Early Fusion Research Articles

The sodium/ascorbic acid co-transporter SVCT2 distributes in a striated membrane-enriched domain at the M-band level in slow-twitch skeletal muscle fibers

BackgroundVitamin C plays key roles in cellular homeostasis, functioning as a potent antioxidant and a positive regulator of cell differentiation. In skeletal muscle, the vitamin C/sodium co-transporter SVCT2 is preferentially expressed in oxidative slow fibers. SVCT2 is up-regulated during the early fusion of primary myoblasts and decreases during initial myotube growth, indicating the relevance of vitamin C uptake via SVCT2 for early skeletal muscle differentiation and fiber-type definition. However, our understanding of SVCT2 expression and function in adult skeletal muscles is still limited.ResultsIn this study, we demonstrate that SVCT2 exhibits an intracellular distribution in chicken slow skeletal muscles, following a highly organized striated pattern. A similar distribution was observed in human muscle samples, chicken cultured myotubes, and isolated mouse myofibers. Immunohistochemical analyses, combined with biochemical cell fractionation experiments, reveal a strong co-localization of SVCT2 with intracellular detergent-soluble membrane fractions at the central sarcomeric M-band, where it co-solubilizes with sarcoplasmic reticulum proteins. Remarkably, electrical stimulation of cultured myofibers induces the redistribution of SVCT2 into a vesicular pattern.ConclusionsOur results provide novel insights into the dynamic roles of SVCT2 in different intracellular compartments in response to functional demands.

Anastrozole improves height outcomes in growing children with congenital adrenal hyperplasia due to 21-OHD.

Hyperandrogenemia resulting in estrogen-mediated accelerated bone maturation and early growth plate fusion contributes to short stature in children with congenital adrenal hyperplasia (CAH) due to 21OHD. Aromatase inhibitors block androgen conversion to estrogen and have been used off-label in children with short stature to improve adult height. There are no adequately powered studies examining the use of aromatase inhibitors in children with CAH with advanced bone age and reduced predicted adult height. Records of CAH patients treated with anastrozole were reviewed. Z-scores of bone age, predicted adult height and height corrected for bone age were examined over an 8-year period. Outcome changes were analyzed using weighted mixed-effects models, adjusting for sex, diagnosis, age at diagnosis, and average hydrocortisone dose before and during treatment with anastrozole. In 60 patients (26 females, 52 classic, 8 non-classic) started on anastrozole therapy, the mean bone age Z-score decreased from 4.2 to 2.0 at 4 years and 1.3 at 6 years (both p <0.001); predicted adult height Z-score improved from -2.1 to -0.45 at 4 years and 0.18 at 6 years (both p <0.001); corrected height Z-scores improved from -1.7 to -0.33 at 4 years and 0.18 at 6 years (p <0.001). There was no significant difference in the average total daily hydrocortisone dose used before or during treatment. Anastrozole decreased the rate of bone maturation and led to improved height outcomes, indicating that anastrozole could have a role as an adjunct therapy in children with CAH and advanced bone age.

Development and validation of a cross-modality tensor fusion model using multi-modality MRI radiomics features and clinical radiological characteristics for the prediction of microvascular invasion in hepatocellular carcinoma

ObjectivesTo develop and validate a cross-modality tensor fusion (CMTF) model using multi-modality MRI radiomics features and clinical radiological characteristics for the prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC). Materials and methodsThis study included 174 HCC patients (47 MVI-positive and 127 MVI-negative) confirmed by postoperative pathology. The synthetic minority over-sampling technique was used to augment MVI-positive samples. The amplified dataset of 254 samples (127 MVI-positive and 127 MVI-negative) was randomly divided into training and test cohorts in a 7:3 ratio. Radiomics features were respectively extracted from arterial phase, delayed phase, diffusion-weighted imaging, and fat-suppressed T2-weighted imaging. The least absolute shrinkage and selection operator was used for feature selection. Univariate and multivariate logistic regression analyses were employed to identify clinical and radiological independent predictors. The selected multi-modality MRI radiomics features, clinical and radiological characteristics were used to construct the CMTF model, single modality (SM) model, early fusion (EF) model. ResultsThe CMTF model demonstrated superior performance in predicting MVI compared to the SM and EF models. When integrating four MRI modalities, the CMTF model achieved a high area under the curve (AUC) with 95% confidence interval (95% CI) of 0.894 (0.820-0.968). Additionally, incorporating clinical and radiological characteristics further enhanced the predictive performance of CMTF model, the AUC (95% CI) value increased to 0.945 (0.892-0.998). ConclusionThe CMTF model showed promising performance in preoperative MVI prediction, providing a more effective non-invasive detection tool for HCC patients.

