Search

Femoral neck fractures are a common type of fracture, accounting for approximately 3.58% of total body fractures and about 50% of proximal femoral fractures. They are particularly prevalent in elderly individuals with osteoporosis, especially those aged 65 and older. This study aims to develop and implement a progressive balance training program for elderly femoral neck fracture patients, guided by the behavior change wheel theory. Through literature review and expert consultation, we developed a progressive balance training program using the behavior change wheel theory. We selected 83 patients admitted to our orthopedics department for hip surgery between January 2022 and December 2022 and divided them into a control group (n = 42) and an intervention group (n = 41). The control group followed a standard exercise program, while the intervention group underwent the progressive balance training program. Their rehabilitation outcomes were compared using the Berg Balance Scale, Harris hip joint function assessment, and the Chinese version of the Fall Efficiency Scale at the first bedside standing, as well as at 2 weeks, 6 weeks and 12 weeks after the operation. Repeated measures analysis of variance revealed statistically significant time-related effects, interaction effects and between-group effects in both groups for the Berg Balance Scale scores (Ftime = 5753.969, Finteraction = 221.20, Fbetween−groups = 1496.285), Harris hip joint function scores (Ftime = 2750.864, Finteraction = 115.315, Fbetween−groups = 760.690), and Fall Efficiency Scale scores (Ftime = 2590.021, Finteraction = 176.961, Fbetween−groups = 625.033) postoperatively. We conclude that the progressive balance training program developed based on the behavior change wheel theory can accelerate the postoperative balance recovery in total hip arthroplasty patients, promote hip joint function recovery, and reduce the fear of falling among patients.

The main differences in images of footprints are the proportion of the parts of foot and the distribution of pressure, which can be considered as fine-grained image classification. Moreover, the deviation of human body weight and muscle strength increases the difficulty of identifying the left and right feet. While using a fine-grained image classification network to solve the footprint image classification problem is certainly a feasible approach, the number of parameters in a fine-grained image classification network is generally large, and therefore we would like to build a lightweight classification network that is suitable for several small footprint datasets. In this paper, a multimodal footprint recognition algorithm based on progressive multi-granularity feature fusion is proposed. First, the shallow dense connection network is used to extract features. The feature extraction ability of the model is improved with the help of channel splicing and feature multiplexing. Second, to learn footprint images of different granularities, the progressive training strategy and puzzle scrambler are applied to the model. Finally, factorized bilinear coding can aggregate local features to obtain more discriminative global representation features. Experiments show that our network achieves comparable classification accuracy to some fine-grained image classification models (PMG, MSEC) on the complete pressure footprint dataset, but the number of parameters in our network is greatly reduced. Meanwhile, our network also achieves good classification results on several other footprint datasets, which demonstrates the effectiveness of our network. At the same time, an ablation experiment was carried out to verify the effectiveness of the progressive strategy and the factorized bilinear coding. [ABSTRACT FROM AUTHOR]

Progressive training has unfolded its superiority on a wide range of downstream tasks. However, it may fail in fine-grained recognition (FGR) due to special challenges with high intra-class and low inter-class variances. In this paper, we propose an active self-pace learning method to exploit the full potential of progressive training strategy in FGR. The key innovation of our design is to integrate submodular optimization and self-pace learning into a maximum–minimum optimization framework. The submodular optimization is regarded as a dynamic regularization to select active sample groups in each training round for restricting the search space of self-pace optimization. This can overcome the limitation of traditional self-pace learning that is easily trapped into local minimums when facing challenging samples. Extensive experiments on three public FGR datasets show that the proposed method can win at least 1.5% performance gain in various kinds of network backbones including swin-transformer. • We are the first to exploit the sub–modularity for active sample selection. By our problem formulation, the optimal category subsets can be progressively selected for obtaining steady cumulative gain. • We combine submodular optimization with self-paced learning to generate a collaborated maximum–minimum optimization framework. The constructed framework can achieve smooth and stable progressive learning through using active samples to restrict the search space of self-paced optimization. • The proposed collaborated optimization framework can be deployed on various types of FGR networks. Extensive experiments on three fine-grained recognition datasets can verify the superiority of progressive training, where the averaged recognition gain surpasses 1.5%. [ABSTRACT FROM AUTHOR]

Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works are mainly part-driven (either explicitly or implicitly), with the assumption that fine-grained information naturally rests within the parts. In this paper, we take a different stance, and show that part operations are not strictly necessary – the key lies with encouraging the network to learn at different granularities and progressively fusing multi-granularity features together. In particular, we propose: (i) a progressive training strategy that effectively fuses features from different granularities, and (ii) a consistent block convolution that encourages the network to learn the category-consistent features at specific granularities. We evaluate on several standard FGVC benchmark datasets, and demonstrate the proposed method consistently outperforms existing alternatives or delivers competitive results. Codes are available at https://github.com/PRIS-CV/PMG-V2. [ABSTRACT FROM AUTHOR]

In fine-grained visual classification(FGVC), small inter-class variations and large intra-class variations are always inherent attributes, so it is much more challenging than traditional classification tasks. Recent studies have mainly tackled this problem by employing attention mechanisms to locate the most discriminative parts. However, these methods tend to neglect other inconspicuous but distinguishable parts, and can not effectively fuse the features information of different scales and different degrees of discrimination. In this paper, we propose a multi-scale progressive complementary fusion network (MPCF-Net) to address these problems. In particular, we propose the following: (i) A three-step multi-scale progressive training method, which employs an image slicer to generate puzzle images at different scales followed by multi-step progressive training. This enables the network to capture multi-granularity local feature information and gradually expand its attention to global structural information as the training progresses for multi-granularity information fusion. (ii) A plug-and-play feature complementary enhancement module (FCEM) that explicitly enhances the features extracted by the current layer of the network, while also enabling the next layer of the network to extract potential complementary feature information to diversify the features. Our experiments were conducted on four FGVC benchmark datasets and yielded state-of-the-art and competitive results.

In practical classification tasks, the sample distribution of the dataset is often unbalanced; for example, this is the case in a dataset that contains a massive quantity of samples with weak labels and for which concrete identification is unavailable. Even in samples with exact labels, the number of samples corresponding to many labels is small, resulting in difficulties in learning the concepts through a small number of labeled samples. In addition, there is always a small interclass variance and a large intraclass variance among categories. Weak labels, few-shot problems, and fine-grained analysis are the key challenges affecting the performance of the classification model. In this paper, we develop a progressive training technique to address the few-shot challenge, along with a weak-label boosting method, by considering all of the weak IDs as negative samples of every predefined ID in order to take full advantage of the more numerous weak-label data. We introduce an instance-aware hard ID mining strategy in the classification loss and then further develop the global and local feature-mapping loss to expand the decision margin. We entered the proposed method into the Kaggle competition, which aims to build an algorithm to identify individual humpback whales in images. With a few other common training tricks, the proposed approach won first place in the competition. All three problems (weak labels, few-shot problems, and fine-grained analysis) exist in the dataset used in the competition. Additionally, we applied our method to CUB-2011 and Cars-196, which are the most widely-used datasets for fine-grained visual categorization tasks, and achieved respective accuracies of 90.1% and 94.9%. This experiment shows that the proposed method achieves the optimal effect compared with other common baselines, and verifies the effectiveness of our method. Our solution has been made available as an open source project. [ABSTRACT FROM AUTHOR]

Abstract Background and purpose To explore whether a highly refined dose volume histograms (DVH) prediction model can improve the accuracy and reliability of knowledge-based volumetric modulated arc therapy (VMAT) planning for cervical cancer. Methods and materials The proposed model underwent repeated refining through progressive training until the training samples increased from initial 25 prior plans up to 100 cases. The estimated DVHs derived from the prediction models of different runs of training were compared in 35 new cervical cancer patients to analyze the effect of such an interactive plan and model evolution method. The reliability and efficiency of knowledge-based planning (KBP) using this highly refined model in improving the consistency and quality of the VMAT plans were also evaluated. Results The prediction ability was reinforced with the increased number of refinements in terms of normal tissue sparing. With enhanced prediction accuracy, more than 60% of automatic plan-6 (AP-6) plans (22/35) can be directly approved for clinical treatment without any manual revision. The plan quality scores for clinically approved plans (CPs) and manual plans (MPs) were on average 89.02 ± 4.83 and 86.48 ± 3.92 (p

