Current Problems in Diagnostic Radiology最新文献

Purpose

To validate the performance of a recently created risk stratification system (RSS) for thyroid nodules on ultrasound, the Artificial Intelligence Thyroid Imaging Reporting and Data System (AI TI-RADS).

Materials and methods

378 thyroid nodules from 320 patients were included in this retrospective evaluation. All nodules had ultrasound images and had undergone fine needle aspiration (FNA). 147 nodules were Bethesda V or VI (suspicious or diagnostic for malignancy), and 231 were Bethesda II (benign). Three radiologists assigned features according to the AI TI-RADS lexicon (same categories and features as the American College of Radiology TI-RADS) to each nodule based on ultrasound images. FNA recommendations using AI TI-RADS and ACR TI-RADS were then compared and sensitivity and specificity for each RSS were calculated.

Results

Across three readers, mean sensitivity of AI TI-RADS was lower than ACR TI-RADS (0.69 vs 0.72, p < 0.02), while mean specificity was higher (0.40 vs 0.37, p < 0.02). Overall total number of points assigned by all three readers decreased slightly when using AI TI-RADS (5,998 for AI TI-RADS vs 6,015 for ACR TI-RADS), including more values of 0 to several features.

Conclusion

AI TI-RADS performed similarly to ACR TI-RADS while eliminating point assignments for many features, allowing for simplification of future TI-RADS versions.

Introduction

The rise of transformer-based large language models (LLMs), such as ChatGPT, has captured global attention with recent advancements in artificial intelligence (AI). ChatGPT demonstrates growing potential in structured radiology reporting—a field where AI has traditionally focused on image analysis.

Methods

A comprehensive search of MEDLINE and Embase was conducted from inception through May 2024, and primary studies discussing ChatGPT's role in structured radiology reporting were selected based on their content.

Results

Of the 268 articles screened, eight were ultimately included in this review. These articles explored various applications of ChatGPT, such as generating structured reports from unstructured reports, extracting data from free text, generating impressions from radiology findings and creating structured reports from imaging data. All studies demonstrated optimism regarding ChatGPT's potential to aid radiologists, though common critiques included data privacy concerns, reliability, medical errors, and lack of medical-specific training.

Conclusion

ChatGPT and assistive AI have significant potential to transform radiology reporting, enhancing accuracy and standardization while optimizing healthcare resources. Future developments may involve integrating dynamic few-shot prompting, ChatGPT, and Retrieval Augmented Generation (RAG) into diagnostic workflows. Continued research, development, and ethical oversight are crucial to fully realize AI's potential in radiology.

Objective

In May 2009, we created a Facebook page for radiology education. While we shared a host of learning materials such as case images, quiz questions, and medical illustrations, we also posted world news, music, and memes. In February 2023, we eliminated everything from the site not related to radiology education. Our aim was to determine how focusing on radiology education alone would affect audience growth for our Facebook page.

Materials and methods

We exported our Facebook post data for the dates March 1, 2023 through February 29, 2024, to represent the full calendar year after we revised our content presentation, which we compared to data from November 1, 2020 to October 31, 2021. The mean and standard deviation for each post type's reach for 2023/24 were analyzed and compared against the 2020/21 statistics, and Wilcoxon rank sum tests were used to obtain p-values. Linear regressions for each year were performed to understand the relationship between reach and engagement.

Results

A total of 4,270 posts were included in our new analysis. Our average number of posts per day decreased from 24.8 to 11.71, reducing by more than half the amount of content shared to our social media page. Our posts had a mean overall reach of 4,660—compared to 1,743 in 2021 (p=0.0000). There was a statistically significant increase in reach for posts on artificial intelligence, case images, medical illustrations, pearls, quiz images, quiz videos, slideshow images, and both types of instructional videos (p<0.005). For both 2021 and 2024, the linear regression slopes were positive (y=0.0687x−65.0279 and y=0.006334x+21.3425, respectively).

Conclusions

Facebook and other social media have been found to be helpful sources for radiology education. Our experience and statistics with radiology education via social media may help other radiology educators better curate their own pages. To optimize experiences for students, professionals, and other users, and to reach more people, we found that providing readily accessible radiology education is preferred to the social aspects of social media.

Objective

MRI utilization in the United States is relatively higher than in other parts of the world and inpatient MRI utilization is particularly difficult to manage given the lack of direct reimbursement. Body MRI studies present an opportunity to reduce inpatient MRI utilization since they are generally the least emergent. Our objective was to use a targeted questionnaire to probe the necessity of inpatient body MRI orders and present an opportunity to either cancel them or transition them to the outpatient realm

Methods

A 9-item questionnaire was devised asking questions about the urgency of the inpatient MRI order including the urgent management question, an inpatient procedure or whether it was recommended by a consultant. Peer-to-peer discussion walking through each of the questions was conducted by radiology housestaff with the ordering clinicians and responses recorded.

