Associations Between Noticing E-Cigarette Advertising Features and E-Cigarette Appeal and Switching Interest Among Young Adult Dual Users.

BACKGROUND: E-cigarette advertising, which often includes various features, may prompt e-cigarette use and product switching. This study examined the associations between noticing e-cigarette ad features and perceived product appeal and interest in completely switching from cigarettes to advertised e-cigarettes among young adult dual users of both products. METHODS: We analyzed data from an online heatmap experiment among young adult dual users defined as established cigarette smokers who currently used e-cigarettes (ages 18-34 years; n = 1,821). Participants viewed 12 e-cigarette ads, clicked on ad features (e.g., fruit flavors, nicotine warnings, price promotions, smoker-targeted claims) that attracted their attention (defined as "noticing"), and answered questions about e-cigarette product appeal and interest in completely switching from cigarettes to the e-cigarettes shown. We examined within-person associations between noticing specific ad features and outcomes, controlling for demographic and tobacco use-related characteristics. RESULTS: Noticing fruit flavors (AOR = 1.67 and 1.28) and fruit images (AOR = 1.53 and 1.21) was positively associated with having any e-cigarette product appeal and switching interest. Noticing price promotions (AOR = 1.23) was positively associated with product appeal. In contrast, noticing nicotine warnings (AOR = 0.74 and 0.86), smoker-targeted claims (AOR = 0.78 and 0.89), and tobacco flavors (AOR = 0.92 and 0.90) was negatively associated with product appeal and switching interest. CONCLUSIONS: Noticing certain e-cigarette ad features (e.g., fruit flavors and nicotine warnings) may be associated with product appeal and/or switching interest among young adult dual users. More research is needed to assess the influence of e-cigarette ad features that promote product switching interests among cigarette smokers while discourage interests among tobacco-naïve individuals.

Boosting integral-based human pose estimation through implicit heatmap learning.

Human pose estimation typically encompasses three categories: heatmap-, regression-, and integral-based methods. While integral-based methods possess advantages such as end-to-end learning, full-convolution learning, and being free from quantization errors, they have garnered comparatively less attention due to inferior performance. In this paper, we revisit integral-based approaches for human pose estimation and propose a novel implicit heatmap learning framework. The framework learns the true distribution of keypoints from the perspective of maximum likelihood estimation, aiming to mitigate inherent ambiguity in shape and variance associated with implicit heatmaps. Specifically, Simple Implicit Heatmap Normalization (SIHN) is first introduced to calculate implicit heatmaps as an efficient and effective representation for keypoint localization, which replaces the vanilla softmax normalization method. As implicit heatmaps may introduce potential challenges related to variance and shape ambiguity arising from the inherent nature of implicit heatmaps, we thus propose a Differentiable Spatial-to-Distributive Transform (DSDT) method to aptly map those implicit heatmaps onto the transformation coefficients of a deformed distribution. The deformed distribution is predicted by a likelihood-based generative model to unravel the shape ambiguity quandary effectively, and the transformation coefficients are learned by a regression model to resolve the variance ambiguity issue. Additionally, to expedite the acquisition of precise shape representations throughout the training process, we introduce a Wasserstein Distance-based Constraint (WDC) to ensure stable and reasonable supervision during the initial generation of implicit heatmaps. Experimental results on both the MSCOCO and MPII datasets demonstrate the effectiveness of our proposed method, achieving competitive performance against heatmap-based approaches while maintaining the advantages of integral-based approaches. Our source codes and pre-trained models are available at https://github.com/ducongju/IHL.

Enhancing Wheat Growth, Physiology, Yield, and Water Use Efficiency under Deficit Irrigation by Integrating Foliar Application of Salicylic Acid and Nutrients at Critical Growth Stages.