Premature Thelarche: An Updated Review.

Premature thelarche is the most common pubertal disorder in girls. The condition should be differentiated from central precocious puberty which may result in early epiphyseal fusion and reduced adult height, necessitating treatment. The purpose of this article is to familiarize physicians with the clinical manifestations of premature thelarche and laboratory tests that may help distinguish premature thelarche from central precocious puberty. A search was conducted in September 2022 in PubMed Clinical Queries using the key term "Premature thelarche". The search strategy included all clinical trials, observational studies, and reviews published within the past 10 years. Only papers published in the English literature were included in this review. The information retrieved from the above search was used to compile the present article. Premature thelarche denotes isolated breast development before the age of 8 years in girls who do not manifest other signs of pubertal development. The condition is especially prevalent during the first two years of life. The majority of cases of premature thelarche are idiopathic. The condition may result from an unsuppressed hypothalamic-pituitary-gonadal axis in the early years of life, an "overactivation" of the hypothalamic-pituitary axis in early childhood secondary to altered sensitivity to steroids of the hypothalamic receptors controlling sexual maturation, increased circulating free estradiol, increased sensitivity of breast tissue to estrogens, and exposure to exogenous estrogens. The cardinal feature of premature thelarche is breast development which occurs without additional signs of pubertal development in girls under 8 years of age. The enlargement may involve only one breast, both breasts asymmetrically, or both breasts symmetrically. The breast size may fluctuate cyclically. The enlarged breast tissue may be transiently tender. There should be no significant changes in the nipples or areolae and no pubic or axillary hair. The vulva, labia majora, labia minora, and vagina remain prepubertal. Affected girls have a childlike body habitus and do not have mature contours. They are of average height and weight. Growth and osseous maturation, the onset of puberty and menarche, and the pattern of adolescent sexual development remain normal. Most cases of premature thelarche can be diagnosed on clinical grounds. Laboratory tests are seldom indicated. No single test can reliably differentiate premature thelarche from precocious puberty. Premature thelarche is benign, and no therapy is necessary apart from parental reassurance. As enlargement of breasts may be the first sign of central precocious puberty, a prolonged follow- up period every 3 to 6 months with close monitoring of other pubertal events and linear growth is indicated in all instances.

Multimodal biometric identification: leveraging convolutional neural network (CNN) architectures and fusion techniques with fingerprint and finger vein data

Advancements in multimodal biometrics, which integrate multiple biometric traits, promise to enhance the accuracy and robustness of identification systems. This study focuses on improving multimodal biometric identification by using fingerprint and finger vein images as the primary traits. We utilized the “NUPT-FPV” dataset, which contains a substantial number of finger vein and fingerprint images, which significantly aided our research. Convolutional neural networks (CNNs), renowned for their efficacy in computer vision tasks, are used in our model to extract distinct discriminative features. Specifically, we incorporate three popular CNN architectures: ResNet, VGGNet, and DenseNet. We explore three fusion strategies used in security applications: early fusion, late fusion, and score-level fusion. Early fusion integrates raw images at the input layer of a single CNN, combining information at the initial stages. Late fusion, in contrast, merges features after individual learning from each CNN model. Score-level fusion employs weighted aggregation to combine scores from each modality, leveraging the complementary information they provide. We also use contrast limited adaptive histogram equalization (CLAHE) to enhance fingerprint contrast and vein pattern features, improving feature visibility and extraction. Our evaluation metrics include accuracy, equal error rate (EER), and ROC curves. The fusion of CNN architectures and enhancement methods shows promising performance in identifying multimodal biometrics, aiming to increase identification accuracy. The proposed model offers a reliable authentication system using multiple biometrics to verify identity.