Results

845 recorded responses reported a lack of specific clinical question in 23.9% of orders, 68.9% were recommended by a non-radiology consulting service and 16.1% were recommended by radiology studies. 17.0% orders were felt to be outpatient appropriate and 23.3% were considered possibly appropriate for the outpatient setting. 3.9% were canceled and 4.9% were transitioned to outpatient orders.

Discussion

Engaging in a focused discussion about the urgency and appropriateness of an inpatient MRI body order following a list of scripted questions has the potential to reduce utilization. This approach also highlights the relatively high rate of indication uncertainty among ordering clinicians and the central role of consultants in prompting orders.

Thoracic endovascular aneurysm repair (TEVAR) has replaced open surgical repair as the treatment of choice for several aortic conditions. Despite its lower morbidity and mortality, several TEVAR-related complications can occur and some of which may necessitate surgical or endovascular re-intervention. The current article reviews common and rare complications of TEVAR procedure with emphasis on complications identifiable on cross-sectional imaging and potential pitfalls of pre-procedural planning.

Purpose

The purpose of this study is to identify if the local institutional shift from routine overnight observation to same-day discharge following percutaneous cryoablation (PCA) of renal tumors increases 30 day re-admission rates or serious adverse events (AEs).

Materials and methods

This retrospective study included 133 adult patients. PCA patients in calendar years 2018-2019 were routinely observed overnight in the hospital, comprising the control group (Group A). PCA patients in calendar years 2021-2022 were routinely discharged the same day, comprising the test group (Group B). Relevant demographic information, tumor characteristics, technical outcomes, and clinical outcomes were recorded.

Results

15 patients (11.3 %) from the total cohort were re-admitted to the hospital within 30 days of PCA for any reason. Seven patients (10.4 %) and eight patients (12.1 %) were re-admitted for any reason within 30 days in Group A and Group B, respectively, with no difference between the two groups (p = 0.76). Nine patients (6.8 %) from the total cohort were re-admitted to the hospital within 30 days for a diagnosis secondary to the procedure. Four patients (6 %) and five patients (7.6 %) were re-admitted within 30 days for reasons related to PCA in Group A and Group B, respectively, with no significant difference between the groups (p = 0.71). Eight patients (12 %) and four patients (6 %) had major AEs following PCA in Group A and Group B, respectively, with no difference between the two groups (p = 0.43).

Conclusion

Overall, the change in post-procedural care after PCA did not have a deleterious effect on 30 day re-admission rates or rates of major AEs.

This article is about two highly diverse radiologists, who fortuitously came together by working as Career and Professional Advisors in the Student Affairs Department of a U.S. medical school. This job opportunity offered each radiologist, albeit for markedly different reasons, a means to transition from full-time Radiology to the opportune world of medical school education. The focus of this paper will be on Career and Professional Advising, while also highlighting the many opportunities for radiologists in current medical school education.

Introduction

Medical imaging has undergone significant technical advancements in recent years, posing a considerable challenge for radiologists to stay up-to-date with emerging modalities and their applications in daily practice. This challenge is even more daunting in developing countries with limited resources compared to the US and other developed nations with greater economic assets. The collaboration between the United States and other advanced nations with radiological institutions in Latin America has been a significant achievement in the pursuit of new opportunities for continuous medical education. The aim of this study was to evaluate the effectiveness of international collaborations among Spanish-speaking Latin American institutions and radiologists through a survey.

Materials and Methods

A group of radiologists and institutions from various countries, including the USA, Spain, and Argentina, who have been working together for several years to improve Radiology education across Latin America, were selected. An online survey was conducted. The survey included questions about interest in the activities, participation, and impact of radiologic education during these educational efforts.

Results

The survey received responses from 166 participants, all of whom reported knowledge of at least one type of educational activity. The most well-known activity was ALAT Webinars. The primary motivators for participation were the quality of the content and the opportunity to learn new information. Additionally, improving local education in radiology and receiving expert advice on radiology issues were identified as priorities for participation in international collaborations. The Cronbach alpha coefficient was calculated for individual and global Likert questions, resulting in a global score of 0.96.

Conclusion

The study confirms the significance of a multifaceted approach to address gaps in radiology education. While traditional models have relied on hosting international visitors or sending US teachers abroad, the results suggest that using a variety of methods will have a greater impact than relying on a single technique for those who benefit most from collaborative efforts.