Search

Background: Preclinical cell tracking is enhanced with a multimodal imaging approach. Bioluminescence imaging (BLI) is a highly sensitive optical modality that relies on engineering cells to constitutively express a luciferase gene. Magnetic particle imaging (MPI) is a newer imaging modality that directly detects superparamagnetic iron oxide (SPIO) particles used to label cells. Here, we compare BLI and MPI for imaging cells in vitro and in vivo. Methods: Mouse 4T1 breast carcinoma cells were transduced to express firefly luciferase, labeled with SPIO (ProMag), and imaged as cell samples after subcutaneous injection into mice. Results: For cell samples, the BLI and MPI signals were strongly correlated with cell number. Both modalities presented limitations for imaging cells in vivo. For BLI, weak signal penetration, signal attenuation, and scattering prevented the detection of cells for mice with hair and for cells far from the tissue surface. For MPI, background signals obscured the detection of low cell numbers due to the limited dynamic range, and cell numbers could not be accurately quantified from in vivo images. Conclusions: It is important to understand the shortcomings of these imaging modalities to develop strategies to improve cellular detection sensitivity.

We investigated the design and characterization of a Lab-On-a-Chip (LoC) cell detection system primarily designed to support immunotherapy in cancer treatment. Immunotherapy uses Chimeric Antigen Receptors (CARs) and T Cell Receptors (TCRs) to fight cancer, engineering the response of the immune system. In recent years, it has emerged as a promising strategy for personalized cancer treatment. However, it requires bioreactor-based cell culture expansion and manual quality control (QC) of the modified cells, which is time-consuming, labour-intensive, and prone to errors. The miniaturized LoC device for automated QC demonstrated here is simple, has a low cost, and is reliable. Its final target is to become one of the building blocks of an LoC for immunotherapy, which would take the place of present labs and manual procedures to the benefit of throughput and affordability. The core of the system is a commercial, on-chip-integrated capacitive sensor managed by a microcontroller capable of sensing cells as accurately measured charge variations. The hardware is based on standardized components, which makes it suitable for mass manufacturing. Moreover, unlike in other cell detection solutions, no external AC source is required. The device has been characterized with a cell line model selectively labelled with gold nanoparticles to simulate its future use in bioreactors in which labelling can apply to successfully engineered CAR-T-cells. Experiments were run both in the air—free drop with no microfluidics—and in the channel, where the fluid volume was considerably lower than in the drop. The device showed good sensitivity even with a low number of cells—around 120, compared with the 107 to 108 needed per kilogram of body weight—which is desirable for a good outcome of the expansion process. Since cell detection is needed in several contexts other than immunotherapy, the usefulness of this LoC goes potentially beyond the scope considered here. [ABSTRACT FROM AUTHOR]

Microscopy image analysis plays a crucial role in understanding cellular behavior and uncovering important insights in various biological and medical research domains. Tracking cells within the time‐lapse microscopy images is a fundamental technique that enables the study of cell dynamics, interactions, and migration. While manual cell tracking is possible, it is time‐consuming and prone to subjective biases that impact results. In order to solve this issue, we sought to create an automated software solution, named cell analyzer, which is able to track cells within microscopy images with minimal input required from the user. The program of cell analyzer was written in Python utilizing the open source computer vision (OpenCV) library and featured a graphical user interface that makes it easy for users to access. The functions of all codes were verified through closeness, area, centroid, contrast, variance, and cell tracking test. Cell analyzer primarily utilizes image preprocessing and edge detection techniques to isolate cell boundaries for detection and analysis. It uniquely recorded the area, displacement, speed, size, and direction of detected cell objects and visualized the data collected automatically for fast analysis. Our cell analyzer provides an easy‐to‐use tool through a graphical user interface for tracking cell motion and analyzing quantitative cell images. [ABSTRACT FROM AUTHOR]

Background: Preclinical cell tracking is enhanced with a multimodal imaging approach. Bioluminescence imaging (BLI) is a highly sensitive optical modality that relies on engineering cells to constitutively express a luciferase gene. Magnetic particle imaging (MPI) is a newer imaging modality that directly detects superparamagnetic iron oxide (SPIO) particles used to label cells. Here, we compare BLI and MPI for imaging cells in vitro and in vivo. Methods: Mouse 4T1 breast carcinoma cells were transduced to express firefly luciferase, labeled with SPIO (ProMag), and imaged as cell samples after subcutaneous injection into mice. Results: For cell samples, the BLI and MPI signals were strongly correlated with cell number. Both modalities presented limitations for imaging cells in vivo. For BLI, weak signal penetration, signal attenuation, and scattering prevented the detection of cells for mice with hair and for cells far from the tissue surface. For MPI, background signals obscured the detection of low cell numbers due to the limited dynamic range, and cell numbers could not be accurately quantified from in vivo images. Conclusions: It is important to understand the shortcomings of these imaging modalities to develop strategies to improve cellular detection sensitivity. [ABSTRACT FROM AUTHOR]

Objectives: This article focuses on the detection of cells in low-contrast brightfield microscopy images; in our case, it is chronic lymphocytic leukaemia cells. The automatic detection of cells from brightfield time-lapse microscopic images brings new opportunities in cell morphology and migration studies; to achieve the desired results, it is advisable to use state-of-the-art image segmentation methods that not only detect the cell but also detect its boundaries with the highest possible accuracy, thus defining its shape and dimensions. Methods: We compared eight state-of-the-art neural network architectures with different backbone encoders for image data segmentation, namely U-net, U-net++, the Pyramid Attention Network, the Multi-Attention Network, LinkNet, the Feature Pyramid Network, DeepLabV3, and DeepLabV3+. The training process involved training each of these networks for 1000 epochs using the PyTorch and PyTorch Lightning libraries. For instance segmentation, the watershed algorithm and three-class image semantic segmentation were used. We also used StarDist, a deep learning-based tool for object detection with star-convex shapes. Results: The optimal combination for semantic segmentation was the U-net++ architecture with a ResNeSt-269 background with a data set intersection over a union score of 0.8902. For the cell characteristics examined (area, circularity, solidity, perimeter, radius, and shape index), the difference in mean value using different chronic lymphocytic leukaemia cell segmentation approaches appeared to be statistically significant (Mann–Whitney U test, P <.0001). Conclusion: We found that overall, the algorithms demonstrate equal agreement with ground truth, but with the comparison, it can be seen that the different approaches prefer different morphological features of the cells. Consequently, choosing the most suitable method for instance-based cell segmentation depends on the particular application, namely, the specific cellular traits being investigated. [ABSTRACT FROM AUTHOR]

