Search

Recent increase in the number of digital photos in the content sharing and social networking websites has created an endless demand for techniques to analyze, navigate, and summarize these images. In this paper, we focus on image collection summarization. Earlier methods in image collection summarization consider representativeness and diversity criteria while recent ones also consider other criteria such as image quality, aesthetic or appeal. In this paper, we propose a multi-criteria context-sensitive approach for social image collection summarization. In the proposed method, two different sets of features are combined while each one looks at different criteria for image collection summarization: social attractiveness features and semantic features. The first feature set considers different aspects that make an image appealing such as image quality, aesthetic, and emotion to create attractiveness score for input images while the second one covers semantic content of images and assigns semantic score to them. We use social network infrastructure to identify attractiveness features and domain ontology for extracting ontology features. The final summarization is provided by integrating the attractiveness and semantic features of input images. The experimental results on a collection of human generated summaries on a set of Flickr images demonstrate the effectiveness of the proposed image collection summarization approach. [ABSTRACT FROM AUTHOR]

Ventilator-associated pneumonia (VAP) is one of the most important problems of intensive care units. Eighty-four neurologic patients with acute stroke (Glasgow Coma Score ≤8) were entered into a double-blind clinical trial. Patients in the intervention group received piperacillin-tazobactam 4 g/0.5 g at the time of intubation and 12 h later. The incidences of early-onset (within four days of intubation) and late-onset VAP were 9.2 and 26.9 episodes per 1000 days of mechanical ventilation in the intervention and control groups, respectively (odds ratio: 0.217; 95% confidence interval: 0.056-0.085; P = 0.028). Administration of prophylactic piperacillin-tazobactam may reduce early-onset VAP, but the benefit does not extend to late-onset VAP. [ABSTRACT FROM AUTHOR]

Abstract The eye possesses a paravascular solute transport pathway that is driven by physiological pulsations, resembling the brain glymphatic pathway. We developed synchronous multimodal imaging tools aimed at measuring the driving pulsations of the human eye, using an eye-tracking functional eye camera (FEC) compatible with magnetic resonance imaging (MRI) for measuring eye surface pulsations. Special optics enabled integration of the FEC with MRI-compatible video ophthalmoscopy (MRcVO) for simultaneous retinal imaging along with functional eye MRI imaging (fMREye) of the BOLD (blood oxygen level dependent) contrast. Upon optimizing the fMREye parameters, we measured the power of the physiological (vasomotor, respiratory, and cardiac) eye and brain pulsations by fast Fourier transform (FFT) power analysis. The human eye pulsated in all three physiological pulse bands, most prominently in the respiratory band. The FFT power means of physiological pulsation for two adjacent slices was significantly higher than in one-slice scans (RESP1 vs. RESP2; df = 5, p = 0.045). FEC and MRcVO confirmed the respiratory pulsations at the eye surface and retina. We conclude that in addition to the known cardiovascular pulsation, the human eye also has respiratory and vasomotor pulsation mechanisms, which are now amenable to study using non-invasive multimodal imaging of eye fluidics.

• An automatic IQA model for CMR images with different views is presented. • A generalised optimisation-based deep meta-learning model is proposed. • The model can detect respiratory and cardiac motions, aliasing and Gibbs artefacts. • This model is able to address the lack of large annotated datasets. Cardiovascular magnetic resonance (CMR) imaging is a powerful modality in functional and anatomical assessment for various cardiovascular diseases. Sufficient image quality is essential to achieve proper diagnosis and treatment. A large number of medical images, the variety of imaging artefacts, and the workload of imaging centres are amongst the factors that reveal the necessity of automatic image quality assessment (IQA). However, automated IQA requires access to bulk annotated datasets for training deep learning (DL) models. Labelling medical images is a tedious, costly and time-consuming process, which creates a fundamental challenge in proposing DL-based methods for medical applications. This study aims to present a new method for CMR IQA when there is limited access to annotated datasets. The proposed generalised deep meta-learning model can evaluate the quality by learning tasks in the prior stage and then fine-tuning the resulting model on a small labelled dataset of the desired tasks. This model was evaluated on the data of over 6,000 subjects from the UK Biobank for five defined tasks, including detecting respiratory motion, cardiac motion, Aliasing and Gibbs ringing artefacts and images without artefacts. The results of extensive experiments show the superiority of the proposed model. Besides, comparing the model's accuracy with the domain adaptation model indicates a significant difference by using only 64 annotated images related to the desired tasks. The proposed model can identify unknown artefacts in images with acceptable accuracy, which makes it suitable for medical applications and quality assessment of large cohorts. https://github.com/HosseinSimchi/META-IQA-CMRImages [ABSTRACT FROM AUTHOR]