Transitioning from full to deficit irrigation (DI) has become a key strategy in arid regions to combat water scarcity and enhance irrigation water use efficiency (IWUE). However, implementing DI requires additional approaches to counter its negative effects on wheat production. One effective approach is the foliar application of salicylic acid (SA), micronutrients (Mic; zinc and manganese), and macronutrients (Mac; nitrogen, phosphorus, and potassium). However, there is a lack of knowledge on the optimal combinations and timing of foliar application for these components to maximize their benefits under arid conditions, which is the primary focus of this study. A two-year field study was conducted to assess the impact of the foliar application of SA alone and in combination with Mic (SA + Mic) or Mic and Mac (SA + Mic + Mac) at various critical growth stages on wheat growth, physiology, productivity, and IWUE under DI conditions. Our result demonstrated that the foliar application of different components, the timing of application, and their interaction had significant effects on all investigated wheat parameters with few exceptions. Applying different components through foliar application at multiple growth stages, such as tillering and heading or tillering, heading, and grain filling, led to significant enhancements in various wheat parameters. The improvements ranged from 7.7% to 23.2% for growth parameters, 8.7% to 24.0% for physiological traits, 1.4% to 21.0% for yield and yield components, and 14.8% to 19.0% for IWUE compared to applying the components only at the tillering stage. Plants treated with different components (SA, Mic, Mac) exhibited enhanced growth, production, and IWUE in wheat compared to untreated plants. The most effective treatment was SA + Mic, followed by SA alone and SA + Mic + Mac. The foliar application of SA, SA + Mic, and SA + Mic + Mac improved growth parameters by 1.2-50.8%, 2.7-54.6%, and 2.5-43.9%, respectively. Yield parameters were also enhanced by 1.3-33.0%, 2.4-37.2%, and 3.0-26.6% while IWUE increased by 28.6%, 33.0%, and 18.5% compared to untreated plants. A heatmap analysis revealed that the foliar application of SA + Mic at multiple growth stages resulted in the highest values for all parameters, followed by SA alone and SA + Mic + Mac applications at multiple growth stages. The lowest values were observed in untreated plants and with the foliar application of different components only at the tillering stage. Thus, this study suggested that the foliar application of SA + Mic at various growth stages can help sustain wheat production in arid regions with limited water resources.

Vehicle Occupant Detection Based on MM-Wave Radar.

With the continuous development of automotive intelligence, vehicle occupant detection technology has received increasing attention. Despite various types of research in this field, a simple, reliable, and highly private detection method is lacking. This paper proposes a method for vehicle occupant detection using millimeter-wave radar. Specifically, the paper outlines the system design for vehicle occupant detection using millimeter-wave radar. By collecting the raw signals of FMCW radar and applying Range-FFT and DoA estimation algorithms, a range-azimuth heatmap was generated, visually depicting the current status of people inside the vehicle. Furthermore, utilizing the collected range-azimuth heatmap of passengers, this paper integrates the Faster R-CNN deep learning networks with radar signal processing to identify passenger information. Finally, to test the performance of the detection method proposed in this article, an experimental verification was conducted in a car and the results were compared with those of traditional machine learning algorithms. The findings indicated that the method employed in this experiment achieves higher accuracy, reaching approximately 99%.

Contributing factors for reduction in maternal mortality ratio in India.

Maternal mortality ratio (MMR) estimates have been studied over time for understanding its variation across the country. However, it is never sufficient without accounting for presence of variability across in terms of space, time, maternal and system level factors. The study endeavours to estimate and quantify the effect of exposures encompassing all maternal health indicators and system level indicators along with space-time effects influencing MMR in India. Using the most recent level of possible -factors of MMR, maternal health indicators from the National Family Health Survey (NFHS: 2019-21) and system level indicators from government reports a heatmap compared the relative performance of all 19 SRS states. Facet plots with a regression line was utilised for studying patterns of MMR for different states in one frame. Using Bayesian Spatio-temporal random effects, evidence for different MMR patterns and quantification of spatial risks among individual states was produced using estimates of MMR from SRS reports (2014-2020). India has witnessed a decline in MMR, and for the majority of the states, this drop is linear. Few states exhibit cyclical trend such as increasing trends for Haryana and West Bengal which was evident from the two analytical models i.e., facet plots and Bayesian spatio- temporal model. Period of major transition in MMR levels which was common to all states is identified as 2009-2013. Bihar and Assam have estimated posterior probabilities for spatial risk that are relatively greater than other SRS states and are classified as hot spots. More than the individual level factors, health system factors account for a greater reduction in MMR. For more robust findings district level reliable estimates are required. As evident from our study the two most strong health system influencers for reducing MMR in India are Institutional delivery and Skilled birth attendance.

