Clinical Imaging最新文献

This article explores the practice of immobilization during fluoroscopy procedures for infants, discussing its advantages and disadvantages. The authors examine contrasting policies and thoughts on immobilization across different medical institutions. While some advocate for its routine use to minimize patient motion, enhance imaging quality, and decrease radiation exposure, others question its necessity and raise concerns about patient consent and parental distress. Ethical dilemmas are also discussed regarding patient autonomy and psychological impact on families. The authors advocate for a balanced approach, recognizing the utility of immobilization in certain clinical scenarios while still emphasizing patient-centered care. Ultimately, the article underscores the importance of institutional policies that prioritize both patient safety and ethical principles in pediatric radiology practices.

Purpose

To compare the demographic characteristics of active physicians, trainees, medical school clinical sciences faculty, and department chairs in radiology with those in other medical specialties.

Methods

An analysis was conducted using publicly available deidentified aggregate data from the Association of American Medical Colleges (AAMC). Our data collection included information from the 2022 AAMC Physician Specialty Data Report, the 2022 AAMC Report on Residents, and the 2022 AAMC Faculty Roster. We examined factors such as graduation country, gender, and self-identified race/ethnicity. MedCalc software was used for the analyses.

Results

Compared to other specialties, active radiologists exhibited a significantly lower percentage of females, International Medical Graduates (IMGs), individuals of American Indian/Alaska Native (AIAN) descent, Black/African-American individuals, and individuals of Hispanic/Latino/Spanish origin. Conversely, the proportion of White active radiologists was higher. Among radiology trainees, there was a notably lower percentages of females, IMGs, individuals of Black/African-American descent, and individuals of Hispanic/Latino/Spanish origin, while the percentage of Asians was significantly higher. Furthermore, medical school radiology faculty showed a significant lower proportion of females, Black/African-American individuals, Hispanic/Latino/Spanish individuals, and individuals categorized under the white race/ethnicity, with Asians having a higher representation. As radiology department chairs, Asians were noted at significantly lower percentages compared to their proportions among medical school radiology faculty, while Black/African-American individuals were observed at significantly higher percentages in the same comparison.

Conclusion

This study revealed a notable underrepresentation of females, individuals of Black/African-American descent, and those of Hispanic/Latino/Spanish origin among active radiologists, radiology trainees, and medical school radiology faculty when compared to their counterparts in other medical specialties. Given these findings, further investigation into the underlying causes of these disparities is warranted.

Purpose

As the field of medicine witnesses evolving attitudes towards work-life balance, barriers to family planning emerge as an important theme. Though these challenges have been investigated in many fields, there has been little work done on this subject within radiology. Here we present the first formal survey of radiologists on topics related to family planning.

Materials and methods

In this single-institution prospective study, a 40-question comprehensive survey was developed and distributed via email. Responses from 76 participants were analyzed.

Results

Of the 76 respondents, a diverse number of ages, points in the career path, and practice settings were represented. A majority of respondents were male (52/76; 68 %) and married (56/75; 73.7 %). Respondents reported a miscarriage rate of 25 %, which is slightly higher than the reported rate for the general population of 20 %. Significantly more female respondents reported a negative stigma associated with being pregnant as a radiologist as compared to their male colleagues (60.9 % vs. 15.4 %; p < 0.001)). Male respondents reported significantly less parental leave than their female colleagues, most commonly reporting zero weeks of leave as compared to 10 weeks for female respondents (p < 0.001). Numerous respondents cited lack of childcare support as a major issue.

Conclusion

We have identified several key areas of concern, including a need for improving parental leave policies, addressing pregnancy stigma, and increasing access to childcare support. Overall, our study lays the groundwork for discussions and policy changes within radiology at both the institutional and national level to ensure the continued interest of trainees and satisfaction of radiologists.

