A Deep Learning Reconstruction Framework for Differential Phase-Contrast Computed Tomography With Incomplete Data
36
Citation
65
Reference
10
Related Paper
Citation Trend
Abstract:
Differential phase-contrast computed tomography (DPC-CT) is a powerful analysis tool for soft-tissue and low-atomic-number samples. Limited by the implementation conditions, DPC-CT with incomplete projections happens quite often. Conventional reconstruction algorithms face difficulty when given incomplete data. They usually involve complicated parameter selection operations, which are also sensitive to noise and are time-consuming. In this paper, we report a new deep learning reconstruction framework for incomplete data DPC-CT. It involves the tight coupling of the deep learning neural network and DPC-CT reconstruction algorithm in the domain of DPC projection sinograms. The estimated result is not an artifact caused by the incomplete data, but a complete phase-contrast projection sinogram. After training, this framework is determined and can be used to reconstruct the final DPC-CT images for a given incomplete projection sinogram. Taking the sparse-view, limited-view and missing-view DPC-CT as examples, this framework is validated and demonstrated with synthetic and experimental data sets. Compared with other methods, our framework can achieve the best imaging quality at a faster speed and with fewer parameters. This work supports the application of the state-of-the-art deep learning theory in the field of DPC-CT.Cite
Citations (1)
The Intel Collaborative Research Institute for Computational Intelligence (ICRI-CI) has been heavily supporting Machine Learning and Deep Learning research from its foundation in 2012. We have asked six leading ICRI-CI Deep Learning researchers to address the challenge of Why & When Deep Learning works, with the goal of looking inside Deep Learning, providing insights on how deep networks function, and uncovering key observations on their expressiveness, limitations, and potential. The output of this challenge resulted in five papers that address different facets of deep learning. These different facets include a high-level understating of why and when deep networks work (and do not work), the impact of geometry on the expressiveness of deep networks, and making deep networks interpretable.
Foundation (evidence)
Deep time
Cite
Citations (1)
Hollingsworth recently showed a posttest contrast for ANOVA situations that, for equal N, had several favorable qualities; the contrast is maximized so that if the overall F test were significant, the contrast would also be significant. The coefficients are chosen such that , which is said to help interpret the resulting contrast. However, for unequal N, the contrast suggested by Hollingsworth fails to achieve status as a maximized contrast; thus the contrast is not insured to be significant when the overall F test is significant, requiring separate testing of the contrast.
Contrast effect
Cite
Citations (1)
We acquire the first experimental 3-D tomographic images with magnetic particle imaging (MPI) using projection reconstruction methodology, which is similar to algorithms employed in X-ray computed tomography. The primary advantage of projection reconstruction methods is an order of magnitude increase in signal-to-noise ratio (SNR) due to averaging. We first derive the point spread function, resolution, number of projections required, and the SNR gain in projection reconstruction MPI. We then design and construct the first scanner capable of gathering the necessary data for nonaliased projection reconstruction and experimentally verify our mathematical predictions. We demonstrate that filtered backprojection in MPI is experimentally feasible and illustrate the SNR and resolution improvements with projection reconstruction. Finally, we show that MPI is capable of producing three dimensional imaging volumes in both phantoms and postmortem mice.
Tomographic reconstruction
Magnetic Particle Imaging
Point spread function
Cite
Citations (77)
For these years,besides the contrast of the two language structures,linguists also have made contrast research for the two kinds of cultures.From language contrast to culture contrast, it shows the development of contrast has entered a new stage.It is not difficult to indicate the diffrence between things,but to indicate why it is different is not easy.That is just the aim of contrast research.
Cite
Citations (0)
We report psychophysical evidence for a categorical dichotomy in the perception of contrast. Observers were required to rate the contrast of sinusoidal gratings (2.3 c/d) with contrast varying over a given range relative to two standards. One standard was designated "high" contrast and the other was designated "low." There was a boundary effect: contrast judgment depended upon whether the tested ranges included 10-15% contrast and discrimination was sharpest at the boundary between 10 and 15% contrast. These results are consistent with the existence of two systems underlying perceived contrast; one primarily sensitive below 10%, and the other primarily sensitive above 15% contrast.
High contrast
Categorical variable
Contrast effect
Cite
Citations (10)
Abstract: Deep fake is a rapidly growing concern in society, and it has become a significant challenge to detect such manipulated media. Deep fake detection involves identifying whether a media file is authentic or generated using deep learning algorithms. In this project, we propose a deep learning-based approach for detecting deep fakes in videos. We use the Deep fake Detection Challenge dataset, which consists of real and Deep fake videos, to train and evaluate our deep learning model. We employ a Convolutional Neural Network (CNN) architecture for our implementation, which has shown great potential in previous studies. We pre-process the dataset using several techniques such as resizing, normalization, and data augmentation to enhance the quality of the input data. Our proposed model achieves high detection accuracy of 97.5% on the Deep fake Detection Challenge dataset, demonstrating the effectiveness of the proposed approach for deep fake detection. Our approach has the potential to be used in real-world scenarios to detect deep fakes, helping to mitigate the risks posed by deep fakes to individuals and society. The proposed methodology can also be extended to detect in other types of media, such as images and audio, providing a comprehensive solution for deep fake detection.
