Stakeholders' perspectives on the future of artificial intelligence in radiology: a scoping review.

OBJECTIVES: Artificial intelligence (AI) has the potential to impact clinical practice and healthcare delivery. AI is of particular significance in radiology due to its use in automatic analysis of image characteristics. This scoping review examines stakeholder perspectives on AI use in radiology, the benefits, risks, and challenges to its integration. METHODS: A search was conducted from 1960 to November 2019 in EMBASE, PubMed/MEDLINE, Web of Science, Cochrane Library, CINAHL, and grey literature. Publications reflecting stakeholder attitudes toward AI were included with no restrictions. RESULTS: Commentaries (n = 32), surveys (n = 13), presentation abstracts (n = 8), narrative reviews (n = 8), and a social media study (n = 1) were included from 62 eligible publications. These represent the views of radiologists, surgeons, medical students, patients, computer scientists, and the general public. Seven themes were identified (predicted impact, potential replacement, trust in AI, knowledge of AI, education, economic considerations, and medicolegal implications). Stakeholders anticipate a significant impact on radiology, though replacement of radiologists is unlikely in the near future. Knowledge of AI is limited for non-computer scientists and further education is desired. Many expressed the need for collaboration between radiologists and AI specialists to successfully improve patient care. CONCLUSIONS: Stakeholder views generally suggest that AI can improve the practice of radiology and consider the replacement of radiologists unlikely. Most stakeholders identified the need for education and training on AI, as well as collaborative efforts to improve AI implementation. Further research is needed to gain perspectives from non-Western countries, non-radiologist stakeholders, on economic considerations, and medicolegal implications. KEY POINTS: Stakeholders generally expressed that AI alone cannot be used to replace radiologists. The scope of practice is expected to shift with AI use affecting areas from image interpretation to patient care. Patients and the general public do not know how to address potential errors made by AI systems while radiologists believe that they should be "in-the-loop" in terms of responsibility. Ethical accountability strategies must be developed across governance levels. Students, residents, and radiologists believe that there is a lack in AI education during medical school and residency. The radiology community should work with IT specialists to ensure that AI technology benefits their work and centres patients.

Image Exchange in Canada: Examples from the Province of Ontario.

An increased number of healthcare providers across the continuum of care share responsibility for providing treatment and care to the patient. Treatment is often provided at community-based facilities and not necessarily at the hospital that performed the imaging. As a result, there is an increased dependency on readily available access to a patient's longitudinal imaging records. The ways in which diagnostic images and results are exchanged among providers within a patient's circle of care have expanded. This article explores three varieties of image exchange. First, we examine image exchange patterns within a regional Diagnostic Imaging Repository and identify missed sharing opportunities. Secondly, we explore the use of a regional clinical viewer widely used in southwestern Ontario, called ClinicalConnect™, and examine the adoption of the viewer by providers. Finally, the paper provides a high-level look at how patients can leverage patient portals to view their imaging data to empower their healthcare experience.

An Environmental Scan of the National and Provincial Diagnostic Reference Levels in Canada for Common Adult Computed Tomography Scans.

Several regulatory bodies have agreed that low-dose radiation used in medical imaging is a weak carcinogen that follows a linear, non-threshold model of cancer risk. While avoiding radiation is the best course of action to mitigate risk, computed tomography (CT) scans are often critical for diagnosis. In addition to the as low as reasonably achievable principle, a more concrete method of dose reduction for common CT imaging exams is the use of a diagnostic reference level (DRL). This paper examines Canada's national DRL values from the recent CT survey and compares it to published provincial DRLs as well as the DRLs in the United Kingdom and the United States of America for the 3 most common CT exams: head, chest, and abdomen/pelvis. Canada compares well on the international scale, but it should consider using more electronic dose monitoring solutions to create a culture of dose optimization.

Accelerated muscle and adipose tissue loss may predict survival in pancreatic cancer patients: the relationship with diabetes and anaemia.