GROWTH-FRIENDLY SPINAL SURGERY: REVIEW OF THE EFFECT ON TRUNCAL GROWTH

BackgroundPediatric spinal deformity surgery affects ultimate spinal height in the growing child. This effect on ultimate spinal height has also been shown to affect pulmonary development and ultimately pulmonary function. There has been an increasing trend toward growth-friendly spinal surgery in early onset scoliosis to minimize the negative consequences of early spinal fusion surgery. Such growth-friendly techniques include VEPTR, MCGR, and Shilla. Which technique allows for the most growth after initial implantation is still not clear. MethodsAn extensive literature review on the topic of pediatric spinal growth was undertaken. Topics reviewed include: normal growth, growth after intervention by various methods, and the effect on pulmonary function. We have summarized the literature for the techniques identified and compared these with normal population data.. ResultsThe data for various surgical techniques were reviewed. These included VEPTR, standard growing rods, and MCGR. The measurement techniques for determining ultimate spinal growth varied based upon the technique for measurement and the timing of initial and final measurements. The results of attained spinal growth were not directly correlated to pulmonary function values. ConclusionsThere is still no standardized ideal time or technique for assessing the best results in this area. We suggest that some of what is called growth from growth-friendly techniques is lengthening from the initial deformity correction. This nomenclature needs to be clarified. In addition, how and when to determine ultimate spinal growth from each surgical technique and by which radiographic technique needs to be standardized.

Graph-based stock prediction with multisource information and relational data fusion

With the application of multisource information in different fields, the combination of different types of information, such as numerical data and text information, has become a favourable choice for performing stock market analyses. Despite the rich information provided by multisource data, building structured relationships remains challenging. In addition, some market relationship-based analysis methods use a predefined graph structure as a stock relationship graph, which makes it impossible to sensitively aggregate attribute features, and these methods cannot dynamically update market relationships or relationship strengths. In this paper, we propose a novel dynamic attribute-driven graph attention network incorporating sentiment (AGATS) information, transaction data, and text data. Inspired by behavioural finance, we separately extract sentiment information as a factor of technical indicators, and further realize the early fusion of technical indicators and textual data through tensor fusion. In particular, real-time intramarket dependencies and key attribute information are captured with graph networks, enabling dynamic relationship and relationship strength updates. Experiments conducted on real datasets show that our model is capable of ourperforming previously developed methods in prediction and trading.

TAG-fusion: Two-stage attention guided multi-modal fusion network for semantic segmentation

In the current research, leveraging auxiliary modalities, such as depth information or point cloud information, to improve RGB semantic segmentation has shown significant potential. However, existing methods mainly use convolutional modules for aggregating features from auxiliary modalities, thereby lacking sufficient exploitation of long-range dependencies. Moreover, fusion strategies are typically limited to singular approaches. In this paper, we propose a transformer-based multimodal fusion framework to better utilize auxiliary modalities for enhancing semantic segmentation results. Specifically, we employ a dual-stream architecture for extracting features from RGB and auxiliary modalities, respectively. We incorporate both early fusion and deep feature fusion techniques. At each layer, we introduce mixed attention mechanisms to leverage features from other modalities, guiding and enhancing the current modality's features before propagating them to the subsequent stage of feature extraction. After the extraction of features from different modalities, we employ an enhanced cross-attention mechanism for feature interaction, followed by channel fusion to obtain the final semantic features. Subsequently, we provide separate supervision to the network on the RGB stream, auxiliary stream, and fusion stream to facilitate the learning of representations for different modalities. The experimental results demonstrate that our framework exhibits superior performance across diverse modalities. Specifically, our approach achieves state-of-the-art results on the NYU Depth V2, SUN-RGBD, DELIVER and MFNet datasets.

Prediction of prostate cancer recurrence after radiotherapy using a fused machine learning approach: utilizing radiomics from pretreatment T2W MRI images with clinical and pathological information

The risk of biochemical recurrence (BCR) after radiotherapy for localized prostate cancer (PCa) varies widely within standard risk groups. There is a need for low-cost tools to more robustly predict recurrence and personalize therapy. Radiomic features from pretreatment MRI show potential as noninvasive biomarkers for BCR prediction. However, previous research has not fully combined radiomics with clinical and pathological data to predict BCR in PCa patients following radiotherapy.&#xD;Purpose: This study aims to predict 5-year BCR using radiomics from pretreatment T2W MRI and clinical-pathological data in PCa patients treated with radiation therapy, and to develop a unified model compatible with both 1.5T and 3T MRI scanners.&#xD;Methods: A total of 150 T2W scans and clinical parameters were preprocessed. Of these, 120 cases were used for training and validation, and 30 for testing. Four distinct machine learning models were developed: Model 1 used radiomics, Model 2 used clinical and pathological data, and Model 3 combined these using late fusion. Model 4 integrated radiomic and clinical-pathological data using early fusion.&#xD;Results: Model 1 achieved an AUC of 0.73, while Model 2 had an AUC of 0.64 for predicting outcomes in 30 new test cases. Model 3, using late fusion, had an AUC of 0.69. Early fusion models showed strong potential, with Model 4 reaching an AUC of 0.84, highlighting the effectiveness of the early fusion model.&#xD;Conclusions: This study is the first to use a fusion technique for predicting BCR in PCa patients following radiotherapy, utilizing pre-treatment T2W MRI images and clinical-pathological data. The methodology improves predictive accuracy by fusing radiomics with clinical-pathological information, even with a relatively small dataset, and introduces the first unified model for both 1.5T and 3T MRI images.

