GOLD-Grade Specific Disease Characterization and Phenotyping of COPD Using Quantitative Computed Tomography in the Nationwide COSYCONET Multicenter Trial in Germany.

INTRODUCTION: The aim of this study was to apply quantitative computed tomography (QCT) for GOLD-grade specific disease characterization and phenotyping of air-trapping, emphysema, and airway abnormalities in patients with chronic obstructive pulmonary disease (COPD) from a nationwide cohort study. METHODS: As part of the COSYCONET multicenter study, standardized CT in ex- and inspiration, lung function assessment (FEV1/FVC), and clinical scores (BODE index) were prospectively acquired in 525 patients (192 women, 327 men, aged 65.7 ± 8.5 years) at risk for COPD and at GOLD1-4. QCT parameters such as total lung volume (TLV), emphysema index (EI), parametric response mapping (PRM) for emphysema (PRMEmph) and functional small airway disease (PRMfSAD), total airway volume (TAV), wall percentage (WP), and total diameter (TD) were computed using automated software. RESULTS: TLV, EI, PRMfSAD, and PRMEmph increased incrementally with each GOLD grade (p < 0.001). Aggregated WP5-10 of subsegmental airways was higher from GOLD1 to GOLD3 and lower again at GOLD4 (p < 0.001), whereas TD5-10 was significantly dilated only in GOLD4 (p < 0.001). Fifty-eight patients were phenotyped as "non-airway non-emphysema type," 202 as "airway type," 96 as "emphysema type," and 169 as "mixed type." FEV1/FVC was best in "non-airway non-emphysema type" compared to other phenotypes, while "mixed type" had worst FEV1/FVC (p < 0.001). BODE index was 0.56 ± 0.72 in the "non-airway non-emphysema type" and highest with 2.55 ± 1.77 in "mixed type" (p < 0.001). CONCLUSION: QCT demonstrates increasing hyperinflation and emphysema depending on the GOLD grade, while airway wall thickening increases until GOLD3 and airway dilatation occur in GOLD4. QCT identifies four disease phenotypes with implications for lung function and prognosis.

Optimizing Corn Tar Spot Measurement: A Deep Learning Approach Using Red-Green-Blue Imaging and Stromata Contour Detection Algorithm for Leaf-Level Disease Severity Analysis.

Visual detection of stromata (brown-black, elevated fungal fruiting bodies) is a primary method for quantifying tar spot early in the season, as these structures are definitive signs of the disease and essential for effective disease monitoring and management. Here, we present Stromata Contour Detection Algorithm version 2 (SCDA v2), which addresses the limitations of the previously developed SCDA version 1 (SCDA v1) without the need for empirical search of the optimal Decision Making Input Parameters (DMIPs), while achieving higher and consistent accuracy in tar spot stromata detection. SCDA v2 operates in two components: (i) SCDA v1 producing tar-spot-like region proposals for a given input corn leaf Red-Green-Blue (RGB) image, and (ii) a pre-trained Convolutional Neural Network (CNN) classifier identifying true tar spot stromata from the region proposals. To demonstrate the enhanced performance of the SCDA v2, we utilized datasets of RGB images of corn leaves from field (low, middle, and upper canopies) and glasshouse conditions under variable environments, exhibiting different tar spot severities at various corn developmental stages. Various accuracy analyses (F1-score, linear regression, and Lin's concordance correlation), showed that SCDA v2 had a greater agreement with the reference data (human visual annotation) than SCDA v1. SCDA v2 achievd 73.7% mean Dice values (overall accuracy), compared to 30.8% for SCDA v1. The enhanced F1-score primarily resulted from eliminating overestimation cases using the CNN classifier. Our findings indicate the promising potential of SCDA v2 for glasshouse and field-scale applications, including tar spot phenotyping and surveillance projects.

Inheritance of Resistance to Chickpea Fusarium Wilt Disease (Fusarium oxysporum f. sp. ciceris Race 2) in a Wide-Cross Cicer arietinum × Cicer reticulatum Mapping Family.

