Search

Due to the high sensitivity of diffusion tensor imaging (DTI) to physiological motion, clinical DTI scans often suffer a significant amount of artifacts. Tensor-fitting-based, post-processing outlier rejection is often used to reduce the influence of motion artifacts. Although it is an effective approach, when there are multiple corrupted data, this method may no longer correctly identify and reject the corrupted data. In this paper, we introduce a new criterion called "corrected Inter-Slice Intensity Discontinuity" (cISID) to detect motion-induced artifacts. We compared the performance of algorithms using cISID and other existing methods with regard to artifact detection. The experimental results show that the integration of cISID into fitting-based methods significantly improves the retrospective detection performance at post-processing analysis. The performance of the cISID criterion, if used alone, was inferior to the fitting-based methods, but cISID could effectively identify severely corrupted images with a rapid calculation time. In the second part of this paper, an outlier rejection scheme was implemented on a scanner for real-time monitoring of image quality and reacquisition of the corrupted data. The real-time monitoring, based on cISID and followed by post-processing, fitting-based outlier rejection, could provide a robust environment for routine DTI studies.

Convolutional Neural Network’s (CNN’s) performance disparity on clean and corrupted datasets has recently come under scrutiny. In this work, we analyse common corruptions in the frequency domain, i.e., High Frequency corruptions (HFc, e.g., noise) and Low Frequency corruptions (LFc, e.g., blur). Although a simple solution to HFc is low-pass filtering, ReLU – a widely used Activation Function (AF), does not have any filtering mechanism. In this work, we instill low-pass filtering into the AF (LP-ReLU) to improve robustness against HFc. To deal with LFc, we complement LP-ReLU with Discrete Cosine Transform based augmentation. LP-ReLU, coupled with DCT augmentation, enables a deep network to tackle the entire spectrum of corruption. We use CIFAR-10-C and Tiny ImageNet-C for evaluation and demonstrate improvements of 5% and 7.3% in accuracy respectively, compared to the State-Of-The-Art (SOTA). We further evaluate our method’s stability on a variety of perturbations in CIFAR-10-P and Tiny ImageNet-P, achieving new SOTA in these experiments as well. To further strengthen our understanding regarding CNN’s lack of robustness, a decision space visualisation process is proposed and presented in this work.

Medical visual question answering (VQA) bridges the gap between visual information and clinical decision-making, enabling doctors to extract understanding from clinical images and videos. In particular, surgical VQA can enhance the interpretation of surgical data, aiding in accurate diagnoses, effective education, and clinical interventions. However, the inability of VQA models to visually indicate the regions of interest corresponding to the given questions results in incomplete comprehension of the surgical scene. To tackle this, we propose the surgical visual question localized-answering (VQLA) for precise and context-aware responses to specific queries regarding surgical images. Furthermore, to address the strong demand for safety in surgical scenarios and potential corruptions in image acquisition and transmission, we propose a novel approach called Calibrated Co-Attention Gated Vision-Language (C 2 G-ViL) embedding to integrate and align multimodal information effectively. Additionally, we leverage the adversarial sample-based contrastive learning strategy to boost our performance and robustness. We also extend our EndoVis-18-VQLA and EndoVis-17-VQLA datasets to broaden the scope and application of our data. Extensive experiments on the aforementioned datasets demonstrate the remarkable performance and robustness of our solution. Our solution can effectively combat real-world image corruption. Thus, our proposed approach can serve as an effective tool for assisting surgical education, patient care, and enhancing surgical outcomes. Our code and data will be released at https://github.com/longbai1006/Surgical-VQLAPlus. • We propose a Surgical-VQLA++ framework to connect answering and localization. • We incorporate feature calibration and adversarial contrastive training techniques. • We expand our datasets by including additional queries related to surgical tools. • Extensive experiments prove the effectiveness and robustness of our solution. [ABSTRACT FROM AUTHOR]

