Large Language Models for Simplified Interventional Radiology Reports: A Comparative Analysis.

PURPOSE: To quantitatively and qualitatively evaluate and compare the performance of leading large language models (LLMs), including proprietary models (GPT-4, GPT-3.5 Turbo, Claude-3-Opus, and Gemini Ultra) and open-source models (Mistral-7b and Mistral-8×7b), in simplifying 109 interventional radiology reports. METHODS: Qualitative performance was assessed using a five-point Likert scale for accuracy, completeness, clarity, clinical relevance, naturalness, and error rates, including trust-breaking and post-therapy misconduct errors. Quantitative readability was assessed using Flesch Reading Ease (FRE), Flesch-Kincaid Grade Level (FKGL), SMOG Index, and Dale-Chall Readability Score (DCRS). Paired t-tests and Bonferroni-corrected p-values were used for statistical analysis. RESULTS: Qualitative evaluation showed no significant differences between GPT-4 and Claude-3-Opus for any metrics evaluated (all Bonferroni-corrected p-values: p = 1), while they outperformed other assessed models across five qualitative metrics (p < 0.001). GPT-4 had the fewest content and trust-breaking errors, with Claude-3-Opus second. However, all models exhibited some level of trust-breaking and post-therapy misconduct errors, with GPT-4-Turbo and GPT-3.5-Turbo with few-shot prompting showing the lowest error rates, and Mistral-7B and Mistral-8×7B showing the highest. Quantitatively, GPT-4 surpassed Claude-3-Opus in all readability metrics (all p < 0.001), with a median FRE score of 69.01 (IQR: 64.88-73.14) versus 59.74 (IQR: 55.47-64.01) for Claude-3-Opus. GPT-4 also outperformed GPT-3.5-Turbo and Gemini Ultra (both p < 0.001). Inter-rater reliability was strong (κ = 0.77-0.84). CONCLUSIONS: GPT-4 and Claude-3-Opus demonstrated superior performance in generating simplified IR reports, but the presence of errors across all models, including trust-breaking errors, highlights the need for further refinement and validation before clinical implementation. CLINICAL RELEVANCE/APPLICATIONS: With the increasing complexity of interventional radiology (IR) procedures and the growing availability of electronic health records, simplifying IR reports is critical to improving patient understanding and clinical decision-making. This study provides insights into the performance of various LLMs in rewriting IR reports, which can help in selecting the most suitable model for clinical patient-centered applications.

Global cross-sectional student survey on AI in medical, dental, and veterinary education and practice at 192 faculties.

BACKGROUND: The successful integration of artificial intelligence (AI) in healthcare depends on the global perspectives of all stakeholders. This study aims to answer the research question: What are the attitudes of medical, dental, and veterinary students towards AI in education and practice, and what are the regional differences in these perceptions? METHODS: An anonymous online survey was developed based on a literature review and expert panel discussions. The survey assessed students' AI knowledge, attitudes towards AI in healthcare, current state of AI education, and preferences for AI teaching. It consisted of 16 multiple-choice items, eight demographic queries, and one free-field comment section. Medical, dental, and veterinary students from various countries were invited to participate via faculty newsletters and courses. The survey measured technological literacy, AI knowledge, current state of AI education, preferences for AI teaching, and attitudes towards AI in healthcare using Likert scales. Data were analyzed using descriptive statistics, Mann-Whitney U-test, Kruskal-Wallis test, and Dunn-Bonferroni post hoc test. RESULTS: The survey included 4313 medical, 205 dentistry, and 78 veterinary students from 192 faculties and 48 countries. Most participants were from Europe (51.1%), followed by North/South America (23.3%) and Asia (21.3%). Students reported positive attitudes towards AI in healthcare (median: 4, IQR: 3-4) and a desire for more AI teaching (median: 4, IQR: 4-5). However, they had limited AI knowledge (median: 2, IQR: 2-2), lack of AI courses (76.3%), and felt unprepared to use AI in their careers (median: 2, IQR: 1-3). Subgroup analyses revealed significant differences between the Global North and South (r = 0.025 to 0.185, all P < .001) and across continents (r = 0.301 to 0.531, all P < .001), with generally small effect sizes. CONCLUSIONS: This large-scale international survey highlights medical, dental, and veterinary students' positive perceptions of AI in healthcare, their strong desire for AI education, and the current lack of AI teaching in medical curricula worldwide. The study identifies a need for integrating AI education into medical curricula, considering regional differences in perceptions and educational needs. TRIAL REGISTRATION: Not applicable (no clinical trial).