In the bloodstream, erythrocytes stand as vital carriers of oxygen and carbon dioxide, facilitated by the presence of hemoglobin within their structures. However, deviations in erythrocyte size can lead to the formation of Poikilocyte cells, a characteristic feature of conditions like Iron Deficiency Anemia. Variants of Poikilocytoses, such as Degmacyte, Dacrocyte, Schistocyte, and Elliptocyte, denote distinct alterations in erythrocyte morphology, often associated with diminished iron levels crucial for haemoglobin synthesis. In a recent study, the differentiation between normal RBCs and Poikilocyte cells has been addressed through the application of Artificial Neural Network (ANN) algorithms, leveraging extracted features from digital images of blood smears. This approach offers a more precise means of identifying blood disorders compared to traditional visual inspection, utilizing image analysis techniques to detect deviations in color, size, and statistical parameters. The methodology involves a series of computational steps including preprocessing, segmentation, morphological operations, feature extraction, and classification, all executed within the Matlab environment. Furthermore, to enhance diagnostic capabilities, the system integrates glucose level measurement alongside erythrocyte analysis, transmitting data to a controller which relays results via GSM signal as SMS and LCD display. This comprehensive approach not only automates cell identification and classification but also ensures efficient and accurate analysis, including the automated separation of overlapped cells. [ABSTRACT FROM AUTHOR]

Single-cell analysis provides a more information-rich approach to disease diagnosis than traditional methods. At the cellular level, electrical properties have been established as reliable disease markers, capable of revealing variations between individual cells. This study focuses on optimising the geometry of a coplanar micro-electrode structure for detecting human lung adenocarcinoma cells (A549) within a fluid channel using impedance flow cytometry. A549 cells were chosen due to their frequent occurrence in cancer cases and the extensive documentation of their electrical properties and size. To further investigate the electric field and optimise the electrode design for single-cell detection, a numerical 3D model based on the finite element method (FEM) was developed and implemented. The functionality of the sensing structure was validated using COMSOL Multiphysics, with the Electric Current module defining scalar electric potential within the 3D model. Simulations explored various parameters, including electrode dimensions, frequency range, object sizes, and electrical conductivity, to fine-tune the sensor’s performance. Additionally, the study elucidates the impact of cell position within the channel structure and cell size on impedance measurements. This numerical investigation provides insights into the acquired impedance signals, contributing to the optimisation and standardisation of the device. The proposed sensor system holds significant potential across various applications in biomedicine and chemistry, particularly in point-of-care scenarios, where the sensor chip can be conveniently configured for measurements and discarded after use.

Abstract 3D reconstruction of human brain volumes at high resolution is now possible thanks to advancements in tissue clearing methods and fluorescence microscopy techniques. Analyzing the massive data produced with these approaches requires automatic methods able to perform fast and accurate cell counting and localization. Recent advances in deep learning have enabled the development of various tools for cell segmentation. However, accurate quantification of neurons in the human brain presents specific challenges, such as high pixel intensity variability, autofluorescence, non-specific fluorescence and very large size of data. In this paper, we provide a thorough empirical evaluation of three techniques based on deep learning (StarDist, CellPose and BCFind-v2, an updated version of BCFind) using a recently introduced three-dimensional stereological design as a reference for large-scale insights. As a representative problem in human brain analysis, we focus on a $$4~\text {-cm}^3$$ 4 -cm 3 portion of the Broca’s area. We aim at helping users in selecting appropriate techniques depending on their research objectives. To this end, we compare methods along various dimensions of analysis, including correctness of the predicted density and localization, computational efficiency, and human annotation effort. Our results suggest that deep learning approaches are very effective, have a high throughput providing each cell 3D location, and obtain results comparable to the estimates of the adopted stereological design.

Recent advances in deep learning have shown significant potential for accurate cell detection via density map regression using point annotations. However, existing deep learning models often struggle with multi-scale feature extraction and integration in complex histopathological images. Moreover, in multi-class cell detection scenarios, current density map regression methods typically predict each cell type independently, failing to consider the spatial distribution priors of different cell types. To address these challenges, we propose CellRegNet, a novel deep learning model for cell detection using point annotations. CellRegNet integrates a hybrid CNN/Transformer architecture with innovative feature refinement and selection mechanisms, addressing the need for effective multi-scale feature extraction and integration. Additionally, we introduce a contrastive regularization loss that models the mutual exclusiveness prior in multi-class cell detection cases. Extensive experiments on three histopathological image datasets demonstrate that CellRegNet outperforms existing state-of-the-art methods for cell detection using point annotations, with F1-scores of 86.38% on BCData (breast cancer), 85.56% on EndoNuke (endometrial tissue) and 93.90% on MBM (bone marrow cells), respectively. These results highlight CellRegNet's potential to enhance the accuracy and reliability of cell detection in digital pathology. [ABSTRACT FROM AUTHOR]

Antibody (Ab)‐based drugs have been widely used in targeted therapies and immunotherapies, leading to significant improvements in tumor therapy. However, the failure of Ab therapy due to the loss of target antigens or Ab modifications that affect its function limits its application. In this study, we expanded the application of antibodies (Abs) by constructing a fusion protein as a versatile tool for Ab‐based target cell detection, delivery, and therapy. We first constructed a SpaC Catcher (SpaCC for short) fusion protein that included the C domains of Staphylococcal protein A (SpaC) and the SpyCatcher. SpaCC conjugated with SpyTag‐X (S‐X) to form the SpaCC‐S‐X complex, which binds non‐covalently to an Ab to form the Ab‐SpaCC‐S‐X protein complex. The "X" can be a variety of small molecules such as fluoresceins, cell‐penetrating peptide TAT, Monomethyl auristatin E (MMAE), and DNA. We found that Ab‐SpaCC‐S‐FITC(−TAT) could be used for target cell detection and delivery. Besides, we synthesized the Ab‐SpaCC‐SN3‐MMAE complex by linking Ab with MMAE by SpaCC, which improved the cytotoxicity of small molecule toxins. Moreover, we constructed an Ab‐DNA complex by conjugating SpaCC with the aptamer (Ap) and found that Ab‐SpaCC‐SN3‐Ap boosted the tumor‐killing function of T‐cells by retargeting tumor cells. Thus, we developed a multifunctional tool that could be used for targeted therapies and immunotherapies, providing a cheap and convenient novel drug development strategy. [ABSTRACT FROM AUTHOR]

