Risk Prediction of Diabetes Progression Using Big Data Mining with Multifarious Physical Examination Indicators.

Purpose: The purpose of this study is to explore the independent-influencing factors from normal people to prediabetes and from prediabetes to diabetes and use different prediction models to build diabetes prediction models. Methods: The original data in this retrospective study are collected from the participants who took physical examinations in the Health Management Center of Peking University Shenzhen Hospital. Regression analysis is individually applied between the populations of normal and prediabetes, as well as the populations of prediabetes and diabetes, for feature selection. Afterward,the independent influencing factors mentioned above are used as predictive factors to construct a prediction model. Results: Selecting physical examination indicators for training different ML models through univariate and multivariate logistic regression, the study finds Age, PRO, TP, and ALT are four independent risk factors for normal people to develop prediabetes, and GLB and HDL.C are two independent protective factors, while logistic regression performs best on the testing set (Acc: 0.76, F-measure: 0.74, AUC: 0.78). We also find Age, Gender, BMI, SBP, U.GLU, PRO, ALT, and TG are independent risk factors for prediabetes people to diabetes, and AST is an independent protective factor, while logistic regression performs best on the testing set (Acc: 0.86, F-measure: 0.84, AUC: 0.74). Conclusion: The discussion of the clinical relationships between these indicators and diabetes supports the interpretability of our feature selection. Among four prediction models, the logistic regression model achieved the best performance on the testing set.

Age-Related RPE changes in Wildtype C57BL/6J Mice between 2 and 32 Months.

Purpose: This study provides a systematic evaluation of age-related changes in RPE cell structure and function using a morphometric approach. We aim to better capture nuanced predictive changes in cell heterogeneity that reflect loss of RPE integrity during normal aging. Using C57BL6/J mice ranging from P60-P730, we sought to evaluate how regional changes in RPE shape reflect incremental losses in RPE cell function with advancing age. We hypothesize that tracking global morphological changes in RPE is predictive of functional defects over time. Methods: We tested three groups of C57BL/6J mice (young: P60-180; Middle-aged: P365-729; aged: 730+) for function and structural defects using electroretinograms, immunofluorescence, and phagocytosis assays. Results: The largest changes in RPE morphology were evident between the young and aged groups, while the middle-aged group exhibited smaller but notable region-specific differences. We observed a 1.9-fold increase in cytoplasmic alpha-catenin expression specifically in the central-medial region of the eye between the young and aged group. There was an 8-fold increase in subretinal, IBA-1-positive immune cell recruitment and a significant decrease in visual function in aged mice compared to young mice. Functional defects in the RPE corroborated by changes in RPE phagocytotic capacity. Conclusions: The marked increase of cytoplasmic alpha-catenin expression and subretinal immune cell deposition, and decreased visual output coincide with regional changes in RPE cell morphometrics when stratified by age. These cumulative changes in the RPE morphology showed predictive regional patterns of stress associated with loss of RPE integrity.

Self-supervised semantic segmentation of retinal pigment epithelium cells in flatmount fluorescent microscopy images.

MOTIVATION: Morphological analyses with flatmount fluorescent images are essential to retinal pigment epithelial (RPE) aging studies and thus require accurate RPE cell segmentation. Although rapid technology advances in deep learning semantic segmentation have achieved great success in many biomedical research, the performance of these supervised learning methods for RPE cell segmentation is still limited by inadequate training data with high-quality annotations. RESULTS: To address this problem, we develop a Self-Supervised Semantic Segmentation (S4) method that utilizes a self-supervised learning strategy to train a semantic segmentation network with an encoder-decoder architecture. We employ a reconstruction and a pairwise representation loss to make the encoder extract structural information, while we create a morphology loss to produce the segmentation map. In addition, we develop a novel image augmentation algorithm (AugCut) to produce multiple views for self-supervised learning and enhance the network training performance. To validate the efficacy of our method, we applied our developed S4 method for RPE cell segmentation to a large set of flatmount fluorescent microscopy images, we compare our developed method for RPE cell segmentation with other state-of-the-art deep learning approaches. Compared with other state-of-the-art deep learning approaches, our method demonstrates better performance in both qualitative and quantitative evaluations, suggesting its promising potential to support large-scale cell morphological analyses in RPE aging investigations. AVAILABILITY AND IMPLEMENTATION: The codes and the documentation are available at: https://github.com/jkonglab/S4_RPE.

Artificial intelligence based liver portal tract region identification and quantification with transplant biopsy whole-slide images.