As MR Rician noise and CT low-dose perfusion noise have a complicated distribution, it is still a challenging task to automatically and accurately remove the noises existing in MR and CT images. Recently, convolutional neural networks have shown favorable performance on image denoising tasks. However, existing methods ignored the hierarchical features extracted from multi-supervision inner layers and estimated the denoised image just by the last single layer, which can not adequately reserve the details of the image. In this paper, we propose a cascaded multi-supervision convolutional neural network named CMSNet to remove the low-dose perfusion noise in CT images and the Rician noise exist in MR images. The CMSNet consists of a multi-supervision network (MSNet) followed with a Refinement network. MSNet is presented to predict the noise constrained by the supervisions from last three convolution layers, which can help acquire more accurate noise prediction and thus obtain the noise-free image. Refinement network is introduced to relief the details lost problem caused by the denoising operation. We employ a progressive training strategy, i.e. , MSNet is first trained independently to predict the preliminary noise and then jointly trained with Refinement network for more accurate noise estimating, which can boost the network performance. Experiments are conducted on clinic abdominal MR and CT images, and the results show that our proposed model achieved a promising performance in terms of unknown noise level, a specific noise level on peak signal to noise ratio (PSNR) and global structure similarity index measurement (SSIM). [ABSTRACT FROM AUTHOR]

A novel morphing strategy based on reinforcement learning (RL) is developed to solve the morphing decision-making problem with minimum flight time for a long-range variable-sweep morphing aircraft. The proposed morphing strategy focuses on the sparse-reward no-reference decision-making problem caused by terminal performance objectives and long-range missions. A double-layer morphing-flight control framework is established to decouple the design of morphing strategy from flight controller while ensuring flight stability. Under this framework, an RL agent is designed to learn the minimum-flight-time morphing strategy. Specifically, the reward function is divided into primary goal rewards and sub-goal rewards to deal with the sparse-reward no-reference issue. A multi-stage progressive training scheme is developed to train the designed RL agent with a trail of training environments gradually converging to the actual world. This scheme accelerates the training process and promotes the convergence of the RL agent during training. Simulation results in nominal and dispersed conditions indicate the optimality and robustness of the proposed morphing strategy. Moreover, the generalization ability is validated in an untrained scenario. [ABSTRACT FROM AUTHOR]

Background and Purpose: To explore whether a highly refined dose volume histograms (DVH) prediction model can improve the accuracy and reliability of knowledge-based volumetric modulated arc therapy (VMAT) planning for cervical cancer.Methods and Materials: The proposed model underwent repeated refining through progressive training until the training samples increased from initial 25 prior plans up to 100 cases. The estimated DVHs derived from the prediction models of different runs of training were compared in 35 new cervical cancer patients to analyze the effect of such an interactive plan and model evolution method. The reliability and efficiency of knowledge-based planning (KBP) using this highly refined model in improving the consistency and quality of the VMAT plans were also evaluated.Results: The prediction ability was reinforced with the increased number of refinements in terms of normal tissue sparing. With enhanced prediction accuracy, more than 60% of automatic plan-6 (AP-6) plans (22/35) can be directly approved for clinical treatment without any manual revision. The plan quality scores for clinically approved plans (CPs) and manual plans (MPs) were on average 89.02 ± 4.83 and 86.48 ± 3.92 (p < 0.001). Knowledge-based planning significantly reduced the Dmean and V18 Gy for kidney (L/R), the Dmean, V30 Gy, and V40 Gy for bladder, rectum, and femoral head (L/R).Conclusion: The proposed model evolution method provides a practical way for the KBP to enhance its prediction ability with minimal human intervene. This highly refined prediction model can better guide KBP in improving the consistency and quality of the VMAT plans. [ABSTRACT FROM AUTHOR]

The recent end-to-end co-saliency models have good performance, however, they cannot express the semantic consistency among a group of images well and usually require many co-saliency labels. To this end, a two-stream encoder generative adversarial network (TSE-GAN) with progressive training is proposed in this paper. In the pre-training stage, the salient object detection generative adversarial networks (SOD-GAN) and classification network (CN) are separately trained by the salient object detection (SOD) datasets and co-saliency datasets with only category labels to learn the intra-saliency and preliminary inter-saliency cues and alleviate the problem of insufficient co-saliency labels. In the second training stage, the backbone of TSE-GAN is inherited from the trained SOD-GAN, the encoder of trained SOD-GAN (SOD-Encoder) is used to extract intra-saliency features, the group-wise semantic encoder (GS-Encoder) is constructed by the multi-level group-wise category features extracted from CN for extracting inter-saliency features with better semantic consistency, the TSE-GAN constructed by incorporating the GS-Encoder into SOD-GAN is trained on co-saliency datasets for co-saliency detection. The comprehensive comparisons with 13 state-of-the-art methods demonstrate the effectiveness of proposed method. [ABSTRACT FROM AUTHOR]