This article proposes a novel concept for a two-step Ki-67/lymphocytes classification cell detection pipeline on Ki-67 stained histopathological slides utilizing commonly available and undedicated, in terms of the medical problem considered, deep learning models. Models used vary in implementation, complexity, and applications, allowing for the use of a dedicated architecture depending on the physician’s needs. Moreover, generic models’ performance was compared with the problem-dedicated one. Experiments highlight that with relatively small training datasets, commonly used architectures for instance segmentation and object detection are competitive with a dedicated model. To ensure generalization and minimize biased sampling, experiments were performed on data derived from two unrelated histopathology laboratories. [ABSTRACT FROM AUTHOR]

Although deep learning and computer vision based approaches have demonstrated success in the field of cell counting and detection in microscopic images, they continue to have certain limitations. More specifically, they experience an overall increase in false positives when dealing with cell populations that show high density and heterogeneity. Existing approaches require the reselection of parameters for each new dataset to improve the accuracy of cell counting. Therefore, it is necessary to revise the fundamental models for each new microscopic image. This study introduces a novel neural network-based method that eliminates the need for retraining by combining the pretrained Cellpose and Stardist models. The accuracy of our proposed approach was evaluated on a variety of microscopic images. Despite variations in cell densities, our proposed approach demonstrated a notably improved cell counting performance in comparison to solely utilizing the Cellpose and Stardist models.

Tuberculosis (TB) is one of the leading infectious causes of death worldwide. The effective management and public health control of this disease depends on early detection and careful treatment monitoring. For many years, the microscopy-based analysis of sputum smears has been the most common method to detect and quantify Mycobacterium tuberculosis (Mtb) bacteria. Nonetheless, this form of analysis is a challenging procedure since sputum examination can only be reliably performed by trained personnel with rigorous quality control systems in place. Additionally, it is affected by subjective judgement. Furthermore, although fluorescence-based sample staining methods have made the procedure easier in recent years, the microscopic examination of sputum is a time-consuming operation. Over the past two decades, attempts have been made to automate this practice. Most approaches have focused on establishing an automated method of diagnosis, while others have centred on measuring the bacterial load or detecting and localising Mtb cells for further research on the phenotypic characteristics of their morphology. The literature has incorporated machine learning (ML) and computer vision approaches as part of the methodology to achieve these goals. In this review, we first gathered publicly available TB sputum smear microscopy image sets and analysed the disparities in these datasets. Thereafter, we analysed the most common evaluation metrics used to assess the efficacy of each method in its particular field. Finally, we generated comprehensive summaries of prior work on ML and deep learning (DL) methods for automated TB detection, including a review of their limitations.

Multi-class segmentation of unlabelled living cells in time-lapse light microscopy images is challenging due to the temporal behaviour and changes in cell life cycles and the complexity of these images. The deep-learning-based methods achieved promising outcomes and remarkable success in single- and multi-class medical and microscopy image segmentation. The main objective of this study is to develop a hybrid deep-learning-based categorical segmentation and classification method for living HeLa cells in reflected light microscopy images. A symmetric simple U-Net and three asymmetric hybrid convolution neural networks—VGG19-U-Net, Inception-U-Net, and ResNet34-U-Net—were proposed and mutually compared to find the most suitable architecture for multi-class segmentation of our datasets. The inception module in the Inception-U-Net contained kernels with different sizes within the same layer to extract all feature descriptors. The series of residual blocks with the skip connections in each ResNet34-U-Net's level alleviated the gradient vanishing problem and improved the generalisation ability. The m-IoU scores of multi-class segmentation for our datasets reached 0.7062, 0.7178, 0.7907, and 0.8067 for the simple U-Net, VGG19-U-Net, Inception-U-Net, and ResNet34-U-Net, respectively. For each class and the mean value across all classes, the most accurate multi-class semantic segmentation was achieved using the ResNet34-U-Net architecture (evaluated as the m-IoU and Dice metrics). [ABSTRACT FROM AUTHOR]

Raman spectroscopy technique was successfully employed to study the difference between leukemic cells (Jurkat cell line) and normal human bone marrow mononuclear cells using near-infrared laser (785 nm) excitation in this study. Significant differences in Raman spectra from two kinds of cell lines showed special changes in the percentage of biochemical constituents in different cells. The obtained spectral data were used to develop diagnostic algorithms by multivariate statistical analysis, including principal component analysis combined with linear discriminate analysis. The multivariate statistical analysis method for classification between cancer and normal cells has achieved good differentiation with high diagnostic sensitivity (100%), specificity (100%), and accuracy (100%), respectively. These results showed that Raman spectroscopy is a novel, nondestructive method, that provided interesting information about the changes in biochemical properties of cells. Raman spectroscopy combined with multivariate statistical analysis can serve as a potential clinical diagnosis method of leukemia. [ABSTRACT FROM AUTHOR]

The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model's performance improved as the quality of the labels used for training increased. [ABSTRACT FROM AUTHOR]

