Explore the vast range of titles available.

Walking is an exercise that uses muscles and joints of the human body and is essential for understanding body condition. Analyzing body movements through gait has been studied and applied in human identification, sports science, and medicine. This study investigated a spatiotemporal graph convolutional network model (ST-GCN), using attention techniques applied to pathological-gait classification from the collected skeletal information. The focus of this study was twofold. The first objective was extracting spatiotemporal features from skeletal information presented by joint connections and applying these features to graph convolutional neural networks. The second objective was developing an attention mechanism for spatiotemporal graph convolutional neural networks, to focus on important joints in the current gait. This model establishes a pathological-gait-classification system for diagnosing sarcopenia. Experiments on three datasets, namely NTU RGB+D, pathological gait of GIST, and multimodal-gait symmetry (MMGS), validate that the proposed model outperforms existing models in gait classification.

COVID-19 has infected millions of people worldwide over the past few years. The main technique used for COVID-19 detection is reverse transcription, which is expensive, sensitive, and requires medical expertise. X-ray imaging is an alternative and more accessible technique. This study aimed to improve detection accuracy to create a computer-aided diagnostic tool. Combining other artificial intelligence applications techniques with radiological imaging can help detect different diseases. This study proposes a technique for the automatic detection of COVID-19 and other chest-related diseases using digital chest X-ray images of suspected patients by applying transfer learning (TL) algorithms. For this purpose, two balanced datasets, Dataset-1 and Dataset-2, were created by combining four public databases and collecting images from recently published articles. Dataset-1 consisted of 6000 chest X-ray images with 1500 for each class. Dataset-2 consisted of 7200 images with 1200 for each class. To train and test the model, TL with nine pretrained convolutional neural networks (CNNs) was used with augmentation as a preprocessing method. The network was trained to classify using five classifiers: two-class classifier (normal and COVID-19); three-class classifier (normal, COVID-19, and viral pneumonia), four-class classifier (normal, viral pneumonia, COVID-19, and tuberculosis (Tb)), five-class classifier (normal, bacterial pneumonia, COVID-19, Tb, and pneumothorax), and six-class classifier (normal, bacterial pneumonia, COVID-19, viral pneumonia, Tb, and pneumothorax). For two, three, four, five, and six classes, our model achieved a maximum accuracy of 99.83, 98.11, 97.00, 94.66, and 87.29%, respectively.

BackgroundSpinal percutaneous biportal endoscopic surgery (PBES) is a minimally invasive surgery; however, it is associated with several poor outcomes. This study aimed to analyze unsuccessful PBES outcomes and verify their relationships with patient satisfaction.MethodsFrom May 2015 to June 2018, PBES was performed at several institutions. Unsuccessful outcomes (reoperation and prolonged hospital stay) due to various reasons (hematoma, lesion recurrence, incomplete decompression, dural tear, instability, ascites, and infection) were analyzed. To verify the relationships between surgical experience and unsuccessful outcomes, the first 50 cases and the later cases were compared. Logistic regression was used to assess the relationships between unsuccessful outcomes and patient dissatisfaction.ResultsAmong 866 patients, 797 cases with 1-year follow-up and complete data were analyzed. In total, 82 patients with unsuccessful outcomes were identified (10.29%). The incidences of hematoma (p < 0.04), incomplete operation (p < 0.01), and dural tear (p < 0.01) were significantly higher in the first 50 cases than in the later cases. Analyses of the relationship between unsuccessful outcomes and patient dissatisfaction showed that incomplete decompression (odds ratio (OR) 4.06), postoperative instability (OR 3.64), hematoma (OR 3.25), ascite (OR 3.25), dural tear (OR 3.02), and local recurrence (OR 2.45, 95%) contributed significantly.ConclusionsUnsuccessful PBES outcomes were mostly associated with hematomas, incomplete decompression, and dural tears; instability, ascites, and infection contributed to a lesser extent. Incomplete decompression, instability, hematoma, ascite, dural tear, and local recurrence were significantly related to patient dissatisfaction. The potential for poor outcomes should be described to the patient and considered prior to surgery.

