Search

Spinal metastasis is the most common disease in bone metastasis and may cause pain, instability and neurological injuries. Early detection of spinal metastasis is critical for accurate staging and optimal treatment. The diagnosis is usually facilitated with Computed Tomography (CT) scans, which requires considerable efforts from well-trained radiologists. In this paper, we explore a learning-based automatic bone quality classification method for spinal metastasis based on CT images. We simultaneously take the posterolateral spine involvement classification task into account, and employ multi-task learning (MTL) technique to improve the performance. MTL acts as a form of inductive bias which helps the model generalize better on each task by sharing representations between related tasks. Based on the prior knowledge that the mixed type can be viewed as both blastic and lytic, we model the task of bone quality classification as two binary classification sub-tasks, i.e., whether blastic and whether lytic, and leverage a multiple layer perceptron to combine their predictions. In order to make the model more robust and generalize better, self-paced learning is adopted to gradually involve from easy to more complex samples into the training process. The proposed learning-based method is evaluated on a proprietary spinal metastasis CT dataset. At slice level, our method significantly outperforms an 121-layer DenseNet classifier in sensitivities by $+12.54\%$, $+7.23\%$ and $+29.06\%$ for blastic, mixed and lytic lesions, respectively, meanwhile $+12.33\%$, $+23.21\%$ and $+34.25\%$ at vertebrae level.

Vertebral body (VB) segmentation is an important preliminary step towards medical visual diagnosis for spinal diseases. However, most previous works require pixel/voxel-wise strong supervisions, which is expensive, tedious and time-consuming for experts to annotate. In this paper, we propose a Weakly supervised Iterative Spinal Segmentation (WISS) method leveraging only four corner landmark weak labels on a single sagittal slice to achieve automatic volumetric segmentation from CT images for VBs. WISS first segments VBs on an annotated sagittal slice in an iterative self-training manner. This self-training method alternates between training and refining labels in the training set. Then WISS proceeds to segment the whole VBs slice by slice with a slice-propagation method to obtain volumetric segmentations. We evaluate the performance of WISS on a private spinal metastases CT dataset and the public lumbar CT dataset. On the first dataset, WISS achieves distinct improvements with regard to two different backbones. For the second dataset, WISS achieves dice coefficients of $91.7\%$ and $83.7\%$ for mid-sagittal slices and 3D CT volumes, respectively, saving a lot of labeling costs and only sacrificing a little segmentation performance., Comment: arXiv admin note: text overlap with arXiv:1412.7062 by other authors

The mismatch of acoustic impedance at water-air interface can lead a low transmitted sound energy. In this paper, we propose a discrete metasurface for extreme sound transmission based on the impedance matching theory. By employing topology optimization, discrete unit cells with different aspect ratios are designed with unitary sound transmission. The unit cell of continuous metasurface is also obtained for comparison. After analyzing the wide-angle performance of discrete unit cells, samples of both discrete and continuous metasurfaces are fabricated. Sound transmission enhancement of discrete metasurface is clearly measured compared to the bare water-air interface. And the amplitude is relatively larger than that of the continuous sample. Experimental results are in general agreement with numerical ones when viscosity of the sample is considered. Furthermore, the frequency shifts between experiment and simulation are attributed to the random immersion of unit cells for discrete metasurface and the bending of continuous metasurface, respectively. The present work suggests an alternative way for improving the efficiency of water-air acoustic communication., Comment: 18pages, 10figures

Open phononic systems including resonators radiating inside an unbounded medium support localized phonons characterized by a complex frequency. In this context, the concept of elastic quasinormal mode (QNM) arises naturally, as in the cases of nanophotonic and plasmonic open systems. Based on a complex, unconjugated form of reciprocity theorem for elastodynamics, the eigenfunction expansion theorem expressed on the elastic QNM basis yields an accurate approximation to the response function, for an arbitrary excitation. The description of the elastic Purcell effect then requires defining a complex-valued modal volume for each QNM. For validation, we first consider the case a vibrating nylon rod radiating in water. As a second test example, we consider a slender nickel ridge on the surface of a fused silica substrate, before extending our attention to a nanoscale tuning fork composed of two such ridges. In all cases, the response estimated from only a few elastic QNMs agrees with the solution to the elastodynamic equation.