Discriminating bacterial adhesion profiles at strain‐specific level is crucial for simulating and predicting infections and persistence, as well as developing more efficient antibacterial therapies. Herein, it is proposed that label‐ and receptor‐free bacterial discrimination can be achieved by dynamic viscoelastic and adhesion monitoring over specified timescales using the quartz crystal microbalance with dissipation monitoring (QCM‐D). Using two closely related E. coli strains, ATCC 8739 and JM109(DE3), it is shown that their viscoelastic and adhesion properties evolve in time through strain‐specific profiles that are clearly distinguishable over a period of 3–4 h. In addition, the viscoelasticity of both E. coli strains shows a strong strain‐specific dependence on the medium ionic strength, allowing to further amplify the differences in the bacterial adhesion signatures. Furthermore, the viscoelastic and adhesion behaviors of the two E. coli strains with two additional bacteria, Citrobacter freundii and Serratia marcescens, are compared. For all four bacteria, distinct viscoelastic profiles and adhesion fingerprints emerge over similar timescales that allow to reliably discriminate the various bacteria. These results and similar studies on other bacteria might have pharmacological benefits, for instance, by highlighting the role of bacterial–substrate adhesion and viscoelastic properties on disease pathogenesis and persistence, toward developing more effective therapies. [ABSTRACT FROM AUTHOR]

• Fast and accurate end-to-end detection of multi-class urine sediment particles. • Determined a data augmentation strategy more applicable to urine sediment image. • Combined attention module and novel loss function to improve performance. • Mitigates the adverse effects of class confusion, imbalance, and boundary ambiguity. • Provide a new approach for applying other methods in urinary sediment detection. Urine microscopy is an essential diagnostic tool for kidney and urinary tract diseases, with automated analysis of urinary sediment particles improving diagnostic efficiency. However, some urinary sediment particles remain challenging to identify due to individual variations, blurred boundaries, and unbalanced samples. This research aims to mitigate the adverse effects of urine sediment particles while improving multi-class detection performance. We proposed an innovative model based on improved YOLOX for detecting urine sediment particles (YUS-Net). The combination of urine sediment data augmentation and overall pre-trained weights enhances model optimization potential. Furthermore, we incorporate the attention module into the critical feature transfer path and employ a novel loss function, Varifocal loss, to facilitate the extraction of discriminative features, which assists in the identification of densely distributed small objects. Based on the USE dataset, YUS-Net achieves the mean Average Precision (mAP) of 96.07%, 99.35% average precision, and 96.77% average recall, with a latency of 26.13 ms per image. The specific metrics for each category are as follows: cast: 99.66% AP; cryst: 100% AP; epith: 92.31% AP; epithn: 100% AP; eryth: 92.31% AP; leuko: 99.90% AP; mycete: 99.96% AP. With a practical network structure, YUS-Net achieved efficient, accurate, end-to-end urinary sediment particle detection. The model takes native high-resolution images as input without additional steps. Finally, a data augmentation strategy appropriate for the urinary microscopic image domain is established, which provides a novel approach for applying other methods in urine microscopic images. [ABSTRACT FROM AUTHOR]

Tuberculosis (TB) is one of the leading infectious causes of death worldwide. The effective management and public health control of this disease depends on early detection and careful treatment monitoring. For many years, the microscopy-based analysis of sputum smears has been the most common method to detect and quantify Mycobacterium tuberculosis (Mtb) bacteria. Nonetheless, this form of analysis is a challenging procedure since sputum examination can only be reliably performed by trained personnel with rigorous quality control systems in place. Additionally, it is affected by subjective judgement. Furthermore, although fluorescence-based sample staining methods have made the procedure easier in recent years, the microscopic examination of sputum is a time-consuming operation. Over the past two decades, attempts have been made to automate this practice. Most approaches have focused on establishing an automated method of diagnosis, while others have centred on measuring the bacterial load or detecting and localising Mtb cells for further research on the phenotypic characteristics of their morphology. The literature has incorporated machine learning (ML) and computer vision approaches as part of the methodology to achieve these goals. In this review, we first gathered publicly available TB sputum smear microscopy image sets and analysed the disparities in these datasets. Thereafter, we analysed the most common evaluation metrics used to assess the efficacy of each method in its particular field. Finally, we generated comprehensive summaries of prior work on ML and deep learning (DL) methods for automated TB detection, including a review of their limitations. [ABSTRACT FROM AUTHOR]

Biological tissue information of the lung, such as cells and proteins, can be obtained from bronchoalveolar lavage fluid (BALF), through which it can be used as a complement to lung biopsy pathology. BALF cells can be confused with each other due to the similarity of their characteristics and differences in the way sections are handled or viewed. This poses a great challenge for cell detection. In this paper, An Improved Yolov5s Based on Transformer Backbone Network for Detection and Classification of BALF Cells is proposed, focusing on the detection of four types of cells in BALF: macrophages, lymphocytes, neutrophils and eosinophils. The network is mainly based on the Yolov5s network and uses Swin Transformer V2 technology in the backbone network to improve cell detection accuracy by obtaining global information; the C3Ghost module (a variant of the Convolutional Neural Network architecture) is used in the neck network to reduce the number of parameters during feature channel fusion and to improve feature expression performance. In addition, embedding intersection over union Loss (EIoU_Loss) was used as a bounding box regression loss function to speed up the bounding box regression rate, resulting in higher accuracy of the algorithm. The experiments showed that our model could achieve mAP of 81.29% and Recall of 80.47%. Compared to the original Yolov5s, the mAP has improved by 3.3% and Recall by 3.67%. We also compared it with Yolov7 and the newly launched Yolov8s. mAP improved by 0.02% and 2.36% over Yolov7 and Yolov8s respectively, while the FPS of our model was higher than both of them, achieving a balance of efficiency and accuracy, further demonstrating the superiority of our model.

