Quantitative phase imaging of living red blood cells combining digital holographic microscopy and deep learning.

Digital holographic microscopy as a non-contacting, non-invasive, and highly accurate measurement technology, is becoming a valuable method for quantitatively investigating cells and tissues. Reconstruction of phases from a digital hologram is a key step in quantitative phase imaging for biological and biomedical research. This study proposes a two-stage deep convolutional neural network named VY-Net, to realize the effective and robust phase reconstruction of living red blood cells. The VY-Net can obtain the phase information of an object directly from a single-shot off-axis digital hologram. We also propose two new indices to evaluate the reconstructed phases. In experiments, the mean of the structural similarity index of reconstructed phases can reach 0.9309, and the mean of the accuracy of reconstructions of reconstructed phases is as high as 91.54%. An unseen phase map of a living human white blood cell is successfully reconstructed by the trained VY-Net, demonstrating its strong generality.

Synchronous Phase-Shifting Interference for High Precision Phase Imaging of Objects Using Common Optics.

Quantitative phase imaging and measurement of surface topography and fluid dynamics for objects, especially for moving objects, is critical in various fields. Although effective, existing synchronous phase-shifting methods may introduce additional phase changes in the light field due to differences in optical paths or need specific optics to implement synchronous phase-shifting, such as the beamsplitter with additional anti-reflective coating and a micro-polarizer array. Therefore, we propose a synchronous phase-shifting method based on the Mach-Zehnder interferometer to tackle these issues in existing methods. The proposed method uses common optics to simultaneously acquire four phase-shifted digital holograms with equal optical paths for object and reference waves. Therefore, it can be used to reconstruct the phase distribution of static and dynamic objects with high precision and high resolution. In the experiment, the theoretical resolution of the proposed system was 1.064 µm while the actual resolution could achieve 1.381 µm, which was confirmed by measuring a phase-only resolution chart. Besides, the dynamic phase imaging of a moving standard object was completed to verify the proposed system's effectiveness. The experimental results show that our proposed method is suitable and promising in dynamic phase imaging and measurement of moving objects using phase-shifting digital holography.

Cholesterol homeostasis regulated by ABCA1 is critical for retinal ganglion cell survival.

Genome-wide association studies have suggested a link between primary open-angle glaucoma and the function of ABCA1. ABCA1 is a key regulator of cholesterol efflux and the biogenesis of high-density lipoprotein (HDL) particles. Here, we showed that the POAG risk allele near ABCA1 attenuated ABCA1 expression in cultured cells. Consistently, POAG patients exhibited lower ABCA1 expression, reduced HDL, and higher cholesterol in white blood cells. Ablation of Abca1 in mice failed to form HDL, leading to elevated cholesterol levels in the retina. Counting retinal ganglion cells (RGCs) by using an artificial intelligence (AI) program revealed that Abca1-deficient mice progressively lost RGCs with age. Single-cell RNA sequencing (scRNA-seq) revealed aberrant oxidative phosphorylation in the Abca1-/- retina, as well as activation of the mTORC1 signaling pathway and suppression of autophagy. Treatment of Abca1-/- mice using atorvastatin reduced the cholesterol level in the retina, thereby improving metabolism and protecting RGCs from death. Collectively, we show that lower ABCA1 expression and lower HDL are risk factors for POAG. Accumulated cholesterol in the Abca1-/- retina causes profound aberrant metabolism, leading to a POAG-like phenotype that can be prevented by atorvastatin. Our findings establish statin use as a preventive treatment for POAG associated with lower ABCA1 expression.

CGUN-2A: Deep Graph Convolutional Network via Contrastive Learning for Large-Scale Zero-Shot Image Classification.