Urdu and English are widely used for visual text communications worldwide in public spaces such as signboards and navigation boards. Text in such natural scenes contains useful information for modern-era applications such as language translation for foreign visitors, robot navigation, and autonomous vehicles, highlighting the importance of extracting these texts. Previous studies focused on Urdu alone or printed text pasted manually on images and lacked sufficiently large datasets for effective model training. Herein, a pipeline for Urdu and English (bilingual) text detection and recognition in complex natural scene images is proposed. Additionally, a unilingual dataset is converted into a bilingual dataset and augmented using various techniques. For implementations, a customized convolutional neural network is used for feature extraction, a recurrent neural network (RNN) is used for feature learning, and connectionist temporal classification (CTC) is employed for text recognition. Experiments are conducted using different RNNs and hidden units, which yield satisfactory results. Ablation studies are performed on the two best models by eliminating model components. The proposed pipeline is also compared to existing text detection and recognition methods. The proposed models achieved average accuracies of 98.5% for Urdu character recognition, 97.2% for Urdu word recognition, and 99.2% for English character recognition.

The phantom array effect is one of the temporal light artefacts that can decrease performance and increase fatigue. The phantom array effect visibility shows large individual differences; however, the dominant factors that can explain these individual differences remain unclear. We investigated the relationship between saccadic eye movement speed and phantom array visibility at two different angles and four different directions of saccadic eye movement. The peak speed of saccadic eye movement and the phantom array effect visibility were measured at different modulation frequencies of the light source. Our results show that phantom array visibility increased as eye movement speed increased; the phantom array visibility was higher at a wide viewing angle with fast eye movement speed than at a narrow viewing angle. Moreover, when clustered into subgroups according to individual eye movement speed, the mean speed of the saccadic eye movement of each subgroup is related to the variations in the visibility of the phantom array effect of the subgroup. Therefore, saccadic eye movement speed is related to variations in phantom array effect visibility.

Background The unilateral biportal endoscopic (UBE) technique is a minimally invasive procedure for spinal surgery, while open microscopic discectomy is the most common surgical treatment for ruptured or herniated discs of the lumbar spine. A new endoscopic technique that uses a UBE approach has been applied to conventional arthroscopic systems for the treatment of spinal disease. In this study, we aimed to compare and evaluate the perioperative parameters and clinical outcomes, including recovery from surgery, pain and life quality modification, patient’s satisfaction, and complications, between UBE and open lumbar microdiscectomy (OLM) for single-level discectomy procedures. Methods This study included 141 patients with degenerative disc disease requiring discectomy at a single level from L2–L3 to L5–S1. A total of 60 and 81 patients underwent UBE and OLM, respectively. Analysis was based on comparison of perioperative metrics, operation time (OT); estimated blood loss (EBL); length of hospital stay (HS); clinical outcomes, including assessment using the Visual Analogue Scale (VAS) and Oswestry Disability Index (ODI); patient satisfaction (the MacNab score); and the incidence of reoperation and complications. Results The study cohort was 56.7% women, and the mean patient age was 50.98 ± 18.23 years. The mean VAS (the back and leg), MacNab score, and ODI improved significantly from the preoperative period to the last follow-up (12.92 ± 3.92) in both groups ( p  < 0.001). One week after operation, the back VAS score in the UBE group showed significantly more improvement than that in the OLM group. However, the 1-week, 3-month, and 12-month VAS (the back and leg), ODI improvement, modified MacNab score, and OT were not significantly different between the two groups. In the UBE group, EBL (34.67 ± 16.92) was smaller and HS (2.77 ± 1.2) was shorter than that of the OLM group (140.05 ± 57.8, 6.37 ± 1.39). However, OT (70.15 ± 22.0) was longer in the UBE group than in the OLM group (60.38 ± 15.5), and the difference was statistically significant. Meanwhile, the differences in the rate of surgical conversion and complications between the two groups were not statistically significant. Conclusions The UBE for single-level discectomy yielded similar clinical outcomes to OLM, including pain control, functional disability, and patient satisfaction, but incurred minimal EBL, HS, and postoperative back pain. Trial registration Not applicable.

