Vocal Cord Leukoplakia Classification Using Siamese Network Under Small Samples of White Light Endoscopy Images.

OBJECTIVE: Accurate vocal cord leukoplakia classification is instructive for clinical diagnosis and surgical treatment. This article introduces a reliable very deep Siamese network for accurate vocal cord leukoplakia classification. STUDY DESIGN: A study of a classification network based on a retrospective database. SETTING: Academic university and hospital. METHODS: The white light image datasets of vocal cord leukoplakia used in this article were classified into 6 classes: normal tissues, inflammatory keratosis, mild dysplasia, moderate dysplasia, severe dysplasia, and squamous cell carcinoma. The classification performance was assessed by comparing it with 6 classical deep learning models, including AlexNet, VGG Net, Google Inception, ResNet, DenseNet, and Vision Transformer. RESULTS: Experiments show the superior classification performance of our proposed network compared to state-of-the-art methods. The overall accuracy is 0.9756. The values of sensitivity and specificity are very high as well. The confusion matrix provides information for the 6-class classification task and demonstrates the superiority of our proposed network. CONCLUSION: Our very deep Siamese network can provide accurate classification results of vocal cord leukoplakia, which facilitates early detection, clinical diagnosis, and surgical treatment. The excellent performance obtained in white light images can reduce the cost for patients, especially those living in developing countries.

Vocal cord leukoplakia classification using deep learning models in white light and narrow band imaging endoscopy images.

BACKGROUND: Accurate vocal cord leukoplakia classification is critical for the individualized treatment and early detection of laryngeal cancer. Numerous deep learning techniques have been proposed, but it is unclear how to select one to apply in the laryngeal tasks. This article introduces and reliably evaluates existing deep learning models for vocal cord leukoplakia classification. METHODS: We created white light and narrow band imaging (NBI) image datasets of vocal cord leukoplakia which were classified into six classes: normal tissues (NT), inflammatory keratosis (IK), mild dysplasia (MiD), moderate dysplasia (MoD), severe dysplasia (SD), and squamous cell carcinoma (SCC). Vocal cord leukoplakia classification was performed using six classical deep learning models, AlexNet, VGG, Google Inception, ResNet, DenseNet, and Vision Transformer. RESULTS: GoogLeNet (i.e., Google Inception V1), DenseNet-121, and ResNet-152 perform excellent classification. The highest overall accuracy of white light image classification is 0.9583, while the highest overall accuracy of NBI image classification is 0.9478. These three neural networks all provide very high sensitivity, specificity, and precision values. CONCLUSION: GoogLeNet, ResNet, and DenseNet can provide accurate pathological classification of vocal cord leukoplakia. It facilitates early diagnosis, providing judgment on conservative treatment or surgical treatment of different degrees, and reducing the burden on endoscopists.

Clinical characteristics and risk factors of cardiac surgery associated-acute kidney injury progressed to chronic kidney disease in adults: A retrospective, observational cohort study.

Introduction: To retrospectively investigate the clinical characteristics and risk factors of cardiac surgery associated-acute kidney injury (CS-AKI) progressed to chronic kidney disease (CKD) in adults and to evaluate the performance of clinical risk factor model for predicting CS-AKI to CKD. Methods: In this retrospective, observational cohort study, we included patients who were hospitalized for CS-AKI without a prior CKD [estimated glomerular filtration rate (eGFR) < 60 ml · min-1·1.73 m-2] at Central China Fuwai Hospital from January 2018 to December 2020. Survived patients were followed up for 90 days, the endpoint was CS-AKI to CKD, and then divided them into two groups (with or without CS-AKI to CKD). The baseline data including demographics, comorbidities, renal function, and other laboratory parameters were compared between two groups. The logistic regression model was used to analyze the risk factors for CS-AKI to CKD. Finally, receiver operator characteristic (ROC) curve was drawn to evaluate the performance of the clinical risk factor model for predicting CS-AKI to CKD. Results: We included 564 patients with CS-AKI (414 males, 150 females; age: 57.55 ± 11.86 years); 108 (19.1%) patients progressed to new-onset CKD 90 days after CS-AKI. Patients with CS-AKI to CKD had a higher proportion of females, hypertension, diabetes, congestive heart failure, coronary heart disease, low baseline eGFR and hemoglobin level, higher serum creatinine level at discharge (P < 0.05) than those without CS-AKI to CKD. Multivariate logistic regression analysis revealed that female sex(OR = 3.478, 95% CI: 1.844-6.559, P = 0.000), hypertension (OR = 1.835, 95% CI: 1.046-3.220, P = 0.034), coronary heart disease (OR = 1.779, 95% CI: 1.015-3.118, P = 0.044), congestive heart failure (OR = 1.908, 95% CI: 1.124-3.239, P = 0.017), preoperative low baseline eGFR (OR = 0.956, 95% CI: 0.938-0.975, P = 0.000), and higher serum creatinine level at discharge (OR = 1.109, 95% CI: 1.014-1.024, P = 0.000) were independent risk factors for CS-AKI to CKD. The clinical risk prediction model including female sex, hypertension, coronary heart disease, congestive heart failure, preoperative low baseline eGFR, and higher serum creatinine level at discharge produced a moderate performance for predicting CS-AKI to CKD (area under ROC curve = 0.859, 95% CI: 0.823-0.896). Conclusion: Patients with CS-AKI are at high risk for new-onset CKD. Female sex, comorbidities, and eGFR can help identify patients with a high risk for CS-AKI to CKD.

