Automatic classification of acute lymphoblastic leukemia cells and lymphocyte subtypes based on a novel convolutional neural network.

Acute lymphoblastic leukemia (ALL) is a life-threatening disease that commonly affects children and is classified into three subtypes: L1, L2, and L3. Traditionally, ALL is diagnosed through morphological analysis, involving the examination of blood and bone marrow smears by pathologists. However, this manual process is time-consuming, laborious, and prone to errors. Moreover, the significant morphological similarity between ALL and various lymphocyte subtypes, such as normal, atypic, and reactive lymphocytes, further complicates the feature extraction and detection process. The aim of this study is to develop an accurate and efficient automatic system to distinguish ALL cells from these similar lymphocyte subtypes without the need for direct feature extraction. First, the contrast of microscopic images is enhanced using histogram equalization, which improves the visibility of important features. Next, a fuzzy C-means clustering algorithm is employed to segment cell nuclei, as they play a crucial role in ALL diagnosis. Finally, a novel convolutional neural network (CNN) with three convolutional layers is utilized to classify the segmented nuclei into six distinct classes. The CNN is trained on a labeled dataset, allowing it to learn the distinguishing features of each class. To evaluate the performance of the proposed model, quantitative metrics are employed, and a comparison is made with three well-known deep networks: VGG-16, DenseNet, and Xception. The results demonstrate that the proposed model outperforms these networks, achieving an approximate accuracy of 97%. Moreover, the model's performance surpasses that of other studies focused on 6-class classification in the context of ALL diagnosis. RESEARCH HIGHLIGHTS: Deep neural networks eliminate the requirement for feature extraction in ALL classification The proposed convolutional neural network achieves an impressive accuracy of approximately 97% in classifying six ALL and lymphocyte subtypes.

RedTell: an AI tool for interpretable analysis of red blood cell morphology.

Introduction: Hematologists analyze microscopic images of red blood cells to study their morphology and functionality, detect disorders and search for drugs. However, accurate analysis of a large number of red blood cells needs automated computational approaches that rely on annotated datasets, expensive computational resources, and computer science expertise. We introduce RedTell, an AI tool for the interpretable analysis of red blood cell morphology comprising four single-cell modules: segmentation, feature extraction, assistance in data annotation, and classification. Methods: Cell segmentation is performed by a trained Mask R-CNN working robustly on a wide range of datasets requiring no or minimum fine-tuning. Over 130 features that are regularly used in research are extracted for every detected red blood cell. If required, users can train task-specific, highly accurate decision tree-based classifiers to categorize cells, requiring a minimal number of annotations and providing interpretable feature importance. Results: We demonstrate RedTell's applicability and power in three case studies. In the first case study we analyze the difference of the extracted features between the cells coming from patients suffering from different diseases, in the second study we use RedTell to analyze the control samples and use the extracted features to classify cells into echinocytes, discocytes and stomatocytes and finally in the last use case we distinguish sickle cells in sickle cell disease patients. Discussion: We believe that RedTell can accelerate and standardize red blood cell research and help gain new insights into mechanisms, diagnosis, and treatment of red blood cell associated disorders.

AIMIC: Deep Learning for Microscopic Image Classification.

BACKGROUND AND OBJECTIVE: Deep learning techniques are powerful tools for image analysis. However, the lack of programming experience makes it difficult for novice users to apply this technology. This project aims to lower the barrier for clinical users to implement deep learning methods in microscopic image classification. METHODS: In this study, an out-of-the-box software, AIMIC (artificial intelligence-based microscopy image classifier), was developed for users to apply deep learning technology in a code-free manner. The platform was equipped with state-of-the-art deep learning techniques and data preprocessing approaches. Furthermore, we evaluated the built-in networks on four benchmark microscopy image datasets to assist entry-level practitioners in selecting a suitable algorithm. RESULTS: The entire deep learning pipeline, from training a new network to inferring unseen samples using the trained model, could be implemented on the proposed platform without the need for programming. In the evaluation experiments, the ResNeXt-50-32×4d outperformed other competitor algorithms in terms of average accuracy (96.83%) and average F1-score (96.82%). In addition, the MobileNet-V2 achieved a good balance between the performance (accuracy of 95.72%) and computational cost (inference time of 0.109s for identifying one sample). CONCLUSIONS: The proposed AI platform allows people without programming experience to use artificial intelligence methods in microscopy image analysis. Besides, the ResNeXt-50-32×4d is a preferable solution for microscopic image classification, and MobileNet-V2 is most likely to be an alternative selection for the scenario when computing resources are limited.

Spatial Metrics of Interaction between CD163-Positive Macrophages and Cancer Cells and Progression-Free Survival in Chemo-Treated Breast Cancer.

