Radiology Workflow Research Articles

Computational Radiology in Breast Cancer Screening and Diagnosis Using Artificial Intelligence.

Breast cancer screening has been shown to significantly reduce mortality in women. The increased utilization of screening examinations has led to growing demands for rapid and accurate diagnostic reporting. In modern breast imaging centers, full-field digital mammography (FFDM) has replaced traditional analog mammography, and this has opened new opportunities for developing computational frameworks to automate detection and diagnosis. Artificial intelligence (AI), and its subdomain of deep learning, is showing promising results and improvements on diagnostic accuracy, compared to previous computer-based methods, known as computer-aided detection and diagnosis.In this commentary, we review the current status of computational radiology, with a focus on deep neural networks used in breast cancer screening and diagnosis. Recent studies are developing a new generation of computer-aided detection and diagnosis systems, as well as leveraging AI-driven tools to efficiently interpret digital mammograms, and breast tomosynthesis imaging. The use of AI in computational radiology necessitates transparency and rigorous testing. However, the overall impact of AI to radiology workflows will potentially yield more efficient and standardized processes as well as improve the level of care to patients with high diagnostic accuracy.

Implementation of an Artificial Intelligence-Based Double Read System in Capturing Pulmonary Nodule Discrepancy in CT Studies

Studies show that up to 80% of all radiology errors are due to errors in perception. Early detection is critical for good outcomes in patients with primary lung cancer and lung metastasis. However, pulmonary nodules can be easily missed due to their small size. We prospectively applied a machine vision algorithm to CT studies containing lung parenchyma to detect pulmonary nodules, as well as a natural language processing algorithm to the text of the report to identify documentation of pulmonary nodules. Apparent discrepancies in perception – instances where a pulmonary nodule was not reported – were flagged for a secondary review by a radiologist. Four thousand and nine hundred studies were prospectively processed, of which 450 cases with potential discrepancies were detected. Preliminary manual analysis was performed to analyze the base error rate and to optimize thresholds for the machine vision and natural language processing algorithms, and 104 cases were flagged for final review. Of these 104 cases, 50 cases contained undocumented pulmonary nodules. Among these cases, 7 cases were classified as likely to be significant, where report addendums were done and the clinicians notified. We have successfully implemented an automated double read system to detect pulmonary nodule discrepancies, with minimal disruption to the radiology workflow and while keeping personal health information on-premises. This successful implementation demonstrates the viability of using an automated and secure radiology double-read system to improve patient safety in radiology workflows, either at a health system or an independent radiology practice.

AI in Radiology: Where are we today in Multiple Sclerosis Imaging?

MR imaging is an essential component in managing patients with Multiple sclerosis (MS). This holds true for the initial diagnosis as well as for assessing the clinical course of MS. In recent years, a growing number of computer tools were developed to analyze imaging data in MS. This review gives an overview of the most important applications with special emphasis on artificial intelligence (AI). Relevant studies were identified through a literature search in recognized databases, and through parsing the references in studies found this way. Literature published as of November 2019 was included with a special focus on recent studies from 2018 and 2019. There are a number of studies which focus on optimizing lesion visualization and lesion segmentation. Some of these studies accomplished these tasks with high accuracy, enabling a reproducible quantitative analysis of lesion loads. Some studies took a radiomics approach and aimed at predicting clinical endpoints such as the conversion from a clinically isolated syndrome to definite MS. Moreover, recent studies investigated synthetic imaging, i. e. imaging data that is not measured during an MR scan but generated by a computer algorithm to optimize the contrast between MS lesions and brain parenchyma. Computer-based image analysis and AI are hot topics in imaging MS. Some applications are ready for use in clinical routine. A major challenge for the future is to improve prediction of expected disease courses and thereby helping to find optimal treatment decisions on an individual level. With technical improvements, more questions arise about the integration of new tools into the radiological workflow. · Computer algorithms have a growing impact on analyzing MR imaging in MS.. · Artificial intelligence is more and more commonly employed in such computer tools.. · Applications include lesion segmentation, prediction of clinical parameters and image synthesizing.. · Eichinger P, Zimmer C, Wiestler B. AI in Radiology: Where are we today in Multiple Sclerosis Imaging?. Fortschr Röntgenstr 2020; 192: 847 - 853.

