Involvement Of Radiologists Research Articles

Which images to label for few-shot medical image analysis?

The success of deep learning methodologies hinges upon the availability of meticulously labeled extensive datasets. However, when dealing with medical images, the annotation process for such abundant training data often necessitates the involvement of experienced radiologists, thereby consuming their limited time resources. In order to alleviate this burden, few-shot learning approaches have been developed, which manage to achieve competitive performance levels with only several labeled images. Nevertheless, a crucial yet previously overlooked problem in few-shot learning is about the selection of template images for annotation before learning, which affects the final performance. In this study, we propose a novel TEmplate Choosing Policy (TECP) that aims to identify and select “the most worthy” images for annotation, particularly within the context of multiple few-shot medical tasks, including landmark detection, anatomy detection, and anatomy segmentation. TECP is composed of four integral components: (1) Self-supervised training, which entails training a pre-existing deep model to extract salient features from radiological images; (2) Alternative proposals for localizing informative regions within the images; and (3) Representative Score Estimation, which involves the evaluation and identification of the most representative samples or templates. (4) Ranking, which rank all candidates and select one with highest representative score. The efficacy of the TECP approach is demonstrated through a series of comprehensive experiments conducted on multiple public datasets. Across all three medical tasks, the utilization of TECP yields noticeable improvements in model performance.

The role of urology and radiology in prostate biopsy: current trends and future perspectives.

Prostate biopsy is central to the accurate histological diagnosis of prostate cancer. In current practice, the biopsy procedure can be performed using a transrectal or transperineal route with different technologies available for targeting of lesions within the prostate. Historically, the biopsy procedure was performed solely by urologists, but with the advent of image-guided techniques, the involvement of radiologists in prostate biopsy has become more common. Herein, we discuss the pros, cons and future considerations regarding their ongoing role. A narrative review regarding the current evidence was completed. PubMed and Cochrane central register of controlled trials were search until January 2024. All study types were of consideration if published after 2000 and an English language translation was available. There are no published studies that directly compare outcomes of prostate biopsy when performed by a urologist or radiologist. In all published studies regarding the learning curve for prostate biopsy, the procedure was performed by urologists. These studies suggest that the learning curve for prostate biopsy is between 10 and 50 cases to reach proficiency in terms of prostate cancer detection and complications. It is recognised that many urologists are poorly able to accurately interpret multi parametric (mp)-MRI of theprostate. Collaboration between the specialities is of importance with urology offering the advantage of being involved in prior and future care of the patient while radiology has the advantage of being able to expertly interpret preprocedure MRI. There is no evidence to suggest that prostate biopsy should be solely performed by a specific specialty. The most important factor remains knowledge of the relevant anatomy and sufficient volume of cases to develop and maintain skills.

Competence of radiologists in cardiac CT and MR imaging in Europe: insights from the ESCR Registry

RationaleTo provide an overview of the current status of cardiac multimodality imaging practices in Europe and radiologist involvement using data from the European Society of Cardiovascular Radiology (ESCR) MRCT-registry.Materials and methodsNumbers on cardiac CT and MRI examinations were extracted from the MRCT-registry of the ESCR, entered between January 2011 and October 2023 (n = 432,265). Data collection included the total/annual numbers of examinations, indications, complications, and reporting habits.ResultsThirty-two countries contributed to the MRCT-registry, including 29 European countries. Between 2011 and 2022, there was a 4.5-fold increase in annually submitted CT examinations, from 3368 to 15,267, and a 3.8-fold increase in MRI examinations, from 3445 to 13,183. The main indications for cardiac CT were suspected coronary artery disease (CAD) (59%) and transcatheter aortic valve replacement planning (21%). The number of patients with intermediate pretest probability who underwent CT for suspected CAD showed an increase from 61% in 2012 to 82% in 2022. The main MRI indications were suspected myocarditis (26%), CAD (21%), and suspected cardiomyopathy (19%). Adverse event rates were very low for CT (0.3%) and MRI (0.7%) examinations. Reporting of CT and MRI examinations was performed mainly by radiologists (respectively 76% and 71%) and, to a lesser degree, in consensus with non-radiologists (19% and 27%, respectively). The remaining examinations (4.9% CT and 1.7% MRI) were reported by non-radiological specialties or in separate readings of radiologists and non-radiologists.ConclusionsReal-life data on cardiac imaging in Europe using the largest available MRCT-registry demonstrate a considerable increase in examinations over the past years, the vast majority of which are read by radiologists. These findings indicate that radiologists contribute to meeting the increasing demands of competent and effective care in cardiac imaging to a relevant extent.Clinical relevance statementThe number of cardiac CT and MRI examinations has risen over the past years, and radiologists read the vast majority of these studies as recorded in the MRCT-registry.Key Points• The number of cardiac imaging examinations is constantly increasing.• Radiologists play a central role in providing cardiac CT and MR imaging services to a large volume of patients.• Cardiac CT and MR imaging examinations performed and read by radiologists show a good safety profile.Graphical

