Inflammatory endotypes of adenoidal hypertrophy based on a cluster analysis of biomarkers.

OBJECTIVE: To identify adenoid inflammatory endotypes based on inflammatory markers, match endotypes to phenotypes, and predict endotypes. METHODS: This cross-sectional study included 72 children with adenoid hypertrophy. Thirteen inflammatory markers and total immunoglobulin E (TIgE) in adenoid tissue were analyzed using Luminex and enzyme-linked immunosorbent assay (ELISA) for performing cluster analysis. Correlation analysis was used to examine the characteristics of each cluster. Receiver operating characteristic (ROC) curve analysis was performed to screen for preoperative characteristic data with predictive value for adenoid inflammation endotype. RESULTS: The patients were divided into four clusters. Cluster 1 exhibited non-type 2 signatures with low inflammatory marker concentrations, except for the highest expression of Th1-related cytokines. Cluster 2 showed a non-type 2 endotype with the highest concentration of interleukin (IL)-17A and IL-22. Cluster 3 exhibited moderate type 2 inflammation, with the highest concentration of neutrophil factors. Cluster 4 demonstrated significant type 2 inflammation and moderate neutrophil levels. The proportions of AR and serum TIgE levels increased from clusters 1 to 4, and there was a gradual increase in the prevalence of chronic sinusitis from low to high neutrophilic inflammation. The area under the ROC curve for serum TIgE was higher than those for combined or other separate preoperative characteristics for predicting non-type 2 and type 2 inflammation in the adenoid tissue. CONCLUSIONS: The evaluation of cytokines in adenoid tissue revealed four endotypes. Serum TIgE level was an important indicator of the endotype of adenoid inflammation. Identification of adenoid inflammatory endotypes can facilitate targeted treatment decisions.

Deep learning for the prediction of residual tumor after radiotherapy and treatment decision-making in patients with nasopharyngeal carcinoma based on magnetic resonance imaging.

Background: Concurrent chemoradiotherapy (CCRT) and induction chemotherapy (IC) plus CCRT (IC + CCRT) are the main treatments for patients with advanced nasopharyngeal carcinoma (NPC). We aimed to develop deep learning (DL) models using magnetic resonance (MR) imaging to predict the risk of residual tumor after each of the 2 treatments and to provide a reference for patients to select the best treatment option. Methods: A retrospective study was conducted on 424 patients with locoregionally advanced NPC who underwent CCRT or IC + CCRT between June 2012 and June 2019 in the Renmin Hospital of Wuhan University. According to the evaluation of MR images taken 3 to 6 months after radiotherapy, patients were divided into 2 categories: residual tumor and non-residual tumor. Transferred U-net and Deeplabv3 neural networks were trained, and the better-performance segmentation model was used to segment the tumor area on axial T1-weighted enhanced MR images. Then, 4 pretrained neural networks for prediction of residual tumors were trained with CCRT and IC + CCRT datasets, and the performances of the models trained using each image and each patient as a unit were evaluated. Patients in the test cohort of CCRT and IC + CCRT datasets were successively classified by the trained CCRT and IC + CCRT models. Model recommendations were formed according to the classification and compared with the treatment decisions of physicians. Results: The Dice coefficient of Deeplabv3 (0.752) was higher than that of U-net (0.689). The average area under the curve (aAUC) of the 4 networks was 0.728 for the CCRT and 0.828 for the IC + CCRT models trained using a single image as a unit, whereas the aAUC for models trained using each patient as a unit was 0.928 for the CCRT and 0.915 for the IC + CCRT models, respectively. The accuracy of the model recommendation and the decision of physicians was 84.06% and 60.00%, respectively. Conclusions: The proposed method can effectively predict the residual tumor status of patients after CCRT and IC + CCRT. Recommendations based on the model prediction results can protect some patients from receiving additional IC and improve the survival rate of patients with NPC.