Prospective Analysis of Radiology Resource Utilization and Outcomes for Participation in Oncology Multidisciplinary Conferences

Rationale and ObjectivesRadiology participation is necessary in oncology multidisciplinary conferences (MDCs), but the resources required to do so are often unaccounted for. In this prospective study we provide an analysis of resource utilization as a function of outcomes for all MDCs covered by an entire radiology section and provide a time-based cost estimate.Materials and MethodsFollowing institutional review board approval, prospective data on all MDCs covered by abdominal radiologists at a single tertiary care academic center were obtained over nine weeks. A predefined questionnaire was used by a single observer who attended every imaging review and recorded the total time spent by the radiologists and several outcome measures. The total time recorded was used to provide a time-based cost estimate using a national salary survey.ResultsSix radiologists participated in a total of 57 MDCs, with 577 cases reviewed and discussed. 181 (31%) cases were performed at outside facilities requiring full reinterpretation. Clinically significant revisions to original reports were recorded in 107 (18.5%) cases. Radiologist input directly resulted in alteration of cancer staging in 65 (11%) patients and specific recommendations for follow-up diagnostic workup in 280 (48%) of cases. The mean total time devoted by the staff radiologist per week to MDCs was 18.7 hours/week, nearly a half of full-time effort, or 8% of total effort per radiologist. The total annual projected cost of radiology coverage for each weekly MDC was $26,920.ConclusionSection-wide radiologist participation in MDCs directly resulted in change in clinical management in nearly half of reviewed cases. This was achieved at a notable time cost, highlighting the need for efficient integration of radiology MDC participation into radiologist workflow and compensation models.

Vascular and Interventional Radiology Workflow Management During the COVID-19 Pandemic: Position Statement by the Saudi Interventional Radiology Society

Vascular and Interventional Radiology Workflow Management During the COVID-19 Pandemic: Position Statement by the Saudi Interventional Radiology Society

Radiological management of COVID-19: structure your diagnostic path to guarantee a safe path.

The current COVID-19 outbreak is requiring a tremendous effort not only regarding the diagnostic and therapeutic approach but also in terms of global management of the delivered care. Hospital administrations had to provide a prompt response to a rapidly evolving emergency characterized by the necessity of giving access to an enormous number of infected patients, guaranteeing appropriate care to patients in need of other types of treatment, and simultaneously preserving the well-being of healthcare providers. To optimize the diagnostic pathway during the current COVID-19 outbreak, the hospital administration of our tertiary center applied a highly structured framework assigning specific tasks to the different units composing the Department of Imaging. In particular, since the beginning of the pandemic, a mobile CT scanner in a truck was rented and became operative for all patients with a confirmed diagnosis of COVID-19 and another CT was assigned for all suspected cases. The success and efficacy of the management applied by our administration is demonstrated by the fact that during the outbreak, the radiological workflow was never interrupted. In fact, despite the national lockdown only a 29.3% decrease of CT scans occurred compared to the previous year. Moreover, none of the healthcare providers of the Department contracted the infection at work. Thus, according to the experience gained in our center, we recommend to all hospital administrations facing the COVID-19 outbreak to promptly adapt their resources, creating precise and safe pathways for their diagnostic units.

Mimicking the radiologists' workflow: Estimating pediatric hand bone age with stacked deep neural networks.