Weight loss leading to cachexia is associated with poor treatment response and reduced survival in pancreatic cancer patients. We aim to identify indicators that allow for early detection that will advance our understanding of cachexia and will support targeted anti-cachexia therapies. A total of fifty pancreatic cancer patients were analysed for skeletal muscle and visceral adipose tissue (VAT) changes using computed tomography (CT) scans. These changes were related to physical characteristics, secondary disease states and treatment parameters. Overall, patients lost 1.72 (SD 3.29) kg of muscle and 1.04 (SD 1.08) kg of VAT during the disease trajectory (413 (SD 213) d). After sorting patients into tertiles by rate of VAT and muscle loss, patients losing VAT at > -0.40 kg/100 d had poorer survival outcomes compared with patients with < -0.10 kg/100 d of VAT loss (P= 0.020). Patients presenting with diabetes at diagnosis demonstrated significantly more and accelerated VAT loss compared with non-diabetic patients. In contrast, patients who were anaemic at the first CT scan lost significantly more muscle tissue and at accelerated rates compared with non-anaemic patients. Accelerated rates of VAT loss are associated with reduced survival. Identifying associated features of cachexia, such as diabetes and anaemia, is essential for the early detection of cachexia and may facilitate the attenuation of complications associated with cachexia.

Evaluation of irreversible compression ratios for medical images thin slice CT and update of Canadian Association of Radiologists (CAR) guidelines.

In June 2008, the Canadian Association of Radiologists published its Standards for Irreversible Compression in Digital Diagnostic Imaging within Radiology (Canadian Association of Radiologists 2012). The study suggested that at low levels of compression there was no difference in diagnostic accuracy between uncompressed JPEG and JPEG 2000. There were two exceptions; CT neurological and CT body images resulted in lower rating of image quality (Koff et al., J Digit Imaging 22(6):569-78, 2009). The slice thicknesses used in the previous study were greater than 5 mm. However, other studies (Ringl et al., Radiology 240:869-87, 2006) suggest that thin CT slices might modify image tolerance to irreversible compression. Therefore, a new clinical evaluation using CT slices less than 3 mm was initiated. We examined CT images in four body regions (chest, body, musculoskeletal, and neurological). Twenty-five radiologists from across Canada participated. Each read a total of 70 CTs in his specialty; 10 at each of seven levels of compression (uncompressed, JPEG and JPEG 2000 at low, medium, and high compression (varying by region)). Each reader diagnosed the case, rated his confidence, and compared the compressed to the uncompressed image and rated the degree of degradation. Data were analyzed for sensitivity, specificity, accuracy, confidence, and degradation at three levels and two types of compression as well as the original image. There were no overall differences in sensitivity, specificity, accuracy, or confidence. JPEG images, at all levels of compression, were rated lower in terms of perceived difference (4.16/5 vs. 4.53/5 for JPEG 2000 and 4.68/5 for uncompressed). However, the rating of perceived difference was not significantly correlated with accuracy. Analysis of individual body regions did not reveal any systematic effects of compression in any region.

COVID-Net CT-2: Enhanced Deep Neural Networks for Detection of COVID-19 From Chest CT Images Through Bigger, More Diverse Learning.

The COVID-19 pandemic continues to rage on, with multiple waves causing substantial harm to health and economies around the world. Motivated by the use of computed tomography (CT) imaging at clinical institutes around the world as an effective complementary screening method to RT-PCR testing, we introduced COVID-Net CT, a deep neural network tailored for detection of COVID-19 cases from chest CT images, along with a large curated benchmark dataset comprising 1,489 patient cases as part of the open-source COVID-Net initiative. However, one potential limiting factor is restricted data quantity and diversity given the single nation patient cohort used in the study. To address this limitation, in this study we introduce enhanced deep neural networks for COVID-19 detection from chest CT images which are trained using a large, diverse, multinational patient cohort. We accomplish this through the introduction of two new CT benchmark datasets, the largest of which comprises a multinational cohort of 4,501 patients from at least 16 countries. To the best of our knowledge, this represents the largest, most diverse multinational cohort for COVID-19 CT images in open-access form. Additionally, we introduce a novel lightweight neural network architecture called COVID-Net CT S, which is significantly smaller and faster than the previously introduced COVID-Net CT architecture. We leverage explainability to investigate the decision-making behavior of the trained models and ensure that decisions are based on relevant indicators, with the results for select cases reviewed and reported on by two board-certified radiologists with over 10 and 30 years of experience, respectively. The best-performing deep neural network in this study achieved accuracy, COVID-19 sensitivity, positive predictive value, specificity, and negative predictive value of 99.0%/99.1%/98.0%/99.4%/99.7%, respectively. Moreover, explainability-driven performance validation shows consistency with radiologist interpretation by leveraging correct, clinically relevant critical factors. The results are promising and suggest the strong potential of deep neural networks as an effective tool for computer-aided COVID-19 assessment. While not a production-ready solution, we hope the open-source, open-access release of COVID-Net CT-2 and the associated benchmark datasets will continue to enable researchers, clinicians, and citizen data scientists alike to build upon them.