Objective: Artificial intelligence (AI)–based cytopathology studies conducted using deep learning have enabled cell detection and classification. Liquid‐based cytology (LBC) has facilitated the standardisation of specimen preparation; however, cytomorphology varies according to the LBC processing technique used. In this study, we elucidated the relationship between two LBC techniques and cell detection and classification using a deep learning model. Methods: Cytological specimens were prepared using the ThinPrep and SurePath methods. The accuracy of cell detection and cell classification was examined using the one‐ and five‐cell models, which were trained with one and five cell types, respectively. Results: When the same LBC processing techniques were used for the training and detection preparations, the cell detection and classification rates were high. The model trained on ThinPrep preparations was more accurate than that trained on SurePath. When the preparation types used for training and detection were different, the accuracy of cell detection and classification was significantly reduced (P < 0.01). The model trained on both ThinPrep and SurePath preparations exhibited slightly reduced cell detection and classification rates but was highly accurate. Conclusions: For the two LBC processing techniques, cytomorphology varied according to cell type; this difference affects the accuracy of cell detection and classification by deep learning. Therefore, for highly accurate cell detection and classification using AI, the same processing technique must be used for both training and detection. Our assessment also suggests that a deep learning model should be constructed using specimens prepared via a variety of processing techniques to construct a globally applicable AI model. [ABSTRACT FROM AUTHOR]

Label‐free imaging and identification of fast‐moving cells is a very challenging task. A kind of phase flow cytometry using coherent modulation imaging was proposed to realize label‐free imaging and identification on fast‐moving cells with compact optical alignment and high accuracy. Phase image of cells under inspection could be computed qualitatively from their diffraction patterns at the accuracy of about 0.01 wavelength and the resolution of about 1.23 μm and the view field of 0.126 mm2. Since the imaging system was mainly composed by a piece of random phase plate a detector without using commonly adopted reference beam and corresponding complex optical alignment, this method has much compacter optical structure and much higher tolerance capability to environmental instability in comparison with other kinds of phase flow cytometry. Current experimental results prove it could be an efficient optical tool for label‐free tumor cell detection. [ABSTRACT FROM AUTHOR]

Objectives Cytomorphology is known to differ depending on the processing technique, and these differences pose a problem for automated diagnosis using deep learning. We examined the as-yet unclarified relationship between cell detection or classification using artificial intelligence (AI) and the AutoSmear (Sakura Finetek Japan) and liquid-based cytology (LBC) processing techniques. Methods The "You Only Look Once" (YOLO), version 5x, algorithm was trained on the AutoSmear and LBC preparations of 4 cell lines: lung cancer (LC), cervical cancer (CC), malignant pleural mesothelioma (MM), and esophageal cancer (EC). Detection and classification rates were used to evaluate the accuracy of cell detection. Results When preparations of the same processing technique were used for training and detection in the 1-cell (1C) model, the AutoSmear model had a higher detection rate than the LBC model. When different processing techniques were used for training and detection, detection rates of LC and CC were significantly lower in the 4-cell (4C) model than in the 1C model, and those of MM and EC were approximately 10% lower in the 4C model. Conclusions In AI-based cell detection and classification, attention should be paid to cells whose morphologies change significantly depending on the processing technique, further suggesting the creation of a training model. [ABSTRACT FROM AUTHOR]

Flexible biosensors exhibit great potential for the detection of various biomarkers with the ability to adapt to different surface textures. Here, a lab‐on‐a‐needle biosensing platform based on ultra‐flexible giant magnetoresistance (GMR) biosensors is developed. The fabricated flexible GMR sensors exhibit a MR ratio of 5.2% and a sensitivity of 0.13%/Oe in the linear region, which are comparable to their rigid counterparts. It is found that the magnetic properties of the flexible GMR sensors remain unchanged after 500 cycles of compressive and tensile stress, indicating strong robustness even when applied to a surface that is constantly in motion. The developed platform is then employed for the detection of different concentrations of canine osteosarcoma (OSCA‐8) cells with a limit of detection (LOD) of 200 cells in 20 µL sample (104 cells per mL), which demonstrate the ability to perform real‐time, sensitive, and quantitative cell detection. [ABSTRACT FROM AUTHOR]

White blood cell (WBC) detection plays a vital role in peripheral blood smear analysis. However, cell detection remains a challenging task due to multi‐cell adhesion, different staining and imaging conditions. Owing to the powerful feature extraction capability of deep learning, object detection methods based on convolutional neural networks (CNNs) have been widely applied in medical image analysis. Nevertheless, the CNN training is time‐consuming and inaccuracy, especially for large‐scale blood smear images, where most of the images are background. To address the problem, we propose a two‐stage approach that treats WBC detection as a small salient object detection task. In the first saliency detection stage, we use the Itti's visual attention model to locate the regions of interest (ROIs), based on the proposed adaptive center‐surround difference (ACSD) operator. In the second WBC detection stage, the modified CenterNet model is performed on ROI sub‐images to obtain a more accurate localization and classification result of each WBC. Experimental results showed that our method exceeds the performance of several existing methods on two different data sets, and achieves a state‐of‐the‐art mAP of over 98.8%. [ABSTRACT FROM AUTHOR]

• Propose a dual-branch model that realizes the mutual benefits of both detections. • DB-FCN combines the advantages of both one-stage and two-stage object detections. • Coarse detection suppresses the background of the image to improve the accuracy. • We designs a three-stage training method to fully exploit the model's performance. • DB-FCN achieves highest scores on various datasets. Detecting cells or nuclei in histopathological image analysis is a crucial prerequisite for subsequent cancer diagnosis. By precisely locating cell nuclei, pathologists can quantitatively analyze the morphology of each cell nucleus. This enables accurate cancer grading, allowing for the implementation of tailored treatment plans based on distinct cancer stages. Manual nucleus detection methods are labor-intensive, making the development of automatic cell nucleus detection algorithms highly necessary. However, due to the small size of the nucleus and increased adhesions between cells, tissue staining may be uneven, leading to a higher occurrence of false positives in the results of the current automatic nucleus detection algorithm. This paper introduces an end-to-end dual-branch-based fully convolutional neural network (DB-FCN) that effectively addresses the aforementioned challenges, thereby enhancing the accuracy of automatic nucleus detection. This algorithm introduces for the first time the use of two detection branches, namely the coarse detection branch and the fine detection branch, to accomplish the detection task. The role of the coarse detection branch is to identify all cell regions in the pathological image as comprehensively as possible and then transmit the detection results as prior information to the fine detection branch. The fine detection branch is necessary solely to conduct more precise detection based on the coarse detection results. Given that the coarse detection branch has already eliminated interference from many background regions, the fine detection branch can focus on detecting the nucleus region, thereby significantly enhancing the efficiency and accuracy of model detection. The detection model proposed in this paper was evaluated on three classic datasets and compared with many existing detection algorithms. Compared with other algorithms, the detection algorithm proposed in this paper has made significant progress in detecting cell nuclei in histopathological images. [ABSTRACT FROM AUTHOR]

