Registration of multimodal bone images based on edge similarity metaheuristic.

OBJECTIVE: Blurry medical images affect the accuracy and efficiency of multimodal image registration, whose existing methods require further improvement. METHODS: We propose an edge-based similarity registration method optimised for multimodal medical images, especially bone images, by a balance optimiser. First, we use a GPU (graphics processing unit) rendering simulation to convert computed tomography data into digitally reconstructed radiographs. Second, we introduce the improved cascaded edge network (ICENet), a convolutional neural network that extracts edge information of blurry medical images. Then, the bilateral Gaussian-weighted similarity of pairs of X-ray images and digitally reconstructed radiographs is measured. The a balanced optimiser is iteratively applied to finally estimate the best pose to perform image registration. RESULTS: Experimental results show that, on average, the proposed method with ICENet outperforms other edge detection networks by 20%, 12%, 18.83%, and 11.93% in the overall Dice similarity, overall intersection over union, peak signal-to-noise ratio, and structural similarity index, respectively, with a registration success rate up to 90% and average reduction of 220% in registration time. CONCLUSION: The proposed method with ICENet can achieve a high registration success rate even for blurry medical images, and its efficiency and robustness are higher than those of existing methods. SIGNIFICANCE: Our proposal may be suitable for supporting medical diagnosis, radiation therapy, image-guided surgery, and other clinical applications.

Local imperceptible adversarial attacks against human pose estimation networks.

Deep neural networks are vulnerable to attacks from adversarial inputs. Corresponding attack research on human pose estimation (HPE), particularly for body joint detection, has been largely unexplored. Transferring classification-based attack methods to body joint regression tasks is not straightforward. Another issue is that the attack effectiveness and imperceptibility contradict each other. To solve these issues, we propose local imperceptible attacks on HPE networks. In particular, we reformulate imperceptible attacks on body joint regression into a constrained maximum allowable attack. Furthermore, we approximate the solution using iterative gradient-based strength refinement and greedy-based pixel selection. Our method crafts effective perceptual adversarial attacks that consider both human perception and attack effectiveness. We conducted a series of imperceptible attacks against state-of-the-art HPE methods, including HigherHRNet, DEKR, and ViTPose. The experimental results demonstrate that the proposed method achieves excellent imperceptibility while maintaining attack effectiveness by significantly reducing the number of perturbed pixels. Approximately 4% of the pixels can achieve sufficient attacks on HPE.

BPCN: bilateral progressive compensation network for lung infection image segmentation.

Lung infection image segmentation is a key technology for autonomous understanding of the potential illness. However, current approaches usually lose the low-level details, which leads to a considerable accuracy decrease for lung infection areas with varied shapes and sizes. In this paper, we propose bilateral progressive compensation network (BPCN), a bilateral progressive compensation network to improve the accuracy of lung lesion segmentation through complementary learning of spatial and semantic features. The proposed BPCN are mainly composed of two deep branches. One branch is the multi-scale progressive fusion for main region features. The other branch is a flow-field based adaptive body-edge aggregation operations to explicitly learn detail features of lung infection areas which is supplement to region features. In addition, we propose a bilateral spatial-channel down-sampling to generate a hierarchical complementary feature which avoids losing discriminative features caused by pooling operations. Experimental results show that our proposed network outperforms state-of-the-art segmentation methods in lung infection segmentation on two public image datasets with or without a pseudo-label training strategy.

An End-to-End Shape-Preserving Point Completion Network.

Shape completion for 3-D point clouds is an important issue in the literature of computer graphics and computer vision. We propose an end-to-end shape-preserving point completion network through encoder-decoder architecture, which works directly on incomplete 3-D point clouds and can restore their overall shapes and fine-scale structures. To achieve this task, we design a novel encoder that encodes information from neighboring points in different orientations and scales, as well as a decoder that outputs dense and uniform complete point clouds. We augment a 3-D object dataset based on ModelNet40 and validate the effectiveness of our shape-preserving completion network. Experimental results demonstrate that the recovered point clouds lie close to ground truth points. Our method outperforms state-of-the-art approaches in terms of Chamfer distance (CD) error and earth mover's distance (EMD) error. Furthermore, our end-to-end completion network is robust to model noise, the different levels of incomplete data, and can also generalize well to unseen objects and real-world data.

Mental representation of fractions: It all depends on whether they are common or uncommon.

This study examined whether common and uncommon fractions are mentally represented differently and whether common ones are used in accessing the magnitudes of uncommon ones. In Experiments 1 and 2, college education majors, most of whom were female, Caucasian, and in their early 20s, made comparisons involving common and uncommon fractions. In Experiment 3, participants were presented with comparison tasks involving uncommon fractions and asked to describe the strategies which they used in making such comparisons. Analysis of reaction times and error rates support the hypothesis that for common fractions, it is their holistic real value, rather than their individual components, that gets represented. For uncommon fractions, the access of their magnitudes is a process of retrieving and using a known common one having a similar value. Such results suggest that the development of the cognisance of the magnitudes of fractions may be principally a matter of common ones only and that learners' handling of uncommon fractions may be greatly facilitated through instructions on matching them with common ones having a similar value.

Simultaneous photocatalytic and microbial degradation of dye-containing wastewater by a novel g-C3N4-P25/photosynthetic bacteria composite.

Azo dyes are very resistant to light-induced fading and biodegradation. Existing advanced oxidative pre-treatment methods based on the generation of non-selective radicals cannot efficiently remove these dyes from wastewater streams, and post-treatment oxidative dye removal is problematic because it may leave many byproducts with unknown toxicity profiles in the outgoing water, or cause expensive complete mineralization. These problems could potentially be overcome by combining photocatalysis and biodegradation. A novel visible-light-responsive hybrid dye removal agent featuring both photocatalysts (g-C3N4-P25) and photosynthetic bacteria encapsulated in calcium alginate beads was prepared by self-assembly. This system achieved a removal efficiency of 94% for the dye reactive brilliant red X-3b and also reduced the COD of synthetic wastewater samples by 84.7%, successfully decolorized synthetic dye-contaminated wastewater and reduced its COD, demonstrating the advantages of combining photocatalysis and biocatalysis for wastewater purification. The composite apparently degrades X-3b by initially converting the dye into aniline and phenol derivatives whose aryl moieties are then attacked by free radicals to form alkyl derivatives, preventing the accumulation of aromatic hydrocarbons that might suppress microbial activity. These alkyl intermediates are finally degraded by the photosynthetic bacteria.

Exact and Adaptive Signed Distance Fields Computation for Rigid and Deformable Models on GPUs.

Most techniques for real-time construction of a signed distance field, whether on a CPU or GPU, involve approximate distances. We use a GPU to build an exact adaptive distance field, constructed from an octree by using the Morton code. We use rectangle-swept spheres to construct a bounding volume hierarchy (BVH) around a triangulated model. To speed up BVH construction, we can use a multi-BVH structure to improve the workload balance between GPU processors. An upper bound on distance to the model provided by the octree itself allows us to reduce the number of BVHs involved in determining the distances from the centers of octree nodes at successively lower levels, prior to an exact distance query involving the remaining BVHs. Distance fields can be constructed 35-64 times as fast as a serial CPU implementation of a similar algorithm, allowing us to simulate a piece of fabric interacting with the Stanford Bunny at 20 frames per second.