Pediatric endocrinologists regularly order radiographs of the left hand to estimate the degree of bone maturation in order to assess their patients for advanced or delayed growth, physical development, and to monitor consecutive therapeutic measures. The reading of such images is a labor-intensive task that requires a lot of experience and is normally performed by highly trained experts like pediatric radiologists. In this paper we build an automated system for pediatric bone age estimation that mimics and accelerates the workflow of the radiologist without breaking it. The complete system is based on two neural network based models: on the one hand a detector network, which identifies the ossification areas, on the other hand gender and region specific regression networks, which estimate the bone age from the detected areas. With a small annotated dataset an ossification area detection network can be trained, which is stable enough to work as part of a multi-stage approach. Furthermore, our system achieves competitive results on the RSNA Pediatric Bone Age Challenge test set with an average error of 4.56 months. In contrast to other approaches, especially purely encoder-based architectures, our two-stage approach provides self-explanatory results. By detecting and evaluating the individual ossification areas, thus simulating the workflow of the Tanner-Whitehouse procedure, the results are interpretable for a radiologist.

An Open-Source, Vender Agnostic Hardware and Software Pipeline for Integration of Artificial Intelligence in Radiology Workflow.

Although machine learning (ML) has made significant improvements in radiology, few algorithms have been integrated into clinical radiology workflow. Complex radiology IT environments and Picture Archiving and Communication System (PACS) pose unique challenges in creating a practical ML schema. However, clinical integration and testing are critical to ensuring the safety and accuracy of ML algorithms. This study aims to propose, develop, and demonstrate a simple, efficient, and understandable hardware and software system for integrating ML models into the standard radiology workflow and PACS that can serve as a framework for testing ML algorithms. A Digital Imaging and Communications in Medicine/Graphics Processing Unit (DICOM/GPU) server and software pipeline was established at a metropolitan county hospital intranet to demonstrate clinical integration of ML algorithms in radiology. A clinical ML integration schema, agnostic to the hospital IT system and specific ML models/frameworks, was implemented and tested with a breast density classification algorithm and prospectively evaluated for time delays using 100 digital 2D mammograms. An open-source clinical ML integration schema was successfully implemented and demonstrated. This schema allows for simple uploading of custom ML models. With the proposed setup, the ML pipeline took an average of 26.52s per second to process a batch of 100 studies. The most significant processing time delays were noted in model load and study stability times. The code is made available at " http://bit.ly/2Z121hX ". We demonstrated the feasibility to deploy and utilize ML models in radiology without disrupting existing radiology workflow.

Off-Site Radiology Workflow Changes Due to the Coronavirus Disease 2019 (COVID-19) Pandemic.

Medical practices have been taken by surprise by the coronavirus disease 2019 (COVID-19) pandemic as they rush and react daily to changing patient needs, government policies, and provider protection. Diagnostic radiology, as a largely non-patient-facing specialty, is unique in that it can be practiced away from where the patient is diagnosed and treated and that this off-site reading has been part of standard radiology practice since at least the late 1990s [1]. The two main ways off-site reading is conducted is through at-home reading by radiologists who are members of the practice (internal teleradiology) or by contracting corporate teleradiology practices (external teleradiology).

Automated abnormality classification of chest radiographs using deep convolutional neural networks

As one of the most ubiquitous diagnostic imaging tests in medical practice, chest radiography requires timely reporting of potential findings and diagnosis of diseases in the images. Automated, fast, and reliable detection of diseases based on chest radiography is a critical step in radiology workflow. In this work, we developed and evaluated various deep convolutional neural networks (CNN) for differentiating between normal and abnormal frontal chest radiographs, in order to help alert radiologists and clinicians of potential abnormal findings as a means of work list triaging and reporting prioritization. A CNN-based model achieved an AUC of 0.9824 ± 0.0043 (with an accuracy of 94.64 ± 0.45%, a sensitivity of 96.50 ± 0.36% and a specificity of 92.86 ± 0.48%) for normal versus abnormal chest radiograph classification. The CNN model obtained an AUC of 0.9804 ± 0.0032 (with an accuracy of 94.71 ± 0.32%, a sensitivity of 92.20 ± 0.34% and a specificity of 96.34 ± 0.31%) for normal versus lung opacity classification. Classification performance on the external dataset showed that the CNN model is likely to be highly generalizable, with an AUC of 0.9444 ± 0.0029. The CNN model pre-trained on cohorts of adult patients and fine-tuned on pediatric patients achieved an AUC of 0.9851 ± 0.0046 for normal versus pneumonia classification. Pretraining with natural images demonstrates benefit for a moderate-sized training image set of about 8500 images. The remarkable performance in diagnostic accuracy observed in this study shows that deep CNNs can accurately and effectively differentiate normal and abnormal chest radiographs, thereby providing potential benefits to radiology workflow and patient care.