Genetic Heterogeneity in Cowpea Genotypes (Vigna unguiculata L. Walp) Using DArTseq (GBS)-Derived Single Nucleotide Polymorphisms.

Cowpeas (Vigna unguiculata L. Walp) have been credible constituents of nutritious food and forage in human and animal diets since the Neolithic era. The modern technique of Diversity Array Technology (DArTseq) is both cost-effective and rapid in producing thousands of high-throughputs, genotyped, single nucleotide polymorphisms (SNPs) in wide-genomic analyses of genetic diversity. The aim of this study was to assess the heterogeneity in cowpea genotypes using DArTseq-derived SNPs. A total of 92 cowpea genotypes were selected, and their fourteen-day-old leaves were freeze-dried for five days. DNA was extracted using the CTAB protocol, genotyped using DArTseq, and analysed using DArTsoft14. A total of 33,920 DArTseq-derived SNPs were recalled for filtering analysis, with a final total of 16,960 SNPs. The analyses were computed using vcfR, poppr, and ape in R Studio v1.2.5001-3 software. The heatmap revealed that the TVU 9596 (SB26), Orelu (SB72), 90K-284-2 (SB55), RV 403 (SB17), and RV 498 (SB16) genotypes were heterogenous. The mean values for polymorphic information content, observed heterozygosity, expected heterozygosity, major allele frequency, and the inbreeding coefficient were 0.345, 0.386, 0.345, 0.729, and 0.113, respectively. Moreover, they validated the diversity of the evaluated cowpea genotypes, which could be used for potential breeding programmes and management of cowpea germplasm.

Effects of Eurotium Cristatum on soybean (Glycine max L.) polyphenols and the inhibitory ability of soybean polyphenols on acetylcholinesterase under different conditions.

Most phenolic compounds in beans exist in complex, insoluble binding forms that bind to cell wall components via ether, ester, or glucoside bonds. In the process of solid-state fermentation, Eurotium Cristatum can produce many hydrolase enzymes, such as α-amylase, pectinase, cellulase and ß-glucosidase, which can effectively hydrolyze ether, ester or glucoside bond, release bound polyphenols, and increase polyphenol content in soybeans. When the fermentation conditions of soybean were fermentation time 12 days, inoculation amount 15% and initial pH 2, the content of free polyphenols in fermented soybean was 2.79 mg GAE/g d.w, which was 4.98 times that of unfermented soybean. The contents of bound polyphenols and total phenols in fermented soybean were 0.62 mg GAE/g d.w and 3.41 mg GAE/g d.w, respectively, which were 2.38 times and 4.16 times of those in unfermented soybean. At the same time, the inhibitory effect of free polyphenols in fermented soybean on acetylcholinesterase reached 91.51%. Thus, our results demonstrated that solid state fermentation and Eurotium Cristatum can be used as an effective way to increase soybean polyphenol content and combat Alzheimer's disease.

Radiographic chest wall abnormalities in primary spontaneous pneumothorax identified by artificial intelligence.