Spoofing countermeasure for fake speech detection using brute force features

Due to the progress in deep learning technology, techniques that generate spoofed speech have significantly emerged. Such synthetic speech can be exploited for harmful purposes, like impersonation or disseminating false information. Researchers in the area investigate the useful features for spoof detection. This paper extensively investigates three problems in spoof detection in speech, namely, the imbalanced sample per class, which may negatively affect the performance of any detection models, the effect of the feature early and late fusion, and the analysis of unseen attacks on the model. Regarding the imbalanced issue, we have proposed two approaches (a Synthetic Minority Over Sampling Technique (SMOTE)-based and a Bootstrap-based model). We have used the OpenSMILE toolkit, to extract different feature sets, their results and early and late fusion of them have been investigated. The experiments are evaluated using the ASVspoof 2019 datasets which encompass synthetic, voice-conversion, and replayed speech samples. Additionally, Support Vector Machine (SVM) and Deep Neural Network (DNN) have been adopted in the classification. The outcomes from various test scenarios indicated that neither the imbalanced nature of the dataset nor a specific feature or their fusions outperformed the brute force version of the model as the best Equal Error Rate (EER) achieved by the Imbalance model is 6.67 % and 1.80 % for both Logical Access (LA) and Physical Access (PA) respectively.

Feature-level Fusion vs. Score-level Fusion for Image Retrieval Based on Pre-trained Deep Neural Networks

Today’s complex multimedia content made retrieving images similar to the user’s query from the database a challenging task. The performance of a Content-Based Image Retrieval System (CBIR) system highly depends on the image representation in a form of low-level features and similarity measurement. The traditional visual descriptors that do not provide good prior domain knowledge could lead to poor performance retrieval results. On the other hand, Deep Convolutional Neural Networks (DCNNs) have recently achieved a remarkable success as methods for image classification in various domains. Recently, pre-trained deep convolution neural networks on thousands of classes have the ability to extract very accurate and representative features which, in addition to classification, can also be successfully used in image retrieval systems. ResNet152, GoogLeNet and InceptionV3 are some of the effective and successful examples of pre-trained DCNNs recently applied in a computer vision tasks such as object recognition, clustering, and classification. In this paper, two approaches for a CBIR system, namely early fusion and late fusion, have been presented and compared. The early fusion utilizes concatenation of the features extracted by each possible pair of DCNNs, that is ResNet152-GoogLeNet, ResNet152-InceptionV3, and GoogLeNet-InceptionV3, and the late fusion apply CombSum method with Z-Score standardization to combine the score results provided by each DCNN of the aforementioned pairs. In the experiments on a popular WANG dataset it has been shown that late fusion approach slightly outperforms early fusion approach. The best performance of our experiments in terms of Average Precision (AP) for the top 20 results reaches 96.82%.

Text-image multimodal fusion model for enhanced fake news detection.

In the era of rapid internet expansion and technological progress, discerning real from fake news poses a growing challenge, exposing users to potential misinformation. The existing literature primarily focuses on analyzing individual features in fake news, overlooking multimodal feature fusion recognition. Compared to single-modal approaches, multimodal fusion allows for a more comprehensive and enriched capture of information from different data modalities (such as text and images), thereby improving the performance and effectiveness of the model. This study proposes a model using multimodal fusion to identify fake news, aiming to curb misinformation. The framework integrates textual and visual information, using early fusion, joint fusion and late fusion strategies to combine them. The proposed framework processes textual and visual information through data cleaning and feature extraction before classification. Fake news classification is accomplished through a model, achieving accuracy of 85% and 90% in the Gossipcop and Fakeddit datasets, with F1-scores of 90% and 88%, showcasing its performance. The study presents outcomes across different training periods, demonstrating the effectiveness of multimodal fusion in combining text and image recognition for combating fake news. This research contributes significantly to addressing the critical issue of misinformation, emphasizing a comprehensive approach for detection accuracy enhancement.