Taxonomy illustrates that natural creatures can be classified with a hierarchy. The connections between species are explicit and objective and can be organized into a knowledge graph (KG). It is a challenging task to mine features of known categories from KG and to reason on unknown categories. Graph Convolutional Network (GCN) has recently been viewed as a potential approach to zero-shot learning. GCN enables knowledge transfer by sharing the statistical strength of nodes in the graph. More layers of graph convolution are stacked in order to aggregate the hierarchical information in the KG. However, the Laplacian over-smoothing problem will be severe as the number of GCN layers deepens, which leads the features between nodes toward a tendency to be similar and degrade the performance of zero-shot image classification tasks. We consider two parts to mitigate the Laplacian over-smoothing problem, namely reducing the invalid node aggregation and improving the discriminability among nodes in the deep graph network. We propose a top-k graph pooling method based on the self-attention mechanism to control specific node aggregation, and we introduce a dual structural symmetric knowledge graph additionally to enhance the representation of nodes in the latent space. Finally, we apply these new concepts to the recently widely used contrastive learning framework and propose a novel Contrastive Graph U-Net with two Attention-based graph pooling (Att-gPool) layers, CGUN-2A, which explicitly alleviates the Laplacian over-smoothing problem. To evaluate the performance of the method on complex real-world scenes, we test it on the large-scale zero-shot image classification dataset. Extensive experiments show the positive effect of allowing nodes to perform specific aggregation, as well as homogeneous graph comparison, in our deep graph network. We show how it significantly boosts zero-shot image classification performance. The Hit@1 accuracy is 17.5% relatively higher than the baseline model on the ImageNet21K dataset.

VDE-Net: a two-stage deep learning method for phase unwrapping.

Phase unwrapping is a critical step to obtaining a continuous phase distribution in optical phase measurements and coherent imaging techniques. Traditional phase-unwrapping methods are generally low performance due to significant noise or undersampling. This paper proposes a deep convolutional neural network (DCNN) with a weighted jump-edge attention mechanism, namely, VDE-Net, to realize effective and robust phase unwrapping. Experimental results revealed that the weighted jump-edge attention mechanism, which is first proposed and simple to calculate, is useful for phase unwrapping. The proposed algorithm outperformed other networks or common attention mechanisms. In addition, an unseen wrapped phase image of a living red blood cell (RBC) was successfully unwrapped by the trained VDE-Net, thereby demonstrating its strong generalization capability.

Automatic counting of retinal ganglion cells in the entire mouse retina based on improved YOLOv5.

Glaucoma is characterized by the progressive loss of retinal ganglion cells (RGCs), although the pathogenic mechanism remains largely unknown. To study the mechanism and assess RGC degradation, mouse models are often used to simulate human glaucoma and specific markers are used to label and quantify RGCs. However, manually counting RGCs is time-consuming and prone to distortion due to subjective bias. Furthermore, semi-automated counting methods can produce significant differences due to different parameters, thereby failing objective evaluation. Here, to improve counting accuracy and efficiency, we developed an automated algorithm based on the improved YOLOv5 model, which uses five channels instead of one, with a squeeze-and-excitation block added. The complete number of RGCs in an intact mouse retina was obtained by dividing the retina into small overlapping areas and counting, and then merging the divided areas using a non-maximum suppression algorithm. The automated quantification results showed very strong correlation (mean Pearson correlation coefficient of 0.993) with manual counting. Importantly, the model achieved an average precision of 0.981. Furthermore, the graphics processing unit (GPU) calculation time for each retina was less than 1 min. The developed software has been uploaded online as a free and convenient tool for studies using mouse models of glaucoma, which should help elucidate disease pathogenesis and potential therapeutics.

A Data-Efficient Framework for the Identification of Vaginitis Based on Deep Learning.

