these limitations a computer-aided detection system, capable of discriminating cancer from noncancer cases and identifying the cancerous cell subtypes, seems to be necessary. In this article an automatic detection method is proposed; first cell nucleus is segmented by fuzzy c-means clustering algorithm. Then a rich set of features including geometric, first- and second-order statistical features are obtained from the nucleus. A principal component analysis is used to reduce feature matrix dimensionality. Finally, an ensemble of SVM classifiers with different kernels and parameters is applied to classify cells into four groups, that is noncancerous, L1, L2, and L3. Results show that the proposed method can be used as an assistive diagnostic tool in laboratories.

Segmentation of white blood cells and comparison of cell morphology by linear and naïve Bayes classifiers

Background

Blood smear microscopic images are routinely investigated by haematologists to diagnose most blood diseases. However, the task is quite tedious and time consuming. An automatic detection and classification of white blood cells within such images can accelerate the process tremendously. In this paper we propose a system to locate white blood cells within microscopic blood smear images, segment them into nucleus and cytoplasm regions, extract suitable features and finally, classify them into five types: basophil, eosinophil, neutrophil, lymphocyte and monocyte.

Dataset

Two sets of blood smear images were used in this study’s experiments. Dataset 1, collected from Rangsit University, were normal peripheral blood slides under light microscope with 100× magnification; 555 images with 601 white blood cells were captured by a Nikon DS-Fi2 high-definition color camera and saved in JPG format of size 960 × 1,280 pixels at 15 pixels per 1 μm resolution. In dataset 2, 477 cropped white blood cell images were downloaded from CellaVision.com. They are in JPG format of size 360 × 363 pixels. The resolution is estimated to be 10 pixels per 1 μm.

Methods

The proposed system comprises a pre-processing step, nucleus segmentation, cell segmentation, feature extraction, feature selection and classification. The main concept of the segmentation algorithm employed uses white blood cell’s morphological properties and the calibrated size of a real cell relative to image resolution. The segmentation process combined thresholding, morphological operation and ellipse curve fitting. Consequently, several features were extracted from the segmented nucleus and cytoplasm regions. Prominent features were then chosen by a greedy search algorithm called sequential forward selection. Finally, with a set of selected prominent features, both linear and naïve Bayes classifiers were applied for performance comparison. This system was tested on normal peripheral blood smear slide images from two datasets.

Results

Two sets of comparison were performed: segmentation and classification. The automatically segmented results were compared to the ones obtained manually by a haematologist. It was found that the proposed method is consistent and coherent in both datasets, with dice similarity of 98.9 and 91.6% for average segmented nucleus and cell regions, respectively. Furthermore, the overall correction rate in the classification phase is about 98 and 94% for linear and naïve Bayes models, respectively.

Conclusions

The proposed system, based on normal white blood cell morphology and its characteristics, was applied to two different datasets. The results of the calibrated segmentation process on both datasets are fast, robust, efficient and coherent. Meanwhile, the classification of normal white blood cells into five types shows high sensitivity in both linear and naïve Bayes models, with slightly better results in the linear classifier.

Feature selection and classification of leukocytes using random forest

In automatic segmentation of leukocytes from the complex morphological background of tissue section images, a vast number of artifacts/noise are also extracted causing large amount of multivariate data generation. This multivariate data degrades the performance of a classifier to discriminate between leukocytes and artifacts/noise. However, the selection of prominent features plays an important role in reducing the computational complexity and increasing the performance of the classifier as compared to a high-dimensional features space. Therefore, this paper introduces a novel Gini importance-based binary random forest feature selection method. Moreover, the random forest classifier is used to classify the extracted objects into artifacts, mononuclear cells, and polymorphonuclear cells. The experimental results establish that the proposed method effectively eliminates the irrelevant features, maintaining the high classification accuracy as compared to other feature reduction methods.

Automated microscopic image analysis for leukocytes identification: a survey

Automatic quantification and classification of leukocytes in microscopic images are of paramount importance in the perspective of disease identification, its progress and drugs development. Extracting numerical values of leukocytes from microscopic images of blood or tissue sections represents a tricky challenge. Research efforts in quantification of these cells include normalization of images, segmentation of its nuclei and cytoplasm followed by their classification. However, there are several related problems viz., coarse background, overlapped nuclei, conversion of 3-D nuclei into 2-D nuclei etc. In this review, we have categorized, evaluated, and discussed recently developed methods for leukocyte identification. After reviewing these methods and finding their constraints, a future research perspective has been presented. Further, the challenges faced by the pathologists with respect to these problems are also discussed.

