Search

This study aims to investigate user perceptions of software tools to conduct title and abstract screening and full-text review in systematic reviews by administering a survey to researchers conducting systematic reviews. With technological development, in the past few years, dozens of software tools were developed to assist the search and screening stages in systematic reviews. Usage of such new tools is starting to increase in the educational field, yet little is known about the actual pattens of preferred tools and reasons behind these choices and preferences. This survey study aims to investigate educational researchers’ opinions on software tools to conduct title and abstract screening and full-text review in systematic reviews. A previous study (Pellegrini & Marsili, 2021). identified the software tools used in educational systematic reviews and assessed the quality and properties through a feature analysis. The purpose of the present study is to determine the user perceptions of the identified tools, such as Abstrackr, Covidence, ASReview, RevMan, Rayyan, EPPI-Reviewer, DistillerSR, Paperfetcher, CitationChaser. This survey helps us understand tool usage in systematic reviews because this section is usually not well-described in published studies (Zhang & Neitzel, 2022). Knowing the current tool use status in the field of education would lay the basis for future research comparing features of different tools. The research results could also lead to more and better systematic reviews.

Deploying deep learning (DL) on mobile devices has been a notable trend in recent years. To support fast inference of on-device DL, DL libraries play a critical role as algorithms and hardware do. Unfortunately, no prior work ever dives deep into the ecosystem of modern DL libs and provides quantitative results on their performance. In this paper, we first build a comprehensive benchmark that includes 6 representative DL libs and 15 diversified DL models. We then perform extensive experiments on 10 mobile devices, which help reveal a complete landscape of the current mobile DL libs ecosystem. For example, we find that the best-performing DL lib is severely fragmented across different models and hardware, and the gap between those DL libs can be rather huge. In fact, the impacts of DL libs can overwhelm the optimizations from algorithms or hardware, e.g., model quantization and GPU/DSP-based heterogeneous computing. Finally, atop the observations, we summarize practical implications to different roles in the DL lib ecosystem.

Handsearch is an important technique that contributes to thorough literature search in systematic reviews. Traditional handsearch requires reviewers to systematically browse through each issue of a curated list of field-specific journals and conference proceedings to find articles relevant to their review. This manual process is not only time-consuming, laborious, costly, and error-prone, but it also lacks replicability and cross-checking mechanisms. In an attempt to solve these problems, this paper presents a free and open-source Python package and an accompanying web-app, Paperfetcher, to automate handsearch for systematic reviews. With Paperfetcher's assistance, researchers can retrieve articles from designated journals within a specified time frame with just a few clicks. In addition to handsearch, this tool also incorporates snowballing in both directions. Paperfetcher allows researchers to download retrieved studies as a list of DOIs or as an RIS database to facilitate seamless import into citation management and systematic review screening software. To our knowledge, Paperfetcher is the first tool that automates handsearch with high usability and a multi-disciplinary focus.

Recently, the use of deep learning techniques to reconstruct computed tomography (CT) images has become a hot research topic, including sinogram domain methods, image domain methods and sinogram domain to image domain methods. All these methods have achieved favorable results. In this article, we have studied the important functions of fully connected layers used in the sinogram domain to image domain approach. First, we present a simple domain mapping neural networks. Then, we analyze the role of the fully connected layers of these networks and visually analyze the weights of the fully connected layers. Finally, by visualizing the weights of the fully connected layer, we found that the main role of the fully connected layer is to implement the back projection function in CT reconstruction. This finding has important implications for the use of deep learning techniques to reconstruct computed tomography (CT) images. For example, since fully connected layer weights need to consume huge memory resources, the back-projection function can be implemented by using analytical algorithms to avoid resource occupation, which can be embedded in the entire network.

In dental computed tomography (CT) scanning, high-quality images are crucial for oral disease diagnosis and treatment. However, many artifacts, such as metal artifacts, downsampling artifacts and motion artifacts, can degrade the image quality in practice. The main purpose of this article is to reduce motion artifacts. Motion artifacts are caused by the movement of patients during data acquisition during the dental CT scanning process. To remove motion artifacts, the goal of this study was to develop a dental CT motion artifact-correction algorithm based on a deep learning approach. We used dental CT data with motion artifacts reconstructed by conventional filtered back-projection (FBP) as inputs to a deep neural network and used the corresponding high-quality CT data as labeled data during training. We proposed training a generative adversarial network (GAN) with Wasserstein distance and mean squared error (MSE) loss to remove motion artifacts and to obtain high-quality CT dental images. In our network, to improve the generator structure, the generator used a cascaded CNN-Net style network with residual blocks. To the best of our knowledge, this work describes the first deep learning architecture method used with a commercial cone-beam dental CT scanner. We compared the performance of a general GAN and the m-WGAN. The experimental results confirmed that the proposed algorithm effectively removes motion artifacts from dental CT scans. The proposed m-WGAN method resulted in a higher peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) and a lower root-mean-squared error (RMSE) than the general GAN method.

Breast cancer is the most common type of cancer in women. Mammography has been a good method of performing early screening to detect breast cancer. An alternative technique, digital breast tomosynthesis (DBT), which is based on limited-angle tomography, solves the overlapping problem associated with mammography but also has limitations. To decrease the limitations of motion artifacts and poor reconstructed image quality that are imposed by the use of a rotating anode with a single X-ray source in conventional DBT, we have developed and demonstrated a stationary DBT (s-DBT) system that uses a carbon nanotube (CNT) X-ray source array. This arc array consists of 9 X-ray-generating focal spots distributed across a 38.7° angle. Compared with a traditional thermal emission X-ray source, a CNT X-ray source has several desirable attributes, such as miniaturization, fast response time, efficient focusing and improved control of emitted electrons; as a result, the tested system can acquire projection images by electronically switching individual X-ray sources on and off conveniently without mechanical motion of either the X-ray source or the detector, leading to improved spatial resolution of acquired images and reduced radiation doses. The tested system was developed in an attempt to find a feasible method to avoid adverse effects and improve image quality relative to conventional DBT systems, and the results reconstructed using a modified form of FDK algorithm indicate the achievement of this objective.