Vaginitis is a gynecological disease affecting the health of millions of women all over the world. The traditional diagnosis of vaginitis is based on manual microscopy, which is time-consuming and tedious. The deep learning method offers a fast and reliable solution for an automatic early diagnosis of vaginitis. However, deep neural networks require massive well-annotated data. Manual annotation of microscopic images is highly cost extensive because it not only is a time-consuming process but also needs highly trained people (doctors, pathologists, or technicians). Most existing active learning approaches are not applicable in microscopic images due to the nature of complex backgrounds and numerous formed elements. To address the problem of high cost of labeling microscopic images, we present a data-efficient framework for the identification of vaginitis based on transfer learning and active learning strategies. The proposed informative sample selection strategy selected the minimal training subset, and then the pretrained convolutional neural network (CNN) was fine-tuned on the selected subset. The experiment results show that the proposed pipeline can save 37.5% annotation cost while maintaining competitive performance. The proposed promising novel framework can significantly save the annotation cost and has the potential of extending widely to other microscopic imaging applications, such as blood microscopic image analysis.

End-to-End Deep Learning-Based Cells Detection in Microscopic Leucorrhea Images.

Vaginitis is a prevalent gynecologic disease that threatens millions of women's health. Although microscopic examination of vaginal discharge is an effective method to identify vaginal infections, manual analysis of microscopic leucorrhea images is extremely time-consuming and labor-intensive. To automate the detection and identification of visible components in microscopic leucorrhea images for early-stage diagnosis of vaginitis, we propose a novel end-to-end deep learning-based cells detection framework using attention-based detection with transformers (DETR) architecture. The transfer learning was applied to speed up the network convergence while maintaining the lowest annotation cost. To address the issue of detection performance degradation caused by class imbalance, the weighted sampler with on-the-fly data augmentation module was integrated into the detection pipeline. Additionally, the multi-head attention mechanism and the bipartite matching loss system of the DETR model perform well in identifying partially overlapping cells in real-time. With our proposed method, the pipeline achieved a mean average precision (mAP) of 86.00% and the average precision (AP) of epithelium, leukocyte, pyocyte, mildew, and erythrocyte was 96.76, 83.50, 74.20, 89.66, and 88.80%, respectively. The average test time for a microscopic leucorrhea image is approximately 72.3 ms. Currently, this cell detection method represents state-of-the-art performance.

Morphological components detection for super-depth-of-field bio-micrograph based on deep learning.

Accompanied with the clinical routine examination demand increase sharply, the efficiency and accuracy are the first priority. However, automatic classification and localization of cells in microscopic images in super depth of Field (SDoF) system remains great challenges. In this paper, we advance an object detection algorithm for cells in the SDoF micrograph based on Retinanet model. Compared with the current mainstream algorithm, the mean average precision (mAP) index is significantly improved. In the experiment of leucorrhea samples and fecal samples, mAP indexes are 83.1% and 88.1%, respectively, with an average increase of 10%. The object detection model proposed in this paper can be applied to feces and leucorrhea detection equipment, and significantly improve the detection efficiency and accuracy.

SDoF-Net: Super Depth of Field Network for Cell Detection in Leucorrhea Micrograph.

Accompanied with the rapid increase of the demand for routine examination of leucorrhea, efficiency and accuracy become the primary task. However, in super depth of field (SDoF) system, the problem of automatic detection and localization of cells in leucorrhea micro-images is still a big challenge. The changing of the relative position between the cell center and focus plane of microscope lead to variable cell morphological structure in the two-dimensional image, which is an important reason for the low accuracy of current deep learning target detection algorithms. In this paper, an object detection method based on Retinanet in state of super depth of field is proposed, which can achieve high precision detecting of leucorrhea components by the SDoF feature aggregation module. Compared with the current mainstream algorithms, the mean average accuracy (mAP) index has been improved significantly, the mAP index is 82.7% for SDoF module and 83.0% for SDoF+ module, with an average increase of more than 10%. These improved features can significantly improve the efficiency and accuracy of the algorithm. The algorithm proposed in this paper can be integrated into the leucorrhea automatic detection system.

Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN.