How COVID-19 kick-started online learning in medical education-The DigiMed study.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic led to far-reaching restrictions of social and professional life, affecting societies all over the world. To contain the virus, medical schools had to restructure their curriculum by switching to online learning. However, only few medical schools had implemented such novel learning concepts. We aimed to evaluate students' attitudes to online learning to provide a broad scientific basis to guide future development of medical education. METHODS: Overall, 3286 medical students from 12 different countries participated in this cross-sectional, web-based study investigating various aspects of online learning in medical education. On a 7-point Likert scale, participants rated the online learning situation during the pandemic at their medical schools, technical and social aspects, and the current and future role of online learning in medical education. RESULTS: The majority of medical schools managed the rapid switch to online learning (78%) and most students were satisfied with the quantity (67%) and quality (62%) of the courses. Online learning provided greater flexibility (84%) and led to unchanged or even higher attendance of courses (70%). Possible downsides included motivational problems (42%), insufficient possibilities for interaction with fellow students (67%) and thus the risk of social isolation (64%). The vast majority felt comfortable using the software solutions (80%). Most were convinced that medical education lags behind current capabilities regarding online learning (78%) and estimated the proportion of online learning before the pandemic at only 14%. In order to improve the current curriculum, they wish for a more balanced ratio with at least 40% of online teaching compared to on-site teaching. CONCLUSION: This study demonstrates the positive attitude of medical students towards online learning. Furthermore, it reveals a considerable discrepancy between what students demand and what the curriculum offers. Thus, the COVID-19 pandemic might be the long-awaited catalyst for a new "online era" in medical education.

Interactive modeling and evaluation of tumor growth.

This paper addresses the need to quantify tumor growth and detect changes as this information is relevant to manage the patient treatment and to aid biotechnological efforts to cure cancer (Silva et al. 2008). An interactive tumor segmentation technique is used to recover the shape and size of tumors without imposing shape constraints. This segmentation algorithm provides good convergence, is robust to the initialization conditions, and requires simple and intuitive user interactions. A parametric approach to model tumor growth analytically is proposed in this paper. The preliminary experimental results are encouraging. The segmentation method is shown to be robust and simple to use, even in situations where the tumor boundary definition is challenging. Also, the experiments indicate that the proposed model potentially can be used to extrapolate the available data and help predict the tumor size (assuming unconstrained growth). Additionally, the proposed method potentially can provide a quantitative reference to compare the tumor shrinkage rate in cancer treatments.

Emphasizing the Diagnostic Value of Digital Tomosynthesis in Detecting Hip Fractures.