Locoregional Therapies for Primary and Secondary Hepatic Malignancies.

Management of hepatic malignancies is a multidisciplinary task with the involvement of hepatologists, medical/surgical/radiation oncologists, transplant surgeons, and interventional radiologists. Patients should be selected for a specific targeted therapy after multidisciplinary consensus. Interventional oncology, with image-guided locoregional cancer therapies, can decrease systemic toxicity without compromising tumoricidal effect.

Learning from experience - Radiology ancillary review of prospective research studies involving imaging

This report describes the operational process of a big academic children's hospital's Radiology Scientific Review Committee, with a focus on its role in integrating radiology services into pediatric clinical research. We define the step-by-step workflow used to assess research proposals involving imaging and share insights from the past three years of data collection. Trends in modalities, radiologist involvement, and interpretation possibilities are outlined in the data. This systematic methodology provides essential resource allocation concepts and promotes high-quality pediatric clinical research.

How We Got Here: The Legacy of Anti-Black Discrimination in Radiology

Current disparities in the access to diagnostic imaging for Black patients and the underrepresentation of Black physicians in radiology, relative to their representation in the general U.S. population, reflect contemporary consequences of historical anti-Black discrimination. These disparities have existed within the field of radiology and professional medical organizations since their inception. Explicit and implicit racism against Black patients and physicians was institutional policy in the early 20th century when radiology was being developed as a clinical medical field. Early radiology organizations also embraced this structural discrimination, creating strong barriers to professional Black radiologist involvement. Nevertheless, there were numerous pioneering Black radiologists who advanced scholarship, patient care, and diversity within medicine and radiology during the early 20th century. This work remains important in the present day, as race-based health care disparities persist and continue to decrease the quality of radiology-delivered patient care. There are also structural barriers within radiology affecting workforce diversity that negatively impact marginalized groups. Multiple opportunities exist today for antiracism work to improve quality of care and to apply standards of social justice and health equity to the field of radiology. An initial step is to expand education on the disparities in access to imaging and health care among Black patients. Institutional interventions include implementing community-based outreach and applying antibias methodology in artificial intelligence algorithms, while systemic interventions include identifying national race-based quality measures and ensuring imaging guidelines properly address the unique cancer risks in the Black patient population. These approaches reflect some of the strategies that may mutually serve to address health care disparities in radiology. © RSNA, 2023 See the invited commentary by Scott in this issue. Quiz questions for this article are available in the supplemental material.

Leveraging Artificial Intelligence to Enhance Peer Review: Missed Liver Lesions on Computed Tomographic Pulmonary Angiography.

The aim of this study was to use artificial intelligence (AI) to facilitate peer review for detection of missed suspicious liver lesions (SLLs) on CT pulmonary angiographic (CTPA) examinations. This retrospective study included 1 month of consecutive CTPA examinations from a multisite teleradiology practice. Visual classification (VC) software analyzed images for the presence (+) or absence (-) of SLLs (>1 cm, >20 Hounsfield units). Separately, a natural language processing (NLP) algorithm evaluated corresponding reports for description (+) of an SLL or lack thereof (-). Studies containing possible missed SLLs (VC+/NLP-) were reviewed by three abdominal radiologists in a two-step adjudication process to confirm if an SLL was missed by the interpreting radiologist. The number of VC+/NLP- cases, the number of images needing radiologist review, and the number of cases with confirmed missed SLLs were recorded. Interobserver agreement for SLLs was calculated for the radiologist readers. A total of 2,573 CTPA examinations were assessed, and 136 were classified as potentially containing missed SLLs (VC+/NLP-). After radiologist review, 13 cases with missed SLLs were confirmed, representing 0.5% of analyzed CT studies. Using AI, the ratio of CT studies requiring review to missed SLLs identified was 10:1; the ratio without the help of AI would be at least 66:1. Among the 136 cases reviewed by radiologists, interobserver agreement for SLLs was excellent (κ= 0.91). AI can accelerate meaningful peer review by rapidly assessing thousands of examinations to identify potentially clinically significant errors. Although radiologist involvement is necessary, the amount of effort required after initial AI screening is dramatically reduced.

