Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAn efficient pre-object collimator based on an x-ray lens
103
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
A multi-prism lens (MPL) is a refractive x-ray lens with one-dimensional focusing properties. If used as a pre-object collimator in a scanning system for medical x-ray imaging, it reduces the divergence of the radiation and improves on photon economy compared to a slit collimator. Potential advantages include shorter acquisition times, a reduced tube loading, or improved resolution. We present the first images acquired with an MPL in a prototype for a scanning mammography system. The lens showed a gain of flux of 1.32 compared to a slit collimator at equal resolution, or a gain in resolution of 1.31-1.44 at equal flux. We expect the gain of flux in a clinical set-up with an optimized MPL and a custom-made absorption filter to reach 1.67, or 1.45-1.54 gain in resolution.
rate research
Read More
In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection. Montage pre-training needs only the target detection dataset while taking only 1/4 computational resources compared to the widely adopted ImageNet pre-training.To build such an efficient paradigm, we reduce the potential redundancy by carefully extracting useful samples from the original images, assembling samples in a Montage manner as input, and using an ERF-adaptive dense classification strategy for model pre-training. These designs include not only a new input pattern to improve the spatial utilization but also a novel learning objective to expand the effective receptive field of the pretrained model. The efficiency and effectiveness of Montage pre-training are validated by extensive experiments on the MS-COCO dataset, where the results indicate that the models using Montage pre-training are able to achieve on-par or even better detection performances compared with the ImageNet pre-training.
The nuclides inhaled during nuclear accidents usually cause internal contamination of the lungs with low activity. Although a parallel-hole imaging system, which is widely used in medical gamma cameras, has a high resolution and good image quality, owing to its extremely low detection efficiency, it remains difficult to obtain images of inhaled lung contamination. In this study, the Monte Carlo method was used to study the internal lung contamination imaging using the MPA-MURA coded-aperture collimator. The imaging system consisted of an adult male lung model, with a mosaicked, pattern-centered, and anti-symmetric MURA coded-aperture collimator model and a CsI(Tl) detector model. The MLEM decoding algorithm was used to reconstruct the internal contamination image, and the complementary imaging method was used to reduce the number of artifacts. The full width at half maximum of the I-131 point source image reconstructed by the mosaicked, pattern-centered, and anti-symmetric Modified uniformly redundant array (MPA-MURA) coded-aperture imaging reached 2.51 mm, and the signal-to-noise ratio of the simplified respiratory tract source (I-131) image reconstructed through MPA-MURA coded-aperture imaging was 3.98 dB. Although the spatial resolution of MPA-MURA coded aperture imaging is not as good as that of parallel-hole imaging, the detection efficiency of PMA-MURA coded-aperture imaging is two orders of magnitude higher than that of parallel hole collimator imaging. Considering the low activity level of internal lung contamination caused by nuclear accidents, PMA-MURA coded-aperture imaging has significant potential for the development of lung contamination imaging.
Purpose: Using linear transformation of the data allows studying detectability of an imaging system on a large number of signals. An appropriate transformation will produce a set of signals with different contrast and different frequency contents. In this work both strategies are explored to present a task-based test for the detectability of an x-ray imaging system. Methods: Images of a new star-bar phantom are acquired with different entrance air KERMA and with different beam qualities. Then, after a wavelet packet is applied to both input and output of the system, conventional statistical decision theory is applied to determine detectability on the different images or nodes resulting from the transformation. A non-prewhitening matching filter is applied to the data in the spatial domain, and ROC analysis is carried out in each of the nodes. Results: AUC maps resulting from the analysis present the area under the ROC curve over the whole 2D frequency space for the different doses and beam qualities. Also, AUC curves, obtained by radially averaging the AUC maps allows comparing detectability of the different techniques as a function of the frequency in one only figure. The results obtained show differences between images acquired with different doses for each of the beam qualities analyzed. Conclusions: Combining a star-bar as test object, a wavelet packet as linear transformation, and ROC analysis results in an appropriate task-based test for detectability performance of an imaging system. The test presented in this work allows quantification of system detectability as a function of the 2D frequency interval of the signal to detect. It also allows calculation of detectability differences between different acquisition techniques and beam qualities.
Deep neural networks based object detection models have revolutionized computer vision and fueled the development of a wide range of visual recognition applications. However, recent studies have revealed that deep object detectors can be compromised under adversarial attacks, causing a victim detector to detect no object, fake objects, or mislabeled objects. With object detection being used pervasively in many security-critical applications, such as autonomous vehicles and smart cities, we argue that a holistic approach for an in-depth understanding of adversarial attacks and vulnerabilities of deep object detection systems is of utmost importance for the research community to develop robust defense mechanisms. This paper presents a framework for analyzing and evaluating vulnerabilities of the state-of-the-art object detectors under an adversarial lens, aiming to analyze and demystify the attack strategies, adverse effects, and costs, as well as the cross-model and cross-resolution transferability of attacks. Using a set of quantitative metrics, extensive experiments are performed on six representative deep object detectors from three popular families (YOLOv3, SSD, and Faster R-CNN) with two benchmark datasets (PASCAL VOC and MS COCO). We demonstrate that the proposed framework can serve as a methodical benchmark for analyzing adversarial behaviors and risks in real-time object detection systems. We conjecture that this framework can also serve as a tool to assess the security risks and the adversarial robustness of deep object detectors to be deployed in real-world applications.
In this paper, we propose a binarized neural network learning method called BiDet for efficient object detection. Conventional network binarization methods directly quantize the weights and activations in one-stage or two-stage detectors with constrained representational capacity, so that the information redundancy in the networks causes numerous false positives and degrades the performance significantly. On the contrary, our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal, through which the detection precision is enhanced with alleviated false positives. Specifically, we generalize the information bottleneck (IB) principle to object detection, where the amount of information in the high-level feature maps is constrained and the mutual information between the feature maps and object detection is maximized. Meanwhile, we learn sparse object priors so that the posteriors are concentrated on informative detection prediction with false positive elimination. Extensive experiments on the PASCAL VOC and COCO datasets show that our method outperforms the state-of-the-art binary neural networks by a sizable margin.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