Automatic cervical cell segmentation and classification in Pap smears

Cervical cancer is one of the leading causes of cancer death in females worldwide. The disease can be cured if the patient is diagnosed in the pre-cancerous lesion stage or earlier. A common physical examination technique widely used in the screening is Papanicolaou test or Pap test. In this research, a method for automatic cervical cancer cell segmentation and classification is proposed. A single-cell image is segmented into nucleus, cytoplasm, and background, using the fuzzy C-means (FCM) clustering technique. Four cell classes in the ERUDIT and LCH datasets, i.e., normal, low grade squamous intraepithelial lesion (LSIL), high grade squamous intraepithelial lesion (HSIL), and squamous cell carcinoma (SCC), are considered. The 2-class problem can be achieved by grouping the last 3 classes as one abnormal class. Whereas, the Herlev dataset consists of 7 cell classes, i.e., superficial squamous, intermediate squamous, columnar, mild dysplasia, moderate dysplasia, severe dysplasia, and carcinoma in situ. These 7 classes can also be grouped to form a 2-class problem. These 3 datasets were tested on 5 classifiers including Bayesian classifier, linear discriminant analysis (LDA), K-nearest neighbor (KNN), artificial neural networks (ANN), and support vector machine (SVM). For the ERUDIT dataset, ANN with 5 nucleus-based features yielded the accuracies of 96.20% and 97.83% on the 4-class and 2-class problems, respectively. For the Herlev dataset, ANN with 9 cell-based features yielded the accuracies of 93.78% and 99.27% for the 7-class and 2-class problems, respectively. For the LCH dataset, ANN with 9 cell-based features yielded the accuracies of 95.00% and 97.00% for the 4-class and 2-class problems, respectively. The segmentation and classification performances of the proposed method were compared with that of the hard C-means clustering and watershed technique. The results show that the proposed automatic approach yields very good performance and is better than its counterparts.

A neural-network-based approach to white blood cell classification

This paper presents a new white blood cell classification system for the recognition of five types of white blood cells. We propose a new segmentation algorithm for the segmentation of white blood cells from smear images. The core idea of the proposed segmentation algorithm is to find a discriminating region of white blood cells on the HSI color space. Pixels with color lying in the discriminating region described by an ellipsoidal region will be regarded as the nucleus and granule of cytoplasm of a white blood cell. Then, through a further morphological process, we can segment a white blood cell from a smear image. Three kinds of features (i.e., geometrical features, color features, and LDP-based texture features) are extracted from the segmented cell. These features are fed into three different kinds of neural networks to recognize the types of the white blood cells. To test the effectiveness of the proposed white blood cell classification system, a total of 450 white blood cells images were used. The highest overall correct recognition rate could reach 99.11% correct. Simulation results showed that the proposed white blood cell classification system was very competitive to some existing systems.

Identifying neutrophils in H&E staining histology tissue images

Identifying neutrophils lays a crucial foundation for diagnosing acute inflammation diseases. But, such computerized methods on the commonly used H&E staining histology tissue images are lacking, due to various inherent difficulties of identifying cells in such image modality and the challenge that a considerable portion of neutrophils do not have a "textbook" appearance. In this paper, we propose a new method for identifying neutrophils in H&E staining histology tissue images. We first segment the cells by applying iterative edge labeling, and then identify neutrophils based on the segmentation results by considering the "context" of each candidate cell constructed by a new Voronoi diagram of clusters of other neutrophils. We obtain good performance compared with two baseline algorithms we constructed, on clinical images collected from patients suspected of having inflammatory bowl diseases.

Scalable system for classification of white blood cells from Leishman stained blood stain images

INTRODUCTION

The White Blood Cell (WBC) differential count yields clinically relevant information about health and disease. Currently, pathologists manually annotate the WBCs, which is time consuming and susceptible to error, due to the tedious nature of the process. This study aims at automation of the Differential Blood Count (DBC) process, so as to increase productivity and eliminate human errors.