Tumor-associated macrophages (TAMs) promote progression of breast cancer and other solid malignancies via immunosuppressive, pro-angiogenic and pro-metastatic effects. Tumor-promoting TAMs tend to express M2-like macrophage markers, including CD163. Histopathological assessments suggest that the density of CD163-positive TAMs within the tumor microenvironment is associated with reduced efficacy of chemotherapy and unfavorable prognosis. However, previous analyses have required research-oriented pathologists to visually enumerate CD163+ TAMs, which is both laborious and subjective and hampers clinical implementation. Objective, operator-independent image analysis methods to quantify TAM-associated information are needed. In addition, since M2-like TAMs exert local effects on cancer cells through direct juxtacrine cell-to-cell interactions, paracrine signaling, and metabolic factors, we hypothesized that spatial metrics of adjacency of M2-like TAMs to breast cancer cells will have further information value. Immunofluorescence histo-cytometry of CD163+ TAMs was performed retrospectively on tumor microarrays of 443 cases of invasive breast cancer from patients who subsequently received adjuvant chemotherapy. An objective and automated algorithm was developed to phenotype CD163+ TAMs and calculate their density within the tumor stroma and derive several spatial metrics of interaction with cancer cells. Shorter progression-free survival was associated with a high density of CD163+ TAMs, shorter median cancer-to-CD163+ nearest neighbor distance, and a high number of either directly adjacent CD163+ TAMs (within juxtacrine proximity <12 µm to cancer cells) or communicating CD163+ TAMs (within paracrine communication distance <250 µm to cancer cells) after multivariable adjustment for clinical and pathological risk factors and correction for optimistic bias due to dichotomization.

Multi-stage malaria parasite recognition by deep learning.

MOTIVATION: Malaria, a mosquito-borne infectious disease affecting humans and other animals, is widespread in tropical and subtropical regions. Microscopy is the most common method for diagnosing the malaria parasite from stained blood smear samples. However, this technique is time consuming and must be performed by a well-trained professional, yet it remains prone to errors. Distinguishing the multiple growth stages of parasites remains an especially challenging task. RESULTS: In this article, we develop a novel deep learning approach for the recognition of malaria parasites of various stages in blood smear images using a deep transfer graph convolutional network (DTGCN). To our knowledge, this is the first application of graph convolutional network (GCN) on multi-stage malaria parasite recognition in such images. The proposed DTGCN model is based on unsupervised learning by transferring knowledge learnt from source images that contain the discriminative morphology characteristics of multi-stage malaria parasites. This transferred information guarantees the effectiveness of the target parasite recognition. This approach first learns the identical representations from the source to establish topological correlations between source class groups and the unlabelled target samples. At this stage, the GCN is implemented to extract graph feature representations for multi-stage malaria parasite recognition. The proposed method showed higher accuracy and effectiveness in publicly available microscopic images of multi-stage malaria parasites compared to a wide range of state-of-the-art approaches. Furthermore, this method is also evaluated on a large-scale dataset of unseen malaria parasites and the Babesia dataset. AVAILABILITY: Code and dataset are available at https://github.com/senli2018/DTGCN_2021 under a MIT license.

AdipoGauge software for analysis of biological microscopic images.

Obesity is a complex disease of global epidemic proportions. Adipose tissue expansion and chronic low-grade inflammation, locally and systemically, are hallmark features of obesity. Obesity is associated with several other chronic diseases, which are also characterized by inflammation. Determination of adipocyte size and macrophage content in adipose tissue is a critical step in assessing changes in this tissue with obesity. Here, we introduce a complete standalone software package, AdipoGauge, to analyse microscopic images derived from haematoxylin and eosin (H&E)-stained and immunofluorescently stained histology sections of adipose tissue. The software package is a user-friendly application that does not require a vast knowledge of computer science or costly commercial tools. AdipoGauge includes analysing tools that are capable of cell counting and colour separation. Furthermore, it can quantify the cell data in images both with and without clear boundaries around the cells. It can also remove objects from the image that are not intended for analysis, such as blood vessels or partial cells at edges of slide sections. The simple and state-of-the-art graphical user interface requires minimal time and learning.

Elevated CO2 promotes satellite stomata production in young cotyledons of Arabidopsis thaliana.