Primary spontaneous pneumothorax (PSP) primarily affects slim and tall young males. Exploring the etiological link between chest wall structural characteristics and PSP is crucial for advancing treatment methods. In this case-control study, chest computed tomography (CT) images from patients undergoing thoracic surgery, with or without PSP, were analyzed using Artificial Intelligence. Convolutional Neural Network (CNN) model of EfficientNetB3 and InceptionV3 were used with transfer learning on the Imagenet to compare the images of both groups. A heatmap was created on the chest CT scans to enhance interoperability, and the scale-invariant feature transform (SIFT) was adopted to further compare the image level. A total of 2,312 CT images of 26 non-PSP patients and 1,122 CT images of 26 PSP patients were selected. Chest-wall apex pit (CAP) was found in 25 PSP and three non-PSP patients (p < 0.001). The CNN achieved a testing accuracy of 93.47 % in distinguishing PSP from non-PSP based on chest wall features by identifying the existence of CAP. Heatmap analysis demonstrated CNN's precision in targeting the upper chest wall, accurately identifying CAP without undue influence from similar structures, or inappropriately expanding or minimizing the test area. SIFT results indicated a 10.55 % higher mean similarity within the groups compared to between PSP and non-PSP (p < 0.001). In conclusion, distinctive radiographic chest wall configurations were observed in PSP patients, with CAP potentially serving as an etiological factor linked to PSP. This study accentuates the potential of AI-assisted analysis in refining diagnostic approaches and treatment strategies for PSP.

Deconvolution Enhancement Keypoint Network for Efficient Fish Fry Counting.

Fish fry counting has been vital in fish farming, but current computer-based methods are not feasible enough to accurately and efficiently calculate large number of fry in a single count due to severe occlusion, dense distribution and the small size of fish fry. To address this problem, we propose the deconvolution enhancement keypoint network (DEKNet), a method for fish fry counting that features a single-keypoint approach. This novel approach models the fish fry as a point located in the central part of the fish head, laying the foundation for our innovative counting strategy. To be specific, first, a fish fry feature extractor (FFE) characterized by parallel dual branches is designed for high-resolution representation. Next, two identical deconvolution modules (TDMs) are added to the generation head for a high-quality and high-resolution keypoint heatmap with the same resolution size as the input image, thus facilitating the precise counting of fish fry. Then, the local peak value of the heatmap is obtained as the keypoint of the fish fry, so the number of these keypoints with coordinate information equals the number of fry, and the coordinates of the keypoint can be used to locate the fry. Finally, FishFry-2023, a large-scale fish fry dataset, is constructed to evaluate the effectiveness of the method proposed by us. Experimental results show that an accuracy rate of 98.59% was accomplished in fish fry counting. Furthermore, DEKNet achieved a high degree of accuracy on the Penaeus dataset (98.51%) and an MAE of 13.32 on a public dataset known as Adipocyte Cells. The research outcomes reveal that DEKNet has superior comprehensive performance in counting accuracy, the number of parameters and computational effort.

AI-Enhanced evaluation of YouTube content on post-surgical incontinence following pelvic cancer treatment.

Background: Several pelvic area cancers exhibit high incidence rates, and their surgical treatment can result in adverse effects such as urinary and fecal incontinence, significantly impacting patients' quality of life. Post-surgery incontinence is a significant concern, with prevalence rates ranging from 25 to 45% for urinary incontinence and 9-68% for fecal incontinence. Cancer survivors are increasingly turning to YouTube as a platform to connect with others, yet caution is warranted as misinformation is prevalent. Objective: This study aims to evaluate the information quality in YouTube videos about post-surgical incontinence after pelvic area cancer surgery. Methods: A YouTube search for "Incontinence after cancer surgery" yielded 108 videos, which were subsequently analyzed. To evaluate these videos, several quality assessment tools were utilized, including DISCERN, GQS, JAMA, PEMAT, and MQ-VET. Statistical analyses, such as descriptive statistics and intercorrelation tests, were employed to assess various video attributes, including characteristics, popularity, educational value, quality, and reliability. Also, artificial intelligence techniques like PCA, t-SNE, and UMAP were used for data analysis. HeatMap and Hierarchical Clustering Dendrogram techniques validated the Machine Learning results. Results: The quality scales presented a high level of correlation one with each other (p < 0.01) and the Artificial Intelligence-based techniques presented clear clustering representations of the dataset samples, which were reinforced by the Heat Map and Hierarchical Clustering Dendrogram. Conclusions: YouTube videos on "Incontinence after Cancer Surgery" present a "High" quality across multiple scales. The use of AI tools, like PCA, t-SNE, and UMAP, is highlighted for clustering large health datasets, improving data visualization, pattern recognition, and complex healthcare analysis.