Impact of the Closure of a Large, Urban Safety-Net Hospital on a Neighboring Academic Center: A Philadelphia Case Study.

We examined how the closure of 496-bed Hahnemann University Hospital (HUH), a level I trauma and stroke center and safety-net hospital in Philadelphia, Pennsylvania, impacted the emergency department (ED) and radiology workflow in our neighboring hospital (Thomas Jefferson University Hospital) located <1 mile away. On June 30, 2019, HUH announced its imminent closure and began diverting trauma patients, with its ED officially closing in mid-August. Trends of our ED and radiology workflow were analyzed using QlikView analytics software for 3 months before and after the closure. Data were compared to workflow from the same time period in2018. The average monthly number of patients presenting to our ED after the closure increased 20.2% with a corresponding 16% increase in ED imaging studies, primarily in radiographs (+16%) and CT (+20%). Radiology orders by advanced practice providers increased 74%. Turnaround time from imaging order placed to final diagnostic radiology report did not change substantially after the closure. Workflow in our ED and radiology department was significantly impacted by the closure of HUH. This study provides insight into how our practice patterns changed and compensated after the closure of a neighboring, large, urban safety-net hospital; it is important for radiologists to be aware of citywide practice patterns to adapt to acute change.

Interventional radiology workflow during the COVID-19 pandemic: recommendations of the Swiss Society of Vascular and Interventional Radiology.

Given the importance of continuum in providing services and exigence of protecting health care professionals during this period, the Swiss Society of Vascular and Interventional Radiology (SSVIR) is releasing guidance for interventional radiologists as preparedness to manage COVID-19 patients, the workflow of non-COVID-19 patients and optimize interactions with other healthcare professionals.

Promises of artificial intelligence in neuroradiology: a systematic technographic review

PurposeTo conduct a systematic review of the possibilities of artificial intelligence (AI) in neuroradiology by performing an objective, systematic assessment of available applications. To analyse the potential impacts of AI applications on the work of neuroradiologists.MethodsWe identified AI applications offered on the market during the period 2017–2019. We systematically collected and structured information in a relational database and coded for the characteristics of the applications, their functionalities for the radiology workflow and their potential impacts in terms of ‘supporting’, ‘extending’ and ‘replacing’ radiology tasks.ResultsWe identified 37 AI applications in the domain of neuroradiology from 27 vendors, together offering 111 functionalities. The majority of functionalities ‘support’ radiologists, especially for the detection and interpretation of image findings. The second-largest group of functionalities ‘extends’ the possibilities of radiologists by providing quantitative information about pathological findings. A small but noticeable portion of functionalities seek to ‘replace’ certain radiology tasks.ConclusionArtificial intelligence in neuroradiology is not only in the stage of development and testing but also available for clinical practice. The majority of functionalities support radiologists or extend their tasks. None of the applications can replace the entire radiology profession, but a few applications can do so for a limited set of tasks. Scientific validation of the AI products is more limited than the regulatory approval.

Using Quality Improvement Methodology to Reduce Costs while Improving Efficiency and Provider Satisfaction in a Busy, Academic Musculoskeletal Radiology Division.