Improvising and developing state of the art techniques for breast cancer detection have always been an area of great interest in the field of imaging. Adding intravenous contrast to any imaging study, is well-known to increase the sensitivity and specificity of detection of a pathological process, especially in the setting of neoplasia secondary to tumor neoangiogenesis. Contrast enhanced MRI is known to be highly sensitive breast cancer screening tool till date, however, has been limited by long scan times, claustrophobia experienced by some women and high false positive findings. Despite continued advances in digital mammography technique, significant limitations have always been experienced in detection of small cancers especially in the setting of dense breast parenchyma. Implementing dual energy subtraction technique to digital mammography, made contrast enhanced mammography a viable technique to improve cancer detection. We aim to discuss the status of contrast enhanced mammography in this brief communication, emphasizing technical background, image acquisition, clinical applications, and future directions.

Purpose

Clinical trials play a pivotal role in assessing the safety and efficacy of medical therapies. Addressing sex distribution among enrollees in clinical trials of radiologic contrast agents is essential for ensuring the generalizability of trial outcomes. Previous research has highlighted the influence of demographic factors, particularly sex, on treatment responses, emphasizing the need for equitable representation in clinical trials. Our study aim was to determine the sex distribution of enrollees in clinical trials of radiologic contrast agents.

Methods

Our retrospective study included a total of 65 clinical trials conducted between 1990 and 2017 identified on clinicaltrials.gov after a comprehensive review including searching individually for all FDA approved contrast agents. Data collected included the year of FDA approval, the number of participants, sex distribution, trial location, trial phase, and study type. Inter-rater validation ensured data accuracy.

Results

Our analysis revealed fluctuations in sex distribution of trial enrollees. Enrollment of males exceeded females in most years, with a shift towards a more equitable representation in recent trials. Trials conducted in the United States had a higher rate of enrollment by females. Phase I trials had the most balanced representation, whereas Phase IV trials had the highest sex disparity.

Conclusion

Across all trials, females made up 47.3 % of enrollees [3316 out of 7016 total enrollees]. Enrollment of males exceeded females in 44 of the 65 trials studied, females outnumbered males in 19 trials, and enrollment was equal between the sexes in 2 trials. While the sex distribution observed across all trials represents an equitable representation of enrollees, the wide variance of sex distribution at the level of individual trials has the potential to limit the generalizability of results.

Background

Clinical adoption of AI applications requires stakeholders see value in their use. AI-enabled opportunistic-CT-screening (OS) capitalizes on incidentally-detected findings within CTs for potential health benefit. This study evaluates primary care providers' (PCP) perspectives on OS.

Methods

A survey was distributed to US Internal and Family Medicine residencies. Assessed were familiarity with AI and OS, perspectives on potential value/costs, communication of results, and technology implementation.

Results

62 % of respondents (n = 71) were in Family Medicine, 64.8 % practiced in community hospitals. Although 74.6 % of respondents had heard of AI/machine learning, 95.8 % had little-to-no familiarity with OS. The majority reported little-to-no trust in AI. Reported concerns included AI accuracy (74.6 %) and unknown liability (73.2 %). 78.9 % of respondents reported that OS applications would require radiologist oversight. 53.5 % preferred OS results be included in a separate “screening” section within the Radiology report, accompanied by condition risks and management recommendations. The majority of respondents reported results would likely affect clinical management for all queried applications, and that atherosclerotic cardiovascular disease risk, abdominal aortic aneurysm, and liver fibrosis should be included within every CT report regardless of reason for examination. 70.5 % felt that PCP practices are unlikely to pay for OS. Added costs to the patient (91.5 %), the healthcare provider (77.5 %), and unknown liability (74.6 %) were the most frequently reported concerns.

Conclusion

PCP preferences and concerns around AI-enabled OS offer insights into clinical value and costs. As AI applications grow, feedback from end-users should be considered in the development of such technology to optimize implementation and adoption. Increasing stakeholder familiarity with AI may be a critical prerequisite first step before stakeholders consider implementation.

Purpose

Adequate communication of scientific findings is crucial to enhance knowledge transfer. This study aimed to determine the key features of a good scientific oral presentation on artificial intelligence (AI) in medical imaging.

Methods

A total of 26 oral presentations dealing with original research on AI studies in medical imaging at the 2023 RSNA annual meeting were included and systematically assessed by three observers. The presentation quality of the research question, inclusion criteria, reference standard, method, results, clinical impact, presentation clarity, presenter engagement, and the presentation's quality of knowledge transfer were assessed using five-point Likert scales. The number of slides, the average number of words per slide, the number of interactive slides, the number of figures, and the number of tables were also determined for each presentation. Mixed-effects ordinal regression was used to assess the association between the above-mentioned variables and the quality of knowledge transfer of the presentation.