Fecal samples can easily be collected and are representative of a person's current health state; therefore, the demand for routine fecal examination has increased sharply. However, manual operation may pollute the samples, and low efficiency limits the general examination speed; therefore, automatic analysis is needed. Nevertheless, recognition exhaustion time and accuracy remain major challenges in automatic testing. Here, we introduce a fast and efficient cell-detection algorithm based on the Faster-R-CNN technique: the Resnet-152 convolutional neural network architecture. Additionally, a region proposal network and a network combined with principal component analysis are proposed for cell location and recognition in microscopic images. Our algorithm achieved a mean average precision of 84% and a 723 ms detection time per sample for 40,560 fecal images. Thus, this approach may provide a solid theoretical basis for real-time detection in routine clinical examinations while accelerating the process to satisfy increasing demand.

Detection and compensation of dispersion mismatch for frequency-domain optical coherence tomography based on A-scan's spectrogram.

Balanced dispersion between reference and sample arms is critical in frequency-domain optical coherence tomography (FD-OCT) to perform imaging with the optimal axial resolution, and the spectroscopic analysis of each voxel in FD-OCT can provide the metric of the spectrogram. Here we revisited dispersion mismatch in the spectrogram view using the spectroscopic analysis of voxels in FD-OCT and uncovered that the dispersion mismatch disturbs the A-scan's spectrogram and reshapes the depth-resolved spectra in the spectrogram. Based on this spectroscopic effect of dispersion mismatch on A-scan's spectrogram, we proposed a numerical method to detect dispersion mismatch and perform dispersion compensation for FD-OCT. The proposed method can visually and quantitatively detect and compensate for dispersion mismatch in FD-OCT, with visualization, high sensitivity, and independence from sample structures. Experimental results of tape and mouse eye suggest that this technique can be an effective method for the detection and compensation of dispersion mismatch in FD-OCT.

Automatic classification of cells in microscopic fecal images using convolutional neural networks.

The analysis of fecal-type components for clinical diagnosis is important. The main examination involves the counting of red blood cells (RBCs), white blood cells (WBCs), and molds under the microscopic. With the development of machine vision, some vision-based detection schemes have been proposed. However, these methods have a single target for detection, with low detection efficiency and low accuracy. We proposed an algorithm to identify the visible image of fecal composition based on intelligent deep learning. The algorithm mainly includes region proposal and candidate recognition. In the process of segmentation, we proposed a morphology extraction algorithm in a complex background. As for the candidate recognition, we proposed a new convolutional neural network (CNN) architecture based on Inception-v3 and principal component analysis (PCA). This method achieves high-average Precision of 90.7%, which is better than the other mainstream CNN models. Finally, the images within the rectangle marks were obtained. The total time for detection of an image was roughly 1200 ms. The algorithm proposed in the present paper can be integrated into an automatic fecal detection system.

Trichomonas Detection in Leucorrhea Based on VIBE Method.

Trichomonas examination is one of the important items in the leucorrhea routine detection. And it cannot be recognized by still images because of the unstable morphology and unfixed focal location caused by motion characteristic. We proposed an improved VIBE algorithm. 6 videos (totally 1414 frames) are collected for testing. In order to compare the effects of the algorithms, we segment each frame artificially as ground truth. Experiments show that percentage of correct classification (PCC) achieves 88%. The proposed improved method can effectively suppress the false detection caused by the formed components such as epithelial cells in the leucorrhea microscopic image and the missed detection caused by the background model update during the movement. At the same time, improvements can effectively suppress smear and ghost areas. The algorithm proposed in this paper can be integrated into the leucorrhea automatic detection system.

Leukocyte recognition in human fecal samples using texture features.

Unlike urine or blood samples with a single background, human fecal samples contain large amounts of food debris, amorphous particles, and undigested plant cells. It is difficult to segment such impurities when mixed with leukocytes. Cell degradation results in ambiguous nuclei, incompleteness of the cell membrane, and a changeable cell morphology, which are difficult to recognize. Aiming at the segmentation problem, a threshold segmentation method combining an inscribed circle and circumscribed circle is proposed to effectively remove the adhesion impurities with a segmentation accuracy reaching 97.6%. For the identification problem, five texture features (i.e., LBP-uniform, Gabor, HOG, GLCM, and Haar) were extracted and classified using four kinds of classifiers (support vector machine (SVM), artificial neural network, AdaBoost, and random forest). The experimental results show that using a histogram of oriented gradient features with an SVM classifier can achieve precision of 88.46% and recall of 88.72%.

