“…Readers can refer to [202] for more works about it. Security [203] and privacy-perserving problem [204] are also important in image reconstruction, especially in medical image reconstruction tasks. However, they have not been studied deeply.…”
Section: Discussion and Future Directionsmentioning
Compressed sensing (CS) and its medical applications are active areas of research. In this paper, we review recent works using deep learning method to solve CS problem for images or medical imaging reconstruction including computed tomography (CT), magnetic resonance imaging (MRI) and positron-emission tomography (PET). We propose a novel framework to unify traditional iterative algorithms and deep learning approaches. In short, we define two projection operators toward image prior and data consistency, respectively, and any reconstruction algorithm can be decomposed to the two parts. Though deep learning methods can be divided into several categories, they all satisfies the framework. We built the relationship between different reconstruction methods of deep learning, and connect them to traditional methods through the proposed framework. It also indicates that the key to solve CS problem and its medical applications is how to depict the image prior. Based on the framework, we analyze the current deep learning methods and point out some important directions of research in the future.
“…Readers can refer to [202] for more works about it. Security [203] and privacy-perserving problem [204] are also important in image reconstruction, especially in medical image reconstruction tasks. However, they have not been studied deeply.…”
Section: Discussion and Future Directionsmentioning
Compressed sensing (CS) and its medical applications are active areas of research. In this paper, we review recent works using deep learning method to solve CS problem for images or medical imaging reconstruction including computed tomography (CT), magnetic resonance imaging (MRI) and positron-emission tomography (PET). We propose a novel framework to unify traditional iterative algorithms and deep learning approaches. In short, we define two projection operators toward image prior and data consistency, respectively, and any reconstruction algorithm can be decomposed to the two parts. Though deep learning methods can be divided into several categories, they all satisfies the framework. We built the relationship between different reconstruction methods of deep learning, and connect them to traditional methods through the proposed framework. It also indicates that the key to solve CS problem and its medical applications is how to depict the image prior. Based on the framework, we analyze the current deep learning methods and point out some important directions of research in the future.
“…WHT is used to extract directional features from each image block to assure the robustness of our proposed approach against geometrical attacks [37]. Then, LBP is used to extract the texture feature representation of image blocks that are robust to false positives and geometrical attacks [33]. Lastly, DWT is used to extract multiscale features from image blocks that represent the important features of each block at the different scales [41].…”
Section: Shares Construction Phasementioning
confidence: 99%
“…Kumar el al. [33] developed an approach using an optimization algorithm and visual cryptography to protect the authenticity and integrity of digital videos by embedding robust watermarks inside them.…”
The usage of images in different fields has increased dramatically, especially in medical image analysis and social media. Many risks can threaten the integrity and confidentiality of digital images transmitted through the internet. As such, the preservation of the contents of these images is of the utmost importance for sensitive healthcare systems. In this paper, the researchers propose a block-based approach to protect the integrity of digital images by detecting and localizing forgeries. It employs a visual cryptography-based watermarking approach to provide the capabilities of forgery detection and localization. In this watermarking scheme, features and key and secret shares are generated. The feature share is constructed by extracting features from equal-sized blocks of the image by using a Walsh transform, a local binary pattern and a discrete wavelet transform. Then, the key share is generated randomly from each image block, and the secret share is constructed by applying the XOR operation between the watermark, feature share and key share. The CASIA V 1.0 and SIPI datasets were used to check the performance and robustness of the proposed method. The experimental results from these datasets revealed that the percentages of the precision, recall and F1 score classification indicators were approximately 97% for these indicators, while the percentages of the TAF and NC image quality indicators were approximately 97% and 96% after applying several known image processing and geometric attacks. Furthermore, the comparative experimental results with the state-of-art approaches proved the robustness and noticeable improvement in the proposed approach for the detection and localization of image forgeries in terms of classification and quality measures.
“…The pretreated data were provided from medical imaging professionals; to preserve patient privacy [14,15], all the identity information was removed. As shown in Figure 1, the image slices have been ordered from head to hip in spatial relation.…”
Image registration is an important research topic in medical image-guided therapy, which is dedicated to registering the high-dose imaging sequences with low-dose/faster means. Registering computer tomography (CT) scanning sequences with cone beam computer tomography (CBCT) scanning sequences is a typical application and has been widely used in CBCT-guided radiotherapy. The main problem is the difference in image clarity of these two image sequences. To solve this problem, for the single projection image sequence matching tasks encountered in medical practice, a novel local quality based curved section encoding strategy is proposed in this paper, which is called the high-quality curved section (HQCS). As an optimized cross-section regularly encoded along the sequence of image, this curved section could be used in order to solve the matching problem. Referencing the independent ground truth provided by medical image physicians, with an experiment combined with the four most widely used indicators used on image registration, matching performance of HQCS on CT/CBCT datasets was tested with varying clarity. Experimental results show that the proposed HQCS can register the CT/CBCT effectively and outperforms the commonly used methods. Specifically, the proposed HQCS has low time complexity and higher scalability, which indicates that the application enhanced the task of diagnosis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.