NeuroBridge: a prototype platform for discovery of the long-tail neuroimaging data.

Introduction: Open science initiatives have enabled sharing of large amounts of already collected data. However, significant gaps remain regarding how to find appropriate data, including underutilized data that exist in the long tail of science. We demonstrate the NeuroBridge prototype and its ability to search PubMed Central full-text papers for information relevant to neuroimaging data collected from schizophrenia and addiction studies. Methods: The NeuroBridge architecture contained the following components: (1) Extensible ontology for modeling study metadata: subject population, imaging techniques, and relevant behavioral, cognitive, or clinical data. Details are described in the companion paper in this special issue; (2) A natural-language based document processor that leveraged pre-trained deep-learning models on a small-sample document corpus to establish efficient representations for each article as a collection of machine-recognized ontological terms; (3) Integrated search using ontology-driven similarity to query PubMed Central and NeuroQuery, which provides fMRI activation maps along with PubMed source articles. Results: The NeuroBridge prototype contains a corpus of 356 papers from 2018 to 2021 describing schizophrenia and addiction neuroimaging studies, of which 186 were annotated with the NeuroBridge ontology. The search portal on the NeuroBridge website https://neurobridges.org/ provides an interactive Query Builder, where the user builds queries by selecting NeuroBridge ontology terms to preserve the ontology tree structure. For each return entry, links to the PubMed abstract as well as to the PMC full-text article, if available, are presented. For each of the returned articles, we provide a list of clinical assessments described in the Section "Methods" of the article. Articles returned from NeuroQuery based on the same search are also presented. Conclusion: The NeuroBridge prototype combines ontology-based search with natural-language text-mining approaches to demonstrate that papers relevant to a user's research question can be identified. The NeuroBridge prototype takes a first step toward identifying potential neuroimaging data described in full-text papers. Toward the overall goal of discovering "enough data of the right kind," ongoing work includes validating the document processor with a larger corpus, extending the ontology to include detailed imaging data, and extracting information regarding data availability from the returned publications and incorporating XNAT-based neuroimaging databases to enhance data accessibility.

Co-Clinical Imaging Metadata Information (CIMI) for Cancer Research to Promote Open Science, Standardization, and Reproducibility in Preclinical Imaging.

Preclinical imaging is a critical component in translational research with significant complexities in workflow and site differences in deployment. Importantly, the National Cancer Institute's (NCI) precision medicine initiative emphasizes the use of translational co-clinical oncology models to address the biological and molecular bases of cancer prevention and treatment. The use of oncology models, such as patient-derived tumor xenografts (PDX) and genetically engineered mouse models (GEMMs), has ushered in an era of co-clinical trials by which preclinical studies can inform clinical trials and protocols, thus bridging the translational divide in cancer research. Similarly, preclinical imaging fills a translational gap as an enabling technology for translational imaging research. Unlike clinical imaging, where equipment manufacturers strive to meet standards in practice at clinical sites, standards are neither fully developed nor implemented in preclinical imaging. This fundamentally limits the collection and reporting of metadata to qualify preclinical imaging studies, thereby hindering open science and impacting the reproducibility of co-clinical imaging research. To begin to address these issues, the NCI co-clinical imaging research program (CIRP) conducted a survey to identify metadata requirements for reproducible quantitative co-clinical imaging. The enclosed consensus-based report summarizes co-clinical imaging metadata information (CIMI) to support quantitative co-clinical imaging research with broad implications for capturing co-clinical data, enabling interoperability and data sharing, as well as potentially leading to updates to the preclinical Digital Imaging and Communications in Medicine (DICOM) standard.

Enabling Scientific Reproducibility through FAIR Data Management: An ontology-driven deep learning approach in the NeuroBridge Project.