CTA of Acute Pulmonary Embolism: Best Practices

Pulmonary CTA is a commonly performed study and the radiologist's role is not limited to simply producing a report. The process from identifying the appropriate patients who will benefit from the study to improving performance in the radiology department requires the radiologist's involvement, expertise, and leadership. The focus of this narrative review is to highlight the different steps and the ways to improve the quality in the assessment of thromboembolic disease where the radiologists can have an impact. This article provides an update on the commonly used and more recently published clinical decision tools, specific parameter adjustments of pulmonary CTA for more challenging patients and potential improvement for the radiology department.

Artificial Intelligence Applications in Aortic Dissection Imaging

Pulmonary CTA is a commonly performed study and the radiologist's role is not limited to simply producing a report. The process from identifying the appropriate patients who will benefit from the study to improving performance in the radiology department requires the radiologist's involvement, expertise, and leadership. The focus of this narrative review is to highlight the different steps and the ways to improve the quality in the assessment of thromboembolic disease where the radiologists can have an impact. This article provides an update on the commonly used and more recently published clinical decision tools, specific parameter adjustments of pulmonary CTA for more challenging patients and potential improvement for the radiology department.

Creating a leadership course: First experiences with the musculoskeletal.avatar train the future project

The European Society of MusculoSkeletal Radiology (ESSR), is a scientific body which rapidly expands over the last two decades. Such a large society needs involvement of young, ambitious and skilled radiologists who will be able to face the challenges of the rapidly induced changes in Medical Imaging and Intervention. A leadership program is a means to offer chances of developing skills that young radiologists may need in order to move forward within the ESSR body and contribute to its further growth. The authors present herein the m.avatar project which was performed under the auspices of ESSR.

Automatic vs manual coronary CT angiography reconstruction for whole-heart coverage CT scanner: a comparison study in general patient population.

Due to the limited temporal resolution and cardiac motion, coronary computed tomography angiography (CCTA) exam is one of the most challenging CT protocols which may require operating radiologist to apply additional phase adjustment or motion correction for image reconstruction. To evaluate image quality between automatic and manual CCTA reconstruction in a 0.25 second rotation time, 16 cm coverage, single-beat, CT scanner with automated phase selection and AI-assisted motion correction. CCTA exams of 535 consecutive patients were included. All exams were first reconstructed with an automatically selected phase. If there was an unacceptable motion artifact, a manual reconstruction process was performed by radiologists. Additionally, automatic image series which consist of auto-phase selection and a follow-up motion correction were reconstructed. For these two manual and automatic image series, a four-point Likert scale rating system was used to evaluate image quality of the coronary artery segment by two experienced radiologists, according to the 18-segment model. Fifty-one patients (9.5%) did not have satisfactory image quality after auto-phase selection. In these patients, the heart rate during scanning was higher (78.3±18.4 bpm) than in the remaining 484 patients (68.9±13.1 bpm). Overall, 734 out of the 918 vessel segments were identified for quality evaluation among 51 patients. Automatic and manual image series were rated as having average Likert scores of 3.48±0.62 and 3.32±0.67 (P < 0.001), respectively. Using a 0.25 second rotation speed, 16 cm z-coverage, CT scanner installed with an AI-assisted motion correction algorithm, the automatic image reconstruction with scanner equipped auto-phase-selection and motion correction algorithm outperforms manually controlled image reconstruction by radiologists. This suggests that the traditional CCTA exam reconstruction workflow could be altered allowing less radiologist involvement and becoming more efficient.

Non-radiologist perception of the use of artificial intelligence (AI) in diagnostic medical imaging reports.