Assessing agronomic performance, chocolate spot resistance, and heat tolerance for diverse Vicia faba genotypes under varying environmental conditions.

Chocolate spot and heat stress devastatingly impact the production of faba bean, particularly under prevailing climatic changes and rising drastic environmental conditions. Hence, the adaptability of faba bean performance is a decisive objective of plant breeders to ensure its sustainable production. The present study aimed to evaluate the agronomic performance and stability of diverse eleven faba bean genotypes for yield characters, chocolate spot, and heat stress in eight different growing environments. The faba bean genotypes were evaluated at two sowing dates in two different locations during two growing seasons. The evaluated eleven faba bean genotypes were sown timely in autumn (25 October) and late sowing in early winter (25 November) in Bilbeis and Elkhatara during 2020 and 2021 growing seasons. The results exhibited substantial differences among the evaluated sowing dates, locations, and faba bean genotypes for all studied characters. The genotypes Sakha-3, Nubaria-3, Nubaria-5, Misr-3, and Wadi-1 were able to produce acceptable yield and quality characters under timely sowing in autumn and late sowing in early winter in all tested environments. Moreover, the genotypes Nubaria-3, Nubaria-4, Nubaria-5, Sakha-4, Giza-3, and Triple White exhibited better resistance to chocolate spot. The assessed faba bean genotypes were evaluated under late sowing to expose the plants to high temperature stress at flowering and throughout the anthesis and seed-filling stages. The genotypes Nubaria-5, Nubaria-3, Nubaria-4, Sakha-3, Sakha-4, Wadi-1, and Misr-3 possessed tolerance to heat stress more than the other genotypes. Different statistical methods were applied to study the stability of assessed genotypes such as joint regression, Additive Main Effect and Multiplicative Interaction (AMMI) analysis, AMMI stability value, Wricke's and Ecovalence values. The estimated stability parameters were consistent in depicting the stability of the assessed faba bean genotypes. The findings revealed that Sakha-1, Misr-3, Nubaria-4, and Nubaria-5 demonstrated stable and desirable performance across all tested environments. The heatmap was employed to classify the assessed faba bean genotypes into different groups based on agronomic performance, chocolate spot resistance and heat stress tolerance. Nubaria-3, Nubaria-4, Nubaria-5, and Misr-3 had the best performance for agronomic performance, chocolate spot resistance, and heat stress tolerance. The obtained results provide evidence of employing promising faba bean genotypes for improving the stability of agronomic performance, chocolate spot resistance, and heat stress tolerance in breeding programs principally under unprecedented climate fluctuations.

Exogenous application of nano-silicon, potassium sulfate, or proline enhances physiological parameters, antioxidant enzyme activities, and agronomic traits of diverse rice genotypes under water deficit conditions.

Water deficit is a critical obstacle that devastatingly impacts rice production, particularly in arid regions under current climatic fluctuations. Accordingly, it is decisive to reinforce the drought tolerance of rice by employing sustainable approaches to enhance global food security. The present study aimed at exploring the effect of exogenous application using different biostimulants on physiological, morphological, and yield attributes of diverse rice genotypes under water deficit and well-watered conditions in 2-year field trial. Three diverse rice genotypes (IRAT-112, Giza-178, and IR-64) were evaluated under well-watered (14400 m3/ha in total for the entire season) and water deficit (9170 m3/ha) conditions and were exogenously sprayed by nano-silicon, potassium sulfate, or proline. The results showed that drought stress substantially decreased all studied photosynthetic pigments, growth traits, and yield attributes compared to well-watered conditions. In contrast, antioxidant enzyme activities and osmoprotectants were considerably increased compared with those under well-watered conditions. However, the foliar application of nano-silicon, potassium sulfate, and proline substantially mitigated the deleterious effects of drought stress and markedly enhanced photosynthetic pigments, antioxidant enzyme activities, growth parameters, and yield contributing traits compared to untreated stressed control. Among the assessed treatments, foliar spray with nano-silicon or proline was more effective in promoting drought tolerance. The exogenous application of proline improved chlorophyll a, chlorophyll b, and carotenoids by 21.4, 19.6 and 21.0% followed by nano-silicon treatment, which enhanced chlorophyll a, chlorophyll b, and carotenoids by 21.1, 17.6 and 9.5% compared to untreated control. Besides, the application of proline demonstrated a superior improvement in the content of proline by 52.5% compared with the untreated control. Moreover, nano-silicon exhibited the maximum enhancement of catalase and peroxidase activity compared to the other treatments. The positive impacts of applied exogenously nano-silicon or proline significantly increased panicle length, number of panicles/plant, number of grains/panicle, fertility percentage, 1000-grain weight, panicle weight, and grain yield, compared to untreated plants under water deficit conditions. In addition, the physiological and agronomic performance of evaluated rice genotypes significantly contrasted under drought conditions. The genotype Giza-178 displayed the best performance under water deficit conditions compared with the other genotypes. Consequently, the integration of applied exogenously nano-silicon or proline with tolerant rice genotype as Giza-178 is an efficient approach to ameliorating drought tolerance and achieving agricultural sustainability under water-scarce conditions in arid environments.

