Assessing the Potential of a Deep Learning Tool to Improve Fracture Detection by Radiologists and Emergency Physicians on Extremity Radiographs.

RATIONALE AND OBJECTIVES: To evaluate the standalone performance of a deep learning (DL) based fracture detection tool on extremity radiographs and assess the performance of radiologists and emergency physicians in identifying fractures of the extremities with and without the DL aid. MATERIALS AND METHODS: The DL tool was previously developed using 132,000 appendicular skeletal radiographs divided into 87% training, 11% validation, and 2% test sets. Stand-alone performance was evaluated on 2626 de-identified radiographs from a single institution in Ohio, including at least 140 exams per body region. Consensus from three US board-certified musculoskeletal (MSK) radiologists served as ground truth. A multi-reader retrospective study was performed in which 24 readers (eight each of emergency physicians, non-MSK radiologists, and MSK radiologists) identified fractures in 186 cases during two independent sessions with and without DL aid, separated by a one-month washout period. The accuracy (area under the receiver operating curve), sensitivity, specificity, and reading time were compared with and without model aid. RESULTS: The model achieved a stand-alone accuracy of 0.986, sensitivity of 0.987, and specificity of 0.885, and high accuracy (> 0.95) across stratification for body part, age, gender, radiographic views, and scanner type. With DL aid, reader accuracy increased by 0.047 (95% CI: 0.034, 0.061; p = 0.004) and sensitivity significantly improved from 0.865 (95% CI: 0.848, 0.881) to 0.955 (95% CI: 0.944, 0.964). Average reading time was shortened by 7.1 s (27%) per exam. When stratified by physician type, this improvement was greater for emergency physicians and non-MSK radiologists. CONCLUSION: The DL tool demonstrated high stand-alone accuracy, aided physician diagnostic accuracy, and decreased interpretation time.

Reproducibility of Deep Learning Algorithms Developed for Medical Imaging Analysis: A Systematic Review.

Since 2000, there have been more than 8000 publications on radiology artificial intelligence (AI). AI breakthroughs allow complex tasks to be automated and even performed beyond human capabilities. However, the lack of details on the methods and algorithm code undercuts its scientific value. Many science subfields have recently faced a reproducibility crisis, eroding trust in processes and results, and influencing the rise in retractions of scientific papers. For the same reasons, conducting research in deep learning (DL) also requires reproducibility. Although several valuable manuscript checklists for AI in medical imaging exist, they are not focused specifically on reproducibility. In this study, we conducted a systematic review of recently published papers in the field of DL to evaluate if the description of their methodology could allow the reproducibility of their findings. We focused on the Journal of Digital Imaging (JDI), a specialized journal that publishes papers on AI and medical imaging. We used the keyword "Deep Learning" and collected the articles published between January 2020 and January 2022. We screened all the articles and included the ones which reported the development of a DL tool in medical imaging. We extracted the reported details about the dataset, data handling steps, data splitting, model details, and performance metrics of each included article. We found 148 articles. Eighty were included after screening for articles that reported developing a DL model for medical image analysis. Five studies have made their code publicly available, and 35 studies have utilized publicly available datasets. We provided figures to show the ratio and absolute count of reported items from included studies. According to our cross-sectional study, in JDI publications on DL in medical imaging, authors infrequently report the key elements of their study to make it reproducible.

Implementing a Streamlined Radiology Workflow to Close the Loop on Incidental Imaging Findings in the Emergency Department.

Actionable incidental findings (AIFs) are common imaging findings unrelated to the clinical indication for the imaging test for which follow-up is recommended. Increasing utilization of imaging in the emergency department (ED) in recent years has resulted in more patients with AIFs. When these findings are not properly communicated and followed up upon, there is harm to the patient's health outcome as well as possible increased financial costs for the patient, the health system, and potential litigation. Tracking these findings can be difficult, especially so in a large health system. In this report, we detail our experience implementing a closed-loop AIF program within the ED of 11 satellite hospitals of a large academic health system. Our new workflow streamlined radiologist reporting of AIFs through system macros and by using a standardized form integrated into the dictation software. Upon completion of the form, an automatic email is sent to a dedicated nurse navigator who documented the findings and closed the loop by coordinating follow-up imaging or clinic visits with patients, primary care providers, and specialists. Through the new workflow, a total of 1207 incidental finding reports have been submitted from July 2021 to May 2022. The vast majority of AIFs were identified on CT, and the most common categories included lung nodules, pancreas lesions, liver lesions, and other potentially cancerous lesions. At least 10 new cancers have been detected. We hope this report can help guide other health systems in the design of a closed-loop incidental findings program.

System-driven longitudinal follow-up of incidental imaging findings.

Increasing utilization of cross-sectional imaging has resulted in more clinically significant incidental findings being discovered. However, the current approach for handling these findings is commonly inconsistent and relies greatly on the efforts of individual clinicians. Making sure every actionable incidental finding is handled in a consistent and reliable manner can be difficult, especially for a large health system. We propose an approach to handling incidental findings aimed at improving patient follow-up rates, which involves implementing system-level processes that standardize the reporting of incidental findings, notification of clinicians and the patient, and centralized monitoring of longitudinal patient follow-up. We will lay out a general framework for standardized reporting of incidental findings by the radiologist using software integrated into the daily workflow. This should enable simultaneous notification of the ordering clinician, the patient's primary-care provider, and an incidental findings navigator. The navigator will "close the loop" by working with clinicians to notify the patient of the finding, coordinate patient follow-up, and document the finding and long-term follow-up. We hope this can serve as a basic framework to help large health systems design an incidental findings workflow to improve follow-up rates and reduce patient harm.

Improved characterization of focal airway lesions using spectral detector dual energy CT.

Clinicians should be aware of SDCT as a useful tool in the assessment of focal airway lesions. Spectral detector dual-energy computed tomography (SDCT) is a relatively novel imaging technology which has been utilized to aid in the diagnosis of many cardiothoracic conditions. Specifically, the availability of generated iodine density maps, virtual monoenergetic images, and effective atomic number maps allow for better evaluation of thoracic lesions compared to conventional CT. SDCT has previously been shown to be useful in the differentiation of benign vs malignant pulmonary nodules, pleural lesions, and lymph nodes. We describe 3 cases in which a patient presents with an indeterminate tracheal or bronchial lesion on conventional CT and subsequent SDCT reconstructions provided additional information which helped guide diagnosis or management of the patient. The goal is to help clinicians understand the benefit of SDCT in the detection and workup of airway lesions.

COVID-19 infection complicated by acute ST-elevation myocardial infarction.

Clinicians should be aware of the potential for cardiovascular involvement in COVID-19 infection. Coronavirus disease-2019 (COVID-19) is a viral illness caused by severe acute respiratory syndrome-coronavirus-2. While it primarily causes a respiratory illness, a number of important cardiovascular implications have been reported. We describe a patient presenting with COVID-19 whose hospital course was complicated by ST elevation myocardial infarction requiring percutaneous coronary intervention. The goal is to help clinicians gain awareness of the possibility of cardiovascular disease in COVID-19 infection, and maintain a high index of suspicion particularly for patients with risk factors or a prior history of cardiovascular disease.