Stomata are tiny pores on plant leaves and stems surrounded by a pair of differentiated epidermal cells known as guard cells. Plants undergo guard cell differentiation in response to environmental cues, including atmospheric CO2 . To quantitatively evaluate stomatal development in response to elevated CO2 , imaging analysis of stomata was conducted using young cotyledons of Arabidopsis thaliana grown under ambient (380 ppm) and elevated (1,000 ppm) CO2 conditions. Our analysis revealed that treatment with 1,000 ppm CO2 did not affect stomatal numbers on abaxial sides of cotyledons but increased cotyledon area, resulting in decreased stomatal density, 7 days after germination. Interestingly, this treatment also perturbed the uniform distribution of stomata via excess satellite stomata and stomatal precursor cells. We used overexpression lines of the DNA replication licensing factor gene CDC6, a reported positive regulator of satellite stomata production. CDC6 overexpression decreased the speed of cotyledon expansion, even under treatment with 1,000 ppm CO2 , possibly by suppressing pavement cell maturation. In contrast, treatment with 1,000 ppm CO2 induced stomatal distribution changes in the overexpressor. These results suggest that treatment with 1,000 ppm CO2 enhances both cotyledon expansion and satellite stomata production via independent pathways, at least in young cotyledons of A. thaliana.

Acute Lymphoblastic Leukemia Detection and Classification of Its Subtypes Using Pretrained Deep Convolutional Neural Networks.

Leukemia is a fatal disease of white blood cells which affects the blood and bone marrow in human body. We deployed deep convolutional neural network for automated detection of acute lymphoblastic leukemia and classification of its subtypes into 4 classes, that is, L1, L2, L3, and Normal which were mostly neglected in previous literature. In contrary to the training from scratch, we deployed pretrained AlexNet which was fine-tuned on our data set. Last layers of the pretrained network were replaced with new layers which can classify the input images into 4 classes. To reduce overtraining, data augmentation technique was used. We also compared the data sets with different color models to check the performance over different color images. For acute lymphoblastic leukemia detection, we achieved a sensitivity of 100%, specificity of 98.11%, and accuracy of 99.50%; and for acute lymphoblastic leukemia subtype classification the sensitivity was 96.74%, specificity was 99.03%, and accuracy was 96.06%. Unlike the standard methods, our proposed method was able to achieve high accuracy without any need of microscopic image segmentation.

Hybrid feature extraction techniques for microscopic hepatic fibrosis classification.

Chronic liver diseases' hallmark is the fibrosis that results in liver function failure in advanced stages. One of the serious parasitic diseases affecting the liver tissues is schistosomiasis. Immunologic reactions to Schistosoma eggs leads to accumulation of collagen in the hepatic parenchyma causing fibrosis. Thus, monitoring and reporting the staging of the histopathological information related to liver fibrosis are essential for accurate diagnosis and therapy of the chronic liver diseases. Automated assessment of the microscopic liver tissue images is an essential process. For accurate and timeless assessment, an automated image analysis and classification of different stages of fibrosis can be employed as an efficient procedure. In this work, granuloma stages, namely cellular, fibrocellular, and fibrotic granulomas along with normal liver samples were classified after features extraction. In this work, a new hybrid combination of statistical features with empirical mode decomposition (EMD) is proposed. These combined features are further classified using the back-propagation neural network (BPNN). A comparative study of the used classifier with the support vector machine is also conducted. The comparative results established that the BPNN achieved superior accuracy of 98.3% compared to the linear SVM, quadratic SVM, and cubic SVM that provided 85%, 84%, and 80%; respectively. In conclusion, this work is of special value that provides promising results for early prediction of the liver fibrosis in schistosomiais and other fibrotic liver diseases in no time with expected better prognosis after treatment.

A Clinicopathological Study of Various Oral Cancer Diagnostic Techniques.

Oral cancer is one of the most commonly occurring malignant tumors in the head and neck regions with high incident rate and mortality rate in the developed countries than in the developing countries. Generally, the survival rate of cancer patients may increase when diagnosed at early stage, followed by prompt treatment and therapy. Recently, cancer diagnosis and therapy design for a specific cancer patient have been performed with the advanced computer-aided techniques. The responses of the cancer therapy could be continuously monitored to ensure the effectiveness of the treatment process that hardly requires diagnostic result as quick as possible to improve the quality and patient care. This paper gives an overview of oral cancer occurrence, different types, and various diagnostic techniques. In addition, a brief introduction is given to various stages of immunoanalysis including tissue image preparation, whole slide imaging, and microscopic image analysis.

Parallel multiple instance learning for extremely large histopathology image analysis.

BACKGROUND: Histopathology images are critical for medical diagnosis, e.g., cancer and its treatment. A standard histopathology slice can be easily scanned at a high resolution of, say, 200,000×200,000 pixels. These high resolution images can make most existing imaging processing tools infeasible or less effective when operated on a single machine with limited memory, disk space and computing power. RESULTS: In this paper, we propose an algorithm tackling this new emerging "big data" problem utilizing parallel computing on High-Performance-Computing (HPC) clusters. Experimental results on a large-scale data set (1318 images at a scale of 10 billion pixels each) demonstrate the efficiency and effectiveness of the proposed algorithm for low-latency real-time applications. CONCLUSIONS: The framework proposed an effective and efficient system for extremely large histopathology image analysis. It is based on the multiple instance learning formulation for weakly-supervised learning for image classification, segmentation and clustering. When a max-margin concept is adopted for different clusters, we obtain further improvement in clustering performance.

