Current Problems in Diagnostic Radiology最新文献

Rational and objective

Diversity, equity, inclusion, and representation in various sectors have garnered increasing attention in the past two decades, including healthcare. In this report we investigate representation of females and underrepresented minorities (URM) in the field of radiology and asses for significant growth trends in representation in residency training programs in the United States.

Materials and methods

De-identified trainee demographic information for active radiology trainees from 2016 to 2021 was queried using the Accreditation Council for Graduate Medical Education (ACGME), and new radiology trainees using the National Resident Matching Program (NRMP)’s Main Residency Match Data and Reports databooks.

Results

In 2021 females represented 26.7% of DR residency trainees and 22% of IR integrated trainees. In the same year URM trainees represented 11.3% of trainees and 8.7% of IR integrated trainees. From 2017 to 2021, diagnostic radiology had a compound average growth rate (CAGR) 1% (p <0.01) of female representation and 1.12% (p<0.01) of URM representation.

Conclusion

This study quantifies female and underrepresented minority representation among radiology trainees for diagnostic radiology and radiology subspecialities, identifying modest uptrends in representation within both demographics.

Medical students are often regarded purely as learners, but many can also perform well as educators. When more senior students are on service with underclassmen, especially when attendings and residents are busy, they can play an important role in helping to advance a radiology department's teaching mission.

Medical imaging is essential for the proper diagnosis and treatment of many diseases. The literature has found that medical imaging generally accounts for a significant percentage of total healthcare spending. We analyzed a national database between 2013 and 2021, with more than 19 million patients on average, to review which health conditions account for the highest spending on medical imaging in the Colombian health system. We segmented the analysis by type of medical imaging, life cycles, health condition and sex. Our findings indicate that cardiac and mental illnesses account for the highest per capita spending on medical imaging, especially for the elderly. As a proportion of total expenditure, hypertension and tuberculosis are added, with special emphasis on the infancy-childhood life cycle.

Seminal vesicles play a crucial role in the male reproductive system, as they are responsible for secreting a fluid that forms most of the ejaculate. Seminal vesicles' pathology can present with non-specific symptoms, making imaging diagnosis essential for proper patient management. Various imaging modalities can be used to evaluate these glands, with MRI beneficial in illustrating the spectrum of seminal vesicle disease. Typical seminal vesicles appear as elongated fluid-containing structures, but congenital anomalies, inflammatory conditions, and neoplastic disorders can alter their appearance. Furthermore, differentiating mimics from actual pathology can be challenging but crucial for proper management.

This article aims to provide an overview of the typical imaging appearance of the seminal vesicles and illustrate the principal imaging characteristics of conditions involving these structures. It will review the imaging characteristics of common and uncommon lesions involving the seminal vesicles by exploring congenital, infectious, and neoplastic in detail. As the seminal vesicles are often evaluated incidentally during prostate imaging, radiologists should be aware of the variability of normal findings and recognize the principal pathologies affecting these structures to ensure proper patient management.

Purpose

We developed machine learning (ML) models to assess demographic and socioeconomic status (SES) variables’ value in predicting continued participation in a low-dose CT lung cancer screening (LCS) program.

Materials and Methods

480 LCS subjects were retrospectively examined for the following outcomes: (#1) no follow-up (single LCS scan) vs. multiple follow-ups (220 and 260 subjects respectively) and (#2) absent or delayed (>1 month past the due date) follow-up vs timely follow-up (356 and 124 subjects respectively). We quantified the contributions of 14 socioeconomic, demographic, and clinical predictors to LCS adherence, and validated and compared prediction performances of multivariate logistic regression (MLR), support vector machine (SVM) and shallow neural network (NN) models.

Results

For outcome #1, age, sex, race, insurance status, personal cancer history, and median household income were found to be associated with returning for follow-ups. For outcome #2, age, sex, race, and insurance status were significant predictor of absent/delayed LCS follow-up. Across 5-fold cross-validation, the MLR model achieved an average AUC of 0.732 (95% CI, 0.661-0.803) for outcome #1 and 0.633 (95% CI, 0.602-0.664) for outcome #2 and is the model with best predictive performance overall, whereas NN and SVM tended to overfit training data and fell short on testing data performance for either outcome.

Conclusions

We identified significant predictors of LCS adherence, and our ML models can predict which subjects are at higher risk of receiving no or delayed LCS follow-ups. Our results could inform data-driven interventions to engage vulnerable populations and extend the benefits of LCS.

Objective

This study aimed to assess the feasibility of GPT-4 for answering questions related to contrast media with and without the context of the European Society of Urogenital Radiology (ESUR) guideline on contrast agents. The overarching goal was to determine whether contextual enrichment by providing guideline information improves answers of GPT-4 for clinical decision-making in radiology.

Methods

A set of 64 questions, based on the ESUR guideline on contrast agents mirroring pertinent sections, was developed and posed to GPT-4 both directly and after providing the guideline using a plugin. Responses were graded by experienced radiologists for quality of information and accuracy in pinpointing information from the guideline as well as by radiology residents for utility, using Likert-scales.