Abstract Flexible biosensors exhibit great potential for the detection of various biomarkers with the ability to adapt to different surface textures. Here, a lab‐on‐a‐needle biosensing platform based on ultra‐flexible giant magnetoresistance (GMR) biosensors is developed. The fabricated flexible GMR sensors exhibit a MR ratio of 5.2% and a sensitivity of 0.13%/Oe in the linear region, which are comparable to their rigid counterparts. It is found that the magnetic properties of the flexible GMR sensors remain unchanged after 500 cycles of compressive and tensile stress, indicating strong robustness even when applied to a surface that is constantly in motion. The developed platform is then employed for the detection of different concentrations of canine osteosarcoma (OSCA‐8) cells with a limit of detection (LOD) of 200 cells in 20 µL sample (104 cells per mL), which demonstrate the ability to perform real‐time, sensitive, and quantitative cell detection.

Aim: Analysis of cerebrospinal fluid (CSF) is essential for diagnostic workup of patients with neurological diseases and includes differential cell typing. The current gold standard is based on microscopic examination by specialised technicians and neuropathologists, which is time-consuming, labour-intensive and subjective. Methods: We, therefore, developed an image analysis approach based on expert annotations of 123,181 digitised CSF objects from 78 patients corresponding to 15 clinically relevant categories and trained a multiclass convolutional neural network (CNN). Results: The CNN classified the 15 categories with high accuracy (mean AUC 97.3%). By using explainable artificial intelligence (XAI), we demonstrate that the CNN identified meaningful cellular substructures in CSF cells recapitulating human pattern recognition. Based on the evaluation of 511 cells selected from 12 different CSF samples, we validated the CNN by comparing it with seven board-certified neuropathologists blinded for clinical information. Inter-rater agreement between the CNN and the ground truth was non-inferior (Krippendorff's alpha 0.79) compared with the agreement of seven human raters and the ground truth (mean Krippendorff's alpha 0.72, range 0.56-0.81). The CNN assigned the correct diagnostic label (inflammatory, haemorrhagic or neoplastic) in 10 out of 11 clinical samples, compared with 7-11 out of 11 by human raters. Conclusions: Our approach provides the basis to overcome current limitations in automated cell classification for routine diagnostics and demonstrates how a visual explanation framework can connect machine decision-making with cell properties and thus provide a novel versatile and quantitative method for investigating CSF manifestations of various neurological diseases. [ABSTRACT FROM AUTHOR]

For comprehensive anatomical analysis of a mouse brain, accurate and efficient registration of the experimental brain samples to a reference atlas is necessary. Here, we introduce Bell Jar, a semiautomated solution that can align and annotate tissue sections with anatomical structures from a reference atlas as well as detect fluorescent signals with cellular resolution (e.g., cell bodies or nuclei). Bell Jar utilizes Mattes mutual information-directed B-spline transformations to achieve precise alignments, even with damaged sample tissues. While user input remains a requirement for fine-tuning section matches, the platform streamlines the process, aiding rapid analyses in high-throughput neuroanatomy studies. As a standalone desktop application with a user-friendly interface, Bell Jar's performance, which surpasses traditional manual and existing automated methods, can improve the reproducibility and throughput of histological analyses., Competing Interests: The authors declare no competing financial interests., (Copyright © 2025 Soronow et al.)

Tissue specimens taken from primary tumors or metastases contain important information for diagnosis and treatment of cancer patients. Multiplex imaging allows in situ visualization of heterogeneous cell populations, such as immune cells, in tissue samples. Most image processing pipelines first segment cell boundaries and then measure marker expression to assign cell phenotypes. In dense tissue environments, this segmentation-first approach can be inaccurate due to segmentation errors or overlapping cells. Here, we introduce the machine-learning pipeline "ImmuNet", which identifies positions and phenotypes of cells without segmenting them. ImmuNet is easy to train: human annotators only need to click on an immune cell and score its expression of each marker-drawing a full cell outline is not required. We trained and evaluated ImmuNet on multiplex images from human tonsil, lung cancer, prostate cancer, melanoma, and bladder cancer tissue samples and found it to consistently achieve error rates below 5%-10% across tissue types, cell types, and tissue densities, outperforming a segmentation-based baseline method. Furthermore, we externally validate ImmuNet results by comparing them to flow cytometric cell count measurements from the same tissue. In summary, ImmuNet is an effective, simpler alternative to segmentation-based approaches when only cell positions and phenotypes, but not their shapes, are required for downstream analyses. Thus, ImmuNet helps researchers to analyze cell positions in multiplex tissue images more easily and accurately., (© The Author(s) 2024. Published by Oxford University Press.)

Due to climate change and the COVID-19 pandemic, the number of malaria cases and deaths, caused by the Plasmodium genus, of which P. falciparum is the most common and lethal to humans, increased between 2019 and 2020. Reversing this trend and eliminating malaria worldwide requires improvements in malaria diagnosis, in which artificial intelligence (AI) has recently been demonstrated to have a great potential. One of the main reasons for the use of neural networks (NNs) is the time saving through automatising the process and the elimination of human error. When classifying with two-dimensional images of red blood cells (RBCs), the number of parameters fitted by the NN for the classification of RBCs is extremely high, which strongly influences the performance of the network, especially for training sets of moderate size. The complicated handling of malaria culturing and sample preparation does not only limit the efficiency of NNs due to small training sets, but also because of the uneven distribution of red blood cell (RBC) categories. To boost the performance of microscopy techniques in malaria diagnosis, our approach aims at resolving these drawbacks by reducing the dimension of the input data and by data augmentation, respectively. We assess the performance of our approach on images recorded by light (LM), atomic force (AFM), and fluorescence microscopy (FM). Our tool, the Malaria Stage Classifier, provides a fast, high-accuracy recognition by (1) identifying individual RBCs in multi-cell microscopy images, (2) extracting characteristic one-dimensional cross-sections from individual RBC images. These cross-sections are selected by a simple algorithm to contain key information about the status of the RBCs and are used to (3) classify the malaria blood stages. We demonstrate that our method is applicable to images recorded by various microscopy techniques and available as a software package. • Identifying individual RBCs in multi-cell microscopy images. • Extracting characteristic one-dimensional cross-sections from individual RBC images. These cross-sections are selected by a simple algorithm to contain key information about the status of the RBCs and are used to. • Classify the malaria blood stages. We demonstrate that our method is applicable to images recorded by various microscopy techniques and available as a software package.