Results

A significant positive association was found between the quality of the presentation of the research question and the presentation's quality of knowledge transfer (odds ratio [OR]: 2.5, P = 0.005). The average number of words per slide was significantly negatively associated with the presentation's quality of knowledge transfer (OR: 0.9, P < 0.001). No other significant associations were found.

Conclusion

Researchers who orally present their scientific findings in the field of AI and medical imaging should pay attention to clearly communicating their research question and minimizing the number of words per slide to maximize the value of their presentation.

Purpose

This meta-analysis aimed to compare the diagnostic effectiveness of [¹⁸F]FDG PET/CT with that of [¹⁸F]FDG PET/MRI in terms of identifying liver metastasis in patients with primary cancer.

Methods

PubMed, Embase, Web of Science, and the Cochrane Library were searched, and studies evaluating the diagnostic efficacy of [¹⁸F]FDG PET/CT and [¹⁸F]FDG PET/MRI in patients with liver metastasis of primary cancer were included. We used a random effects model to analyze their sensitivity and specificity. Subgroup analyses and corresponding meta-regressions focusing on race, image analysis, study design, and analysis methodologies were conducted. Cochrane Q and I² statistics were used to assess intra-group and inter-group heterogeneity.

Results

Seven articles with 343 patients were included in this meta-analysis. The sensitivity of [¹⁸F]FDG PET/CT was 0.82 (95 % CI: 0.63–0.96), and that of [¹⁸F]FDG PET/MRI was 0.91 (95 % CI: 0.82–0.98); there was no significant difference between the two methods (P = 0.32). Similarly, both methods showed equal specificity: 1.00 (95 % CI: 0.95–1.00) for [¹⁸F]FDG PET/CT and 1.00 (95 % CI: 0.96–1.00) for [¹⁸F]FDG PET/MRI, and thus, there was no significant difference between the methods (P = 0.41). Furthermore, the subgroup analyses revealed no differences. Meta-regression analysis revealed that race was a potential source of heterogeneity for [¹⁸F]FDG PET/CT (P = 0.01), while image analysis and contrast agent were found to be potential sources of heterogeneity for [18F]FDG PET/MRI (P = 0.02).

Conclusions

[¹⁸F]FDG PET/MRI has similar sensitivity and specificity to [¹⁸F]FDG PET/CT for detecting liver metastasis of primary cancer in both the general population and in subgroups. [¹⁸F]FDG PET/CT may be a more cost-effective option. However, the conclusions of this meta-analysis are tentative due to the limited number of studies included, and further research is necessary for validation.

Purpose

We created an infrastructure for no code machine learning (NML) platform for non-programming physicians to create NML model. We tested the platform by creating an NML model for classifying radiographs for the presence and absence of clavicle fractures.

Methods

Our IRB-approved retrospective study included 4135 clavicle radiographs from 2039 patients (mean age 52 ± 20 years, F:M 1022:1017) from 13 hospitals. Each patient had two-view clavicle radiographs with axial and anterior-posterior projections. The positive radiographs had either displaced or non-displaced clavicle fractures. We configured the NML platform to automatically retrieve the eligible exams using the series' unique identification from the hospital virtual network archive via web access to DICOM Objects. The platform trained a model until the validation loss plateaus. Once the testing was complete, the platform provided the receiver operating characteristics curve and confusion matrix for estimating sensitivity, specificity, and accuracy.

Results

The NML platform successfully retrieved 3917 radiographs (3917/4135, 94.7 %) and parsed them for creating a ML classifier with 2151 radiographs in the training, 100 radiographs for validation, and 1666 radiographs in testing datasets (772 radiographs with clavicle fracture, 894 without clavicle fracture). The network identified clavicle fracture with 90 % sensitivity, 87 % specificity, and 88 % accuracy with AUC of 0.95 (confidence interval 0.94–0.96).

Conclusion

A NML platform can help physicians create and test machine learning models from multicenter imaging datasets such as the one in our study for classifying radiographs based on the presence of clavicle fracture.