Open Access Data and Deep Learning for Cardiac Device Identification on Standard DICOM and Smartphone-based Chest Radiographs.

Purpose To develop and evaluate a publicly available deep learning model for segmenting and classifying cardiac implantable electronic devices (CIEDs) on Digital Imaging and Communications in Medicine (DICOM) and smartphone-based chest radiographs. Materials and Methods This institutional review board-approved retrospective study included patients with implantable pacemakers, cardioverter defibrillators, cardiac resynchronization therapy devices, and cardiac monitors who underwent chest radiography between January 2012 and January 2022. A U-Net model with a ResNet-50 backbone was created to classify CIEDs on DICOM and smartphone images. Using 2321 chest radiographs in 897 patients (median age, 76 years [range, 18-96 years]; 625 male, 272 female), CIEDs were categorized into four manufacturers, 27 models, and one "other" category. Five smartphones were used to acquire 11 072 images. Performance was reported using the Dice coefficient on the validation set for segmentation or balanced accuracy on the test set for manufacturer and model classification, respectively. Results The segmentation tool achieved a mean Dice coefficient of 0.936 (IQR: 0.890-0.958). The model had an accuracy of 94.36% (95% CI: 90.93%, 96.84%; 251 of 266) for CIED manufacturer classification and 84.21% (95% CI: 79.31%, 88.30%; 224 of 266) for CIED model classification. Conclusion The proposed deep learning model, trained on both traditional DICOM and smartphone images, showed high accuracy for segmentation and classification of CIEDs on chest radiographs. Keywords: Conventional Radiography, Segmentation Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Júdice de Mattos Farina and Celi in this issue.

SenNet recommendations for detecting senescent cells in different tissues.

Once considered a tissue culture-specific phenomenon, cellular senescence has now been linked to various biological processes with both beneficial and detrimental roles in humans, rodents and other species. Much of our understanding of senescent cell biology still originates from tissue culture studies, where each cell in the culture is driven to an irreversible cell cycle arrest. By contrast, in tissues, these cells are relatively rare and difficult to characterize, and it is now established that fully differentiated, postmitotic cells can also acquire a senescence phenotype. The SenNet Biomarkers Working Group was formed to provide recommendations for the use of cellular senescence markers to identify and characterize senescent cells in tissues. Here, we provide recommendations for detecting senescent cells in different tissues based on a comprehensive analysis of existing literature reporting senescence markers in 14 tissues in mice and humans. We discuss some of the recent advances in detecting and characterizing cellular senescence, including molecular senescence signatures and morphological features, and the use of circulating markers. We aim for this work to be a valuable resource for both seasoned investigators in senescence-related studies and newcomers to the field.

Sensitivity of magnetic resonance elastography to extracellular matrix and cell motility in human prostate cancer cell line-derived xenograft models.

Prostate cancer (PCa) is a significant health problem in the male population of the Western world. Magnetic resonance elastography (MRE), an emerging medical imaging technique sensitive to mechanical properties of biological tissues, detects PCa based on abnormally high stiffness and viscosity values. Yet, the origin of these changes in tissue properties and how they correlate with histopathological markers and tumor aggressiveness are largely unknown, hindering the use of tumor biomechanical properties for establishing a noninvasive PCa staging system. To infer the contributions of extracellular matrix (ECM) components and cell motility, we investigated fresh tissue specimens from two PCa xenograft mouse models, PC3 and LNCaP, using magnetic resonance elastography (MRE), diffusion-weighted imaging (DWI), quantitative histology, and nuclear shape analysis. Increased tumor stiffness and impaired water diffusion were observed to be associated with collagen and elastin accumulation and decreased cell motility. Overall, LNCaP, while more representative of clinical PCa than PC3, accumulated fewer ECM components, induced less restriction of water diffusion, and exhibited increased cell motility, resulting in overall softer and less viscous properties. Taken together, our results suggest that prostate tumor stiffness increases with ECM accumulation and cell adhesion - characteristics that influence critical biological processes of cancer development. MRE paired with DWI provides a powerful set of imaging markers that can potentially predict prostate tumor development from benign masses to aggressive malignancies in patients. STATEMENT OF SIGNIFICANCE: Xenograft models of human prostate tumor cell lines, allowing correlation of microstructure-sensitive biophysical imaging parameters with quantitative histological methods, can be investigated to identify hallmarks of cancer.