Automatic identification of fungi in microscopic leucorrhea images.

Identifying fungi in microscopic leucorrhea images provides important information for evaluating gynecological diseases. Subjective judgment and fatigue can greatly affect recognition accuracy. This paper proposes an automatic identification system to detect fungi in leucorrhea images that incorporates a convolutional neural network, the histogram of oriented gradients algorithm, and a binary support vector machine. In experiments, the detection rate of the positive samples was as high as 99.8%. The experimental results demonstrate the effectiveness of the proposed method and its potential as a primary software component of a completely automated system.

Computerized detection of leukocytes in microscopic leukorrhea images.

PURPOSE: Detection of leukocytes is critical for the routine leukorrhea exam, which is widely used in gynecological examinations. An elevated vaginal leukocyte count in women with bacterial vaginosis is a strong predictor of vaginal or cervical infections. In the routine leukorrhea exam, the counting of leukocytes is primarily performed by manual techniques. However, the viewing and counting of leukocytes from multiple high-power viewing fields on a glass slide under a microscope leads to subjectivity, low efficiency, and low accuracy. To date, many biological cells in stool, blood, and breast cancer have been studied to realize computerized detection; however, the detection of leukocytes in microscopic leukorrhea images has not been studied. Thus, there is an increasing need for computerized detection of leukocytes. METHODS: There are two key processes in the computerized detection of leukocytes in digital image processing. One is segmentation; the other is intelligent classification. In this paper, we propose a combined ensemble to detect leukocytes in the microscopic leukorrhea image. After image segmentation and selecting likely leukocyte subimages, we obtain the leukocyte candidates. Then, for intelligent classification, we adopt two methods: feature extraction and classification by a support vector machine (SVM); applying a modified convolutional neural network (CNN) to the larger subimages. If different methods classify a candidate in the same category, the process is finished. If not, the outputs of the methods are provided to a classifier to further classify the candidate. RESULTS: After acquiring leukocyte candidates, we attempted three methods to perform classification. The first approach using features and SVM achieved 88% sensitivity, 97% specificity, and 92.5% accuracy. The second method using CNN achieved 95% sensitivity, 84% specificity, and 89.5% accuracy. Then, in the combination approach, we achieved 92% sensitivity, 95% specificity, and 93.5% accuracy. Finally, the images with marked and counted leukocytes were obtained. CONCLUSION: A novel computerized detection system was developed for automated detection of leukocytes in microscopic images. Different methods resulted in comparable overall qualities by enabling computerized detection of leukocytes. The proposed approach further improved the performance. This preliminary study proves the feasibility of computerized detection of leukocytes in clinical use.

Automatic detection of trichomonads based on an improved Kalman background reconstruction algorithm.

Automatic detection of trichomonads in leukorrhea provides important information for evaluating gynecological diseases. Traditional manual microscopy, which depends on the operator's expertise and subjective factors, has high false-positive rates (i.e., low specificity) and low efficiency. To date, there are many detection methods for biological cells based on morphological characteristics. However, the morphology of trichomonads changes, and its size is not fixed; moreover, they are similar to human leukocytes. Therefore, it is difficult to classify trichomonads based on morphological characteristics. In this study, a moving object detection method based on an improved Kalman background reconstruction algorithm is proposed to detect trichomonads automatically, considering the dynamic characteristics of trichomonads at room temperature. The experimental results show that the trichomonads can be accurately identified, and the phenomena of tailing and ghosts are eliminated. Furthermore, this algorithm easily adapts to continuous or sudden changes in light, focal length variation, and the impact of lens shift, and it has good robustness and only a moderate amount of calculation burden.