Predicting prognosis of nasopharyngeal carcinoma based on deep learning: peritumoral region should be valued.

BACKGROUND: The purpose of this study was to explore whether incorporating the peritumoral region to train deep neural networks could improve the performance of the models for predicting the prognosis of NPC. METHODS: A total of 381 NPC patients who were divided into high- and low-risk groups according to progression-free survival were retrospectively included. Deeplab v3 and U-Net were trained to build segmentation models for the automatic segmentation of the tumor and suspicious lymph nodes. Five datasets were constructed by expanding 5, 10, 20, 40, and 60 pixels outward from the edge of the automatically segmented region. Inception-Resnet-V2, ECA-ResNet50t, EfficientNet-B3, and EfficientNet-B0 were trained with the original, segmented, and the five new constructed datasets to establish the classification models. The receiver operating characteristic curve was used to evaluate the performance of each model. RESULTS: The Dice coefficients of Deeplab v3 and U-Net were 0.741(95%CI:0.722-0.760) and 0.737(95%CI:0.720-0.754), respectively. The average areas under the curve (aAUCs) of deep learning models for classification trained with the original and segmented images and with images expanded by 5, 10, 20, 40, and 60 pixels were 0.717 ± 0.043, 0.739 ± 0.016, 0.760 ± 0.010, 0.768 ± 0.018, 0.802 ± 0.013, 0.782 ± 0.039, and 0.753 ± 0.014, respectively. The models trained with the images expanded by 20 pixels obtained the best performance. CONCLUSIONS: The peritumoral region NPC contains information related to prognosis, and the incorporation of this region could improve the performance of deep learning models for prognosis prediction.

Differentiation of eosinophilic and non-eosinophilic chronic rhinosinusitis on preoperative computed tomography using deep learning.

OBJECTIVES: This study aimed to develop deep learning (DL) models for differentiating between eosinophilic chronic rhinosinusitis (ECRS) and non-ECRS (NECRS) on preoperative CT. DESIGN: Axial spiral CT images were pre-processed and used to build the dataset. Two semantic segmentation models based on U-net and Deeplabv3 were trained to segment the sinus area on CT images. All patient images were segmented using the better-performing segmentation model and used for training and testing of the transferred efficientnet_b0, resnet50, inception_resnet_v2, and Xception neural networks. Additionally, we evaluated the performances of the models trained using each image and each patient as a unit. PARTICIPANTS: A total of 878 chronic rhinosinusitis (CRS) patients undergoing nasal endoscopic surgery at Renmin Hospital of Wuhan University (Hubei, China) between October 2016 to June 2021 were included. MAIN OUTCOME MEASURES: The precision of each model was assessed based on the receiver operating characteristic curve. Further, we analyzed the confusion matrix and accuracy of each model. RESULTS: The Dice coefficients of U-net and Deeplabv3 were 0.953 and 0.961, respectively. The average area under the curve and mean accuracy values of the four networks were 0.848 and 0.762 for models trained using a single image as a unit, while the corresponding values for models trained using each patient as a unit were 0.893 and 0.853, respectively. CONCLUSIONS: Combining semantic segmentation with classification networks could effectively distinguish between patients with ECRS and those with NECRS based on preoperative sinus CT images. Furthermore, labeling each patient to build a dataset for classification may be more reliable than labeling each medical image.

Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging.