Crowd counting has captured wide attention in computer vision, which aims to accurately count the number of people in still images or video scenes. However, it's still a challenging task due to the scale variation and cluttered background in crowd scenes. In this paper, we propose a 2-stage Double Attention convolutional neural network for crowd counting, and call it 2-DA-CNN, which could deal with scale variation and cluttered background in crowd counting. The proposed 2-DA-CNN includes three parts. The first part is the front-end module which consists of a set of convolution operations, whose function is to extract abundant feature of crowd. The second part is the first double attention module, which contains trunk branch and mask branch. The former is mainly composed by multi-column CNN module, which is to deal with scale variation in crowd scenes. The latter can generate two masks, which aims to assign interesting regions reasonably in cluttered situation. The third part is the second double attention module, similar to the first double attention module, which can enhance the performance of multi-column CNN module further. In addition, we propose progressive training method to improve the drawback of using geometry-adaptive kernels to generate ground truth. The experimental results on three mainstream datasets (ShanghaiTech part B, ShanghaiTech part A and UCF_CC_50) suggest that the proposed 2-DA-CNN is competitive with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning-based methods for deformable image registration are attractive alternatives to conventional registration methods because of their short registration times. However, these methods often fail to estimate larger displacements in complex deformation fields, for which a multi-resolution strategy is required. In this article, we propose to train neural networks progressively to address this problem. Instead of training a large convolutional neural network on the registration task all at once, we initially train smaller versions of the network on lower resolution versions of the images and deformation fields. During training, we progressively expand the network with additional layers that are trained on higher resolution data. We show that this way of training allows a network to learn larger displacements without sacrificing registration accuracy and that the resulting network is less sensitive to large misregistrations compared to training the full network all at once. We generate a large number of ground truth example data by applying random synthetic transformations to a training set of images, and test the network on the problem of intrapatient lung CT registration. We analyze the learned representations in the progressively growing network to assess how the progressive learning strategy influences training. Finally, we show that a progressive training procedure leads to improved registration accuracy when learning large and complex deformations. [ABSTRACT FROM AUTHOR]

Starting perceptual training at easy levels before progressing to difficult levels generally produces better learning outcomes than constantly difficult training does. However, little is known about how "easy" these initial levels should be in order to yield easy-to-hard effects. We compared five levels of initial training block difficulty varying from very easy to hard in two auditory-discrimination learning tasks—a frequency modulation rate discrimination (Experiment 1) and a frequency range discrimination (Experiment 2). The degree of difficulty was based on individualized pretraining ~71% correct discrimination thresholds. Both experiments revealed a sweet spot for easy-to-hard effects. Conditions where initial blocks were either too easy or too difficult produced less benefit than did blocks of intermediate difficulty. Results challenge assumptions that sequencing effects in learning are related to attentional spotlighting of task-relevant dimensions. Rather, they support incremental learning models that account for easy-to-hard effects. Further, the results have implications for how perceptual training regimens should be designed to maximize the benefits of rehabilitative perceptual training. [ABSTRACT FROM AUTHOR]

As multimedia data have been the main form of big data, cross-media retrieval becomes a research hotspot. It provides a flexible retrieval paradigm across different media types, such as using an image query to retrieve the relevant text, video, and audio. An effective model to establish cross-media correlation is indispensable for retrieval. Existing methods usually rely on labeled data for model training, but it is extremely labor consuming to collect and label cross-media data. Under this situation, it is a key issue toward the real application to transfer knowledge from existing data to new data, for reducing the human labor. However, little attention has been paid to knowledge transfer between two cross-media domains. Therefore, this paper proposes the approach of two-level progressive cross-media knowledge transfer (TPCKT), which transfers knowledge from large-scale cross-media data, to boost the retrieval accuracy on cross-media data of another domain. Its contributions are: First, two-level adversarial transfer architecture is proposed with domain discriminators in media-specific level and media-shared level, which have partially shared parameters to preserve cross-media consistency of transfer. The domain discrepancy between cross-media domains is fully reduced for boosting the retrieval accuracy. Second, progressive semantic transfer mechanism is proposed to iteratively select semantically related categories in two cross-media domains for transfer. This drives the transfer process with ascending difficulties, for addressing the difficulty from different label spaces, and ensuring the robustness of transfer. For the experiment, the large-scale cross-media dataset PKU XMediaNet serves as the source domain, and three widely used small-scale datasets are adopted as the target domains to perform retrieval. Experimental results show the promising improvement gained by the proposed TPCKT. [ABSTRACT FROM AUTHOR]