Incorporating artificial intelligence (AI) in diagnostic medical imaging reports has the potential to improve efficiency. Although perception of radiologists, radiographers, medical students and patients on AI use in image reporting has been explored, there is limited literature on non-radiologist clinicians' opinion on this topic. Single-centre online survey targeting non-radiologist medical staff conducted from May to August 2021 at a tertiary referral hospital in Melbourne, Australia. Survey questions revolved around clinicians' level of comfort acting on AI-generated reports with varying levels of radiologist involvement and scan complexity, opinion on medicolegal responsibility for erroneous AI-issued reports and perception of data privacy and security. Eighty-eight responses were collected, including 47.9% of consultants. Non-radiologist clinicians across all seniorities and specialties felt significantly less comfortable acting on AI-issued reports compared with radiologist-issued reports (mean comfort radiologist 6.44/7, mean comfort AI 3.35/7, P < 0.001) but felt equally comfortable with an AI-hybrid model of care (mean comfort hybrid 6.38/7, P = 0.676). Non-radiologist clinicians believed that medicolegal responsibility with errors in AI-issued reports mostly lay with hospitals or health service providers (65.9%) and radiologists (54.5%). Regarding data privacy and security, non-radiologist clinicians felt significantly less comfortable with AI issuing image reports instead of radiologists (P < 0.001). A hybrid AI-generated radiologist-confirmed method of image reporting may be the ideal way of integrating AI into clinical practice based on the perception of our referring non-radiologist medical colleagues. Formal guidelines on medicolegal responsibility and data privacy should be established prior to utilising AI in the clinical setting.

334 Localisation of Sentinel Node for Cutaneous Melanoma of Trunk

Abstract Aim Our aim was to review localisation of sentinel node for cutaneous melanoma of trunk based on position. This was to investigate whether we can predict sentinel node position and therefore avoid scintigram. Method We have collected 50 patients with cutaneous melanoma of the trunk who underwent sentinel node biopsy. We have reviewed and recorded position of the melanoma and most likely position of sentinel biopsy. This has been on the day of surgery compared to scintigram. Results Majority of the melanomas have drained into the predicted location. Midline melanomas had tendency to drain bilaterally. The most difficult to predict were melanomas on the anterior aspect of trunk. Conclusions In majority of cases surgeons were able to predict position of sentinel node biopsy and therefore scintigram might not be necessary. If such approach is adapted, the need for radiologist involvement on the day of surgery may decrease.

Pediatric Emergency Imaging Studies in Academic Radiology Departments: A Nationwide Survey of Staffing Practices.

Particularly for pediatric patients presenting with acute conditions or challenging diagnoses, identifying variation in emergency radiology staffing models is essential in establishing a standard of care. We conducted a cross-sectional survey among radiology departments at academic pediatric hospitals to evaluate staffing models for providing imaging interpretation for emergency department imaging requests. We conducted an anonymous telephone survey of academic pediatric hospitals affiliated with an accredited radiology residency program across the United States. We queried the timing, location, and experience of reporting radiologists for initial and final interpretations of emergency department imaging studies, during weekday, overnight, and weekend hours. We compared weekday with overnight, and weekday with weekend, using Fisher's exact test and an α of 0.05. Surveying 42 of 47 freestanding academic pediatric hospitals (89%), we found statistically significant differences for initial reporting radiologist, final reporting radiologist, and final report timing between weekday and overnight. We found statistically significant differences for initial reporting radiologist and final report timing between weekday and weekend. Attending radiologist involvement in initial reports was 100% during daytime, but only 33.3% and 69.0% during overnight and weekends. For initial interpretation during overnight and weekend, 38.1% and 28.6% use resident radiologists without attending radiologists, and 28.6% and 2.4% use teleradiology. All finalized reports as soon as possible during weekdays, but only 52.4% and 78.6% during overnight and weekend. A minority of hospitals use 24-hour in-house radiology attending radiologist coverage. During overnight periods, the majority of academic pediatric emergency departments rely on resident radiologists without attending radiologist supervision or outside teleradiology services to provide initial reports. During weekend periods, over a quarter rely on resident radiologists without attending radiologist supervision for initial reporting. This demonstrates significant variation in staffing practices at academic pediatric hospitals. Future studies should look to determine whether this variation has any impact on standard of care.