Assessing the predictive value of different social media platforms is important to understand the variation in how users reveal themselves across multiple platforms. Most social media platforms allow users to interact in multiple ways: by posting content to the platform, liking others’ posts, or building a user profile. While prior studies offer insights into how language use differs across platforms, differences in image usage is less well understood. In this study, we analyzed variation in image content with user personality across three interaction types (posts, likes and profile images) and two platforms, using a unique data set of users who are active on both Twitter and Flickr. Usage patterns on these two social media platforms revealed different aspects of users’ personality. Cross-platform data fusion is thus shown to improve personality prediction performance. [ABSTRACT FROM AUTHOR]

IntroductionSleep increases brain fluid transport and the power of pulsations driving the fluids. We investigated how sleep deprivation or electrophysiologically different stages of non-rapid-eye-movement (NREM) sleep affect the human brain pulsations.MethodsFast functional magnetic resonance imaging (fMRI) was performed in healthy subjects (n = 23) with synchronous electroencephalography (EEG), that was used to verify arousal states (awake, N1 and N2 sleep). Cardiorespiratory rates were verified with physiological monitoring. Spectral power analysis assessed the strength, and spectral entropy assessed the stability of the pulsations.ResultsIn N1 sleep, the power of vasomotor (VLF < 0.1 Hz), but not cardiorespiratory pulsations, intensified after sleep deprived vs. non-sleep deprived subjects. The power of all three pulsations increased as a function of arousal state (N2 > N1 > awake) encompassing brain tissue in both sleep stages, but extra-axial CSF spaces only in N2 sleep. Spectral entropy of full band and respiratory pulsations decreased most in N2 sleep stage, while cardiac spectral entropy increased in ventricles.DiscussionIn summary, the sleep deprivation and sleep depth, both increase the power and harmonize the spectral content of human brain pulsations.

Most qualitative characteristics cannot be easily reported numerically. In such cases, each product is inspected and usually divided into two conforming and nonconforming groups based on their qualitative characteristics. Since nowadays products and processes have generally several interdependent qualitative characteristics, it is necessary to use multivariate quality control methods to make the relationship between variables and their variations. To do this, the sampling of the considered qualitative characteristic is done at the specified time intervals to check the control of the process over time after drawing the considered statistic on the control chart. A common problem while sampling is measurement error. It affects the performance of control charts, impairs their ability to detect changes in the process, and increases the cost and time to search for out-of-control situations. In this paper, the effect of measurement error on the performance of the Multivariate Nonconforming Proportion (MNP) control chart has been evaluated based on the criterion of Average Run Length (ARL) for the first time. The results imply that the measurement error has a considerable impact on the performance of this chart. Also, the results indicate that if the defective items have been wrongly considered as correct items, we would have a higher ARL compared to an ideal and accurate system. On the other hand, if the system considers right items as defective, we will have a lower ARL than the ideal and accurate system. It is proved that if both errors (considering faulty items as correct ones and vice versa) occur simultaneously, the ARL will be reduced like the previous case.

This study is aimed to develop a novel edible coating based on Plantago major seed mucilage (PMSM) and Citrus limon essential oil (CLEO) to increase the shelf‐life of buffalo meat during cold storage. The CLEO was firstly isolated by the hydrodistillation method, and it contained mainly limonene (40.5%) and carene (15.4%) with remarkable antioxidant activity (55.7%, 63.8%, and 51.85% based on the DPPH‐radical scavenging, ABTS‐radical scavenging, and carotene‐linoleic acid bleaching tests, respectively) and antibacterial effect against some pathogenic and spoilage microorganisms. The CLEO (0%, 0.5%, 1%, 1.5%, and 2%) was then incorporated into PMSM solution to develop a novel CLEO‐loaded PMSM edible coating for improving the shelf‐life of buffalo meat. The edible coating was able to significantly reduce the progression of lipid oxidation (peroxide value) and microbial growth (total viable count, psychrotrophic bacteria, Escherichia coli, Staphylococcus aureus, and fungi) in buffalo meat during storage period of 10 days at 4°C in comparison with the control (noncoated sample). The meat hardness and sensory properties (i.e., odor, color, appearance, texture, and overall acceptability) were also maintained better upon edible coating applications. Based on the results, the CLEO‐rich PMSM edible coating could be applied as a new and effective preservative to improve the stability of meat products to lipid oxidation and microbial spoilage. [ABSTRACT FROM AUTHOR]

Purpose: In this report the design concept and experimental evaluation of the performance of Fluo Vision have been illustrated. Materials and Methods: The Fluo Vision system designed for fluorescence concentration imaging. In order to assess the capability of the system, results of reference design have been analyzed. Results: Results of the Fluo Vision system are matched with the reference design. Conclusion: The evaluation indicated that Fluo Vision is adequate as a fluorescence imaging system for fluorescence concentration imaging.