Scientific reproducibility that effectively leverages existing study data is critical to the advancement of research in many disciplines including neuroscience, which uses imaging and electrophysiology modalities as primary endpoints or key dependency in studies. We are developing an integrated search platform called NeuroBridge to enable researchers to search for relevant study datasets that can be used to test a hypothesis or replicate a published finding without having to perform a difficult search from scratch, including contacting individual study authors and locating the site to download the data. In this paper, we describe the development of a metadata ontology based on the World Wide Web Consortium (W3C) PROV specifications to create a corpus of semantically annotated published papers. This annotated corpus was used in a deep learning model to support automated identification of candidate datasets related to neurocognitive assessment of subjects with drug abuse or schizophrenia using neuroimaging. We built on our previous work in the Provenance for Clinical and Health Research (ProvCaRe) project to model metadata information in the NeuroBridge ontology and used this ontology to annotate 51 articles using a Web-based tool called Inception. The Bidirectional Encoder Representations from Transformers (BERT) neural network model, which was trained using the annotated corpus, is used to classify and rank papers relevant to five research hypotheses and the results were evaluated independently by three users for accuracy and recall. Our combined use of the NeuroBridge ontology together with the deep learning model outperforms the existing PubMed Central (PMC) search engine and manifests considerable trainability and transparency compared with typical free-text search. An initial version of the NeuroBridge portal is available at: https://neurobridges.org/.

A Multisite Study of a Breast Density Deep Learning Model for Full-Field Digital Mammography and Synthetic Mammography.

PURPOSE: To develop a Breast Imaging Reporting and Data System (BI-RADS) breast density deep learning (DL) model in a multisite setting for synthetic two-dimensional mammographic (SM) images derived from digital breast tomosynthesis examinations by using full-field digital mammographic (FFDM) images and limited SM data. MATERIALS AND METHODS: A DL model was trained to predict BI-RADS breast density by using FFDM images acquired from 2008 to 2017 (site 1: 57 492 patients, 187 627 examinations, 750 752 images) for this retrospective study. The FFDM model was evaluated by using SM datasets from two institutions (site 1: 3842 patients, 3866 examinations, 14 472 images, acquired from 2016 to 2017; site 2: 7557 patients, 16 283 examinations, 63 973 images, 2015 to 2019). Each of the three datasets were then split into training, validation, and test. Adaptation methods were investigated to improve performance on the SM datasets, and the effect of dataset size on each adaptation method was considered. Statistical significance was assessed by using CIs, which were estimated by bootstrapping. RESULTS: Without adaptation, the model demonstrated substantial agreement with the original reporting radiologists for all three datasets (site 1 FFDM: linearly weighted Cohen κ [κw] = 0.75 [95% CI: 0.74, 0.76]; site 1 SM: κw = 0.71 [95% CI: 0.64, 0.78]; site 2 SM: κw = 0.72 [95% CI: 0.70, 0.75]). With adaptation, performance improved for site 2 (site 1: κw = 0.72 [95% CI: 0.66, 0.79], 0.71 vs 0.72, P = .80; site 2: κw = 0.79 [95% CI: 0.76, 0.81], 0.72 vs 0.79, P < .001) by using only 500 SM images from that site. CONCLUSION: A BI-RADS breast density DL model demonstrated strong performance on FFDM and SM images from two institutions without training on SM images and improved by using few SM images.Supplemental material is available for this article.Published under a CC BY 4.0 license.

Effect of adverse environmental conditions and protective clothing on temperature rise in a human body exposed to radiofrequency electromagnetic fields.

This study considers the computationally determined thermal profile of a finely discretized, heterogeneous human body model, simulating a radiofrequency electromagnetic field (RF-EMF) worker wearing protective clothing subject to RF-EMF exposure, and subject to various environmental conditions including high ambient temperature and high humidity, with full thermoregulatory mechanisms in place. How the human body responds in various scenarios was investigated, and the information was used to consider safety limits in current international RF-EMF safety guidelines and standards. It was found that different environmental conditions had minimal impact on the magnitude of the thermal response due to RF-EMF exposure, and that the current safety factor of 10 applied in international RF-EMF safety guidelines and standards for RF-EMF workers is generally conservative, though it is only narrowly so when workers are subjected to the most adverse environmental conditions. Bioelectromagnetics. 38:356-363, 2017. © 2017 Wiley Periodicals, Inc.