Liver fibrosis staging is clinically important for liver disease progression prediction. As the portal tract fibrotic quantity and size in a liver biopsy correlate with the fibrosis stage, an accurate analysis of portal tract regions is clinically critical. Manual annotations of portal tract regions, however, are time-consuming and subject to large inter- and intra-observer variability. To address such a challenge, we develop a Multiple Up-sampling and Spatial Attention guided UNet model (MUSA-UNet) to segment liver portal tract regions in whole-slide images of liver tissue slides. To enhance the segmentation performance, we propose to use depth-wise separable convolution, the spatial attention mechanism, the residual connection, and multiple up-sampling paths in the developed model. This study includes 53 histopathology whole slide images from patients who received liver transplantation. In total, 6,012 patches derived from 30 images are used for our deep learning model training and validation. The remaining 23 whole slide images are utilized for the model testing. The average liver portal tract segmentation performance of the developed MUSA-UNet is 0.94 (Precision), 0.85 (Recall), 0.89 (F1 Score), 0.89 (Accuracy), 0.80 (Jaccard Index), and 0.91 (Fowlkes-Mallows Index), respectively. The clinical Scheuer fibrosis stage presents a strong correlation with the resulting average portal tract fibrotic area (R = 0.681, p<0.001) and portal tract percentage (R = 0.335, p = 0.02) computed from the MUSA-UNet segmentation results. In conclusion, our developed deep learning model MUSA-UNet can accurately segment portal tract regions from whole-slide images of liver tissue biopsies, presenting its promising potential to assist liver disease diagnosis in a computational manner.

MultiHeadGAN: A deep learning method for low contrast retinal pigment epithelium cell segmentation with fluorescent flatmount microscopy images.

BACKGROUND: Retinal pigment epithelium (RPE) aging is an important cause of vision loss. As RPE aging is accompanied by changes in cell morphological features, an accurate segmentation of RPE cells is a prerequisite to such morphology analyses. Due the overwhelmingly large cell number, manual annotations of RPE cell borders are time-consuming. Computer based methods do not work well on cells with weak or missing borders in the impaired RPE sheet regions. METHOD: To address such a challenge, we develop a semi-supervised deep learning approach, namely MultiHeadGAN, to segment low contrast cells from impaired regions in RPE flatmount images. The developed deep learning model has a multi-head structure that allows model training with only a small scale of human annotated data. To strengthen model learning, we further train our model with RPE cells without ground truth cell borders by generative adversarial networks. Additionally, we develop a new shape loss to guide the network to produce closed cell borders in the segmentation results. RESULTS: In this study, 155 annotated and 1,640 unlabeled image patches are included for model training. The testing dataset consists of 200 image patches presenting large impaired RPE regions. The average RPE segmentation performance of the developed model MultiHeadGAN is 85.4 (correct rate), 88.8 (weighted correct rate), 87.3 (precision), and 80.1 (recall), respectively. Compared with other state-of-the-art deep learning approaches, our method demonstrates its superior qualitative and quantitative performance. CONCLUSIONS: Suggested by our extensive experimental results, our developed deep learning method can accurately segment cells in RPE flatmount microscopy images and is promising to support large scale cell morphological analyses for RPE aging investigations.

Computational Model-Based Estimation of Mouse Eyeball Structure From Two-Dimensional Flatmount Microscopy Images.

Purpose: Retinal pigment epithelial (RPE) cells serve as a supporter for the metabolism and visual function of photoreceptors and a barrier for photoreceptor protection. Morphology dynamics, spatial organization, distribution density, and growth patterns of RPE cells are important for further research on these RPE main functions. To enable such investigations within the authentic eyeball structure, a new method for estimating the three-dimensional (3D) eyeball sphere from two-dimensional tissue flatmount microscopy images was investigated. Methods: An error-correction term was formulated to compensate for the reconstruction error as a result of tissue distortions. The effect of the tissue-distortion error was evaluated by excluding partial data points from the low- and high-latitude zones. The error-correction parameter was learned automatically using a set of samples with the ground truth eyeball diameters measured with noncontact light-emitting diode micrometry at submicron accuracy and precision. Results: The analysis showed that the error-correction term in the reconstruction model is a valid method for modeling tissue distortions in the tissue flatmount preparation steps. With the error-correction model, the average relative error of the estimated eyeball diameter was reduced from 14% to 5%, and the absolute error was reduced from 0.22 to 0.03 mm. Conclusions: A new method for enabling RPE morphometry analysis with respect to locations on an eyeball sphere was created, an important step in increasing RPE research and eye disease diagnosis. Translational Relevance: This method enables one to derive RPE cell information from the 3D eyeball surface and helps characterize eyeball volume growth patterns under diseased conditions.

Impact of Immunoglobulin Isotype and Epitope on the Functional Properties of Vibrio cholerae O-Specific Polysaccharide-Specific Monoclonal Antibodies.