Comparative Analysis of Multimodal Large Language Model Performance on Clinical Vignette Questions.

This study compares 2 large language models and their performance vs that of competing open-source models.

Artificial intelligence and machine learning in axial spondyloarthritis.

PURPOSE OF REVIEW: To evaluate the current applications and prospects of artificial intelligence and machine learning in diagnosing and managing axial spondyloarthritis (axSpA), focusing on their role in medical imaging, predictive modelling, and patient monitoring. RECENT FINDINGS: Artificial intelligence, particularly deep learning, is showing promise in diagnosing axSpA assisting with X-ray, computed tomography (CT) and MRI analyses, with some models matching or outperforming radiologists in detecting sacroiliitis and markers. Moreover, it is increasingly being used in predictive modelling of disease progression and personalized treatment, and could aid risk assessment, treatment response and clinical subtype identification. Variable study designs, sample sizes and the predominance of retrospective, single-centre studies still limit the generalizability of results. SUMMARY: Artificial intelligence technologies have significant potential to advance the diagnosis and treatment of axSpA, providing more accurate, efficient and personalized healthcare solutions. However, their integration into clinical practice requires rigorous validation, ethical and legal considerations, and comprehensive training for healthcare professionals. Future advances in artificial intelligence could complement clinical expertise and improve patient care through improved diagnostic accuracy and tailored therapeutic strategies, but the challenge remains to ensure that these technologies are validated in prospective multicentre trials and ethically integrated into patient care.

Comparison of diffusion-weighted MRI and [18F]FDG PET/MRI for treatment monitoring in pediatric Hodgkin and non-Hodgkin lymphoma.

OBJECTIVE: To compare tumor therapy response assessments with whole-body diffusion-weighted imaging (WB-DWI) and 18F-fluorodeoxyglucose ([18F]FDG) PET/MRI in pediatric patients with Hodgkin lymphoma and non-Hodgkin lymphoma. MATERIALS AND METHODS: In a retrospective, non-randomized single-center study, we reviewed serial simultaneous WB-DWI and [18F]FDG PET/MRI scans of 45 children and young adults (27 males; mean age, 13 years ± 5 [standard deviation]; age range, 1-21 years) with Hodgkin lymphoma (n = 20) and non-Hodgkin lymphoma (n = 25) between February 2018 and October 2022. We measured minimum tumor apparent diffusion coefficient (ADCmin) and maximum standardized uptake value (SUVmax) of up to six target lesions and assessed therapy response according to Lugano criteria and modified criteria for WB-DWI. We evaluated the agreement between WB-DWI- and [18F]FDG PET/MRI-based response classifications with Gwet's agreement coefficient (AC). RESULTS: After induction chemotherapy, 95% (19 of 20) of patients with Hodgkin lymphoma and 72% (18 of 25) of patients with non-Hodgkin lymphoma showed concordant response in tumor metabolism and proton diffusion. We found a high agreement between treatment response assessments on WB-DWI and [18F]FDG PET/MRI (Gwet's AC = 0.94; 95% confidence interval [CI]: 0.82, 1.00) in patients with Hodgkin lymphoma, and a lower agreement for patients with non-Hodgkin lymphoma (Gwet's AC = 0.66; 95% CI: 0.43, 0.90). After completion of therapy, there was an excellent agreement between WB-DWI and [18F]FDG PET/MRI response assessments (Gwet's AC = 0.97; 95% CI: 0.91, 1). CONCLUSION: Therapy response of Hodgkin lymphoma can be evaluated with either [18F]FDG PET or WB-DWI, whereas patients with non-Hodgkin lymphoma may benefit from a combined approach. CLINICAL RELEVANCE STATEMENT: Hodgkin lymphoma and non-Hodgkin lymphoma exhibit different patterns of tumor response to induction chemotherapy on diffusion-weighted MRI and PET/MRI. KEY POINTS: • Diffusion-weighted imaging has been proposed as an alternative imaging to assess tumor response without ionizing radiation. • After induction therapy, whole-body diffusion-weighted imaging and PET/MRI revealed a higher agreement in patients with Hodgkin lymphoma than in those with non-Hodgkin lymphoma. • At the end of therapy, whole-body diffusion-weighted imaging and PET/MRI revealed an excellent agreement for overall tumor therapy responses for all lymphoma types.

Mapping gender and geographic diversity in artificial intelligence research: Editor representation in leading computer science journals.