Resequencing reveals population structure and genetic diversity in Tibetan sheep

BackgroundThe Tibetan sheep is one of the three major primitive sheep breeds in China, representing a unique and high-quality genetic resource in the Qinghai-Tibet Plateau and neighboring high-altitude regions, exhibiting exceptional adaptability to high-altitude climatic environments. However, research on the genetic relationships among different populations of Tibetan sheep at the whole-genome level remains insufficient. This study aims to explore the population structure and historical dynamics among 11 Tibetan sheep populations, accurately assess the genetic diversity within the populations, and providing a theoretical basis for the development of targeted genetic breeding strategies for Tibetan sheep.ResultsIn this study, a total of 10,884,454 high-quality SNPs were obtained. All Tibetan sheep populations exhibited varying degrees of linkage disequilibrium, with similar decay rates; among them, the WT population showed the fastest decay, while the TS population exhibited the slowest decay rate. Analyses using Tajima’s D and π indicated that the genetic diversity levels of the Tibetan sheep populations are generally low. Fst results revealed that most populations exhibited moderate to low levels of genetic differentiation. The effective population size among Tibetan sheep populations showed an increasing trend over time. The evolutionary relationships among Tibetan sheep populations reflect the correlation between their geographical locations and genomic genetic distances, while also indirectly confirming the impact of historical activities such as early human migration, admixture, fusion, and expansion on the population sizes and distributions of Tibetan sheep.ConclusionsThe results indicate that the genetic diversity levels and genetic differentiation among Tibetan sheep populations are relatively low. In this study, we identified the genetic characteristics of Tibetan sheep populations, which exhibit low levels of diversity, genetic differentiation, and a strong population structure. A deeper genomic exploration of the population structure and diversity status of Tibetan sheep populations will provide theoretical support for subsequent genetic breeding and diversity conservation efforts.

A multimodal cross-transformer-based model to predict mild cognitive impairment using speech, language and vision

Mild Cognitive Impairment (MCI) is an early stage of memory loss or other cognitive ability loss in individuals who maintain the ability to independently perform most activities of daily living. It is considered a transitional stage between normal cognitive stage and more severe cognitive declines like dementia or Alzheimer’s. Based on the reports from the National Institute of Aging (NIA), people with MCI are at a greater risk of developing dementia, thus it is of great importance to detect MCI at the earliest possible to mitigate the transformation of MCI to Alzheimer’s and dementia. Recent studies have harnessed Artificial Intelligence (AI) to develop automated methods to predict and detect MCI. The majority of the existing research is based on unimodal data (e.g., only speech or prosody), but recent studies have shown that multimodality leads to a more accurate prediction of MCI. However, effectively exploiting different modalities is still a big challenge due to the lack of efficient fusion methods. This study proposes a robust fusion architecture utilizing an embedding-level fusion via a co-attention mechanism to leverage multimodal data for MCI prediction. This approach addresses the limitations of early and late fusion methods, which often fail to preserve inter-modal relationships. Our embedding-level fusion aims to capture complementary information across modalities, enhancing predictive accuracy. We used the I-CONECT dataset, where a large number of semi-structured conversations via internet/webcam between participants aged 75+ years old and interviewers were recorded. We introduce a multimodal speech-language-vision Deep Learning-based method to differentiate MCI from Normal Cognition (NC). Our proposed architecture includes co-attention blocks to fuse three different modalities at the embedding level to find the potential interactions between speech (audio), language (transcribed speech), and vision (facial videos) within the cross-Transformer layer. Experimental results demonstrate that our fusion method achieves an average AUC of 85.3% in detecting MCI from NC, significantly outperforming unimodal (60.9%) and bimodal (76.3%) baseline models. This superior performance highlights the effectiveness of our model in capturing and utilizing the complementary information from multiple modalities, offering a more accurate and reliable approach for MCI prediction.

Brain tumor segmentation by combining MultiEncoder UNet with wavelet fusion.