Multiscale segmentation- and error-guided iterative convolutional neural network for cerebral neuron segmentation in microscopic images.

This article uses microscopy images obtained from diverse anatomical regions of macaque brain for neuron semantic segmentation. The complex structure of brain, the large intra-class staining intensity difference within neuron class, the small inter-class staining intensity difference between neuron and tissue class, and the unbalanced dataset increase the difficulty of neuron semantic segmentation. To address this problem, we propose a multiscale segmentation- and error-guided iterative convolutional neural network (MSEG-iCNN) to improve the semantic segmentation performance in major anatomical regions of the macaque brain. After evaluating microscopic images from 17 anatomical regions, the semantic segmentation performance of neurons is improved by 10.6%, 4.0%, 1.5%, and 1.2% compared with Random Forest, FCN-8s, U-Net, and UNet++, respectively. Especially for neurons with brighter staining intensity in the anatomical regions such as lateral geniculate, globus pallidus and hypothalamus, the performance is improved by 66.1%, 23.9%, 11.2%, and 6.7%, respectively. Experiments show that our proposed method can efficiently segment neurons with a wide range of staining intensities. The semantic segmentation results are of great significance and can be further used for neuron instance segmentation, morphological analysis and disease diagnosis. Cell segmentation plays a critical role in extracting cerebral information, such as cell counting, cell morphometry and distribution analysis. Accurate automated neuron segmentation is challenging due to the complex structure of brain, the large intra-class staining intensity difference within neuron class, the small inter-class staining intensity difference between neuron and tissue class, and the unbalanced dataset. The proposed multiscale segmentation- and error-guided iterative convolutional neural network (MSEG-iCNN) improve the segmentation performance in 17 major anatomical regions of the macaque brain. HIGHLIGHTS: Cell segmentation plays a critical role in extracting cerebral information, such as cell counting, cell morphometry and distribution analysis. Accurate automated neuron segmentation is challenging due to the complex structure of brain, the large intra-class staining intensity difference within neuron class, the small inter-class staining intensity difference between neuron and tissue class, and the unbalanced dataset. The proposed multiscale segmentation- and error-guided iterative convolutional neural network (MSEG-iCNN) improve the segmentation performance in 17 major anatomical regions of the macaque brain.

Evaluation of Deep Learning Topcoders Method for Neuron Individualization in Histological Macaque Brain Section.

Cell individualization has a vital role in digital pathology image analysis. Deep Learning is considered as an efficient tool for instance segmentation tasks, including cell individualization. However, the precision of the Deep Learning model relies on massive unbiased dataset and manual pixel-level annotations, which is labor intensive. Moreover, most applications of Deep Learning have been developed for processing oncological data. To overcome these challenges, i) we established a pipeline to synthesize pixel-level labels with only point annotations provided; ii) we tested an ensemble Deep Learning algorithm to perform cell individualization on neurological data. Results suggest that the proposed method successfully segments neuronal cells in both object-level and pixel-level, with an average detection accuracy of 0.93.