Our institution recently implemented the use of digital tomosynthesis (DTS) to workup emergency room patients with suspected hip fractures after initial negative or indeterminate radiographs. Our purpose is to evaluate the diagnostic accuracy of DTS for hip fracture detection. We performed a retrospective review of all DTS studies over a 17-month period (July 2017 to November 2018). The results of the radiographs and DTS were recorded as either positive or negative for fracture based on the radiology report. Our reference standard for a fracture was either confirmation on subsequent CT or MRI from the same visit or documentation of clinical findings supportive of a fracture in the patient's electronic medical record. For patients with negative DTS who did not undergo subsequent cross-sectional imaging, a missed fracture was excluded if they did not return within 30 days with a confirmed fracture. Among 91 patients, there were 34 confirmed fractures-sites including, 7 femoral necks, 10 pubic rami, and 7 greater trochanters. DTS was positive for fracture in 29 patients; 28 of these fractures were true positives, 6 confirmed on cross-sectional imaging, and 22 confirmed clinically. One false positive was observed in a patient with no clinical evidence of a fracture. Six fractures were not detected by tomosynthesis but confirmed on CT/MRI. The sensitivity and specificity of DTS are 82% and 98%, respectively, compared to that of radiographs alone at 47% and 96%, respectively. DTS is a promising adjunct to radiographs for hip fracture detection in an emergency department.

Pan-Canadian evaluation of irreversible compression ratios ("lossy" compression) for development of national guidelines.

New technological advancements including multislice CT scanners and functional MRI, have dramatically increased the size and number of digital images generated by medical imaging departments. Despite the fact that the cost of storage is dropping, the savings are largely surpassed by the increasing volume of data being generated. While local area network bandwidth within a hospital is adequate for timely access to imaging data, efficiently moving the data between institutions requires wide area network bandwidth, which has a limited availability at a national level. A solution to address those issues is the use of lossy compression as long as there is no loss of relevant information. The goal of this study was to determine levels at which lossy compression can be confidently used in diagnostic imaging applications. In order to provide a fair assessment of existing compression tools, we tested and compared the two most commonly adopted DISCOM compression algorithms: JPEG and JPEG-2000. We conducted an extensive pan-Canadian evaluation of lossy compression applied to seven anatomical areas and five modalities using two recognized techniques: objective methods or diagnostic accuracy and subjective assessment based on Just Noticeable Difference. By incorporating both diagnostic accuracy and subjective evaluation techniques, enabled us to define a range of compression for each modality and body part tested. The results of our study suggest that at low levels of compression, there was no significant difference between the performance of lossy JPEG and lossy JPEG 2000, and that they are both appropriate to use for reporting on medical images. At higher levels, lossy JPEG proved to be more effective than JPEG 2000 in some cases, mainly neuro CT. More evaluation is required to assess the effect of compression on thin slice CT. We provide a table of recommended compression ratios for each modality and anatomical area investigated, to be integrated in the Canadian Association of Radiologists standard for the use of lossy compression in medical imaging.

OpenID Connect as a security service in cloud-based medical imaging systems.

The evolution of cloud computing is driving the next generation of medical imaging systems. However, privacy and security concerns have been consistently regarded as the major obstacles for adoption of cloud computing by healthcare domains. OpenID Connect, combining OpenID and OAuth together, is an emerging representational state transfer-based federated identity solution. It is one of the most adopted open standards to potentially become the de facto standard for securing cloud computing and mobile applications, which is also regarded as "Kerberos of cloud." We introduce OpenID Connect as an authentication and authorization service in cloud-based diagnostic imaging (DI) systems, and propose enhancements that allow for incorporating this technology within distributed enterprise environments. The objective of this study is to offer solutions for secure sharing of medical images among diagnostic imaging repository (DI-r) and heterogeneous picture archiving and communication systems (PACS) as well as Web-based and mobile clients in the cloud ecosystem. The main objective is to use OpenID Connect open-source single sign-on and authorization service and in a user-centric manner, while deploying DI-r and PACS to private or community clouds should provide equivalent security levels to traditional computing model.

Comparison of dual energy subtraction chest radiography and traditional chest X-rays in the detection of pulmonary nodules.