Background: The growing role of artificial intelligence (AI) in healthcare, particularly radiology, requires its unbiased and fair development and implementation, starting with the constitution of the scientific community. Purpose: To examine the gender and country distribution among academic editors in leading computer science and AI journals. Material and Methods: This cross-sectional study analyzed the gender and country distribution among editors-in-chief, senior, and associate editors in all 75 Q1 computer science and AI journals in the Clarivate Journal Citations Report and SCImago Journal Ranking 2022. Gender was determined using an open-source algorithm (Gender Guesser™), selecting the gender with the highest calibrated probability. Result: Among 4,948 editorial board members, women were underrepresented in all positions (editors-in-chief/senior editors/associate editors: 14%/18%/17%). The proportion of women correlated positively with the SCImago Journal Rank indicator (ρ = 0.329; p = .004). The U.S., the U.K., and China comprised 50% of editors, while Australia, Finland, Estonia, Denmark, the Netherlands, the U.K., Switzerland, and Slovenia had the highest women editor representation per million women population. Conclusion: Our results highlight gender and geographic disparities on leading computer science and AI journal editorial boards, with women being underrepresented in all positions and a disproportional relationship between the Global North and South.

Artificial intelligence to analyze magnetic resonance imaging in rheumatology.

Rheumatic disorders present a global health challenge, marked by inflammation and damage to joints, bones, and connective tissues. Accurate, timely diagnosis and appropriate management are crucial for favorable patient outcomes. Magnetic resonance imaging (MRI) has become indispensable in rheumatology, but interpretation remains laborious and variable. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), offers a means to improve and advance MRI analysis. This review examines current AI applications in rheumatology MRI analysis, addressing diagnostic support, disease classification, activity assessment, and progression monitoring. AI demonstrates promise, with high sensitivity, specificity, and accuracy, achieving or surpassing expert performance. The review also discusses clinical implementation challenges and future research directions to enhance rheumatic disease diagnosis and management.

Sex-specific diagnostic efficacy of MRI in axial spondyloarthritis: challenging the 'One Size Fits All' notion.

OBJECTIVES: Sex-specific differences in the presentation of axial spondyloarthritis (axSpA) may contribute to a diagnostic delay in women. The aim of this study was to investigate the diagnostic performance of MRI findings comparing men and women. METHODS: Patients with back pain from six different prospective cohorts (n=1194) were screened for inclusion in this post hoc analysis. Two blinded readers scored the MRI data sets independently for the presence of ankylosis, erosion, sclerosis, fat metaplasia and bone marrow oedema. Χ2 tests were performed to compare lesion frequencies. Contingency tables were used to calculate markers for diagnostic performance, with clinical diagnosis as the standard of reference. The positive and negative likelihood ratios (LR+/LR-) were used to calculate the diagnostic OR (DOR) to assess the diagnostic performance. RESULTS: After application of exclusion criteria, 526 patients (379 axSpA (136 women and 243 men) and 147 controls with chronic low back pain) were included. No major sex-specific differences in the diagnostic performance were shown for bone marrow oedema (DOR m: 3.0; f: 3.9). Fat metaplasia showed a better diagnostic performance in men (DOR 37.9) than in women (DOR 5.0). Lower specificity was seen in women for erosions (77% vs 87%), sclerosis (44% vs 66%), fat metaplasia (87% vs 96%). CONCLUSION: The diagnostic performance of structural MRI markers is substantially lower in female patients with axSpA; active inflammatory lesions show comparable performance in both sexes, while still overall inferior to structural markers. This leads to a comparably higher risk of false positive findings in women.

Biomedical Ethical Aspects Towards the Implementation of Artificial Intelligence in Medical Education.

The increasing use of artificial intelligence (AI) in medicine is associated with new ethical challenges and responsibilities. However, special considerations and concerns should be addressed when integrating AI applications into medical education, where healthcare, AI, and education ethics collide. This commentary explores the biomedical ethical responsibilities of medical institutions in incorporating AI applications into medical education by identifying potential concerns and limitations, with the goal of implementing applicable recommendations. The recommendations presented are intended to assist in developing institutional guidelines for the ethical use of AI for medical educators and students.

Tyrosine kinase inhibitor therapy in pediatric sarcoma: Prognostic implications of pulmonary metastatic cavitation.