Accurate segmentation of brain tumors from multimodal magnetic resonance imaging (MRI) holds significant importance in clinical diagnosis and surgical intervention, while current deep learning methods cope with situations of multimodal MRI by an early fusion strategy that implicitly assumes that the modal relationships are linear, which tends to ignore the complementary information between modalities, negatively impacting the model's performance. Meanwhile, long-range relationships between voxels cannot be captured due to the localized character of the convolution procedure. Aiming at this problem, we propose a multimodal segmentation network based on a late fusion strategy that employs multiple encoders and a decoder for the segmentation of brain tumors. Each encoder is specialized for processing distinct modalities. Notably, our framework includes a feature fusion module based on a 3D discrete wavelet transform aimed at extracting complementary features among the encoders. Additionally, a 3D global context-aware module was introduced to capture the long-range dependencies of tumor voxels at a high level of features. The decoder combines fused and global features to enhance the network's segmentation performance. Our proposed model is experimented on the publicly available BraTS2018 and BraTS2021 datasets. The experimental results show competitiveness with state-of-the-art methods. The results demonstrate that our approach applies a novel concept for multimodal fusion within deep neural networks and delivers more accurate and promising brain tumor segmentation, with the potential to assist physicians in diagnosis.

High performance RGB-Thermal Video Object Detection via hybrid fusion with progressive interaction and temporal-modal difference

RGB-Thermal Video Object Detection (RGBT VOD) is to localize and classify the predefined objects in visible and thermal spectrum videos. The key issue in RGBT VOD lies in integrating multi-modal information effectively to improve detection performance. Current multi-modal fusion methods predominantly employ middle fusion strategies, but the inherent modal difference directly influences the effect of multi-modal fusion. Although the early fusion strategy reduces the modality gap in the middle stage of the network, achieving in-depth feature interaction between different modalities remains challenging. In this work, we propose a novel hybrid fusion network called PTMNet, which effectively combines the early fusion strategy with the progressive interaction and the middle fusion strategy with the temporal-modal difference, for high performance RGBT VOD. In particular, we take each modality as a master modality to achieve an early fusion with other modalities as auxiliary information by progressive interaction. Such a design not only alleviates the modality gap but facilitates middle fusion. The temporal-modal difference models temporal information through spatial offsets and utilizes feature erasure between modalities to motivate the network to focus on shared objects in both modalities. The hybrid fusion can achieve high detection accuracy only using three input frames, which makes our PTMNet achieve a high inference speed. Experimental results show that our approach achieves state-of-the-art performance on the VT-VOD50 dataset and also operates at over 70 FPS. The code will be freely released at https://github.com/tzz-ahu for academic purposes.

SFGCN: Synergetic fusion-based graph convolutional networks approach for link prediction in social networks

Accurate Link Prediction (LP) in Social Networks (SNs) is crucial for various practical applications, such as recommendation systems and network security. However, traditional techniques often struggle to capture the intricate and multidimensional nature of these networks. This paper presents a novel approach, the Synergetic Fusion-based Graph Convolutional Networks (SFGCN), designed to enhance LP accuracy in SNs. The SFGCN model utilizes a fusion architecture that combines structural features and other attribute data through early, intermediate, and late fusion mechanisms to create improved node and edge representations. We thoroughly evaluate our SFGCN model on seven real-world datasets, encompassing citation networks, co-purchase networks, and academic publication domains. The results demonstrate its superiority over baseline GCN architectures and other selected LP methods, achieving a 6.88 % improvement in accuracy. The experiments show that our model captures the complex interactions and dependencies within SNs, providing a comprehensive understanding of their underlying dynamics. The approach mentioned can be effectively applied in the domain of SN analysis to enhance the accuracy of LP results. This method not only improves the precision of predictions but also enhances the adaptability of the model in diverse SN scenarios.

Multi-modal fusion deep learning model for excavated soil heterogeneous data with efficient classification

Multimodal fusion, a cutting-edge method aiming to integrate heterogeneous data for prediction tasks, has received limited attention in geotechnical engineering. This study focuses on classifying excavated soils with large quantities rapidly and finely. By using an excavated soil information collecting system at the largest soil transferring platform in China, 3,243 groups of multi-source heterogenous data were created, including soil images, spatial series data of cone index curves, time series data of TDR waveforms, discrete net weight data, and textual descriptions of soil morphology. After data augmentation, a big dataset containing 23,122 sets with labels based on the Unified Soil Classification System, moisture content, and mineral composition was created. Multimodal deep learning models were trained using different fusion strategies: 7 early fusion, 3 intermediate fusion, and 2 late fusion cases. Performance metrics were evaluated, including loss, accuracy, F1 Score, precision, recall, specificity, NPV, FPR, and AUROC. Results showed that intermediate fusions performed best, while late fusions performed the poorest. The two-stage intermediate fusion with five modalities achieved the best results, achieving an accuracy above 0.99 on the test set. This multimodal fusion approach effectively explores the correlation between multi-source heterogeneous data of soils, leading to scientific and engineering value in geotechnics.