Image quality of automatic coronary CT angiography reconstruction for patients with HR\u2009\u2265\u200975\xa0bpm using an AI-assisted 16-cm z-coverage CT scanner

BackgroundCoronary CT angiography (CCTA) is a complicated CT exam in comparison to other CT protocols. Exam success highly depends on image assessment of experienced radiologist and the procedure is often time-consuming. This study aims to evaluate feasibility of automatic CCTA reconstruction in 0.25 s rotation time, 16 cm coverage CT scanner with best phase selection and AI-assisted motion correction.MethodsCCTA exams of 90 patients with heart rates higher than 75 bpm were included in this study. Two image series were reconstructed—one at automatically selected phase and another with additional motion correction. All reconstructions were performed without manual interaction of radiologist. A four-point Likert scale rating system was used to evaluate the image quality of coronary artery segment by two experienced radiologists, according to the 18-segment model. Analysis was done on per-segment basis.ResultsTotal 1194 out of the 1620 segments were identified for quality evaluation in 90 patients. After automatic best phase selection, 1172 segments (98.3%) were rated as having diagnostic image quality (scores 2–4) and the average score is 3.64 ± 0.55. When motion corrections were applied, diagnostic segment number increases to 1192 (99.8%) and the average score is 3.85 ± 0.37.ConclusionsWith the help of 0.25 s rotation speed, 16-cm z-coverage and AI-assisted motion correction algorithm, CCTA exam reconstruction could be performed with minimum radiologist involvement and still meet image quality requirement.

Artificial intelligence in breast cancer screening: primary care provider preferences.

Artificial intelligence (AI) is increasingly being proposed for use in medicine, including breast cancer screening (BCS). Little is known, however, about referring primary care providers' (PCPs') preferences for this technology. We identified the most important attributes of AI BCS for ordering PCPs using qualitative interviews: sensitivity, specificity, radiologist involvement, understandability of AI decision-making, supporting evidence, and diversity of training data. We invited US-based PCPs to participate in an internet-based experiment designed to force participants to trade off among the attributes of hypothetical AI BCS products. Responses were analyzed with random parameters logit and latent class models to assess how different attributes affect the choice to recommend AI-enhanced screening. Ninety-one PCPs participated. Sensitivity was most important, and most PCPs viewed radiologist participation in mammography interpretation as important. Other important attributes were specificity, understandability of AI decision-making, and diversity of data. We identified 3 classes of respondents: "Sensitivity First" (41%) found sensitivity to be more than twice as important as other attributes; "Against AI Autonomy" (24%) wanted radiologists to confirm every image; "Uncertain Trade-Offs" (35%) viewed most attributes as having similar importance. A majority (76%) accepted the use of AI in a "triage" role that would allow it to filter out likely negatives without radiologist confirmation. Sensitivity was the most important attribute overall, but other key attributes should be addressed to produce clinically acceptable products. We also found that most PCPs accept the use of AI to make determinations about likely negative mammograms without radiologist confirmation.

Patient Diversity in Breast Imaging: Barriers and Potential Solutions.

Recent reports have highlighted disparities in breast cancer care related to patient diversity. Breast radiologists represent the face of breast imaging and are key players in advocating for patients to reduce these disparities. Diversity-related barriers for breast imaging patients, as they journey from screening to survivorship, include impediments to access and quality of care, gaps in communication, and lack of knowledge in both providers and patients. Potential strategies for overcoming these specific barriers include "culturally tailored" nurse navigators, mobile mammography, improved communication, patient and provider education, and breast radiologist involvement in advocacy efforts promoting diversity. As current trends in recommendations and guidelines for breast imaging include more numerous and advanced imaging modalities, it is important to acknowledge and address diversity-related disparities.

Involvement of radiologists in oncologic multidisciplinary team meetings: an international survey by the European Society of Oncologic Imaging