Evaluation of automated segmentation algorithms for neurons in macaque cerebral microscopic images.

Accurate cerebral neuron segmentation is required before neuron counting and neuron morphological analysis. Numerous algorithms for neuron segmentation have been published, but they are mainly evaluated using limited subsets from a specific anatomical region, targeting neurons of clear contrast and/or neurons with similar staining intensity. It is thus unclear how these algorithms perform on cerebral neurons in diverse anatomical regions. In this article, we introduce and reliably evaluate existing machine learning algorithms using a data set of microscopy images of macaque brain. This data set highlights various anatomical regions (e.g., cortex, caudate, thalamus, claustrum, putamen, hippocampus, subiculum, lateral geniculate, globus pallidus, etc.), poor contrast, and staining intensity differences of neurons. The evaluation was performed using 10 architectures of six classic machine learning algorithms in terms of typical Recall, Precision, F-score, aggregated Jaccard index (AJI), as well as a performance ranking of algorithms. F-score of most of the algorithms is superior to 0.7. Deep learning algorithms facilitate generally higher F-scores. U-net with suitable layer depth has been evaluated to be excellent classifiers with F-score of 0.846 and 0.837 when performing cross validation. The evaluation and analysis indicate the performance gap among algorithms in various anatomical regions and the strengths and limitations of each algorithm. The comparative result highlights at the same time the importance and difficulty of neuron segmentation and provides clues for future improvement. To the best of our knowledge, this work is the first comprehensive study for neuron segmentation in such large-scale anatomical regions. Neuron segmentation plays a critical role in extracting cerebral information, such as neuron counting and neuron morphological analysis. Accurate automated cerebral neuron segmentation is a challenging task due to different kinds, poor contrast, staining intensity differences, and fuzzy boundaries of neurons. The comprehensive evaluation and analysis of performance among existing machine learning algorithms in diverse anatomical regions allows to make clear of the strengths and limitations of state-of-the-art algorithm. The comprehensive study provides clues for future improvement and creation of automated methods.

Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images.

In biomedical research, cell analysis is important to assess physiological and pathophysiological information. Virtual microscopy offers the unique possibility to study the compositions of tissues at a cellular scale. However, images acquired at such high spatial resolution are massive, contain complex information, and are therefore difficult to analyze automatically. In this article, we address the problem of individualization of size-varying and touching neurons in optical microscopy two-dimensional (2-D) images. Our approach is based on a series of processing steps that incorporate increasingly more information. (1) After a step of segmentation of neuron class using a Random Forest classifier, a novel min-max filter is used to enhance neurons' centroids and boundaries, enabling the use of region growing process based on a contour-based model to drive it to neuron boundary and achieve individualization of touching neurons. (2) Taking into account size-varying neurons, an adaptive multiscale procedure aiming at individualizing touching neurons is proposed. This protocol was evaluated in 17 major anatomical regions from three NeuN-stained macaque brain sections presenting diverse and comprehensive neuron densities. Qualitative and quantitative analyses demonstrate that the proposed method provides satisfactory results in most regions (e.g., caudate, cortex, subiculum, and putamen) and outperforms a baseline Watershed algorithm. Neuron counts obtained with our method show high correlation with an adapted stereology technique performed by two experts (respectively, 0.983 and 0.975 for the two experts). Neuron diameters obtained with our method ranged between 2 and 28.6 µm, matching values reported in the literature. Further works will aim to evaluate the impact of staining and interindividual variability on our protocol.

Hpa1 harpin needs nitroxyl terminus to promote vegetative growth and leaf photosynthesis in Arabidopsis.

Hpa1 is a harpin protein produced by Xanthomonas oryzae, an important bacterial pathogen of rice, and has the growth-promoting activity in plants. To understand the molecular basis for the function of Hpa1, we generated an inactive variant protein, Hpa1 delta NT, by deleting the nitroxyl-terminal region of the Hpa1 sequence and compared Hpa1 delta NT with the full-length protein in terms of the effects on vegetative growth and related physiological responses in Arabidopsis. When Hpa1 was applied to plants, it acted to enhance the vegetative growth but did not affect the floral development. Enhanced plant growth was accompanied by induced expression of growth-promoting genes in plant leaves. The growth-promoting activity of Hpa1 was further correlated with a physiological consequence shown as promoted leaf photosynthesis as a result of facilitated CO2 conduction through leaf stomata and mesophyll cells. On the contrary, plant growth, growth-promoting gene expression, and the physiological consequence changed little in response to the Hpa1 delta NT treatment. These analyses suggest that Hpa1 requires the nitroxyl-terminus to facilitate CO2 transport inside leaf cells and promote leaf photosynthesis and vegetative growth of the plant.