Early Maladaptive Schemas, Cognitive Fusion, and Anabolic-Androgenic Steroid Use Attitudes: The Mediating Role of Muscle Dysmorphia in Iran

In recent decades, the interest in having an ideal body in men has caused a pathological tendency to be muscular, followed by a tendency to use anabolic-androgenic steroids (AASs). This study was designed to evaluate the mediating role of muscle dysmorphia in the relationship between early maladaptive schemas and body image-related cognitive fusion with the tendency to use AAS in male athletes. Out of the total number of men referring to fitness clubs in Isfahan, Iran, 474 men were evaluated using a multistage random cluster sampling method. The questionnaires used in this research included the Muscle Dysmorphic Disorder Inventory, Cognitive Fusion Questionnaire—Body Image, Young Schema Questionnaire—Short Form, and Prototype Willingness Model Questionnaire. The results demonstrated that the relationship of AAS use with body image-related cognitive fusion and the three maladaptive schemas with the mediation of muscle dysmorphia is significant. The present study provides significant implications in the discussion of prevention and treatment of AAS addiction.

Effect of intervertebral bone graft area on the effect of single-level posterior lumbar decompression and bone graft fusion

To study the effect of intervertebral grafting area on the effect of single segment lumbar posterior decompression and intervertebral bone grafting fusion. The clinical data of 52 patients who underwent single-segment lumbar posterior decompression pedicle internal fixation and bone grafting fusion from January 2020 to December 2022 were retrospective reviewed. The area of the intervertebral bone graft was measured one week postoperatively using Computed Tomography (CT), and based on the ratio of the bone graft area to the average area of the endplates, the patients were divided into three groups:17 cases in group A(the intervertebral bone graft area did not exceed the area of one pedicle) included 9 males and 8 females with an average age of (56.0±11.5) years old;15 cases in group B(the intervertebral bone graft area exceeded one pedicle but did not reach the opposite pedicle) included 10 males and 5 females with an average of (52.0±14.0) years old; 20 cases in group C (the intervertebral bone graft area exceeded the opposite pedicle) included 12 males and 8 females with an average of (49.5±12.8) years old. X-rays and CT scans were performed at 3, 6, 12 months, and the final follow-up postoperatively, the interbody fusion Brantigan scores, pain visual analogue scale (VAS), and Oswestry Disability Index (ODI) at each follow-up were recorded. The gender, age, and surgical segments showed no significant differences among three groups(P>0.05). There was also no significant difference in the preoperative VAS and ODI among three groups (P>0.05). All patients of three groups were followed up from 12 to 36 months. Compared with preoperative, VAS and ODI scores of three groups showed significant improvement at 1 week postoperatively and the final follow-up (P<0.05). Compared with preoperative measurements, the height of the intervertebral space was restored at 1 week postoperatively in three groups;at the final follow-up, the loss of height in the intervertebral space was less in groups B and C, and the height of the intervertebral space in group B and C was significantly higher than in group A(P<0.05). The modified Brantigan scores at 3 and 6 months postoperatively were significantly higher in group C than in groups A and B (P<0.05);at 12 months postoperatively, the scores in groups B and C were significantly higher than in group A(P<0.05);however, at the final follow-up, there was no significant difference in the modified Brantigan scores among three groups(P>0.05). The bone graft fusion rate in group C was significantly higher than in groups A and B at 3 months postoperatively(P<0.05);at 6 and 12 months postoperatively, the fusion rates in groups B and C were significantly higher than in group A(P<0.05);at the final follow-up, the fusion rate in group A was still lower than in groups B and C, but the difference among three groups was not significant(P>0.05). Single segment posterior lumbar decompression and interbody fusion surgery can significantly improve the clinical symptoms of patients with lumbar degenerative related diseases. However, as the proportion of bone grafting area increases, the early bone grafting fusion rate and fusion score of patients are significantly improved.