Today, due to the expansion of the Internet and social networks, people are faced with a vast amount of dynamic information. To mitigate the issue of information overload, recommender systems have become pivotal by analyzing users' activity histories to discern their interests and preferences. However, most available social image recommender systems utilize a static strategy, meaning they do not adapt to changes in user preferences. To overcome this challenge, our paper introduces a dynamic image recommender system that leverages a deep reinforcement learning (DRL) framework, enriched with a novel set of features including emotion, style, and personality. These features, uncommon in existing systems, are instrumental in crafting a user's characteristic vector, offering a personalized recommendation experience. Additionally, we overcome the challenge of state representation definition in reinforcement learning by introducing a new state representation. The experimental results show that our proposed method, compared to some related works, significantly improves Recall@k and Precision@k by approximately 7%-10% (for the top 100 images recommended) for personalized image recommendation., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Ahmadkhani, Moghaddam. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Objective . Radiation therapy is one of the primary methods used to treat cancer in the clinic. Its goal is to deliver a precise dose to the planning target volume while protecting the surrounding organs at risk (OARs). However, the traditional workflow used by dosimetrists to plan the treatment is time-consuming and subjective, requiring iterative adjustments based on their experience. Deep learning methods can be used to predict dose distribution maps to address these limitations. Approach . The study proposes a cascade model for OARs segmentation and dose distribution prediction. An encoder-decoder network has been developed for the segmentation task, in which the encoder consists of transformer blocks, and the decoder uses multi-scale convolutional blocks. Another cascade encoder-decoder network has been proposed for dose distribution prediction using a pyramid architecture. The proposed model has been evaluated using an in-house head and neck cancer dataset of 96 patients and OpenKBP, a public head and neck cancer dataset of 340 patients. Main results . The segmentation subnet achieved 0.79 and 2.71 for Dice and HD95 scores, respectively. This subnet outperformed the existing baselines. The dose distribution prediction subnet outperformed the winner of the OpenKBP2020 competition with 2.77 and 1.79 for dose and dose-volume histogram scores, respectively. Besides, the end-to-end model, including both subnets simultaneously, outperformed the related studies. Significance . The predicted dose maps showed good coincidence with ground-truth, with a superiority after linking with the auxiliary segmentation task. The proposed model outperformed state-of-the-art methods, especially in regions with low prescribed doses. The codes are available athttps://github.com/GhTara/Dose&#95;Prediction., (© 2024 Institute of Physics and Engineering in Medicine.)

Coronavirus disease (COVID-19) is an infectious disease caused by a newly discovered coronavirus. The disease presents with symptoms such as shortness of breath, fever, dry cough, and chronic fatigue, amongst others. The disease may be asymptomatic in some patients in the early stages, which can lead to increased transmission of the disease to others. This study attempts to review papers on the role of imaging and medical image computing in COVID-19 diagnosis. For this purpose, PubMed, Scopus and Google Scholar were searched to find related studies until the middle of 2021. The contribution of this study is four-fold: 1) to use as a tutorial of the field for both clinicians and technologists, 2) to comprehensively review the characteristics of COVID-19 as presented in medical images, 3) to examine automated artificial intelligence-based approaches for COVID-19 diagnosis, 4) to express the research limitations in this field and the methods used to overcome them. Using machine learning-based methods can diagnose the disease with high accuracy from medical images and reduce time, cost and error of diagnostic procedure. It is recommended to collect bulk imaging data from patients in the shortest possible time to improve the performance of COVID-19 automated diagnostic methods., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

Background: Human gait as an effective behavioral biometric identifier has received much attention in recent years. However, there are challenges which reduce its performance. In this work we aim at improving performance of gait systems under variations in view angles, which present one of the major challenges to gait algorithms., Methods: We propose employment of a view transformation model based on sparse and redundant (SR) representation. More specifically, our proposed method trains a set of corresponding dictionaries for each viewing angle, which are then used in identification of a probe. In particular, the view transformation is performed by first obtaining the SR representation of the input image using the appropriate dictionary, then multiplying this representation by the dictionary of destination angle to obtain a corresponding image in the intended angle., Results: Experiments performed using CASIA Gait Database, Dataset B, support the satisfactory performance of our method. It is observed that in most tests, the proposed method outperforms the other methods in comparison. This is especially the case for large changes in the view angle, as well as the average recognition rate., Conclusion: A comparison with state-of-the-art methods in the literature showcases the superior performance of the proposed method, especially in the case of large variations in view angle., Competing Interests: There are no conflicts of interest., (Copyright: © 2020 Journal of Medical Signals & Sensors.)