PURPOSES: This study aims to ascertain the prevalence of cavitations in pulmonary metastases among pediatric and young adult patients with sarcoma undergoing tyrosine kinase inhibitor (TKI) therapy, and assess whether cavitation can predict clinical response and survival outcomes. METHODS: In a single-center retrospective analysis, we examined chest computed tomography (CT) scans of 17 patients (median age 16 years; age range: 4-25 years) with histopathologically confirmed bone (n = 10) or soft tissue (n = 7) sarcoma who underwent TKI treatment for lung metastases. The interval between TKI initiation and the onset of lung nodule cavitation and tumor regrowth were assessed. The combination of all imaging studies and clinical data served as the reference standard for clinical responses. Progression-free survival (PFS) was compared between patients with cavitating and solid nodules using Kaplan-Meier survival analysis and log-rank test. RESULTS: Five out of 17 patients (29%) exhibited cavitation of pulmonary nodules during TKI therapy. The median time from TKI initiation to the first observed cavitation was 79 days (range: 46-261 days). At the time of cavitation, all patients demonstrated stable disease. When the cavities began to fill with solid tumor, 60% (3/5) of patients exhibited progression in other pulmonary nodules. The median PFS for patients with cavitated pulmonary nodules after TKI treatment (6.7 months) was significantly longer compared to patients without cavitated nodules (3.8 months; log-rank p-value = .03). CONCLUSIONS: Cavitation of metastatic pulmonary nodules in sarcoma patients undergoing TKI treatment is indicative of non-progressive disease, and significantly correlates with PFS.

Measurement of Tumor T2* Relaxation Times after Iron Oxide Nanoparticle Administration.

T2* relaxometry is one of the established methods to measure the effect of superparamagnetic iron oxide nanoparticles on tumor tissues with magnetic resonance imaging (MRI). Iron oxide nanoparticles shorten the T1, T2, and T2* relaxation times of tumors. While the T1 effect is variable based on the size and composition of the nanoparticles, the T2 and T2* effects are usually predominant, and T2* measurements are the most time-efficient in a clinical context. Here, we present our approach to measuring tumor T2* relaxation times, using multi-echo gradient echo sequences, external software, and a standardized protocol for creating a T2* map with scanner-independent software. This facilitates the comparison of imaging data from different clinical scanners, different vendors, and co-clinical research work (i.e., tumor T2* data obtained in mouse models and patients). Once the software is installed, the T2 Fit Map plugin needs to be installed from the plugin manager. This protocol provides step-by-step procedural details, from importing the multi-echo gradient echo sequences into the software, to creating color-coded T2* maps and measuring tumor T2* relaxation times. The protocol can be applied to solid tumors in any body part and has been validated based on preclinical imaging data and clinical data in patients. This could facilitate tumor T2* measurements for multi-center clinical trials and improve the standardization and reproducibility of tumor T2* measurements in co-clinical and multi-center data analyses.

MegaPro, a clinically translatable nanoparticle for in vivo tracking of stem cell implants in pig cartilage defects.

Rationale: Efficient labeling methods for mesenchymal stem cells (MSCs) are crucial for tracking and understanding their behavior in regenerative medicine applications, particularly in cartilage defects. MegaPro nanoparticles have emerged as a potential alternative to ferumoxytol nanoparticles for this purpose. Methods: In this study, we employed mechanoporation to develop an efficient labeling method for MSCs using MegaPro nanoparticles and compared their effectiveness with ferumoxytol nanoparticles in tracking MSCs and chondrogenic pellets. Pig MSCs were labeled with both nanoparticles using a custom-made microfluidic device, and their characteristics were analyzed using various imaging and spectroscopy techniques. The viability and differentiation capacity of labeled MSCs were also assessed. Labeled MSCs and chondrogenic pellets were implanted into pig knee joints and monitored using MRI and histological analysis. Results: MegaPro-labeled MSCs demonstrated shorter T2 relaxation times, higher iron content, and greater nanoparticle uptake compared to ferumoxytol-labeled MSCs, without significantly affecting their viability and differentiation capacity. Post-implantation, MegaPro-labeled MSCs and chondrogenic pellets displayed a strong hypointense signal on MRI with considerably shorter T2* relaxation times compared to adjacent cartilage. The hypointense signal of both MegaPro- and ferumoxytol-labeled chondrogenic pellets decreased over time. Histological evaluations showed regenerated defect areas and proteoglycan formation with no significant differences between the labeled groups. Conclusion: Our study demonstrates that mechanoporation with MegaPro nanoparticles enables efficient MSC labeling without affecting viability or differentiation. MegaPro-labeled cells show enhanced MRI tracking compared to ferumoxytol-labeled cells, emphasizing their potential in clinical stem cell therapies for cartilage defects.