TTG2-regulated development is related to expression of putative AUXIN RESPONSE FACTOR genes in tobacco.

BACKGROUND: The phytohormone auxin mediates a stunning array of plant development through the functions of AUXIN RESPONSE FACTORs (ARFs), which belong to transcription factors and are present as a protein family comprising 10-43 members so far identified in different plant species. Plant development is also subject to regulation by TRANSPARENT TESTA GLABRA (TTG) proteins, such as NtTTG2 that we recently characterized in tobacco Nicotiana tabacum. To find the functional linkage between TTG and auxin in the regulation of plant development, we performed de novo assembly of the tobacco transcriptome to identify candidates of NtTTG2-regulated ARF genes. RESULTS: The role of NtTTG2 in tobacco growth and development was studied by analyzing the biological effects of gene silencing and overexpression. The NtTTG2 gene silencing causes repressive effects on vegetative growth, floral anthocyanin synthesis, flower colorization, and seed production. By contrast, the plant growth and development processes are promoted by NtTTG2 overexpression. The growth/developmental function of NtTTG2 associates with differential expression of putative ARF genes identified by de novo assembly of the tobacco transcriptome. The transcriptome contains a total of 54,906 unigenes, including 30,124 unigenes (54.86%) with annotated functions and at least 8,024 unigenes (14.61%) assigned to plant growth and development. The transcriptome also contains 455 unigenes (0.83%) related to auxin responses, including 40 putative ARF genes. Based on quantitative analyses, the expression of the putative genes is either promoted or inhibited by NtTTG2. CONCLUSIONS: The biological effects of the NtTTG2 gene silencing and overexpression suggest that NtTTG2 is an essential regulator of growth and development in tobacco. The effects of the altered NtTTG2 expression on expression levels of putative ARF genes identified in the transcriptome suggest that NtTTG2 functions in relation to ARF transcription factors.

Tobacco TTG2 suppresses resistance to pathogens by sequestering NPR1 from the nucleus.

TRANSPARENT TESTA GLABRA (TTG) proteins that contain the WD40 protein interaction domain are implicated in many signalling pathways in plants. The salicylic acid (SA) signalling pathway regulates the resistance of plants to pathogens through defence responses involving pathogenesis-related (PR) gene transcription, activated by the NPR1 (nonexpresser of PR genes 1) protein, which contains WD40-binding domains. We report that tobacco (Nicotiana tabacum) NtTTG2 suppresses the resistance to viral and bacterial pathogens by repressing the nuclear localisation of NPR1 and SA/NPR1-regulated defence in plants. Prevention of NtTTG2 protein production by silencing of the NtTTG2 gene resulted in the enhancement of resistance and PR gene expression, but NtTTG2 overexpression or NtTTG2 protein overproduction caused the opposite effects. Concurrent NtTTG2 and NPR1 gene silencing or NtTTG2 silencing in the absence of SA accumulation compensated for the compromised defence as a result of the NPR1 single-gene silencing or the absence of SA. However, NtTTG2 did not interact with NPR1 but was able to modulate the subcellular localisation of the NPR1 protein. In the absence of NtTTG2 production NPR1 was found predominantly in the nucleus and the PR genes were expressed. By contrast, when NtTTG2 accumulated in transgenic plants, a large proportion of NPR1 was retained in the cytoplasm and the PR genes were not expressed. These results suggest that NtTTG2 represses SA/NPR1-regulated defence by sequestering NPR1 from the nucleus and the transcriptional activation of the defence-response genes.

Apoplastic and cytoplasmic location of harpin protein Hpa1Xoo plays different roles in H2O2 generation and pathogen resistance in Arabidopsis.