Background: Pulmonary movements during radiation therapy can cause damage to healthy tissues. It is necessary to adapt treatment planning based on tumor motion to avoid damage to healthy tissues. A range of approaches has been proposed to monitor the issue. A treatment planning based on fourdimensional computed tomography (4D CT) images can be addressed as one of the most achievable options. Although several methods proposed to predict pulmonary movements based on mathematical algorithms, the use of deep artificial neural networks has recently been considered., Methods: In the current study, convolutional long shortterm memory networks are applied to predict and generate images throughout the breathing cycle. A total of 3295 CT images of six patients in three different views was considered as reference images. The proposed method was evaluated in six experiments based on a leaveonepatientout method similar to crossvalidation., Results: The weighted average results of the experiments in terms of the rootmeansquared error and structural similarity index measure are 9 × 10^-3 and 0.943, respectively., Conclusion: Utilizing the proposed method, because of its generative nature, which results in the generation of CT images during the breathing cycle, improves the radiotherapy treatment planning in the lack of access to 4D CT images., Competing Interests: There are no conflicts of interest., (Copyright: © 2020 Journal of Medical Signals & Sensors.)

Introduction: The impact of stroke on quality of life (QoL) may be different in diverse societies because of varying availability and accessibility of health and social care services provided in various settings. The purpose of the present study was to evaluate changes in patients' QoL within three months after stroke and to address the research question; "What factors influence QoL after stroke in Iranian population?", Methods: A total number of 172 patients admitted to the Stroke Unit of Amiralmomenin Hospital in the city of Arak, Iran, were recruited in this study. The Stroke Impact Scale (SIS-16) was used at three different time-points to evaluate post-stroke QoL. Repeated measures analysis of variance (ANOVA) followed by Bonferroni method and marginal model with generalized estimating equation (GEE) were employed to analyze the data., Results: The findings revealed a significant decline in QoL within the first month after stroke compared with post-stroke state. The mean values of patients' QoL also improved within three months after stroke although they did not reach the pre-stroke level. A positive relationship was also observed between age, high National Institutes of Health Stroke Scale (NIHSS) scores, hypertension, right side lesion and previous stroke, as well as patients' poor QoL. Moreover; gender, level of education, job status, and income had no influence on QoL in stroke survivors., Conclusion: It was concluded that being older, having higher NIHSS score, suffering from hypertension, right side lesion and previous stroke could be significantly correlated with poor patients' QoL. Therefore, effective interventions focusing on older individuals especially those with more severe impairments were assumed to help in improving post-stroke QoL in patients; regardless of their gender, level of education, and social activities., (Copyright © 2019 National Medical Association. All rights reserved.)

Introduction: Proper control of postoperative pain is one of the major challenges after surgery. Such pains result in physical complications, increased metabolism, exacerbations of underlying diseases, and increased blood pressure. The aim of the present study was to compare the effect of apotel and pregabalin on postoperative pain among patients undergoing lower limb surgery., Materials and Methods: This study is a double-blind randomized clinical trial. About 75 patients undergoing lower limb orthopedic surgeries in Valiasr Hospital in Arak, Iran, were enrolled in the study. Patients were divided into three groups as follow: The first group received a 150-mg pregabalin capsule 2 h before the surgery. The placebo group received capsule that was replaced by starch. Furthermore, other group received 1 g of apotel in 200 mL of normal saline, 20 min before surgery. Pain at 2, 4, 12, and 24 h after surgery was recorded based on visual analogue scale. The amount of opioid use was recorded in the first 24 h in milligrams. Patient sedation was recorded by Ramsey Sedation Scale at 2, 6, 12, and 24 h after surgery. Finally, the data were analyzed using SPSS-20., Results: Pain in the apotel group was found to be lower when comparing with other group in 2, 4, 12, and 24 h after surgery ( P = 0.0001). Ramsey score was found to be more in the pregabalin group at 2.6, 12, and 24 h after surgery ( P < 0.05). In addition, the lowest opioid use was in the apotel group ( P = 0.0001)., Conclusion: Our findings revealed that apotel had a better effect on pain management, whereas pregabalin exhibited better effect on the sedation of patients., Competing Interests: There are no conflicts of interest.

Diabetic Retinopathy (DR) is one of the most common complications of long-term diabetes. It is a progressive disease and by damaging retina, it finally results in blindness of patients. Since Microaneurysms (MAs) appear as a first sign of DR in retina, early detection of this lesion is an essential step in automatic detection of DR. In this paper, a new MAs detection method is presented. The proposed approach consists of two main steps. In the first step, the MA candidates are detected based on local applying of Markov random field model (MRF). In the second step, these candidate regions are categorized to identify the correct MAs using 23 features based on shape, intensity and Gaussian distribution of MAs intensity. The proposed method is evaluated on DIARETDB1 which is a standard and publicly available database in this field. Evaluation of the proposed method on this database resulted in the average sensitivity of 0.82 for a confidence level of 75 as a ground truth. The results show that our method is able to detect the low contrast MAs with the background while its performance is still comparable to other state of the art approaches.