Within an everchanging healthcare system, continuous evaluation of standard operating procedures must be performed to ensure optimization of system level organization, communication, and efficiency. Using the Lean management approach, our institution introduced modifications to our musculoskeletal (MSK) radiology workflow in order to facilitate beneficial change that improved clinical workflow efficiency, reduced moonlighting costs, and improved radiologist satisfaction without sacrificing quality of care. The scope of our study included the MSK division of adult inpatient and outpatient populations at three hospitals in a single academic medical center. A root cause analysis was executed to determine the causative factors contributing to clinical inefficiency. Five main factors were identified, and appropriate countermeasures were introduced. Efficiency was measured via the turnaround time (TAT) for radiographic examinations, measured from exam completion to final report submission. Moonlighting expenses were monitored for the fiscal year in which the modifications were implemented. Surveys were administered to MSK radiologists before and after the countermeasures were introduced to determine subjective ratings of efficiency and satisfaction. The average TAT within our MSK division decreased from 40h to 12h after introducing changes to our workflow. During one fiscal year, moonlighting expenses decreased from $26,000 to $5000. Post-study survey results indicated increased efficiency of and satisfaction with our implemented modifications to the scheduling and clinical workflow. Optimization of our radiology department's workflow led to increased productivity, efficiency, and radiologist satisfaction, as well as a reduction in moonlighting costs. This project leveraged Lean management principles to combat clinical inefficiency, waste time, and high costs.

Machine Learning for Automation of Radiology Protocols for Quality and Efficiency Improvement.

The aim of this study was to enhance multispecialty CT and MRI protocol assignment quality and efficiency through development, testing, and proposed workflow design of a natural language processing (NLP)-based machine learning classifier. NLP-based machine learning classification models were developed using order entry input data and radiologist-assigned protocols from more than 18,000 unique CT and MRI examinations obtained during routine clinical use. k-Nearest neighbor, random forest, and deep neural network classification models were evaluated at baseline and after applying class frequency and confidence thresholding techniques. To simulate performance in real-world deployment, the model was evaluated in two operating modes in combination: automation (automated assignment of the top result) and clinical decision support (CDS; top-three protocol suggestion for clinical review). Finally, model-radiologist discordance was subjectively reviewed to guide explainability and safe use. Baseline protocol assignment performance achieved weighted precision of 0.757 to 0.824. Simulating real-world deployment using combined thresholding techniques, the optimized deep neural network model assigned 69% of protocols in automation mode with 95% accuracy. In the remaining 31% of cases, the model achieved 92% accuracy in CDS mode. Analysis of discordance with subspecialty radiologist labels revealed both more and less appropriate model predictions. A multiclass NLP-based classification algorithm was designed to drive local operational improvement in CT and MR radiology protocol assignment at subspecialist quality. The results demonstrate a simulated workflow deployment enabling automated assignment of protocols in nearly 7 of 10 cases with very few errors combined with top-three CDS for remaining cases supporting a high-quality, efficient radiology workflow.

Policies and Guidelines for COVID-19 Preparedness: Experiences from the University of Washington.

The coronavirus disease 2019 (COVID-19) pandemic initially manifested in the United States in the greater Seattle area and has rapidly progressed across the nation in the past 2 months, with the United States having the highest number of cases in the world. Radiology departments play a critical role in policy and guideline development both for the department and for the institutions, specifically in planning diagnostic screening, triage, and management of patients. In addition, radiology workflows, volumes, and access must be optimized in preparation for the expected surges in the number of patients with COVID-19. In this article, the authors discuss the processes that have been implemented at the University of Washington in managing the COVID-19 pandemic as well in preparing for patient surges, which may provide important guidance for other radiology departments who are in the early stages of preparation and management.

Policies and Guidelines for COVID-19 Preparedness: Experiences from the University of Washington.

The Coronavirus Disease 2019 (COVID-19) pandemic initially presented in the United States in the greater Seattle area, and has rapidly progressed across the nation in the past 2 months, with the United States having the highest number of cases in the world. Radiology departments play a critical role in policy and guideline development both for the department and for the institutions, specifically in planning diagnostic screening, triage, and management of patients. In addition, radiology workflows, volumes and access must be optimized in preparation for the expected COVID-19 patient surges. This article discusses the processes that have been implemented at the University of Washington in managing the COVID-19 pandemic as well in preparing for patient surges, which may provide important guidance for other radiology departments who are in the early stages of preparation and management.