Chickpea (Cicer arietinum) is a major food legume providing high quality nutrition, especially in developing regions. Chickpea wilt (Fusarium oxysporum f. sp. ciceris) causes significant annual losses. Integrated disease management of Fusarium wilt is supported by resistant varieties. Relatively few resistance genes are known so there is value in exploring genetic resources in chickpea wild relatives. This study investigates the inheritance of Fusarium wilt resistance (race 2) in recombinant inbred lines (RILs) from a cross between a cultivated susceptible chickpea variety (Gokce) and a wild resistant Cicer reticulatum line (Kayat-077). RILs, parents, resistant and susceptible tester lines were twice grown in the greenhouse with inoculation and disease symptoms scored. DNA was extracted from dried leaves and individuals were single nucleotide polymorphism (SNP) genotyped. SNPs were placed on the reference chickpea genome and quantitative trait locus (QTL) mapping was performed. Significant QTL regions were examined using PulseDB to identify candidate genes. The results showed the segregation of Fusarium wilt resistance conforming to a single gene inheritance. One significant QTL was found at the start of chromosome 8, containing 138 genes, three of which were disease-resistance candidates for chickpea breeding.

Application of a U-Net Neural Network to the Puccinia sorghi-Maize Pathosystem.

Computer vision approaches to analyze plant disease data can be both faster and more reliable than traditional, manual methods. However, the requirement of manually annotating training data for the majority of machine learning applications can present a challenge for pipeline development. Here, we describe a machine learning approach to quantify Puccinia sorghi incidence on maize leaves utilizing U-Net convolutional neural network models. We analyzed several U-Net models with increasing amounts of training image data, either randomly chosen from a large data pool or randomly chosen from a subset of disease time course data. As the training dataset size increases, the models perform better, but the rate of performance decreases. Additionally, the use of a diverse training dataset can improve model performance and reduce the amount of annotated training data required for satisfactory performance. Models with as few as 48 whole-leaf training images are able to replicate the ground truth results within our testing dataset. The final model utilizing our entire training dataset performs similarly to our ground truth data, with an intersection over union value of 0.5002 and an F1 score of 0.6669. This work illustrates the capacity of U-Nets to accurately answer real-world plant pathology questions related to quantification and estimation of plant disease symptoms. [Formula: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license.

Identification of Parkinson's Disease Subtypes from Resting-State Electroencephalography.

BACKGROUND: Parkinson's disease (PD) patients present with a heterogeneous clinical phenotype, including motor, cognitive, sleep, and affective disruptions. However, this heterogeneity is often either ignored or assessed using only clinical assessments. OBJECTIVES: We aimed to identify different PD sub-phenotypes in a longitudinal follow-up analysis and their electrophysiological profile based on resting-state electroencephalography (RS-EEG) and to assess their clinical significance over the course of the disease. METHODS: Using electrophysiological features obtained from RS-EEG recordings and data-driven methods (similarity network fusion and source-space spectral analysis), we have performed a clustering analysis to identify disease sub-phenotypes and we examined whether their different patterns of disruption are predictive of disease outcome. RESULTS: We showed that PD patients (n = 44) can be sub-grouped into three phenotypes with distinct electrophysiological profiles. These clusters are characterized by different levels of disruptions in the somatomotor network (Δ and ß band), the frontotemporal network (α2 band) and the default mode network (α1 band), which consistently correlate with clinical profiles and disease courses. These clusters are classified into either moderate (only-motor) or mild-to-severe (diffuse) disease. We showed that EEG features can predict cognitive evolution of PD patients from baseline, when the cognitive clinical scores were overlapped. CONCLUSIONS: The identification of novel PD subtypes based on electrical brain activity signatures may provide a more accurate prognosis in individual patients in clinical practice and help to stratify subgroups in clinical trials. Innovative profiling in PD can also support new therapeutic strategies that are brain-based and designed to modulate brain activity disruption. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Research Priorities for Precision Medicine in NAFLD.

NAFLD is a multisystem condition and the leading cause of chronic liver disease globally. There are no approved NAFLD-specific dugs. To advance in the prevention and treatment of NAFLD, there is a clear need to better understand the pathophysiology and genetic and environmental risk factors, identify subphenotypes, and develop personalized and precision medicine. In this review, we discuss the main NAFLD research priorities, with a particular focus on socioeconomic factors, interindividual variations, limitations of current NAFLD clinical trials, multidisciplinary models of care, and novel approaches in the management of patients with NAFLD.

Evaluation of Malus Germplasm Identifies Genetic Sources of Powdery Mildew and Frogeye Leaf Spot Resistance for Apple Breeding.