Impact of semolina-barley mixture on the volatolomic profile of dough and pasta: characterization by a multivariate chemometric approach.

BACKGROUND: Barley flour, known to be rich in various phytochemicals, has been demonstrated to improve the technological and nutritional properties of pasta; however, its volatile profile, on which its aromatic properties depend, also plays an important role in the acceptance of barley-enriched pasta. In the present work, volatile organic compounds (VOCs) of semolina doughs enriched with different percentages of barley and of the related pasta were characterized by solid phase micro-extraction (HS-SPME) coupled to gas-chromatography/mass spectrometry (GC-MS), and evaluated using a multivariate statistical approach, including principal component analysis (PCA), cluster heatmaps, Pearson's and Spearman's correlations, and partial least squares correlation (PLSC). RESULTS: The effects of single raw materials, and their interactions, were studied to establish their importance in the volatile profile of the samples, and the correlation between the dough VOCs and the processed product VOCs was assessed. The presence of barley flour markedly affected the volatile profile in comparison with the dough obtained with only durum wheat. For alcohols, esters, terpenes, and some aldehydes there was a clear correlation with the percentage of barley. For some of the VOCs, on the other hand, a strong dependence on the ingredients interaction effect due to the mixing stage has been demonstrated. CONCLUSION: The heatmaps allowed a good graphical visualization of the relationship between molecules and barley percentage, offering the possibility to select the best one according to the desired volatolomic footprint. Pasta with 40% of barley was demonstrated to give pasta with the most complex volatile profile. © 2024 Society of Chemical Industry.

Time-dependent nonmonotonic concentration-response and synergism of alkyl glycosides with different alkyl side chain to Vibrio qinghaiensis sp. -Q67.

Alkyl glycosides (AGs), commonly used nonionic surfactants, may have toxic effects on the environmental organisms. However, the complex concentration-response patterns of AGs with varying alkyl side chains and their mixtures have not been thoroughly studied. Therefore, the luminescence inhibition toxicities of six AGs with different alkyl side chains, namely, ethyl (AG02), butyl (AG04), hexyl (AG06), octyl (AG08), decyl (AG10), and dodecyl (AG12) glucosides, were determined in Vibrio qinghaiensis sp. -Q67 (Q67) at 0.25, 3, 6, 9, and 12 h. The six AGs exhibited time- and side-chain-dependent nonmonotonic concentration- responses toward Q67. AG02, with a short side chain, presented a concentration-response curve (CRC) with two peaks after 6 h and stimulated the luminescence of Q67 at both 6 and 9 h. AG04, AG06, and AG08 showed S-shaped CRCs at five exposure time points, and their toxicities increased with the side-chain length. AG10 and AG12, with long side chains, exhibited hormesis at 9 and 12 h. Molecular docking was performed to explore the mechanism governing the possible influence of AGs on the luminescence response. The effects of AGs on Q67 could be attributed to multiple luminescence-regulatory proteins, including LuxA, LuxC, LuxD, LuxG, LuxI, and LuxR. Notably, LuxR was identified as the primary binding protein among the six AGs. Given that they may co-exist, binary mixtures of AG10 and AG12 were designed to explore their concentration-response patterns and interactions. The results revealed that all AG10-AG12 binary mixture rays showed time-dependent hormesis on Q67, similar to that shown by their individual components. The interactions of these binary mixtures were mainly characterized by low-concentration additive action and high-concentration synergism at different times.