IMPORTANCE: Accurate pre-treatment prediction of distant metastasis in patients with Nasopharyngeal Carcinoma (NPC) enables the implementation of appropriate treatment strategies for high-risk individuals. PURPOSE: To develop and assess a Convolutional Neural Network (CNN) model using pre-therapy Magnetic Resonance (MR) imaging to predict distant metastasis in NPC patients. METHODS: We retrospectively reviewed data of 441 pathologically diagnosed NPC patients who underwent complete radiotherapy and chemotherapy at Renmin Hospital of Wuhan University (Hubei, China) between February 2012 and March 2018. Using Adobe Photoshop, an experienced radiologist segmented MR images with rectangular regions of interest. To develop an accurate model according to the primary tumour, Cervical Metastatic Lymph Node (CMLN), the largest area of invasion of the primary tumour, and image segmentation methods, we constructed intratumoural and intra-peritumoural datasets that were used for training and test of the transfer learning models. Each model's precision was assessed according to its receiver operating characteristic curve and accuracy. Generated high-risk-related Grad-Cams demonstrated how the model captured the image features and further verified its reliability. RESULTS: Among the four models, all intra-peritumoural datasets performed better than the corresponding intratumoural datasets, with the CMLN intra-peritumoural dataset exhibiting the best performance (average area under the curves (AUCs) = 0.88). There was no significant difference between average AUCs of the Max and NPC tumour datasets. AUCs of the eight datasets for the four models were higher than those of the Tumour-Node-Metastasis staging system (AUC=0.67). In most datasets, the xception model had higher AUCs than other models. The efficientnet-b0 and xception models efficiently extracted high-risk features. CONCLUSION: The CNN model predicted distant metastasis in NPC patients with high accuracy. Compared to the primary tumour, the CMLN better predicted distant metastasis. In addition to intratumoural data, peritumoural information can facilitate the prediction of distant metastasis. With a larger sample size, datasets of the largest areas of tumour invasion may achieve meaningful accuracy. Among the models, xception had the best overall performance.

Deep learning for locally advanced nasopharyngeal carcinoma prognostication based on pre- and post-treatment MRI.

PURPOSE: We aimed to predict the prognosis of advanced nasopharyngeal carcinoma (stage Ⅲ-Ⅳa) using Pre- and Post-treatment MR images based on deep learning (DL). METHODS: A total of 206 patients with primary nasopharyngeal carcinoma who were diagnosed and treated at the Renmin Hospital of Wuhan University between June 2012 and January 2018 were retrospectively selected. A rectangular region of interest (ROI), which included the tumor area, surrounding tissues and organs, was delineated on each Pre- and Post-treatment MR image. Two Inception-Resnet-V2 based transfer learning models, named Pre-model and Post-model, were trained with the Pre-treatment images and the Post-treatment images, respectively. In addition, an ensemble learning model based on the Pre-model and Post-models was established. The three established models were evaluated by receiver operating characteristic curve (ROC), confusion matrix, and Harrell's concordance indices (C-index). High-risk-related gradient-weighted class activation mapping (Grad-CAM) images were developed according to the DL models. RESULTS: The Pre-model, Post-model, and ensemble model displayed a C-index of 0.717 (95% CI: 0.639 to 0.795), 0.811 (95% CI: 0.745-0.877), 0.830 (95% CI: 0.767-0.893), and AUC of 0.741 (95% CI: 0.584-0.900), 0.806 (95% CI: 0.670-0.942), and 0.842 (95% CI: 0.718-0.967) for the test cohort, respectively. In comparison with the models, the performance of Post-model was better than the performance of Pre-model, which indicated the importance of Post-treatment images for prognosis prediction. All three DL models performed better than the TNM staging system (0.723, 95% CI: 0.567-0.879). The captured features presented on Grad-CAM images suggested that the areas around the tumor and lymph nodes were related to the prognosis of the tumor. CONCLUSIONS: The three established DL models based on Pre- and Post-treatment MR images have a better performance than TNM staging. Post-treatment MR images are of great significance for prognosis prediction and could contribute to clinical decision-making.

Anatomical Partition-Based Deep Learning: An Automatic Nasopharyngeal MRI Recognition Scheme.