Deep Neural Networks
Normalization
Cite
Citations (2)
Whether contrast adaptation may enhance contrast discrimination is a question that has remained largely unresolved because of conflicting empirical evidence. Greenlee and Heitger (1988), for example, reported that contrast discrimination may be enhanced after contrast adaptation, while Maattanen and Koenderink (1991) did not. This paper aimed to account for the different conclusions reached by these independent researchers by manipulations of key differences that exist between the two studies. It is shown that contrast discrimination may be enhanced after adaptation, but that these effects can vary markedly across subjects and test conditions. Enhancements in contrast discrimination are reported to be significant when adapting and testing at low levels of contrast, but just significant at higher levels of contrast. For high contrast signals; enhancements are shown to be independent of temporal frequency but dependent upon viewing conditions. Under binocular viewing conditions, enhancements in contrast discrimination thresholds are shown to be significantly higher than under monocular viewing conditions. It is suggested that the different conclusions reached by Greenlee and Heitger and by Maattanen and Koenderink may be explained by their respective differences in viewing conditions. The former study used binocular, while the latter study used monocular viewing with an occluding eyepatch.
Monocular
High contrast
Contrast effect
Cite
Citations (48)
The aim of this paper is to rationalize the idea of constructing a contrast category as one of the semantic categories in Chinese Language,as well as to classify it from different perspectives.There are theoretical supports from cognitive psychology and linguistic that contrast as a semantic category in modern Chinese is the reflection of contrast as part of humankinds' cognitive mechanism.As a semantic category revises a certain relationship,contrast is characterized by highlighting difference.From different perspectives we can classify contrast category into different sub-categories as follows:marked contrast and unmarked contrast,antithetical contrast and non-antithetical contrast,two-thing contrast and two-profile contrast,linear contrast and non-linear contrast,overt contrast and implied contrast,unitary contrast and multiple contrast and etc.
Cite
Citations (0)
Floral design에서 contrast는 작품의 개성이 뚜렷해지고 시각적 효과를 강하게 나타낼 수 있다. 본고에서는 Floral design의 예술적 조형성과 독창성을 발전시킬 수 있는 디자인원리로써 contrast를 논제로 삼아 이론적 근거를 제시하고자 하였다. Floral design에서 나타난 contrast의 표현양상들을 형태의 contrast, 면적의 contrast, 색채의 contrast 그리고 질감의 contrast로 분류하여 미적특성을 살펴보았다. Contrast의 표현 양상들을 살려봄으로써 contrast를 구체적으로 시각화하는 방안을 제시하고자 세계 유명 플로리스트들의 작품(10점) 속에 나타난 contrast와 본 연구자 개인전 및 데몬스트레이션 작품(10점)에서 contrast가 잘 표현된 작품들을 제시하여 contrast의 표현양상을 비교분석하였다. 형태의 contrast는 작품의 조형성을 중시하며 기하형태 또는 양감위주의 형태표현을 볼 수 있는 반면 본 연구자는 자연의 생태성을 고려한 자연형태 내지 유기형태 그리고 자연그대로의 선 흐름과 연결된 형태와 공간의 미를 표현하였다. 면적의 contrast는 소재의 grouping에 의한 면적 내지 소재를 다양한 기법으로 재구성한 면적으로 작품에 표현하는 반면 본 연구자는 소재 자체가 지닌 면적 또는 소재의 재구성에 의한 면적으로 contrast를 표현하였다. 질감의 contrast는 규칙적으로 붙이거나 다양한 basketry 기법에 의한 질감 표현 위주임에 반해 본 연구자는 자연소재가 지닌 자체질감 그대로를 표현하였다. Contrast의 표현에서 있어서 이상 열거한 상이점도 있으나 많은 작품에서 표현기법이나 작가의 조형 성향에 따라 공통점도 많이 볼 수 있었다. 색채의 contrast는 유명 플로리스트의 작품과 본 연구자의 작품에서 공통적인 부분을 많이 찾아 볼 수 있었다. Floral design의 원리 중 contrast가 시각적 독창성과 조형성을 유도할 수 있는 원리임을 밝혀 현대 Floral design 창작활동의 발전과 심층적 연구를 위한 방향을 제시하고자 한다.
Color contrast
High contrast
Contrast effect
Cite
Citations (0)