Ocular adnexal sebaceous carcinoma (SebCA) represents one of the most clinically problematic periocular tumors, often requiring aggressive surgical resection. The pathobiology of this tumor remains poorly understood, and few models exist that are suitable for preclinical testing. The aim of this study was to establish new cell lines to serve as models for pathobiological and drug testing. With patient consent, freshly resected tumor tissue was cultured using conditional reprogramming cell conditions. Standard techniques were used to characterize the cell lines in terms of overall growth, clonogenicity, apoptosis, and differentiation in vitro. Additional analyses including Western blotting, short tandem repeat (STR) profiling, and next-generation sequencing (NGS) were performed. Drug screening using mitomycin-C (MMC), 5-fluorouricil (5-FU), and 6-Diazo-5-oxo-L-norleucine (DON) were performed. JHH-SebCA01, JHH-SebCA02, and JHH-SebCA03 cell lines were established from two women and one man undergoing surgical resection of eyelid tumors. At passage 15, they each showed a doubling time of two to three days, and all could form colonies in anchorage-dependent conditions, but not in soft agar. The cells contained cytoplasmic vacuoles consistent with sebaceous differentiation, and adipophilin protein was present in all three lines. STR profiling confirmed that all lines were derived from their respective patients. NGS of the primary tumors and their matched cell lines identified numerous shared mutations, including alterations similar to those previously described in SebCA. Treatment with MMC or 5-FU resulted in dose-dependent growth inhibition and the induction of both apoptosis and differentiation. MYC protein was abundant in all three lines, and the glutamine metabolism inhibitor DON, previously shown to target high MYC tumors, slowed the growth of all our SebCA models. Ocular adnexal SebCA cell lines can be established using conditional reprogramming cell conditions, and our three new models are useful for testing therapies and interrogating the functional role of MYC and other possible molecular drivers. Current topical chemotherapies promote both apoptosis and differentiation in SebCA cells, and these tumors appear sensitive to inhibition or MYC-associated metabolic changes.

Facial expression recognition is very useful for effective human–computer interaction, robot interfaces, and emotion-aware smart agent systems. This paper presents a new framework for facial expression recognition by using a hybrid model: a combination of convolutional neural networks (CNNs) and a support vector machine (SVM) classifier using dynamic facial expression data. In order to extract facial motion characteristics, dense facial motion flows and geometry landmark flows of facial expression sequences were used as inputs to the CNN and SVM classifier, respectively. CNN architectures for facial expression recognition from dense facial motion flows were proposed. The optimal weighting combination of the hybrid classifiers provides better facial expression recognition results than individual classifiers. The system has successfully classified seven facial expressions signalling anger, contempt, disgust, fear, happiness, sadness and surprise classes for the CK+ database, and facial expressions of anger, disgust, fear, happiness, sadness and surprise for the BU4D database. The recognition performance of the proposed system is 99.69% for the CK+ database and 94.69% for the BU4D database. The proposed method shows state-of-the-art results for the CK+ database and is proven to be effective for the BU4D database when compared with the previous schemes.

Classifying pathological gaits is crucial for identifying impairments in specific areas of the human body. Previous studies have extensively employed machine learning and deep learning (DL) methods, using various wearable (e.g., inertial sensors) and non-wearable (e.g., foot pressure plates and depth cameras) sensors. This study proposes early and late fusion methods through DL to categorize one normal and five abnormal (antalgic, lurch, steppage, stiff-legged, and Trendelenburg) pathological gaits. Initially, single-modal approaches were utilized: first, foot pressure data were augmented for transformer-based models; second, skeleton data were applied to a spatiotemporal graph convolutional network (ST-GCN). Subsequently, a multi-modal approach using early fusion by concatenating features from both the foot pressure and skeleton datasets was introduced. Finally, multi-modal fusions, applying early fusion to the feature vector and late fusion by merging outputs from both modalities with and without varying weights, were evaluated. The foot pressure-based and skeleton-based models achieved 99.04% and 78.24% accuracy, respectively. The proposed multi-modal approach using early fusion achieved 99.86% accuracy, whereas the late fusion method achieved 96.95% accuracy without weights and 99.17% accuracy with different weights. Thus, the proposed multi-modal models using early fusion methods demonstrated state-of-the-art performance on the GIST pathological gait database.

Alterations in metabolism and energy production are increasingly being recognized as important drivers of neoplasia, raising the possibility that metabolic analogs could disrupt oncogenic pathways. 3′-deoxyadenosine, also known as cordycepin, is an adenosine analog that inhibits the growth of several types of cancer. However, the effects of cordycepin have only been examined in a limited number of tumor types, and its mechanism of action is poorly understood. We found that cordycepin slows the growth and promotes apoptosis in uveal melanoma, as well as a range of other hard-to-treat malignancies, including retinoblastoma, atypical teratoid rhabdoid tumors, and diffuse midline gliomas. Interestingly, these effects were dependent on low adenosine deaminase (ADA) expression or activity. Inhibition of ADA using either siRNA or pharmacologic approaches sensitized tumors with higher ADA to cordycepin in vitro and in vivo, with increased apoptosis, reduced clonogenic capacity, and slower migration of neoplastic cells. Our studies suggest that ADA is both a biomarker predicting response to cordycepin and a target for combination therapy. We also describe a novel mechanism of action for cordycepin: competition with adenosine triphosphate (ATP) in binding to Hsp90, resulting in impaired processing of oncogenic Hsp90 client proteins.