Pathological images play an important role in the diagnosis, treatment, and prognosis of cancer. Usually, pathological images contain complex environments and cells of different shapes. Pathologists consume a lot of time and labor costs when analyzing and discriminating the cells in the images. Therefore, fully annotated pathological image data sets are not easy to obtain. In view of the problem of insufficient labeled data, we input a large number of unlabeled images into the pretrained model to generate accurate pseudo-labels. In this article, we propose two methods to improve the quality of pseudo-labels, namely, the pseudo-labeling based on adaptive threshold and the pseudo-labeling based on cell count. These two pseudo-labeling methods take into account the distribution of cells in different pathological images when removing background noise, and ensure that accurate pseudo-labels are generated for each unlabeled image. Meanwhile, when pseudo-labels are used for model retraining, we perform data distillation on the feature maps of unlabeled images through an attention mechanism, which further improves the quality of training data. In addition, we also propose a multi-task learning model, which learns the cell detection task and the cell count task simultaneously, and improves the performance of cell detection through feature sharing. We verified the above methods on three different data sets, and the results show that the detection effect of the model with a large number of unlabeled images involved in retraining is improved by 9%–13% compared with the model that only uses a small number of labeled images for pretraining. Moreover, our methods have good applicability on the three data sets. [ABSTRACT FROM AUTHOR]

A novel two-dimensional nanolayered Ti 3 C 2 Cl 2 MXene material derived from MAX phase was synthesized through a HF-free method based on elemental replacement reaction in the A atom of traditional Ti 3 AlC 2 MAX phase and ZnCl 2 molten salts, which possess large specific surface areas, excellent electric conductivity and reducing property. Then the Au/Pt bimetallic nanoparticles decorated Ti 3 C 2 Cl 2 nanoflakes were synthesized by a self-reduction method with Ti 3 C 2 Cl 2 as a natural reducing agent and supporter, which possess peroxidase mimic activity and oxidase mimic activity, simultaneously. Based on the prominent catalytic activity of Au/Pt/Ti 3 C 2 Cl 2 nanocomposite, a novel colorimetric platform was developed for in situ sensing of hydrogen peroxide (H 2 O 2) released from live HeLa cells and colorimetric detection of glutathione (GSH), with the detection ranges of 50–10000 μM and 0.1–20 μM, the detection limits were 10.24 μM and 0.07 μM, respectively. These results allow utilization of the easily accessible 2D surface for the design and application of 2D layered material-supported MXene nanocomposites catalysts in intracellular biosensing. Preparation of Au/Pt/Ti 3 C 2 Cl 2 nanoflakes with a HF-free and self-reduction method for in-situ detection of hydrogen peroxide released from live HeLa cells and colorimetric detection of glutathione. [Display omitted] [ABSTRACT FROM AUTHOR]

Despite the importance of cell characterization and identification for diagnostic and therapeutic applications, developing fast and label‐free methods without (bio)‐chemical markers or surface‐engineered receptors remains challenging. Here, we exploit the natural cellular response to mild thermal stimuli and propose a label‐ and receptor‐free method for fast and facile cell characterization. Cell suspensions in a dedicated sensor are exposed to a temperature gradient, which stimulates synchronized and spontaneous cell‐detachment with sharply defined time‐patterns, a phenomenon unknown from literature. These patterns depend on metabolic activity (controlled through temperature, nutrients, and drugs) and provide a library of cell‐type‐specific indicators, allowing to distinguish several yeast strains as well as cancer cells. Under specific conditions, synchronized glycolytic‐type oscillations are observed during detachment of mammalian and yeast‐cell ensembles, providing additional cell‐specific signatures. These findings suggest potential applications for cell viability analysis and for assessing the collective response of cancer cells to drugs. [ABSTRACT FROM AUTHOR]

Optical flow cytometry is used as the gold standard in single cell function diagnostics with the drawback of involving high complexity and operator costs. Magnetic flow cytometers try to overcome this problem by replacing optical labeling with magnetic nanoparticles to assign each cell a magnetic fingerprint. This allows operators to obtain rich cell information from a biological sample with minimal sample preparation at near in-vivo conditions in a decentralized environment. A central task in flow cytometry is the determination of cell concentrations and cell parameters, e.g. hydrodynamic diameter. For the acquisition of this information, signal processing is an essential component. Previous approaches mainly focus on the processing of one-cell signals, leaving out superimposed signals originating from cells passing the magnetic sensors in close proximity. In this work, we present a framework for joint cell/particle detection and analysis, which is capable of processing one-cell as well as multi-cell signals. We employ deep learning and compressive sensing in this approach, which involves the minimization of an adaptive norm. We evaluate our method on simulated and experimental signals, the latter being obtained with polymer microparticles. Our results show that the framework is capable of counting cells with a relative error smaller than 2%. Inference of cell parameters works reliably at both low and high noise levels. [ABSTRACT FROM AUTHOR]

The detection, identification and counting of bone marrow erythroid cells are vital for evaluating the health status and therapeutic schedules of patients with leukemia or hematopathy. However, traditional methods used in hospitals are still based on chemical reagent staining, manual detection and counting with the help of laboratory equipment. And therefore, these methods are time-consuming, laborious, and tedious. The development of deep learning in the field of image processing makes it possible for effective automated detection and classification of erythroid cells. In this research, we proposed a pipeline called ErythroidCounter, which is based on deep learning approaches to perform fully automated detection and classification of erythroid cells. ErythroidCounter is composed of the detection and extraction module (DEM) followed by classification and counting module (CCM). DEM adapts RetinaNet to locate and detect erythroid cells, and it transmits the detected cell images into CCM, while CCM is based on the DenseNet-121 architecture to perform classification and counting., which has close match in terms of classification accuracy compared to manual examination. When classifying erythroid cells, the ErythroidCounter achieved an accuracy of 86.33%, recall of 87.45%, precision of 87.16%, and F1 score of 87.30%. When detecting erythroid cells, ErythroidCounter achieved an precision of 90.7%, recall of 91.3%, and F1 score of 90.9%. EythroidCounter is robust to underlying color images, cell densities, and cell positions. To the best of our knowledge, this is the first automatic approach for erythroid cell detection, classification, and counting in real clinical scenarios, and it can be used as an assistive tool for medical examinations. [ABSTRACT FROM AUTHOR]