This paper considers few-shot anomaly detection (FSAD), a practical yet under-studied setting for anomaly detection (AD), where only a limited number of normal images are provided for each category at training. So far, existing FSAD studies follow the one-model-per-category learning paradigm used for standard AD, and the inter-category commonality has not been explored. Inspired by how humans detect anomalies, i.e., comparing an image in question to normal images, we here leverage registration, an image alignment task that is inherently generalizable across categories, as the proxy task, to train a category-agnostic anomaly detection model. During testing, the anomalies are identified by comparing the registered features of the test image and its corresponding support (normal) images. As far as we know, this is the first FSAD method that trains a single generalizable model and requires no re-training or parameter fine-tuning for new categories. Experimental results have shown that the proposed method outperforms the state-of-the-art FSAD methods by 3%-8% in AUC on the MVTec and MPDD benchmarks., Comment: ECCV 2022 Oral; Code is available at https://github.com/MediaBrain-SJTU/RegAD

A large gap exists between fully-supervised object detection and weakly-supervised object detection. To narrow this gap, some methods consider knowledge transfer from additional fully-supervised dataset. But these methods do not fully exploit discriminative category information in the fully-supervised dataset, thus causing low mAP. To solve this issue, we propose a novel category transfer framework for weakly supervised object detection. The intuition is to fully leverage both visually-discriminative and semantically-correlated category information in the fully-supervised dataset to enhance the object-classification ability of a weakly-supervised detector. To handle overlapping category transfer, we propose a double-supervision mean teacher to gather common category information and bridge the domain gap between two datasets. To handle non-overlapping category transfer, we propose a semantic graph convolutional network to promote the aggregation of semantic features between correlated categories. Experiments are conducted with Pascal VOC 2007 as the target weakly-supervised dataset and COCO as the source fully-supervised dataset. Our category transfer framework achieves 63.5% mAP and 80.3% CorLoc with 5 overlapping categories between two datasets, which outperforms the state-of-the-art methods. Codes are avaliable at https://github.com/MediaBrain-SJTU/CaT.

Direct contour regression for instance segmentation is a challenging task. Previous works usually achieve it by learning to progressively refine the contour prediction or adopting a shape representation with limited expressiveness. In this work, we argue that the difficulty in regressing the contour points in one pass is mainly due to the ambiguity when discretizing a smooth contour into a polygon. To address the ambiguity, we propose a novel differentiable rendering-based approach named \textbf{ContourRender}. During training, it first predicts a contour generated by an invertible shape signature, and then optimizes the contour with the more stable silhouette by converting it to a contour mesh and rendering the mesh to a 2D map. This method significantly improves the quality of contour without iterations or cascaded refinements. Moreover, as optimization is not needed during inference, the inference speed will not be influenced. Experiments show the proposed ContourRender outperforms all the contour-based instance segmentation approaches on COCO, while stays competitive with the iteration-based state-of-the-art on Cityscapes. In addition, we specifically select a subset from COCO val2017 named COCO ContourHard-val to further demonstrate the contour quality improvements. Codes, models, and dataset split will be released., Comment: Tech report

The propagation of acoustic or elastic waves in artificial crystals, including the case of phononic and sonic crystals, is inherently anisotropic. As is known from the theory of periodic composites, anisotropy is directly dictated by the space group of the unit cell of the crystal and the rank of the elastic tensor. Here, we examine effective velocities in the long wavelength limit of periodic acoustic and elastic composites as a function of the direction of propagation. We derive explicit and efficient formulas for estimating the effective velocity surfaces, based on second-order perturbation theory, generalizing the Christofell equation for elastic waves in solids. We identify strongly anisotropic sonic crystals for scalar acoustic waves and strongly anisotropic phononic crystals for vector elastic waves. Furthermore, we observe that under specific conditions, quasi-longitudinal waves can be made much slower than shear waves propagating in the same direction.