Results

GPT-4′s performance improved significantly with the guideline. Without the guideline, average quality rating was 3.98, which increased to 4.33 with the guideline (p = 0036). In terms of accuracy, 82.3% of answers matched the information from the guideline. Utility scores also reflected a significant improvement with the guideline, with average scores of 4.1 (without) and 4.4 (with) (p = 0.008) with a Fleiss´ Kappa of 0.44.

Conclusion

GPT-4, when contextually enriched with a guideline, demonstrates enhanced capability in providing guideline-backed recommendations. This approach holds promise for real-time clinical decision-support, making guidelines more actionable. However, further refinements are necessary to maximize the potential of large language models (LLMs). Inherent limitations need to be addressed.

Objective

To assess the hepatic disease-free survival (HDFS) and overall survival (OS) of patients who underwent resection of colorectal cancer liver metastases (CRCLM) in our population, and evaluate what factors are associated with these outcomes.

Methods

Patients with resected non-mucinous CRCLM between January 2013-February 2020 were retrospectively identified. Dates of diagnosis, surgery, and, if applicable, death were recorded. HDFS and OS were calculated using a census date of 24 September 2022. Separate Cox multivariate regression analyses were performed to evaluate for association between HDFS and OS and the following factors: pre-operative imaging interval (<4 weeks vs. ≥4 weeks); pre-operative imaging modality (CT only vs. MRI+CT); extrahepatic disease at time of hepatectomy (yes vs. no); tumor burden score (TBS, where TBS² = (largest axial dimension of CRCLM)² + (number of CRCLM)²); pT and pN; and neoadjuvant chemotherapy.

Results

137 subjects (mean age, 61 ± 11 years, 86 males) were included. Associations with recurrent hepatic disease were found with chemotherapy (HR 2.11[95 % CI = 1.13–3.92]), TBS (HR 1.30[95 % CI = 1.17–1.45]), MRI+CT (HR 2.12[95 % CI = 1.29–3.48]), and extrahepatic disease at hepatectomy (HR 2.16[95 % CI = 1.08–4.35]). For mortality, associations were found with TBS (HR 1.22[95 % CI = 1.09–1.37]), pT (HR 1.45[95 % CI = 1.05–2.00]), and extrahepatic disease at hepatectomy (HR 2.10[95 % CI = 1.31–3.36]).

Conclusion

In our population, non-imaging related factors TBS, neoadjuvant chemotherapy, pT and presence of extrahepatic disease at time of hepatectomy were associated with HDFS and/or OS. The preoperative imaging interval and use of preoperative MRI were not associated with improved patient outcomes.

Introduction

The construction and results of a multiple-reader multiple-case prostate MRI study are described and reported to illustrate recommendations for how to standardize artificial intelligence (AI) prostate studies per the review constituting Part I¹.

Methods

Our previously reported approach was applied to review and report an IRB approved, HIPAA compliant multiple-reader multiple-case clinical study of 150 bi-parametric prostate MRI studies across 9 readers, measuring physician performance both with and without the use of the recently FDA cleared CADe/CADx software ProstatID.

Results

Unassisted reader AUC values ranged from 0.418 – 0.759, with AI assisted AUC values ranging from 0.507 – 0.787. This represented a statistically significant AUC improvement of 0.045 (α = 0.05). A free-response ROC (FROC) analysis similarly demonstrated a statistically significant increase in θ from 0.405 to 0.453 (α = 0.05). The standalone performance of ProstatID performed across all prostate tissues demonstrated an AUC of 0.929, while the standalone lesion level performance of ProstatID at all biopsied locations achieved an AUC of 0.710.

Conclusion

This study applies and illustrates suggested reporting and standardization methods for prostate AI studies that will make it easier to understand, evaluate and compare between AI studies. Providing radiologists with the ProstatID CADe/CADx software significantly increased diagnostic performance as assessed by both ROC and free-response ROC metrics. Such algorithms have the potential to improve radiologist performance in the detection and localization of clinically significant prostate cancer.

MRI has firmly established itself as a mainstay for the detection, staging and surveillance of prostate cancer. Despite its success, prostate MRI continues to suffer from poor inter-reader variability and a low positive predictive value. The recent emergence of Artificial Intelligence (AI) to potentially improve diagnostic performance shows great potential. Understanding and interpreting the AI landscape as well as ever-increasing research literature, however, is difficult. This is in part due to widely varying study design and reporting techniques. This paper aims to address this need by first outlining the different types of AI used for the detection and diagnosis of prostate cancer, next deciphering how data collection methods, statistical analysis metrics (such as ROC and FROC analysis) and end points/outcomes (lesion detection vs. case diagnosis) affect the performance and limit the ability to compare between studies. Finally, this work explores the need for appropriately enriched investigational datasets and proper ground truth, and provides guidance on how to best conduct AI prostate MRI studies. Published in parallel, a clinical study applying this suggested study design was applied to review and report a multiple-reader multiple-case clinical study of 150 bi-parametric prostate MRI studies across nine readers, measuring physician performance both with and without the use of a recently FDA cleared Artificial Intelligence software.¹