ObjectivesMultidisciplinary tumour boards (MTBs) play an increasingly important role in managing cancer patients from diagnosis to treatment. However, many problems arise around the organisation of MTBs, both in terms of organisation-administration and time management. In this context, the European Society of Oncologic Imaging (ESOI) conducted a survey among its members, aimed at assessing the quality and amount of involvement of radiologists in MTBs, their role in it and related issues.MethodsAll members were invited to fill in a questionnaire consisting of 15 questions with both open and multiple-choice answers. Simple descriptive analyses and graphs were performed.ResultsA total of 292 ESOI members in full standing for the year 2018 joined the survey. Most respondents (89%) declared to attend MT-Bs, but only 114 respondents (43.9%) review over 70% of exams prior to MTB meetings, mainly due to lack of time due to a busy schedule for imaging and reporting (46.6%). Perceived benefits (i.e. surgical and histological feedback (86.9%), improved knowledge of cancer treatment (82.7%) and better interaction between radiologists and referring clinicians for discussing rare cases (56.9%)) and issues (i.e. attending MTB meetings during regular working hours (71.9%) and lack of accreditation with continuing medical education (CME) (85%)) are reported.ConclusionsDespite the value and benefits of radiologists’ participation in MTBs, issues like improper preparation due to a busy schedule and no counterpart in CME accreditation require efforts to improve the role of radiologists for a better patient care.Key Points• Most radiologists attend multidisciplinary tumour boards, but less than half of them review images in advance, mostly due to time constraints.• Feedback about radiological diagnoses, improved knowledge of cancer treatment and interaction with referring clinicians are perceived as major benefits.• Concerns were expressed about scheduling multidisciplinary tumour boards during regular working hours and lack of accreditation with continuing medical education.

A review of imaging findings in melioidosis: revealing the tropics’ dirty secret

ObjectiveMelioidosis is a neglected tropical disease caused by the Burkholderia pseudomallei bacterium. Currently, serologically-proven cases are likely to represent only the ‘tip of the iceberg’ as culture facilities are not widely available within endemic areas. With globally increasing population and temperatures, it is hypothesised that areas which B. pseudomallei is endemic to will expand. Melioidosis confers significant mortality and morbidity and is associated with a diverse range of imaging findings. This pictorial essay aims to describe the common and life-threatening imaging features of melioidosis. MethodsA retrospective review was undertaken on imaging performed in culture-confirmed cases of melioidosis at a single institution over a 5-year period. ResultsTypical and atypical imaging findings demonstrating involvement of multiple organs are presented. ConclusionEffective treatment for melioidosis requires early diagnosis and a multi-disciplinary approach with involvement of physicians, surgeons, and interventional radiologists. Where available, early CT imaging should be performed to investigate potential bacterial seeding. Radiologists working in endemic areas or examining returned overseas travellers should be familiar with the imaging findings to aid diagnosis and management in these patients.

Provider preferences for attributes of artificial intelligence in breast cancer screening: A discrete choice experiment.

e14118 Background: One of the emerging medical applications of artificial intelligence (AI) is the interpretation of mammograms for breast cancer screening. It is uncertain what attributes would result in acceptance of AI for breast cancer screening (AI BCS) among ordering clinicians. Methods: We performed qualitative interviews to identify the most important attributes of AI BCS for ordering clinicians. We then invited US-based primary care providers (PCPs) to participate in a discrete choice experiment (DCE). The experiment featured 15 choices between radiologist alone and two AI BCS alternatives where respondents traded better metrics on some attributes for worse metrics on others. Responses were analyzed using a mixed logit model adjusting for preference heterogeneity to determine the probability of recommending AI BCS. Results: In qualitative interviews, the six most important attributes to PCPs were AI sensitivity, specificity, radiologist involvement, understandability of AI decision-making, supporting evidence, and diversity of training data. Forty PCPs completed the DCE. Sensitivity was the most important attribute: a 4 percentage point improvement in sensitivity over the average radiologist increased the probability of recommending AI by 0.41 (95% confidence interval (CI), 0.38-0.42). Specificity was approximately half as important. Respondents were indifferent to whether radiologists confirmed all or only screens likely to be abnormal. However, no radiologist involvement reduced the probability of recommendation by 0.31 (95% CI, 0.29-0.31). An AI developed using data from diverse populations increased the probability of recommendation by 0.38 (95% CI, 0.36-0.39). Lastly, an AI that is transparent in the rationale for its decisions increased the probability of recommendation by 0.41 (95% CI, 0.39-0.41). Conclusions: PCPs prefer AI BCS that improves sensitivity versus specificity, and involves radiologists in the confirmation of abnormal screens. Improving sensitivity alone, however, will likely not be sufficient to support widespread PCP acceptance – algorithms will need to be developed with diverse data and more transparent explanations of their decisions.