Apple is an important fruit crop of temperate regions. The narrow genetic base of commercially cultivated apples has resulted in its vulnerability to a large number of fungal, bacterial, and viral pathogens. Apple breeders are always seeking new sources of resistance within the cross-compatible Malus species that can be deployed into elite genetic backgrounds. We have evaluated resistance to two major fungal diseases of apples: powdery mildew and frogeye leaf spot, using a germplasm collection of 174 Malus accessions to identify novel sources of genetic resistance. In 2020 and 2021, we evaluated these accessions for the incidence and severity of powdery mildew and frogeye leaf spot diseases at Cornell AgriTech, Geneva, New York, in a partially managed orchard. The severity and incidence of powdery mildew and frogeye leaf spot, as well as weather parameters were recorded in June, July, and August. Total incidence of powdery mildew and frogeye leaf spot infections increased from 33 to 38%, and 56 to 97% in 2020 and 2021, respectively. Our analysis showed that relative humidity and precipitation correlate with powdery mildew and frogeye leaf spot susceptibility. The predictor variables with highest impact to the variability of powdery mildew were accessions and relative humidity in May. A total of 65 Malus accessions were found to be resistant to powdery mildew, and only one accession showed moderate resistance to frogeye leaf spot. Several of these accessions belong to Malus hybrid species and domesticated apples and can therefore be potential sources of novel resistance alleles for apple breeding.

Wheat Spike Blast Image Classification Using Deep Convolutional Neural Networks.

Wheat blast is a threat to global wheat production, and limited blast-resistant cultivars are available. The current estimations of wheat spike blast severity rely on human assessments, but this technique could have limitations. Reliable visual disease estimations paired with Red Green Blue (RGB) images of wheat spike blast can be used to train deep convolutional neural networks (CNN) for disease severity (DS) classification. Inter-rater agreement analysis was used to measure the reliability of who collected and classified data obtained under controlled conditions. We then trained CNN models to classify wheat spike blast severity. Inter-rater agreement analysis showed high accuracy and low bias before model training. Results showed that the CNN models trained provide a promising approach to classify images in the three wheat blast severity categories. However, the models trained on non-matured and matured spikes images showing the highest precision, recall, and F1 score when classifying the images. The high classification accuracy could serve as a basis to facilitate wheat spike blast phenotyping in the future.

Electronic medical record-based deep data cleaning and phenotyping improve the diagnostic validity and mortality assessment of infective endocarditis: medical big data initiative of CMUH.

BACKGROUND: International Classification of Diseases (ICD) code-based claims databases are often used to study infective endocarditis (IE). However, the quality of ICD coding can influence the reliability of IE research. The impact of complementing the ICD-only approach with data extracted from electronic medical records (EMRs) has yet to be explored. METHODS: We selected the information of adult patients with discharge ICD codes for IE (ICD-9: 421, 112.81, 036.42, 098.84, 115.04, 115.14, 115.94, 424.9; ICD-10: I33, I38, I39) during 2005-2016 in China Medical University Hospital. Data extraction was conducted on the basis of the modified Duke criteria to establish a reference group comprising patients with definite or possible IE. Clinical characteristics and in-hospital mortality were compared between ICD-identified and Duke-confirmed cases. The positive predictive value (PPV) was used to quantify the IE identification performance of various phenotyping algorithms. RESULTS: A total of 593 patients with discharge ICD codes for IE were identified, only 56.7% met the modified Duke criteria. The crude in-hospital mortality for Duke-confirmed and Duke-rejected IE were 24.4% and 8.2%, respectively. The adjusted in-hospital mortality for ICD-identified IE was lower than that for Duke-confirmed IE by a difference of 5.1%. The best PPV was achieved (0.90, 95% CI 0.86-0.93) when major components of the Duke criteria (positive blood culture and vegetation) were integrated with ICD codes. CONCLUSION: Integrating EMR data can considerably improve the accuracy of ICD-only approaches in phenotyping IE, which can improve the validity of EMR-based studies and their applications, including real-time surveillance and clinical decision support.

The Role of Movement Analysis in Diagnosing and Monitoring Neurodegenerative Conditions: Insights from Gait and Postural Control.