Vibrio cholerae causes the severe diarrheal disease cholera. Clinical disease and current oral cholera vaccines generate antibody responses associated with protection. Immunity is thought to be largely mediated by lipopolysaccharide (LPS)-specific antibodies, primarily targeting the O-antigen. However, the properties and protective mechanism of functionally relevant antibodies have not been well defined. We previously reported on the early B cell response to cholera in a cohort of Bangladeshi patients, from which we characterized a panel of human monoclonal antibodies (MAbs) isolated from acutely induced plasmablasts. All antibodies in that previous study were expressed in an IgG1 backbone irrespective of their original isotype. To clearly determine the impact of affinity, immunoglobulin isotype and subclass on the functional properties of these MAbs, we re-engineered a subset of low- and high-affinity antibodies in different isotype and subclass immunoglobulin backbones and characterized the impact of these changes on binding, vibriocidal, agglutination, and motility inhibition activity. While the high-affinity antibodies bound similarly to O-antigen, irrespective of isotype, the low-affinity antibodies displayed significant avidity differences. Interestingly, despite exhibiting lower binding properties, variants derived from the low-affinity MAbs had comparable agglutination and motility inhibition properties to the potently binding antibodies, suggesting that how the MAb binds to the O-antigen may be critical to function. In addition, not only pentameric IgM and dimeric IgA, but also monomeric IgA, was remarkably more potent than their IgG counterparts at inhibiting motility. Finally, analyzing highly purified F(ab) versions of these antibodies, we show that LPS cross-linking is essential for motility inhibition.IMPORTANCE Immunity to the severe diarrheal disease cholera is largely mediated by lipopolysaccharide (LPS)-specific antibodies. However, the properties and protective mechanisms of functionally relevant antibodies have not been well defined. Here, we have engineered low and high-affinity LPS-specific antibodies in different immunoglobulin backbones in order to assess the impact of affinity, immunoglobulin isotype, and subclass on binding, vibriocidal, agglutination, and motility inhibition functional properties. Importantly, we found that affinity did not directly dictate functional potency since variants derived from the low-affinity MAbs had comparable agglutination and motility inhibition properties to the potently binding antibodies. This suggests that how the antibody binds sterically may be critical to function. In addition, not only pentameric IgM and dimeric IgA, but also monomeric IgA, was remarkably more potent than their IgG counterparts at inhibiting motility. Finally, analyzing highly purified F(ab) versions of these antibodies, we show that LPS cross-linking is essential for motility inhibition.

Morphometric Analysis of Retinal Pigment Epithelial Cells From C57BL/6J Mice During Aging.

Purpose: To quantitatively evaluate the changes in orientation and morphometric features of mouse retinal pigment epithelial (RPE) cells in different regions of the eye during aging. Methods: We segmented individual RPE cells from whole RPE flatmount images of C57BL/6J mice (postnatal days 30 to 720) using a machine-learning method and evaluated changes in morphometric features, including our newly developed metric combining alignment and shape of RPE cells during aging. Results: Mainly, the anterior part of the RPE sheet grows during aging, while the posterior part remains constant. Changes in size and shape of the peripheral RPE cells are prominent with aging as cells become larger, elongated, and concave. Conversely, the central RPE cells maintain relatively constant size and numbers with aging. Cell count in the central area and the overall cell count (approximately 50,000) were relatively constant over different age groups. RPE cells also present a specific orientation concordance that matches the shape of the specific region of the eyeball. Those cells near the optic disc or equator have a circumferential orientation to cover the round shape of the eyeball, whereas those cells in the periphery have a radial orientation and corresponding radial elongation, the extent of which increases with aging and matches with axial elongation of the eyeball. Conclusions: These results suggest that the fluid RPE morphology reflects various growth rates of underlying eyeball, and RPE cells could be classified into four regional classes (near the optic disc, central, equatorial, and peripheral) according to their morphometric features.

Clumped Nuclei Segmentation with Adjacent Point Match and Local Shape-Based Intensity Analysis in Fluorescence Microscopy Images.

Highly clumped nuclei captured in fluorescence microscopy images are commonly observed in a wide spectrum of tissue-related biomedical investigations. To ensure the quality of downstream biomedical analyses, it is essential to accurately segment clustered nuclei. However, this presents a technical challenge as fluorescence intensity alone is often insufficient for recovering the true nuclei boundaries. In this paper, we propose an segmentation algorithm that identifies point pair connection candidates and evaluates adjacent point connections with a formulated ellipse fitting quality indicator. After connection relationships are determined, we recover the resulting dividing paths by following points with specific eigenvalues from the image Hessian in a constrained searching space. We validate our algorithm with 560 image patches from two classes of tumor regions of seven brain tumor patients. Both qualitative and quantitative experimental results suggest that our algorithm is promising for dividing overlapped nuclei in fluorescence microscopy images widely used in various biomedical research.