• The latest imaging devices can now measure the activity of thousands to tens of thousands of cells. • We are faced with the problem of how to detect cells from the large-scale imaging data. • We outline automatic cell-detection methods related to non-negative matrix factorization (NMF). • We also introduce our non-NMF method capable of detecting about 17,000 cells. The rapid progress of imaging devices such as two-photon microscopes has made it possible to measure the activity of thousands to tens of thousands of cells at single-cell resolution in a wide field of view (FOV) data. However, it is not possible to manually identify thousands of cells in such wide FOV data. Several research groups have developed machine learning methods for automatically detecting cells from wide FOV data. Many of the recently proposed methods using dynamic activity information rather than static morphological information are based on non-negative matrix factorization (NMF). In this review, we outline cell-detection methods related to NMF. For the purpose of raising issues on NMF cell detection, we introduce our current development of a non-NMF method that is capable of detecting about 17,000 cells in ultra-wide FOV data. [ABSTRACT FROM AUTHOR]

The airway epithelium of children with asthma is characterized by aberrant repair that may be therapeutically modifiable. The development of epithelial-targeting therapeutics that enhance airway repair could provide a novel treatment avenue for childhood asthma. Drug discovery efforts utilizing high-throughput live cell imaging of patient-derived airway epithelial culture-based wound repair assays can be used to identify compounds that modulate airway repair in childhood asthma. Manual cell tracking has been used to determine cell trajectories and wound closure rates, but is time consuming, subject to bias, and infeasible for high-throughput experiments. We therefore developed software, EPIC, that automatically tracks low-resolution low-framerate cells using artificial intelligence, analyzes high-throughput drug screening experiments and produces multiple wound repair metrics and publication-ready figures. Additionally, unlike available cell trackers that perform cell segmentation, EPIC tracks cells using bounding boxes and thus has simpler and faster training data generation requirements for researchers working with other cell types. EPIC outperformed publicly available software in our wound repair datasets by achieving human-level cell tracking accuracy in a fraction of the time. We also showed that EPIC is not limited to airway epithelial repair for children with asthma but can be applied in other cellular contexts by outperforming the same software in the Cell Tracking with Mitosis Detection Challenge (CTMC) dataset. The CTMC is the only established cell tracking benchmark dataset that is designed for cell trackers utilizing bounding boxes. We expect our open-source and easy-to-use software to enable high-throughput drug screening targeting airway epithelial repair for children with asthma. [ABSTRACT FROM AUTHOR]

Label-free cell separation and sorting in a microfluidic system, an essential technique for modern cancer diagnosis, resulted in high-throughput single-cell analysis becoming a reality. However, designing an efficient cell detection model is challenging. Traditional cell detection methods are subject to occlusion boundaries and weak textures, resulting in poor performance. Modern detection models based on convolutional neural networks (CNNs) have achieved promising results at the cost of a large number of both parameters and floating point operations (FLOPs). In this work, we present a lightweight, yet powerful cell detection model named CellNet, which includes two efficient modules, CellConv blocks and the h-swish nonlinearity function. CellConv is proposed as an effective feature extractor as a substitute to computationally expensive convolutional layers, whereas the h-swish function is introduced to increase the nonlinearity of the compact model. To boost the prediction and localization ability of the detection model, we re-designed the model's multi-task loss function. In comparison with other efficient object detection methods, our approach achieved state-of-the-art 98.70% mean average precision (mAP) on our custom sea urchin embryos dataset with only 0.08 M parameters and 0.10 B FLOPs, reducing the size of the model by 39.5× and the computational cost by 4.6×. We deployed CellNet on different platforms to verify its efficiency. The inference speed on a graphics processing unit (GPU) was 500.0 fps compared with 87.7 fps on a CPU. Additionally, CellNet is 769.5-times smaller and 420 fps faster than YOLOv3. Extensive experimental results demonstrate that CellNet can achieve an excellent efficiency/accuracy trade-off on resource-constrained platforms. [ABSTRACT FROM AUTHOR]

Vaginitis is a common disease among women and has a high recurrence rate. The primary diagnosis method is fluorescence microscopic inspection, but manual inspection is inefficient and can lead to false detection or missed detection. Automatic cell identification and localization in microscopic images are necessary. For vaginitis diagnosis, clue cells and trichomonas are two important indicators and are difficult to be detected because of the different scales and image characteristics. This study proposes a Multi-Scale Perceptual YOLO (MSP-YOLO) with super-resolution reconstruction branch to meet the detection requirements of clue cells and trichomonas. Based on the scales and image characteristics of clue cells and trichomonas, we employed a super-resolution reconstruction branch to the detection network. This branch guides the detection branch to focus on subtle feature differences. Simultaneously, we proposed an attention-based feature fusion module that is injected with dilated convolutional group. This module makes the network pay attention to the non-centered features of the large target clue cells, which contributes to the enhancement of detection sensitivity. Experimental results show that the proposed detection network MSP-YOLO can improve sensitivity without compromising specificity. For clue cell and trichomoniasis detection, the proposed network achieved sensitivities of 0.706 and 0.910, respectively, which were 0.218 and 0.051 higher than those of the baseline model. In this study, the characteristics of the super-resolution reconstruction task are used to guide the network to effectively extract and process image features. The novel proposed network has an increased sensitivity, which makes it possible to detect vaginitis automatically., Competing Interests: Declaration of competing interest None Declared., (Copyright © 2024 Elsevier Ltd. All rights reserved.)