BACKGROUND: Dual energy subtraction (DES) radiography is a powerful but underutilized technique which aims to improve the diagnostic value of an X-ray by separating soft tissue from bones, producing two different images. Compared to traditional chest X-rays, DES requires exposure to higher doses of radiation but may achieve higher accuracy. The objective of this study was to assess the clinical benefits of DES radiography by comparing the speed and accuracy of diagnosis of pulmonary nodules with DES versus traditional chest X-rays. METHODS: Five radiologists and five radiology residents read the DES and traditional chest X-rays of 51 patients, 34 with pulmonary nodules and 17 without. Their accuracy and speed in the detection of nodules were measured using specialized image display software. RESULTS: DES radiography reduced reading time from 13 to 10 sec (P<0.0001) in staff and from 21 to 15 sec in residents (P<0.0001). There was also a small increase in sensitivity 0.58 to 0.67 overall (P<0.10) with no change in specificity (0.85 overall). CONCLUSIONS: By eliminating rib shadows in soft tissue images, DES improved the speed and accuracy of radiologists in the diagnosis of pulmonary nodules.

Lung nodule segmentation in chest computed tomography using a novel background estimation method.

BACKGROUND: Lung cancer results in the highest number of cancer deaths worldwide. The segmentation of lung nodules is an important task in computer systems to help physicians differentiate malignant lesions from benign lesions. However, it has already been observed that this may be a difficult task, especially when nodules are connected to an anatomical structure. METHODS: This paper proposes a method to estimate the background of the nodule area and how this estimation is used to facilitate the segmentation task. RESULTS: Our experiments indicate more than 99% of accuracy with less than 1% of false positive rate (FPR). CONCLUSIONS: The proposed methods achieved better results than a state-of-the-art approach, indicating potential to be used in medical image processing systems.

The relative biological effectiveness of low-dose mammography quality X rays in the human breast MCF-10A cell line.

Mammography is used to screen a large fraction of the population for breast cancer, and mammography quality X rays are speculated to be more damaging than the higher energy X rays used for other diagnostic procedures. The radiation dose delivered to breast cells as a result of these screening exposures may be a concern. The purpose of this current study was to determine the relative biological effectiveness (RBE) of low-energy mammography X rays for radiation-induced DNA double-strand breaks evaluated using a highly sensitive automated 53BP1 assay. Automation of the 53BP1 assay enabled the quantification and analysis of meaningful image-based features, including foci counting, within the cell nuclei. Nontumorigenic, human breast epithelial MCF-10A cells were irradiated in the low-dose range with approximately 3-30 mGy of 29 kVp mammography X rays or (137)Cs (662 keV) gamma rays. The induction and resolution of the 53BP1 foci did not differ significantly between exposures to (137)Cs gamma rays and 29 kVp X rays. The RBE was calculated to be 1.1 with a standard deviation of 0.2 for the initial number of radiation-induced double-strand breaks. The radiation dose from a single mammogram did not yield a significant change in the number of detectable foci. However, analysis of additional features revealed subtle differences in the distribution of 53BP1 throughout the nuclei after exposure to the different radiation qualities. A single mammogram was sufficient to alter the distribution of 53BP1 within the nuclear area, but not into discrete foci, while a dose-matched gamma exposure was not sufficient to alter the distribution of 53BP1. Our results indicate that exposure to clinically relevant doses of low-energy mammography quality X rays does not induce more DNA double-strand breaks than exposure to higher energy photons.

Evidence against the involvement of chronic cerebrospinal venous abnormalities in multiple sclerosis. A case-control study.

OBJECTIVE: Multiple sclerosis (MS) is a chronic neurodegenerative disease of the CNS. Recently a controversial vascular hypothesis for MS, termed chronic cerebrospinal venous insufficiency (CCSVI), has been advanced. The objective of this study was to evaluate the relative prevalence of the venous abnormalities that define CCSVI. METHODS: A case-control study was conducted in which 100 MS patients aged between 18-65 y meeting the revised McDonald criteria were randomly selected and stratified into one of four MS subtypes: relapsing/remitting, secondary progressive, primary progressive and benign. Control subjects (16-70 y) with no known history of MS or other neurological condition were matched with the MS cases. All cases and controls underwent ultrasound imaging of the veins of the neck plus the deep cerebral veins, and magnetic resonance imaging of the neck veins and brain. These procedures were performed on each participant on the same day. RESULTS: On ultrasound we found no evidence of reflux, stenosis or blockage in the internal jugular veins (IJV) or vertebral veins (VV) in any study participant. Similarly, there was no evidence of either reflux or cessation of flow in the deep cerebral veins in any subject. Flow was detected in the IJV and VV in all study participants. Amongst 199 participants there was one MS subject who fulfilled the minimum two ultrasound criteria for CCSVI. Using MRI we found no significant differences in either the intra- or extra-cranial venous flow velocity or venous architecture between cases and controls. CONCLUSION: This case-control study provides compelling evidence against the involvement of CCSVI in multiple sclerosis.