De-identification of Medical Images with Retention of Scientific Research Value.

Online public repositories for sharing research data allow investigators to validate existing research or perform secondary research without the expense of collecting new data. Patient data made publicly available through such repositories may constitute a breach of personally identifiable information if not properly de-identified. Imaging data are especially at risk because some intricacies of the Digital Imaging and Communications in Medicine (DICOM) format are not widely understood by researchers. If imaging data still containing protected health information (PHI) were released through a public repository, a number of different parties could be held liable, including the original researcher who collected and submitted the data, the original researcher's institution, and the organization managing the repository. To minimize these risks through proper de-identification of image data, one must understand what PHI exists and where that PHI resides, and one must have the tools to remove PHI without compromising the scientific integrity of the data. DICOM public elements are defined by the DICOM Standard. Modality vendors use private elements to encode acquisition parameters that are not yet defined by the DICOM Standard, or the vendor may not have updated an existing software product after DICOM defined new public elements. Because private elements are not standardized, a common de-identification practice is to delete all private elements, removing scientifically useful data as well as PHI. Researchers and publishers of imaging data can use the tools and process described in this article to de-identify DICOM images according to current best practices.

Modeling the effect of adverse environmental conditions and clothing on temperature rise in a human body exposed to radio frequency electromagnetic fields.

This study considers the computationally determined thermal profile of a fully clothed, finely discretized, heterogeneous human body model, subject to the maximum allowable reference level for a 1-GHz radio frequency electromagnetic field for a worker, and also subject to adverse environmental conditions, including high humidity and high ambient temperature. An initial observation is that while electromagnetic fields at the occupational safety limit will contribute an additional thermal load to the tissues, and subsequently, cause an elevated temperature, the magnitude of this effect is far outweighed by that due to the conditions including the ambient temperature, relative humidity, and the type of clothing worn. It is envisaged that the computational modeling approach outlined in this paper will be suitably modified in future studies to evaluate the thermal response of a body at elevated metabolic rates, and for different body shapes and sizes including children and pregnant women.

Collecting 48,000 CT exams for the lung screening study of the National Lung Screening Trial.

From 2002-2004, the Lung Screening Study (LSS) of the National Lung Screening Trial (NLST) enrolled 34,614 participants, aged 55-74 years, at increased risk for lung cancer due to heavy cigarette smoking. Participants, randomized to standard chest X-ray (CXR) or computed tomography (CT) arms at ten screening centers, received up to three imaging screens for lung cancer at annual intervals. Participant medical histories and radiologist-interpreted screening results were transmitted to the LSS coordinating center, while all images were retained at local screening centers. From 2005-2007, all CT exams were uniformly de-identified and delivered to a central repository, the CT Image Library (CTIL), on external hard drives (94%) or CD/DVD (5.9%), or over a secure Internet connection (0.1%). Of 48,723 CT screens performed, only 176 (0.3%) were unavailable (lost, corrupted, compressed) while 48,547 (99.7%) were delivered to the CTIL. Described here is the experience organizing, implementing, and adapting the clinical-trial workflow surrounding the image retrieval, de-identification, delivery, and archiving of available LSS-NLST CT exams for the CTIL, together with the quality assurance procedures associated with those collection tasks. This collection of CT exams, obtained in a specific, well-defined participant population under a common protocol at evenly spaced intervals, and its attending demographic and clinical information, are now available to lung-disease investigators and developers of computer-aided-diagnosis algorithms. The approach to large scale, multi-center trial CT image collection detailed here may serve as a useful model, while the experience reported should be valuable in the planning and execution of future equivalent endeavors.

Image quality assurance in the prostate, lung, colorectal, and ovarian cancer screening trial network of the National Lung Screening Trial.