BACKGROUND: Training deep learning (DL) models to automatically recognize diseases in nasopharyngeal MRI is a challenging task, and optimizing the performance of DL models is difficult. PURPOSE: To develop a method of training anatomical partition-based DL model which integrates knowledge of clinical anatomical regions in otorhinolaryngology to automatically recognize diseases in nasopharyngeal MRI. STUDY TYPE: Single-center retrospective study. POPULATION: A total of 2485 patients with nasopharyngeal diseases (age range 14-82 years, female, 779[31.3%]) and 600 people with normal nasopharynx (age range 18-78 years, female, 281[46.8%]) were included. SEQUENCE: 3.0 T; T2WI fast spin-echo sequence. ASSESSMENT: Full images (512 × 512) of 3085 patients constituted 100% of the dataset, 50% and 25% of which were randomly retained as two new datasets. Two new series of images (seg112 image [112 × 112] and seg224 image [224 × 224]) were automatically generated by a segmentation model. Four pretrained neural networks for nasopharyngeal diseases classification were trained under the nine datasets (full image, seg112 image, and seg224 image, each with 100% dataset, 50% dataset, and 25% dataset). STATISTICAL TESTS: The receiver operating characteristic curve was used to evaluate the performance of the models. Analysis of variance was used to compare the performance of the models built with different datasets. Statistical significance was set at P < 0.05. RESULTS: When the 100% dataset was used for training, the performances of the models trained with the seg112 images (average area under the curve [aAUC] 0.949 ± 0.052), seg224 images (aAUC 0.948 ± 0.053), and full images (aAUC 0.935 ± 0.053) were similar (P = 0.611). When the 25% dataset was used for training, the mean aAUC of the models that were trained with seg112 images (0.823 ± 0.116) and seg224 images (0.765 ± 0.155) was significantly higher than the models that were trained with full images (0.640 ± 0.154). DATA CONCLUSION: The proposed method can potentially improve the performance of the DL model for automatic recognition of diseases in nasopharyngeal MRI. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 1.

The association between allergy and sinusitis: a cross-sectional study based on NHANES 2005-2006.

BACKGROUND: The relationship between allergies and sinusitis, though extensively studied, remains poorly defined. While several studies proposed a cause-and-effect relationship between allergy and chronic sinusitis, several others reported the lack of any existing association. This study aimed to investigate the relationship between allergy and sinusitis. METHODS: We conducted a cross-sectional study using a representative sample of the US population from the National Health and Nutrition Examination Survey 2005‒2006 (n = 7244). A self-reported allergy questionnaire and total and allergen-specific IgE levels were used for analysis. Participants were divided into positive and negative allergy symptoms groups (PAS, NAS, respectively) to eliminate the influence of allergy symptoms on the apparent incidence of sinusitis. Pearson's chi-square test and the linear regression analysis using Durbin Watson test were used for statistical analysis. RESULTS: Sinusitis incidence in the PAS group (22.4%; 521/2327) was significantly higher than that in the NAS group (7.1%; 348/4917) [odds ratios (OR) = 3.788, 95% confidence interval (CI) 3.272‒4.384, P < 0.001]. sinusitis incidence in non-sensitized and sensitized groups was not statistically different. After controlling for allergy symptoms, there was a negative correlation between sensitization status and the occurrence of sinusitis in the PAS group (OR = 1.407, 95% CI 1.156‒1.711, P < 0.01). Increase in serum total IgE levels correlated with decrease in incidence of sinusitis in both PAS and NAS groups. sinusitis incidence was significantly reduced in the PAS group in participants sensitized to allergens such as cockroaches, ragweed, ryegrass, Bermuda grass, oak, birch, and thistle. CONCLUSION: Allergy is related to sinusitis incidence. It is likely that sensitization status could reduce the incidence of sinusitis, albeit in an antigen-specific manner.

A Comprehensive Review on Radiomics and Deep Learning for Nasopharyngeal Carcinoma Imaging.