Can computerized clinical decision support systems improve practitioners' diagnostic test ordering behavior? A decision-maker-researcher partnership systematic review.

BACKGROUND: Underuse and overuse of diagnostic tests have important implications for health outcomes and costs. Decision support technology purports to optimize the use of diagnostic tests in clinical practice. The objective of this review was to assess whether computerized clinical decision support systems (CCDSSs) are effective at improving ordering of tests for diagnosis, monitoring of disease, or monitoring of treatment. The outcome of interest was effect on the diagnostic test-ordering behavior of practitioners. METHODS: We conducted a decision-maker-researcher partnership systematic review. We searched MEDLINE, EMBASE, Ovid's EBM Reviews database, Inspec, and reference lists for eligible articles published up to January 2010. We included randomized controlled trials comparing the use of CCDSSs to usual practice or non-CCDSS controls in clinical care settings. Trials were eligible if at least one component of the CCDSS gave suggestions for ordering or performing a diagnostic procedure. We considered studies 'positive' if they showed a statistically significant improvement in at least 50% of test ordering outcomes. RESULTS: Thirty-five studies were identified, with significantly higher methodological quality in those published after the year 2000 (p = 0.002). Thirty-three trials reported evaluable data on diagnostic test ordering, and 55% (18/33) of CCDSSs improved testing behavior overall, including 83% (5/6) for diagnosis, 63% (5/8) for treatment monitoring, 35% (6/17) for disease monitoring, and 100% (3/3) for other purposes. Four of the systems explicitly attempted to reduce test ordering rates and all succeeded. Factors of particular interest to decision makers include costs, user satisfaction, and impact on workflow but were rarely investigated or reported. CONCLUSIONS: Some CCDSSs can modify practitioner test-ordering behavior. To better inform development and implementation efforts, studies should describe in more detail potentially important factors such as system design, user interface, local context, implementation strategy, and evaluate impact on user satisfaction and workflow, costs, and unintended consequences.

Fetal sex assignment by sonographic evaluation of the pelvic organs in the second and third trimesters of pregnancy.

OBJECTIVE: The purpose of this study was to determine the feasibility and reliability of fetal sex assignment by prenatal sonography of the pelvic organs in the second and third trimesters. METHODS: A prospective study, on an axial pelvic image with the umbilical arteries in cross section at the midpoint of the bladder, measured the distance between the posterior wall of the bladder and the anterior wall of the rectum. The bladder interface was scored as concave, flat, or convex. Endometrium visualization was recorded. A video loop of the pelvis was obtained. Each case was read by a second reader aware of only the gestational age. RESULTS: The study population included 205 fetuses. The primary reader was 98.8% accurate in identifying true female fetuses and 100% accurate in identifying true male fetuses. The intraclass correlation coefficient for axial measurement was 0.99. Video loop analysis achieved 96% inter-reader concordance. In the second trimester, measurements in 100% of male fetuses were less than 3.3 mm, and those in 94% of female fetuses were greater than 3.3 mm. In the third trimester, measurements in 96% of male fetuses were less than 4.7 mm, and those in 100% of female fetuses were greater than 4.7 mm. Ninety-eight percent of all fetuses with concave interfaces were female. The endometrium was visualized in 74%. The additional time per examination was less than 5 minutes in 87.7%. CONCLUSIONS: Internal pelvic fetal sex assignment is a reliable additional method for fetal sex determination. A numerical discriminatory level can be used to distinguish between male and female internal genitalia. Larger numbers will be required to further refine these values.