RenseNet: A Deep Learning Network Incorporating Residual and Dense Blocks with Edge Conservative Module to Improve Small-Lesion Classification and Model Interpretation.

Deep learning has become an essential tool in medical image analysis owing to its remarkable performance. Target classification and model interpretability are key applications of deep learning in medical image analysis, and hence many deep learning-based algorithms have emerged. Many existing deep learning-based algorithms include pooling operations, which are a type of subsampling used to enlarge the receptive field. However, pooling operations degrade the image details in terms of signal processing theory, which is significantly sensitive to small objects in an image. Therefore, in this study, we designed a Rense block and edge conservative module to effectively manipulate previous feature information in the feed-forward learning process. Specifically, a Rense block, an optimal design that incorporates skip connections of residual and dense blocks, was demonstrated through mathematical analysis. Furthermore, we avoid blurring of the features in the pooling operation through a compensation path in the edge conservative module. Two independent CT datasets of kidney stones and lung tumors, in which small lesions are often included in the images, were used to verify the proposed RenseNet. The results of the classification and explanation heatmaps show that the proposed RenseNet provides the best inference and interpretation compared to current state-of-the-art methods. The proposed RenseNet can significantly contribute to efficient diagnosis and treatment because it is effective for small lesions that might be misclassified or misinterpreted.

Rapid Determination of Different Ripening Stages of Occidental Pears (Pyrus communis L.) by Volatile Organic Compounds Using Proton-Transfer-Reaction Mass Spectrometry (PTR-MS).

Determination of Occidental pear (Pyrus communis) ripening is difficult because the appearance of Occidental pears does not change significantly during the ripening process. Occidental pears at different ripening stages release different volatile organic compounds (VOCs), which can be used to determine fruit ripeness non-destructively and rapidly. In this study, VOCs were detected using proton-transfer-reaction mass spectrometry (PTR-MS). Notably, data were acquired within 1 min. Occidental pears harvested at five separate times were divided into three ripening stages: unripe, ripe, and overripe. The results showed that the composition of VOCs differed depending on the ripening stage. In particular, the concentrations of esters and terpenes significantly increased during the overripe stage. Three ripening stages were clearly discriminated by heatmap clustering and principal component analysis (PCA). This study provided a rapid and non-destructive method to evaluate the ripening stages of Occidental pears. The result can help fruit farmers to decide the optimum harvest time and hence reduce their economic losses.

Multi-task localization of the hemidiaphragms and lung segmentation in portable chest X-ray images of COVID-19 patients.

Background: The COVID-19 can cause long-term symptoms in the patients after they overcome the disease. Given that this disease mainly damages the respiratory system, these symptoms are often related with breathing problems that can be caused by an affected diaphragm. The diaphragmatic function can be assessed with imaging modalities like computerized tomography or chest X-ray. However, this process must be performed by expert clinicians with manual visual inspection. Moreover, during the pandemic, the clinicians were asked to prioritize the use of portable devices, preventing the risk of cross-contamination. Nevertheless, the captures of these devices are of a lower quality. Objectives: The automatic quantification of the diaphragmatic function can determine the damage of COVID-19 on each patient and assess their evolution during the recovery period, a task that could also be complemented with the lung segmentation. Methods: We propose a novel multi-task fully automatic methodology to simultaneously localize the position of the hemidiaphragms and to segment the lung boundaries with a convolutional architecture using portable chest X-ray images of COVID-19 patients. For that aim, the hemidiaphragms' landmarks are located adapting the paradigm of heatmap regression. Results: The methodology is exhaustively validated with four analyses, achieving an 82.31% ± 2.78% of accuracy when localizing the hemidiaphragms' landmarks and a Dice score of 0.9688 ± 0.0012 in lung segmentation. Conclusions: The results demonstrate that the model is able to perform both tasks simultaneously, being a helpful tool for clinicians despite the lower quality of the portable chest X-ray images.