Nasopharyngeal carcinoma (NPC) is one of the most common malignant tumours of the head and neck, and improving the efficiency of its diagnosis and treatment strategies is an important goal. With the development of the combination of artificial intelligence (AI) technology and medical imaging in recent years, an increasing number of studies have been conducted on image analysis of NPC using AI tools, especially radiomics and artificial neural network methods. In this review, we present a comprehensive overview of NPC imaging research based on radiomics and deep learning. These studies depict a promising prospect for the diagnosis and treatment of NPC. The deficiencies of the current studies and the potential of radiomics and deep learning for NPC imaging are discussed. We conclude that future research should establish a large-scale labelled dataset of NPC images and that studies focused on screening for NPC using AI are necessary.

Comprehensive review of the identification of essential genes using computational methods: focusing on feature implementation and assessment.

Essential genes have attracted increasing attention in recent years due to the important functions of these genes in organisms. Among the methods used to identify the essential genes, accurate and efficient computational methods can make up for the deficiencies of expensive and time-consuming experimental technologies. In this review, we have collected researches on essential gene predictions in prokaryotes and eukaryotes and summarized the five predominant types of features used in these studies. The five types of features include evolutionary conservation, domain information, network topology, sequence component and expression level. We have described how to implement the useful forms of these features and evaluated their performance based on the data of Escherichia coli MG1655, Bacillus subtilis 168 and human. The prerequisite and applicable range of these features is described. In addition, we have investigated the techniques used to weight features in various models. To facilitate researchers in the field, two available online tools, which are accessible for free and can be directly used to predict gene essentiality in prokaryotes and humans, were referred. This article provides a simple guide for the identification of essential genes in prokaryotes and eukaryotes.

Anti-CRISPRdb: a comprehensive online resource for anti-CRISPR proteins.

CRISPR-Cas is a tool that is widely used for gene editing. However, unexpected off-target effects may occur as a result of long-term nuclease activity. Anti-CRISPR proteins, which are powerful molecules that inhibit the CRISPR-Cas system, may have the potential to promote better utilization of the CRISPR-Cas system in gene editing, especially for gene therapy. Additionally, more in-depth research on these proteins would help researchers to better understand the co-evolution of bacteria and phages. Therefore, it is necessary to collect and integrate data on various types of anti-CRISPRs. Herein, data on these proteins were manually gathered through data screening of the literatures. Then, the first online resource, anti-CRISPRdb, was constructed for effectively organizing these proteins. It contains the available protein sequences, DNA sequences, coding regions, source organisms, taxonomy, virulence, protein interactors and their corresponding three-dimensional structures. Users can access our database at http://cefg.uestc.edu.cn/anti-CRISPRdb/ without registration. We believe that the anti-CRISPRdb can be used as a resource to facilitate research on anti-CRISPR proteins and in related fields.

Accurate prediction of human essential genes using only nucleotide composition and association information.

MOTIVATION: Previously constructed classifiers in predicting eukaryotic essential genes integrated a variety of features including experimental ones. If we can obtain satisfactory prediction using only nucleotide (sequence) information, it would be more promising. Three groups recently identified essential genes in human cancer cell lines using wet experiments and it provided wonderful opportunity to accomplish our idea. Here we improved the Z curve method into the λ-interval form to denote nucleotide composition and association information and used it to construct the SVM classifying model. RESULTS: Our model accurately predicted human gene essentiality with an AUC higher than 0.88 both for 5-fold cross-validation and jackknife tests. These results demonstrated that the essentiality of human genes could be reliably reflected by only sequence information. We re-predicted the negative dataset by our Pheg server and 118 genes were additionally predicted as essential. Among them, 20 were found to be homologues in mouse essential genes, indicating that some of the 118 genes were indeed essential, however previous experiments overlooked them. As the first available server, Pheg could predict essentiality for anonymous gene sequences of human. It is also hoped the λ-interval Z curve method could be effectively extended to classification issues of other DNA elements. AVAILABILITY AND IMPLEMENTATION: http://cefg.uestc.edu.cn/Pheg. CONTACT: fbguo@uestc.edu.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Zisland Explorer: detect genomic islands by combining homogeneity and heterogeneity properties.