Harpin proteins secreted by phytopathogenic bacteria have been shown to activate the plant defense pathway, which involves transduction of a hydrogen peroxide (H(2)O(2)) signal generated in the apoplast. However, the way in which harpins are recognized in the pathway and what role the apoplastic H(2)O(2) plays in plant defenses are unclear. Here, we examine whether the cellular localization of Hpa1(Xoo), a harpin protein produced by the rice bacterial leaf blight pathogen, impacts H(2)O(2) production and pathogen resistance in Arabidopsis thaliana. Transformation with the hpa1 (Xoo) gene and hpa1 (Xoo) fused to an apoplastic localization signal (shpa1 (Xoo)) generated h pa1 (Xoo)- and sh pa1 (Xoo)-expressing transgenic A . t haliana (HETAt and SHETAt) plants, respectively. Hpa1(Xoo) was associated with the apoplast in SHETAt plants but localized inside the cell in HETAt plants. In addition, Hpa1(Xoo) localization accompanied H(2)O(2) accumulation in both the apoplast and cytoplasm of SHETAt plants but only in the cytoplasm of HETAt plants. Apoplastic H(2)O(2) production via nicotinamide adenine dinucleotide phosphate (NADPH) oxidase (NOX) located in the plasma membrane is a common feature of plant defenses. In SHETAt plants, H(2)O(2) was generated in apoplasts in a NOX-dependent manner but accumulated to a greater extent in the cytoplasm than in the apoplast. After being applied to the wild-type plant, Hpa1(Xoo) localized to apoplasts and stimulated H(2)O(2) production as in SHETAt plants. In both plants, inhibiting apoplastic H(2)O(2) generation abrogated both cytoplasmic H(2)O(2) accumulation and plant resistance to bacterial pathogens. These results suggest the possibility that the apoplastic H(2)O(2) is subject to a cytoplasmic translocation for participation in the pathogen defense.

Harpin-induced expression and transgenic overexpression of the phloem protein gene AtPP2-A1 in Arabidopsis repress phloem feeding of the green peach aphid Myzus persicae.

BACKGROUND: Treatment of plants with HrpNEa, a protein of harpin group produced by Gram-negative plant pathogenic bacteria, induces plant resistance to insect herbivores, including the green peach aphid Myzus persicae, a generalist phloem-feeding insect. Under attacks by phloem-feeding insects, plants defend themselves using the phloem-based defense mechanism, which is supposed to involve the phloem protein 2 (PP2), one of the most abundant proteins in the phloem sap. The purpose of this study was to obtain genetic evidence for the function of the Arabidopsis thaliana (Arabidopsis) PP2-encoding gene AtPP2-A1 in resistance to M. persicae when the plant was treated with HrpNEa and after the plant was transformed with AtPP2-A1. RESULTS: The electrical penetration graph technique was used to visualize the phloem-feeding activities of apterous agamic M. persicae females on leaves of Arabidopsis plants treated with HrpNEa and an inactive protein control, respectively. A repression of phloem feeding was induced by HrpNEa in wild-type (WT) Arabidopsis but not in atpp2-a1/E/142, the plant mutant that had a defect in the AtPP2-A1 gene, the most HrpNEa-responsive of 30 AtPP2 genes. In WT rather than atpp2-a1/E/142, the deterrent effect of HrpNEa treatment on the phloem-feeding activity accompanied an enhancement of AtPP2-A1 expression. In PP2OETAt (AtPP2-A1-overexpression transgenic Arabidopsis thaliana) plants, abundant amounts of the AtPP2-A1 gene transcript were detected in different organs, including leaves, stems, calyces, and petals. All these organs had a deterrent effect on the phloem-feeding activity compared with the same organs of the transgenic control plant. When a large-scale aphid population was monitored for 24 hours, there was a significant decrease in the number of aphids that colonized leaves of HrpNEa-treated WT and PP2OETAt plants, respectively, compared with control plants. CONCLUSIONS: The repression in phloem-feeding activities of M. persicae as a result of AtPP2-A1 overexpression, and as a deterrent effect of HrpNEa treatment in WT Arabidopsis rather than the atpp2-a1/E/142 mutant suggest that AtPP2-A1 plays a role in plant resistance to the insect, particularly at the phloem-feeding stage. The accompanied change of aphid population in leaf colonies suggests that the function of AtPP2-A1 is related to colonization of the plant.