Cell wall accumulation of fluorescent proteins derived from a trans-Golgi cisternal membrane marker and paramural bodies in interdigitated Arabidopsis leaf epidermal cells.

In most dicotyledonous plants, leaf epidermal pavement cells develop jigsaw puzzle-like shapes during cell expansion. The rapid growth and complicated cell shape of pavement cells is suggested to be achieved by targeted exocytosis that is coordinated with cytoskeletal rearrangement to provide plasma membrane and/or cell wall materials for lobe development during their morphogenesis. Therefore, visualization of membrane trafficking in leaf pavement cells should contribute an understanding of the mechanism of plant cell morphogenesis. To reveal membrane trafficking in pavement cells, we observed monomeric red fluorescent protein-tagged rat sialyl transferases, which are markers of trans-Golgi cisternal membranes, in the leaf epidermis of Arabidopsis thaliana. Quantitative fluorescence imaging techniques and immunoelectron microscopic observations revealed that accumulation of the red fluorescent protein occurred mostly in the curved regions of pavement cell borders and guard cell ends during leaf expansion. Transmission electron microscopy observations revealed that apoplastic vesicular membrane structures called paramural bodies were more frequent beneath the curved cell wall regions of interdigitated pavement cells and guard cell ends in young leaf epidermis. In addition, pharmacological studies showed that perturbations in membrane trafficking resulted in simple cell shapes. These results suggested possible heterogeneity of the curved regions of plasma membranes, implying a relationship with pavement cell morphogenesis.

Peripheral blood smear image analysis: A comprehensive review.

Peripheral blood smear image examination is a part of the routine work of every laboratory. The manual examination of these images is tedious, time-consuming and suffers from interobserver variation. This has motivated researchers to develop different algorithms and methods to automate peripheral blood smear image analysis. Image analysis itself consists of a sequence of steps consisting of image segmentation, features extraction and selection and pattern classification. The image segmentation step addresses the problem of extraction of the object or region of interest from the complicated peripheral blood smear image. Support vector machine (SVM) and artificial neural networks (ANNs) are two common approaches to image segmentation. Features extraction and selection aims to derive descriptive characteristics of the extracted object, which are similar within the same object class and different between different objects. This will facilitate the last step of the image analysis process: pattern classification. The goal of pattern classification is to assign a class to the selected features from a group of known classes. There are two types of classifier learning algorithms: supervised and unsupervised. Supervised learning algorithms predict the class of the object under test using training data of known classes. The training data have a predefined label for every class and the learning algorithm can utilize this data to predict the class of a test object. Unsupervised learning algorithms use unlabeled training data and divide them into groups using similarity measurements. Unsupervised learning algorithms predict the group to which a new test object belong to, based on the training data without giving an explicit class to that object. ANN, SVM, decision tree and K-nearest neighbor are possible approaches to classification algorithms. Increased discrimination may be obtained by combining several classifiers together.

Expression of Kiss-1, Ki-67 and VEGF-C in papillary thyroid carcinoma and its stereological determination / 军事医学

Objective To explore the expression and significance of Kiss-1, Ki-67 and VEGF-C in papillary thyroid carcinoma(PTC) and thyroid follicular adenoma (FA).Methods Forty-four cases of PTC and twelve cases of FA paraffin-embedded tissues were used .Immunohistochemical staining and microscopic image analysis technique were used to analyze the expression of Kiss-1, Ki-67 and VEGF-C.Results The integrated optical density (IOD) of Kiss-1, and VEGF-C in the PTC groups was 475.56 ±126.02 and 805.29 ±226.05,respectively.The proliferation index of Ki-67 protein was (3.36 ±1.11) %and the difference between the PTC and FA groups was statistically significant (P<0.05).The IOD of the above two indices was 408.12 ±124.05 and 912.63 ±108.12 in the PTC with lymph node metastasis group , respectively, while the proliferation index of Ki -67 protein was (3.93 ±0.92) % and the difference vs the group without lymph node metastasis was significant ( P <0.05 ) .In the PTC with capsular infiltration group the IOD of above two was 425.58 ±87.38 and 891.37 ±149.36, the proliferation index of Ki -67 protein was (3.79 ±1.09) %and the difference with PTC group without capsular infiltrtion was statistically significant (P<0.05).Linear correlation analysis showed that Ki-67 and VEGF-C were with positively correlated in PTC and FA tissues (P<0.05),while Kiss-1 and Ki-67, VEGF-C were with negatively correlated in PTC and FA tissues (P<0.05).Conclusion Kiss-1, Ki-67 and VEGF-C can facilitate the differential diagnosis of PTC and FA , serving as prognostic indicators in patients with PTC .