Face Recognition Characteristics in Patients with Age-Related Macular Degeneration Determined Using a Virtual Reality Headset with Eye Tracking.

BACKGROUND AND OBJECTIVES: Face recognition is one of the most serious disabilities of patients with age-related macular degeneration (AMD). Our purpose was to study face recognition using a novel method incorporating virtual reality (VR) and eye tracking. MATERIALS AND METHODS: Eighteen patients with AMD (seven male; median age 83 years; 89% with bilateral advanced AMD) and nineteen healthy controls (five male; median age 68 years) underwent the face recognition test IC FACES (Synthesius, Ljubljna, Slovenia) on a VR headset with built-in eye tracking sensors. Analysis included recognition accuracy, recognition time and fixation patterns. Additionally, a screening test for dementia and imaging with fundus autofluorescence and optical coherence tomography was performed. RESULTS: AMD patients had significantly lower face recognition accuracy (42% vs. 92%; p < 0.001) and longer recognition time (median 4.0 vs. 2.0 s; p < 0.001) in comparison to controls. Both parameters were significantly worse in patients with lower visual acuity. In both groups, eye-tracking data revealed the two classical characteristics of the face recognition process, i.e., fixations clustering mainly in the nose-eyes-mouth triangle and starting observation in the nasal area. CONCLUSIONS: The study demonstrates usability of a VR headset with eye tracking for studying visual perception in real-world situations which could be applicable in the design of clinical studies.

Measuring health care continuum with multifaceted indicators for people who use drugs in Vietnam.

Continuum of care is a concept that has been widely applied in HIV prevention and treatment studies. However, measuring care continuum can be challenging because it involves multiple stages and multiple components or domains at each stage of care. In this study, we introduced an analytical framework to (1) estimate intervention effects overall and by domain using a multi-level modeling approach, and (2) learn possible patterns of domains over time utilizing a multi-layer heatmap visualization. Longitudinal data from an intervention study conducted among people who use drugs in Vietnam were used to construct Seek, Test, Treat, and Retain (STTR) domain and overall scores. Findings from the adjusted analysis showed that people who use drugs in the intervention exhibited a significantly greater improvement in the overall STTR score than those in the control (p-values < .0001). The multi-layer heatmap revealed different patterns of the individual domains over time and the inter-relationships among the individual domains. This study demonstrates the feasibility of constructing a general fulfillment score and domain specific scores to measure care continuum among people who use drugs. The analytical framework can be readily extended to evaluate service fulfillment outcomes in health services and treatment studies for other key populations.

Rule-based deep learning method for prognosis of neonatal hypoxic-ischemic encephalopathy by using susceptibility weighted image analysis.

OBJECTIVE: Susceptibility weighted imaging (SWI) of neonatal hypoxic-ischemic brain injury can provide assistance in the prognosis of neonatal hypoxic-ischemic encephalopathy (HIE). We propose a convolutional neural network model to classify SWI images with HIE. MATERIALS AND METHODS: Due to the lack of a large dataset, transfer learning method with fine-tuning a pre-trained ResNet 50 is introduced. We randomly select 11 datasets from patients with normal neurology outcomes (n = 31) and patients with abnormal neurology outcomes (n = 11) at 24 months of age to avoid bias in classification due to any imbalance in the data. RESULTS: We develop a rule-based system to improve the classification performance, with an accuracy of 0.93 ± 0.09. We also compute heatmaps produced by the Grad-CAM technique to analyze which areas of SWI images contributed more to the classification patients with abnormal neurology outcome. CONCLUSION: Such regions that are important in the classification accuracy can interpret the relationship between the brain regions affected by hypoxic-ischemic and neurodevelopmental outcomes of infants with HIE at the age of 2 years.