Background: Simulated computed tomography (CT) images allow for knowledge of the underlying ground truth and for easy variation of imaging conditions, making them ideal for testing and optimization of new applications or algorithms. However, simulating all processes that affect CT images can result in simulations that are demanding in terms of processing time and computer memory. Therefore, it is of interest to determine how much the simulation can be simplified while still achieving realistic results. Purpose: To develop a scanner‐specific CT simulation using physics‐based simulations for the position‐dependent effects and shift‐invariant image corruption methods for the detector effects. And to investigate the impact on image realism of introducing simplifications in the simulation process that lead to faster and less memory‐demanding simulations. Methods: To make the simulator realistic and scanner‐specific, the spatial resolution and noise characteristics, and the exposure‐to‐detector output relationship of a clinical CT system were determined. The simulator includes a finite focal spot size, raytracing of the digital phantom, gantry rotation during projection acquisition, and finite detector element size. Previously published spectral models were used to model the spectrum for the given tube voltage. The integrated energy at each element of the detector was calculated using the Beer–Lambert law. The resulting angular projections were subsequently corrupted by the detector modulation transfer function (MTF), and by addition of noise according to the noise power spectrum (NPS) and signal mean‐variance relationship, which were measured for different scanner settings. The simulated sinograms were reconstructed on the clinical CT system and compared to real CT images in terms of CT numbers, noise magnitude using the standard deviation, noise frequency content using the NPS, and spatial resolution using the MTF throughout the field of view (FOV). The CT numbers were validated using a multi‐energy CT phantom, the noise magnitude and frequency were validated with a water phantom, and the spatial resolution was validated with a tungsten wire. These metrics were compared at multiple scanner settings, and locations in the FOV. Once validated, the simulation was simplified by reducing the level of subsampling of the focal spot area, rotation and of detector pixel size, and the changes in MTFs were analyzed. Results: The average relative errors for spatial resolution within and across image slices, noise magnitude, and noise frequency content within and across slices were 3.4%, 3.3%, 4.9%, 3.9%, and 6.2%, respectively. The average absolute difference in CT numbers was 10.2 HU and the maximum was 22.5 HU. The simulation simplification showed that all subsampling can be avoided, except for angular, while the error in frequency at 10% MTF would be maximum 16.3%. Conclusion: The simulation of a scanner‐specific CT allows for the generation of realistic CT images by combining physics‐based simulations for the position‐dependent effects and image‐corruption methods for the shift‐invariant ones. Together with the available ground truth of the digital phantom, it results in a useful tool to perform quantitative analysis of reconstruction or post‐processing algorithms. Some simulation simplifications allow for reduced time and computer power requirements with minimal loss of realism. [ABSTRACT FROM AUTHOR]

Purpose – The purpose of this paper is to discuss the extent and impact of corruption on public trust and on the stability of the Colombian police. The effectiveness of public controls, civilian oversight, and overseeing bodies is evaluated to determine the degree of impunity and the level of independence from other agencies of control. Design/methodology/approach – The research in this study is based on data analyses of surveys, interviews, and an observational approach. This paper considers four general surveys, namely: Latinobarómetro, Iberobarómetro, Global Corruption Barometer, Corruption Perception Indexes, and World Values Survey. The observation consisted of accompanying Bogotá police department teams for two months during the evenings between 10 p.m. and 7 a.m. This study draws upon 20 interviews with police officers of all ranks. Additionally, an informal observation of police activities during the night was carried out to discover the occurrence of corruption, which was impossible to reveal by a more formal observation. Findings – Although corruption in the Colombian police force is presumably a generalized phenomenon, it is still one of the most appreciated agencies among Colombians. However, scandals have been cleverly mitigated by rhetoric and apparent purges and the setting-up of inoffensive mechanisms of control. Internal inspection and civilian oversight have been weakened – rendered ineffective by an increasingly powerful police leadership. Research limitations/implications – Since corruption is a concealed phenomenon, its analysis always causes problems. Police officers are reluctant to talk about the problem and there is an organizational denial of the phenomenon. Originality/value – The paucity of academic research on police forces in Latin America is still apparent and the field of study lacks a real degree of specialization. Similarly, there has been no empirical examination of issues pertaining to the study of the modern Colombian force. This paper thus attempts to compensate for the lack of empirical research on the Colombian police. It contributes to the overall literature on police corruption by explaining the organizational features of bribing and police corruption on the beat. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) imaging is critical in military and national defense applications. Spaceborne SAR systems operate in fixed orbits, making them vulnerable to the jamming effects of ground radar signals. This study quantitatively analyzed jamming effects based on actual interference cases observed in the currently operational satellite SAR. Subsequently, various jamming scenarios were designed for hostile satellite SAR systems. SAR jamming simulations were conducted based on the ground radar specifications derived from real jamming cases by considering the jamming-to-clutter ratio (JCR) as a key metric for evaluating the jamming performance. The SAR image corruption was quantitatively analyzed for various ground jammers, with the results verified by comparison with real SAR jamming cases. This study attempted to understand the principles of satellite SAR jamming and contribute to the development of defense strategies against adversarial space surveillance systems in the near future. [ABSTRACT FROM AUTHOR]

Despite recent advances in the accuracy of brain tumor segmentation, the results still suffer from low reliability and robustness. Uncertainty estimation is an efficient solution to this problem, as it provides a measure of confidence in the segmentation results. The current uncertainty estimation methods based on quantile regression, Bayesian neural network, ensemble, and Monte Carlo dropout are limited by their high computational cost and inconsistency. In order to overcome these challenges, Evidential Deep Learning (EDL) was developed in recent work but primarily for natural image classification and showed inferior segmentation results. In this paper, we proposed a region-based EDL segmentation framework that can generate reliable uncertainty maps and accurate segmentation results, which is robust to noise and image corruption. We used the Theory of Evidence to interpret the output of a neural network as evidence values gathered from input features. Following Subjective Logic, evidence was parameterized as a Dirichlet distribution, and predicted probabilities were treated as subjective opinions. To evaluate the performance of our model on segmentation and uncertainty estimation, we conducted quantitative and qualitative experiments on the BraTS 2020 dataset. The results demonstrated the top performance of the proposed method in quantifying segmentation uncertainty and robustly segmenting tumors. Furthermore, our proposed new framework maintained the advantages of low computational cost and easy implementation and showed the potential for clinical application. [ABSTRACT FROM AUTHOR]