The National Lung Screening Trial is evaluating the effectiveness of low-dose spiral CT and conventional chest X-ray as screening tests for persons who are at high risk for developing lung cancer. This multicenter trial requires quality assurance (QA) for the image quality and technical parameters of the scans. The electronic system described here helps manage the QA process. The system includes a workstation at each screening center that de-identifies the data, a DICOM storage service at the QA Coordinating Center, and Web-based systems for presenting images and QA evaluation forms to the QA radiologists. Quality assurance data are collated and analyzed by an independent statistical organization. We describe the design and implementation of this electronic QA system, emphasizing issues relating to data security and privacy, the various obstacles encountered in the installation of a common system at different participating screening centers, and the functional success of the system deployed.

Tools for managing image flow in the modality to clinical-image-review chain.

Web-based clinical-image viewing is commonplace in large medical centers. As demands for product and performance escalate, physicians, sold on the concept of "any image, anytime, anywhere," fret when image studies cannot be viewed in a time frame to which they are accustomed. Image delivery pathways in large medical centers are oftentimes complicated by multiple networks, multiple picture archiving and communication systems (PACS), and multiple groups responsible for image acquisition and delivery to multiple destinations. When studies are delayed, it may be difficult to rapidly pinpoint bottlenecks. Described here are the tools used to monitor likely failure points in our modality to clinical-image-viewing chain and tools for reporting volume and throughput trends. Though perhaps unique to our environment, we believe that tools of this type are essential for understanding and monitoring image-study flow, re-configuring resources to achieve better throughput, and planning for anticipated growth. Without such tools, quality clinical-image delivery may not be what it should.

Using the IHE scheduled work flow integration profile to drive modality efficiency.

The IHE (Integrating the Healthcare Enterprise) Scheduled Work Flow integration profile describes a communication and work flow environment that provides benefits for radiology departments who want to standardize system software. The IHE technical framework defines this environment by specifying the systems involved and the messages exchanged by those systems. The Modality Worklist is a key component of the Scheduled Work Flow integration profile that allows an operator at each modality in the department to retrieve a list of scheduled procedure steps to perform and to automate the process of entering the correct patient identification information in all the images created with the modality. The IHE technical framework defines two transactions used by the modality to tell the Image Manager and Order Filler what was performed and how many images were acquired: the Modality Procedure Step in Progress and Modality Procedure Step Completed. Users who specify the Scheduled Work Flow integration profile will benefit immediately by achieving a certain baseline of functionality. However, users will derive further benefits of increased operational efficiency through negotiation with the providers of software solutions. The integration profile defines features that are optional; users should evaluate these features and request those that are determined to be beneficial.

IHE: a model for driving adoption of standards.

The development of communication standards in healthcare is a major ongoing engineering effort. While there is little doubt that this effort has made possible significant advances in the performance of healthcare information and imaging systems, overall levels of systems interoperability have not improved as dramatically as one might reasonably expect and the cost of implementing effectively integrated systems remains high. The lag between the development of information standards and their implementation in real systems and institutions is a genuine problem in healthcare. This paper describes an ongoing initiative that attempts to bring together healthcare professionals and industry experts to coordinate the implementation of standards in ways that enhance operational efficiency and the quality of patient care.

Challenges in image acquisition and distribution for clinical image service.

We have developed a centralized application for acquiring images from multiple picture archiving and communication systems (PACS) and distributing images to a clinical image web server and other repositories. Our flexible strategy addresses a number of administrative challenges associated with delivering images into clinical, research, and test environments. DICOM images flow from PACSs and modalities to a UNIX-based "distributor" application, which relays them to one or more destinations. Image volume and transmission times were collected and analyzed. Three distributors receive an average of 34 gigabytes of image data per day. Images are sent concurrently to two web-based image servers, one used clinically by physicians and one used for testing. Transmission of certain classes of studies is prioritized for key physician groups. Delivery to research systems is also supported. Acquiring images from multi-vendor PACS for distribution to a web server for clinical image viewing is a challenging task. Centralizing the acquisition and distribution process reduces both the administrative effort and the impact on clinical operations associated with maintaining dynamic clinical, testing, and research environments.