Quantifying gait and postural control adds valuable information that aids in understanding neurological conditions where motor symptoms predominate and cause considerable functional impairment. Disease-specific clinical scales exist; however, they are often susceptible to subjectivity, and can lack sensitivity when identifying subtle gait and postural impairments in prodromal cohorts and longitudinally to document disease progression. Numerous devices are available to objectively quantify a range of measurement outcomes pertaining to gait and postural control; however, efforts are required to standardise and harmonise approaches that are specific to the neurological condition and clinical assessment. Tools are urgently needed that address a number of unmet needs in neurological practice. Namely, these include timely and accurate diagnosis; disease stratification; risk prediction; tracking disease progression; and decision making for intervention optimisation and maximising therapeutic response (such as medication selection, disease staging, and targeted support). Using some recent examples of research across a range of relevant neurological conditions-including Parkinson's disease, ataxia, and dementia-we will illustrate evidence that supports progress against these unmet clinical needs. We summarise the novel 'big data' approaches that utilise data mining and machine learning techniques to improve disease classification and risk prediction, and conclude with recommendations for future direction.

Adequacy of endobronchial ultrasound-guided transbronchial needle aspiration samples processed as histopathological samples for genetic mutation analysis in lung adenocarcinoma.

Phenotyping non-small-cell lung cancer is becoming increasingly important with the advent of molecular testing. Tumours harbouring somatic mutations in the gene that encodes for the tyrosine kinase domain of the epidermal growth factor receptor (EGFR) have been found to increase responsiveness to tyrosine kinase inhibitors. Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a minimally invasive technique for mediastinal node sampling. The available prospective data on EBUS-TBNA sample suitability for molecular profiling are currently limited. The aim of this prospective study was to evaluate the adequacy of EBUS-TBNA samples for EGFR and anaplastic lymphoma kinase (ALK) genetic mutation analysis in confirmed primary lung adenocarcinomas. We conducted a prospective analysis of 410 consecutive patients referred for EBUS-TBNA between 2010 and 2014. Rapid on-site cytological evaluation was not used. The samples were obtained using 21-gauge (21G) or 22G needles and were prepared as histopathological samples. A total of 91 samples were confirmed as lung adenocarcinomas and 80 of these samples were sent for EGFR mutation analysis. EBUS-TBNA had a diagnostic accuracy of 98.3% for malignancy. EGFR mutation testing was possible in 79/80 cases (98.75%). EGFR mutations were detected in 5/80 (6.3%) samples. ALK gene analysis, which became available during the study period, was requested and successfully performed in 21/21 samples (100%). The total combined genotyping success rate was 100/101 (99.0%). This UK study confirmed the high clinical utility of EBUS-TBNA samples processed as histopathological specimens for EGFR and ALK genotyping in primary lung adenocarcinoma. The needle gauge did not affect genotyping efficacy.

Impact of needle gauge on characterization of endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) histology samples.

BACKGROUND AND OBJECTIVE: Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a minimally invasive mediastinal node sampling technique used for lung cancer staging and diagnosis of mediastinal lesions. The four published studies assessing sampling with 21-G or 22-G needles conflict. The study objective is to evaluate the diagnostic utility of 21-G versus 22-G EBUS-TBNA needles, and the ability to subcharacterize both benign and malignant lesions using histopathological assessment only. METHODS: A retrospective analysis was performed from 303 patients referred for EBUS-TBNA between January 2011 and July 2013. Sampling needle gauge was selected at the discretion of the operator. Samples were assessed by histopathologists blinded to the needle gauge without rapid on-site evaluation for cytology. Contingency table analysis was performed to compare diagnostic utility and ability to subcharacterize malignant and benign lesions. RESULTS: No difference in diagnostic ability was seen for malignancy (96.6% vs. 95.3% accuracy, 21-G vs. 22-G). Subgroup analysis of benign 21-G tissue samples revealed superior characterization compared with 22-G samples (63/76, 83%, vs. 31/52, 60%, P < 0.01). Characterization of non-small cell lung cancer (NSCLC) was also significantly better with samples obtained with 21-G needles versus 22-G needles (57/65, 88% vs. 34/52, 65%, P < 0.01). CONCLUSIONS: This large UK single-centre study suggests 21-G EBUS-TBNA needles are superior to 22-G in characterizing benign lesions (especially sarcoidosis) and NSCLC when using histopathological assessment. Making a positive benign diagnosis may avoid the need to perform mediastinoscopy. Obtaining sufficient histological material to subcharacterize NSCLC and particularly lung adenocarcinoma allows appropriate testing for genetic mutations facilitating targeted oncological therapy.