Genomic islands are genomic fragments of alien origin in bacterial and archaeal genomes, usually involved in symbiosis or pathogenesis. In this work, we described Zisland Explorer, a novel tool to predict genomic islands based on the segmental cumulative GC profile. Zisland Explorer was designed with a novel strategy, as well as a combination of the homogeneity and heterogeneity of genomic sequences. While the sequence homogeneity reflects the composition consistence within each island, the heterogeneity measures the composition bias between an island and the core genome. The performance of Zisland Explorer was evaluated on the data sets of 11 different organisms. Our results suggested that the true-positive rate (TPR) of Zisland Explorer was at least 10.3% higher than that of four other widely used tools. On the other hand, the new tool did not lose overall accuracy with the improvement in the TPR and showed better equilibrium among various evaluation indexes. Also, Zisland Explorer showed better accuracy in the prediction of experimental island data. Overall, the tool provides an alternative solution over other tools, which expands the field of island prediction and offers a supplement to increase the performance of the distinct predicting strategy. We have provided a web service as well as a graphical user interface and open-source code across multiple platforms for Zisland Explorer, which is available at http://cefg.uestc.edu.cn/Zisland_Explorer/ or http://tubic.tju.edu.cn/Zisland_Explorer/.

An Approach for Predicting Essential Genes Using Multiple Homology Mapping and Machine Learning Algorithms.

Investigation of essential genes is significant to comprehend the minimal gene sets of cell and discover potential drug targets. In this study, a novel approach based on multiple homology mapping and machine learning method was introduced to predict essential genes. We focused on 25 bacteria which have characterized essential genes. The predictions yielded the highest area under receiver operating characteristic (ROC) curve (AUC) of 0.9716 through tenfold cross-validation test. Proper features were utilized to construct models to make predictions in distantly related bacteria. The accuracy of predictions was evaluated via the consistency of predictions and known essential genes of target species. The highest AUC of 0.9552 and average AUC of 0.8314 were achieved when making predictions across organisms. An independent dataset from Synechococcus elongatus, which was released recently, was obtained for further assessment of the performance of our model. The AUC score of predictions is 0.7855, which is higher than other methods. This research presents that features obtained by homology mapping uniquely can achieve quite great or even better results than those integrated features. Meanwhile, the work indicates that machine learning-based method can assign more efficient weight coefficients than using empirical formula based on biological knowledge.

Combining pseudo dinucleotide composition with the Z curve method to improve the accuracy of predicting DNA elements: a case study in recombination spots.

Pseudo dinucleotide composition (PseDNC) and Z curve showed excellent performance in the classification issues of nucleotide sequences in bioinformatics. Inspired by the principle of Z curve theory, we improved PseDNC to give the phase-specific PseDNC (psPseDNC). In this study, we used the prediction of recombination spots as a case to illustrate the capability of psPseDNC and also PseDNC fused with Z curve theory based on a novel machine learning method named large margin distribution machine (LDM). We verified that combining the two widely used approaches could generate better performance compared to only using PseDNC with a support vector machine based (SVM-based) model. The best Mathew's correlation coefficient (MCC) achieved by our LDM-based model was 0.7037 through the rigorous jackknife test and improved by ∼6.6%, ∼3.2%, and ∼2.4% compared with three previous studies. Similarly, the accuracy was improved by 3.2% compared with our previous iRSpot-PseDNC web server through an independent data test. These results demonstrate that the joint use of PseDNC and Z curve enhances performance and can extract more information from a biological sequence. To facilitate research in this area, we constructed a user-friendly web server for predicting hot/cold spots, HcsPredictor, which can be freely accessed from . In summary, we provided a united algorithm by integrating Z curve with PseDNC. We hope this united algorithm could be extended to other classification issues in DNA elements.