Seismic metamaterials (SMs) are expected to assist or replace traditional isolation systems owing to their strong attenuation of seismic waves. In this paper, a one-dimensional inverted T-shaped SM (1D ITSM) with an ultra-wide first bandgap (FBG) is proposed. The complex band structures are calculated to analyze the wave characteristics of the surface waves in the SMs. We find that the FBG of the 1D ITSM is composed of two parts; part 1 with surface evanescent waves and part 2 with no surface modes. Similar results are found in the complex band structure of the FBG of the SM consisting of periodically arranged pillars and substrate. The propagation of seismic surface waves in the 1D ITSM is different in these two frequency ranges of the FBG. In part 1, the seismic surface waves are significantly attenuated in the 1D ITSM, while in part 2, the surface waves are converted into bulk waves. Finally, the ultra-wide FBG is verified by using a kind of the two-dimensional ITSM in large-scale field experiments., Comment: 30 pages,15 figures

This paper explores semi-supervised anomaly detection, a more practical setting for anomaly detection where a small additional set of labeled samples are provided. We propose a new KL-divergence based objective function for semi-supervised anomaly detection, and show that two factors: the mutual information between the data and latent representations, and the entropy of latent representations, constitute an integral objective function for anomaly detection. To resolve the contradiction in simultaneously optimizing the two factors, we propose a novel encoder-decoder-encoder structure, with the first encoder focusing on optimizing the mutual information and the second encoder focusing on optimizing the entropy. The two encoders are enforced to share similar encoding with a consistent constraint on their latent representations. Extensive experiments have revealed that the proposed method significantly outperforms several state-of-the-arts on multiple benchmark datasets, including medical diagnosis and several classic anomaly detection benchmarks., Comment: Accepted by BMVC 2021

In real-world practice, medical images acquired in different phases possess complementary information, {\em e.g.}, radiologists often refer to both arterial and venous scans in order to make the diagnosis. However, in medical image analysis, fusing prediction from two phases is often difficult, because (i) there is a domain gap between two phases, and (ii) the semantic labels are not pixel-wise corresponded even for images scanned from the same patient. This paper studies organ segmentation in two-phase CT scans. We propose Phase Collaborative Network (PCN), an end-to-end framework that contains both generative and discriminative modules. PCN can be mathematically explained to formulate phase-to-phase and data-to-label relations jointly. Experiments are performed on a two-phase CT dataset, on which PCN outperforms the baselines working with one-phase data by a large margin, and we empirically verify that the gain comes from inter-phase collaboration. Besides, PCN transfers well to two public single-phase datasets, demonstrating its potential applications.

Human-Object Interaction (HOI) Detection is an important problem to understand how humans interact with objects. In this paper, we explore Interactiveness Knowledge which indicates whether human and object interact with each other or not. We found that interactiveness knowledge can be learned across HOI datasets, regardless of HOI category settings. Our core idea is to exploit an Interactiveness Network to learn the general interactiveness knowledge from multiple HOI datasets and perform Non-Interaction Suppression before HOI classification in inference. On account of the generalization of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results. We extensively evaluate the proposed method on HICO-DET and V-COCO datasets. Our framework outperforms state-of-the-art HOI detection results by a great margin, verifying its efficacy and flexibility. Code is available at https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network., Comment: CVPR2019

We investigate longitudinal near-field coupling between acoustic resonators grafted onto a waveguide. Experiments are performed in the audible range with a simple acoustic system composed of a finite aperiodic sequence of air resonators. Transmission typically shows a zero around a resonance frequency of a single resonator, as is well known. When two identical resonators are brought in close proximity, however, we observe that longitudinal near-field coupling strongly influences the acoustic transmission. When the separation between resonators is increased so that they can be considered in the far field of one another, we further observe the appearance of Fano-like transmission profiles. We explain this observation by the formation of locally resonant Fabry-Perot interferometers from every pair of resonators. All experimental results are compared to three-dimensional finite element analysis of the acoustic system., Comment: 9 pages, 7 figures

In a multi-wire proportional chamber detector(MWPC), the anode and signal wires must maintain suitable tensions, which is very important for the detector's stable and perfect performance. As a result, wire tension control and measurement is essential in MWPC's construction. The thermal neutron detector of multi-functional reflectometer at China Spallation Neutron Source is designed using a high pressure $^{3}$He MWPC detector, and in the construction of the detector, we developed a wire tension measurement system. This system is accurate, portable and time-saving. With it, the wires' tension on a anode wire plane has been tested, the measurement results show that the wire tension control techniques used in detector manufacture is reliable., Comment: 6 pages,12 figures