MATERIALS AND METHODS

The proposed system takes the peripheral Leishman blood stain images as the input and generates a count for each of the WBC subtypes. The digitized microscopic images are stain normalized for the segmentation, to be consistent over a diverse set of slide images. Active contours are employed for robust segmentation of the WBC nucleus and cytoplasm. The seed points are generated by processing the images in Hue-Saturation-Value (HSV) color space. An efficient method for computing a new feature, 'number of lobes,' for discrimination of WBC subtypes, is introduced in this article. This method is based on the concept of minimization of the compactness of each lobe. The Naive Bayes classifier, with Laplacian correction, provides a fast, efficient, and robust solution to multiclass categorization problems. This classifier is characterized by incremental learning and can also be embedded within the database systems.

RESULTS

An overall accuracy of 92.45% and 92.72% over the training and testing sets has been obtained, respectively.

CONCLUSION

Thus, incremental learning is inducted into the Naive Bayes Classifier, to facilitate fast, robust, and efficient classification, which is evident from the high sensitivity achieved for all the subtypes of WBCs.

Parameter Optimization of Local Fuzzy Patterns Based on Fuzzy Contrast Measure for White Blood Cell Texture Feature Extraction

The parameter optimization of local fuzzy patterns based on the fuzzy contrast measure is proposed for extracting white blood cell texture. The proposed method obtains the optimal parameter values of the nucleus and cytoplasm region of white blood cell image and the best accuracy rate of white blood cell classification can therefore be achieved. To evaluate the performance of the proposed method, 100 microscopic white blood cell images and the supervised learning method are used for white blood cell classification. Results show that the average accuracy rate of white blood cell classification using local fuzzy pattern features with optimal parameter values of a nucleus and a cytoplasm region is 4% more accurate than with uniform parameter values and is 5–18% more accurate than other feature extraction methods. White blood cell feature extraction is part of the white blood cell classification in an automatic cancer diagnosis that is being developed. In addition, the proposed method can be used to obtain the optimal parameter of local fuzzy patterns for other types of datasets.

Unsupervised Leukocyte Image Segmentation Using Rough Fuzzy Clustering

The segmentation of leukocytes and their components acts as the foundation for all automated image-based hematological disease recognition systems. Perfection in image segmentation is a necessary condition for improving the diagnostic accuracy in automated cytology. Since the diagnostic information content of the segmented images is plentiful, suitable segmentation routines need to be developed for better disease recognition. Clustering is an essential image segmentation procedure which segments an image into desired regions. A judicious integration of rough sets and fuzzy sets is suitably employed towards leukocyte segmentation in a clustering framework. In this study, the goodness of fuzzy sets and rough sets is suitably integrated to achieve improved segmentation performance. The membership concept of fuzzy sets endow is efficient handling of overlapping partitions, and the rough sets provide a reasonable solution to deal with uncertainty, vagueness, and incompleteness in data. Such synergistic combination gives the proposed scheme an edge over standard cluster-based segmentation techniques, that is, K-means, K-medoid, fuzzy c-means, and rough c-means. Comparative analysis reveals that the hybrid rough fuzzy c-means algorithm is robust in segmenting stained blood microscopic images. The accomplished segmented nucleus and cytoplasm of a leukocyte can be used for feature extraction which leads to automated leukemia detection.

BLOOD CELL IDENTIFICATION USING A SIMPLE NEURAL NETWORK

Classification of blood cell types can be time consuming and susceptible to error due to the different morphological features of the cells. This paper presents a blood cell identification system that simulates a human visual inspection and identification of the three blood cell types. The proposed system uses global pattern averaging to extract cell features, and a neural network to classify the cell type. Two neural networks are investigated and a comparison between these networks is drawn. Experimental results suggest that the proposed system provides fast, simple and efficient identification which can be used in automating laboratory reporting.

Automatic recognition of five types of white blood cells in peripheral blood

This paper proposes image processing algorithms to recognize five types of white blood cells in peripheral blood automatically. First, a method based on Gram-Schmidt orthogonalization is proposed along with a snake algorithm to segment nucleus and cytoplasm of the cells. Then, a variety of features are extracted from the segmented regions. Next, most discriminative features are selected using a Sequential Forward Selection (SFS) algorithm and performances of two classifiers, Artificial Neural Network (ANN) and Support Vector Machine (SVM), are compared. The results demonstrate that the proposed methods are accurate and sufficiently fast to be used in hematological laboratories.