Contemporary dog training and the ongoing changes within this field, particularly ones related to perceptions of dogs and their roles, are interesting topics for academic inquiry. Present practices generally rely upon either the pack-and-dominance concept--leading to top-down, discipline-heavy treatment--or behaviorism and operant conditioning, where great emphasis is placed on positive reinforcement. The "positive" approach underlies state-of-the-art training programs of the second decade of the 21st century. Authors of such programs go beyond the limitations of behaviorism, embracing up-to-date information about the emotional and cognitive abilities of dogs--something that trainers strongly attached to behaviorism are prone to overlook. Such a new approach to dog training does not oppose critical anthropomorphism, and it challenges prior understanding of the dog-human relationship. The relationship in question ceases to be unilateral and becomes a bond of mutual benefit, where a forcefree, reward-based method of training is in unison with advertising the self-development potential for humans. [ABSTRACT FROM AUTHOR]

Rats received two stages of Pavlovian discrimination training with two flavor stimuli: a compound consisting of saccharin mixed with 0.15 M lithium chloride (LiCl), and the saccharin alone. The concentration of the saccharin solution (i.e., the common element shared by the stimuli to be discriminated) was relatively high in Stage 2 (1.2%). Groups differed in the pre-training that they received in Stage 1. Group Progressive (PROG) was pretrained in easier versions of the discrimination of Stage 2. The difficulty of these discriminations was gradually increased by progressively increasing the initial concentration of saccharin (0.15%). Group PROG learned the hardest discrimination faster than a control group (HARD) that was trained in this discrimination in both Stages 1 and 2 (Experiment 1). We also observed that the enhancement of learning observed in Group PROG was less than that observed after continuous pre-training with the easiest version of the discrimination (Group CONT; Experiment 2). We discuss the implications of these results in relation to other previous demonstrations of the easy-to-hard effect. [ABSTRACT FROM AUTHOR]

Considering the small differences between different types in the diabetic retinopathy (DR) grading task, a retinopathy grading algorithm based on cross-layer bilinear pooling is proposed. Firstly, the input image is cropped according to the Hough circle transform (HCT), and then the image contrast is improved by the preprocessing method; then the squeeze excitation group residual network (SEResNeXt) is used as the backbone of the model, and a cross-layer bilinear pooling module is introduced for classification. Finally, a random puzzle generator is introduced in the training process for progressive training, and the center loss (CL) and focal loss (FL) methods are used to further improve the effect of the final classification. The quadratic weighted Kappa (QWK) is 90.84% in the Indian Diabetic Retinopathy Image Dataset (IDRiD), and the area under the receiver operating characteristic curve (AUC) in the Messidor-2 dataset (Messidor-2) is 88.54%. Experiments show that the algorithm proposed in this paper has a certain application value in the field of diabetic retina grading.

Abstract: The purpose of this study was to examine whether progressive training exercise resulted in changes in neuronal expression of c-Fos in the hypothalamic regions (paraventricular nucleus, supraoptic nucleus and suprachiasmatic nucleus) and subfornical organ of Wistar rats and its relation to hydromineral parameters such as plasma proteins, osmolality and hematocrit. Rats were trained progressively in a running wheel over four days, while control rats were not provided with the opportunity to exercise. c-Fos cellular activity was immunohistochemically stained in accordance with the ABC method. The number of c-Fos immunoreactive cells was counted using standard imaging software. c-Fos in the PVN and SO nuclei was found to be significantly increased in trained rats 1h post-exercise compared with control and 24h post-exercise groups. However, no significant differences were found between trained and control rats in the SQ and SFO. These findings provide useful information of interest for future studies on brain specific regions involved in hydromineral balance in response to progressive exercise. [Copyright &y& Elsevier]

Current theories of skill learning suggest that novices learn optimally in a simplified environment. This information can be incorporated in simulator designs. Our purpose was to assess whether basic visuospatial training is beneficial for performance on an arthroscopy model. One group of trainees practiced three visuomotor tasks while the other group was not given this opportunity. Both groups then performed three different surgical tasks on a simulated arthroscopy model. Practice with the visuomotor tasks enhanced performance on two of the tasks on the arthroscopy model. The basic navigational skills learned through practice transferred to the performance of arthroscopic surgery tasks and these skills should be included in the design of a comprehensive arthroscopy simulator. [ABSTRACT FROM AUTHOR]