Clinical practice of language fMRI in epilepsy centers: a European survey and conclusions by the ESNR Epilepsy Working Group

PurposeTo assess current clinical practices throughout Europe with respect to acquisition, implementation, evaluation, and interpretation of language functional MRI (fMRI) in epilepsy patients.MethodsAn online survey was emailed to all European Society of Neuroradiology members (n = 1662), known associates (n = 6400), and 64 members of European Epilepsy network. The questionnaire featured 40 individual items on demographic data, clinical practice and indications, fMRI paradigms, radiological workflow, data post-processing protocol, and reporting.ResultsA total of 49 non-duplicate entries from European centers were received from 20 countries. Of these, 73.5% were board-certified neuroradiologists and 69.4% had an in-house epilepsy surgery program. Seventy-one percent of centers performed fewer than five scans per month for epilepsy. The most frequently used paradigms were phonemic verbal fluency (47.7%) and auditory comprehension (55.6%), but variants of 13 paradigms were described. Most centers assessed the fMRI task performance (75.5%), ensured cognitive-task adjustment (77.6%), trained the patient before scanning (85.7%), and assessed handedness (77.6%), but only 28.6% had special paradigms for patients with cognitive impairments. fMRI was post-processed mainly by neuroradiologists (42.1%), using open-source software (55.0%). Reporting was done primarily by neuroradiologists (74.2%). Interpretation was done mainly by visual inspection (65.3%). Most specialists (81.6%) were able to determine the hemisphere dominance for language in more than 75% of exams, attributing failure to the patient not performing the task correctly.ConclusionThis survey shows that language fMRI is firmly embedded in the preoperative management of epilepsy patients. The wide variety of paradigms and the use of non-CE-marked software underline the need for establishing reference standards.

Beyond the Artificial Intelligence Hype: What Lies Behind the Algorithms and What We Can Achieve.

The field of artificial intelligence (AI) is currently experiencing a period of extensive growth in a wide variety of fields, medicine not being the exception. The base of AI is mathematics and computer science, and the current fame of AI in industry and research stands on 3 pillars: big data, high performance computing infrastructure, and algorithms. In the current digital era, increased storage capabilities and data collection systems, lead to a massive influx of data for AI algorithm. The size and quality of data are 2 major factors influencing performance of AI applications. However, it is highly dependent on the type of task at hand and algorithm chosen to perform this task. AI may potentially automate several tedious tasks in radiology, particularly in cardiothoracic imaging, by pre-readings for the detection of abnormalities, accurate quantifications, for example, oncologic volume lesion tracking and cardiac volume and image optimization. Although AI-based applications offer great opportunity to improve radiology workflow, several challenges need to be addressed starting from image standardization, sophisticated algorithm development, and large-scale evaluation. Integration of AI into the clinical workflow also needs to address legal barriers related to security and protection of patient-sensitive data and liability before AI will reach its full potential in cardiothoracic imaging.

Implementing a Radiology Residency Quality Curriculum to Develop Physician Leaders and Increase Value for Patients.

Diagnostic and interventional radiology residency programs must educate trainees on quality and patient safety topics to meet board requirements and prepare residents to become effective physician leaders. A quality curriculum should encompass process improvement methodology as well as instruction about crucial patient safety subjects. The authors have developed a standardized and structured approach to fulfill this need using didactic and experiential learning. The educational format includes short lectures, peer-to-peer instruction, and self-study, with the value of presented information reinforced by physician leaders and process improvement specialists. Equally important is a structured experience in departmental quality improvement wherein trainees learn the collaborative nature of effective durable process change in areas of interest to them. This curriculum is implemented during the 3rd year of radiology residency to leverage residents' knowledge and experience with radiology workflows and proximity to the American Board of Radiology Core Exam. Feedback from educators and trainees as well as objective examination data support this approach. This article shares guidance and lessons learned from the authors' radiology residency educational efforts and offers a framework for successful implementation of a comprehensive quality curriculum at any residency training program. This curriculum serves the dual purpose of developing skilled future physician leaders and promoting value for patients. ©RSNA, 2020.