Automatic classification of lymphoma images with transform-based global features

We propose a report on automatic classification of three common types of malignant lymphoma: chronic lymphocytic leukemia, follicular lymphoma, and mantle cell lymphoma. The goal was to find patterns indicative of lymphoma malignancies and allowing classifying these malignancies by type. We used a computer vision approach for quantitative characterization of image content. A unique two-stage approach was employed in this study. At the outer level, raw pixels were transformed with a set of transforms into spectral planes. Simple (Fourier, Chebyshev, and wavelets) and compound transforms (Chebyshev of Fourier and wavelets of Fourier) were computed. Raw pixels and spectral planes were then routed to the second stage (the inner level). At the inner level, the set of multipurpose global features was computed on each spectral plane by the same feature bank. All computed features were fused into a single feature vector. The specimens were stained with hematoxylin (H) and eosin (E) stains. Several color spaces were used: RGB, gray, CIE-L*a*b*, and also the specific stain-attributed H&E space, and experiments on image classification were carried out for these sets. The best signal (98%-99% on earlier unseen images) was found for the HE, H, and E channels of the H&E data set.

Leukocyte nucleus segmentation and nucleus lobe counting

Background

Leukocytes play an important role in the human immune system. The family of leukocytes is comprised of lymphocytes, monocytes, eosinophils, basophils, and neutrophils. Any infection or acute stress may increase or decrease the number of leukocytes. An increased percentage of neutrophils may be caused by an acute infection, while an increased percentage of lymphocytes can be caused by a chronic bacterial infection. It is important to realize an abnormal variation in the leukocytes. The five types of leukocytes can be distinguished by their cytoplasmic granules, staining properties of the granules, size of cell, the proportion of the nuclear to the cytoplasmic material, and the type of nucleolar lobes. The number of lobes increased when leukemia, chronic nephritis, liver disease, cancer, sepsis, and vitamin B12 or folate deficiency occurred. Clinical neutrophil hypersegmentation has been widely used as an indicator of B12 or folate deficiency.Biomedical technologists can currently recognize abnormal leukocytes using human eyes. However, the quality and efficiency of diagnosis may be compromised due to the limitations of the biomedical technologists' eyesight, strength, and medical knowledge. Therefore, the development of an automatic leukocyte recognition system is feasible and necessary. It is essential to extract the leukocyte region from a blood smear image in order to develop an automatic leukocyte recognition system. The number of lobes increased when leukemia, chronic nephritis, liver disease, cancer, sepsis, and vitamin B12 or folate deficiency occurred. Clinical neutrophil hypersegmentation has been widely used as an indicator of B12 or folate deficiency.

Results

The purpose of this paper is to contribute an automatic leukocyte nuclei image segmentation method for such recognition technology. The other goal of this paper is to develop the method of counting the number of lobes in a cell nucleus. The experimental results demonstrated impressive segmentation accuracy.

Conclusions

Insensitive to the variance of images, the LNS (Leukocyte Nuclei Segmentation) method functioned well to isolate the leukocyte nuclei from a blood smear image with much better UR (Under Segmentation Rate), ER (Overall Error Rate), and RDE (Relative Distance Error). The presented LC (Lobe Counting) method is capable of splitting leukocyte nuclei into lobes. The experimental results illuminated that both methods can give expressive performances. In addition, three advanced image processing techniques were proposed as weighted Sobel operator, GDW (Gradient Direction Weight), and GBPD (Genetic-based Parameter Detector).

Boundary detection in medical images using edge following algorithm based on intensity gradient and texture gradient features

Finding the correct boundary in noisy images is still a difficult task. This paper introduces a new edge following technique for boundary detection in noisy images. Utilization of the proposed technique is exhibited via its application to various types of medical images. Our proposed technique can detect the boundaries of objects in noisy images using the information from the intensity gradient via the vector image model and the texture gradient via the edge map. The performance and robustness of the technique have been tested to segment objects in synthetic noisy images and medical images including prostates in ultrasound images, left ventricles in cardiac magnetic resonance (MR) images, aortas in cardiovascular MR images, and knee joints in computerized tomography images. We compare the proposed segmentation technique with the active contour models (ACM), geodesic active contour models, active contours without edges, gradient vector flow snake models, and ACMs based on vector field convolution, by using the skilled doctors' opinions as the ground truths. The results show that our technique performs very well and yields better performance than the classical contour models. The proposed method is robust and applicable on various kinds of noisy images without prior knowledge of noise properties.