Evaluating large language model-generated brain MRI protocols: performance of GPT4o, o3-mini, DeepSeek-R1 and Qwen2.5-72B.

Objectives: To evaluate the potential of LLMs to generate sequence-level brain MRI protocols.

Materials And Methods: This retrospective study employed a dataset of 150 brain MRI cases derived from local imaging request forms. Reference protocols were established by two neuroradiologists.

Spatial tumour characteristics as an indirect marker of metabolic dysregulation: evaluation for non-invasive IDH-genotyping of glioma using hybrid [18 F]FET-PET/MRI.

Purpose: The isocitrate dehydrogenase (IDH) genotype is crucial for diagnosing and managing adult-type diffuse glioma. We investigated spatial tumour characteristics in treatment-naïve glioma using an U-Net-based CNN and evaluated associations with metabolic dysfunction and IDH genotype.

Methods: Between 2015 and 2024 patients with confirmed contrast-enhancing glioma were pre-operatively investigated using MRI or [18 F]FET PET/MRI.

Segmenting Whole-Body MRI and CT for Multiorgan Anatomic Structure Delineation.

Purpose To develop and validate MRSegmentator, a retrospective cross-modality deep learning model for multiorgan segmentation of MRI scans. Materials and Methods This retrospective study trained MRSegmentator on 1,200 manually annotated UK Biobank Dixon MRI sequences (50 participants), 221 in-house abdominal MRI sequences (177 patients), and 1228 CT scans from the TotalSegmentator-CT dataset. A human-in-the-loop annotation workflow leveraged cross-modality transfer learning from an existing CT segmentation model to segment 40 anatomic structures.

AI-Enhanced 3D Gradient Echo MRI: A Radiation-Free Alternative to CT for Lung Nodule Detection and Lung-RADS Classification.

Rationale And Objectives: This study aims to evaluate the capabilities of a 3D gradient echo MRI sequence for the detection and classification of pulmonary nodules, specifically in relation to the lung CT screening reporting and data system (Lung-RADS).

Materials And Methods: In a prospective trial, 75 patients (mean age 65±12years; 44% women) with benign and malignant lung nodules (March 2022-July 2024) underwent chest CT and 3D gradient echo MRI using parallel imaging, compressed sensing, and AI acceleration (CSAI). Three radiologists (experience: 4, 9, and 10 years) assessed detection rates, nodule size, morphology, and Lung-RADS classification in a blinded study.

Privacy-Preserving Generation of Structured Lymphoma Progression Reports from Cross-sectional Imaging: A Comparative Analysis of Llama 3.3 and Llama 4.

Efficient processing of radiology reports for monitoring disease progression is crucial in oncology. Although large language models (LLMs) show promise in extracting structured information from medical reports, privacy concerns limit their clinical implementation. This study evaluates the feasibility and accuracy of two of the most recent Llama models for generating structured lymphoma progression reports from cross-sectional imaging data in a privacy-preserving, real-world clinical setting.

High-resolution 3D whole-heart bright- and black-blood imaging with co-registered T2 mapping at 0.55 T.

Introduction: Conventional CMR exams for assessment of cardiac anatomy and tissue characterization require multiple sequential 2D acquisitions under breath-hold in different orientations, in addition to being limited to 1.5 T and 3 T.

Methods: In this study, we sought to develop a novel 3D motion-compensated free-breathing sequence for comprehensive high-resolution whole-heart assessment of cardiovascular anatomy via simultaneous bright- and black-blood imaging and co-registered myocardial tissue quantification in a one-click scan at 0.

Do We Need Early Detection of Grade Group 2 Prostate Cancer in a Screening Program for Young Men? Results from the PROBASE Screening Trial.

In general, low-risk and favorable intermediate-risk prostate cancers (PCs; International Society of Urological Pathology grade group [GG] 1 and GG 2) are slow-growing cancers with low metastatic potential. Active surveillance is recommended for GG 1 PC and can be recommended for GG 2 PC in the absence of adverse pathological parameters. Therefore, the question arises as to when low-grade PC should be detected in a screening setting.

Performance of open-source and proprietary large language models in generating patient-friendly radiology chest CT reports.

Rationale And Objectives: Large Language Models (LLMs) show promise for generating patient-friendly radiology reports, but the performance of open-source versus proprietary LLMs needs assessment. To compare open-source and proprietary LLMs in generating patient-friendly radiology reports from chest CTs using quantitative readability metrics and qualitative assessments by radiologists.

Materials And Methods: Fifty chest CT reports were processed by seven LLMs: three open-source models (Llama-3-70b, Mistral-7b, Mixtral-8x7b) and four proprietary models (GPT-4, GPT-3.

Leveraging Large Language Models for Accurate AO Fracture Classification from CT Text Reports.

Large language models (LLMs) have shown promising potential in analyzing complex textual data, including radiological reports. These models can assist clinicians, particularly those with limited experience, by integrating and presenting diagnostic criteria within radiological classifications. However, before clinical adoption, LLMs must be rigorously validated by medical professionals to ensure accuracy, especially in the context of advanced radiological classification systems.

Leveraging large language models for accurate classification of liver lesions from MRI reports.

Background & Aims: The rapid advancement of large language models (LLMs) has generated interest in their potential integration in clinical workflows. However, their effectiveness in interpreting complex (imaging) reports remains underexplored and has at times yielded suboptimal results. This study aims to assess the capability of state-of-the-art LLMs to classify liver lesions based solely on textual descriptions from MRI reports, challenging the models to interpret nuanced medical language and diagnostic criteria.

Multinational Attitudes Toward AI in Health Care and Diagnostics Among Hospital Patients.

Importance: The successful implementation of artificial intelligence (AI) in health care depends on its acceptance by key stakeholders, particularly patients, who are the primary beneficiaries of AI-driven outcomes.

Objectives: To survey hospital patients to investigate their trust, concerns, and preferences toward the use of AI in health care and diagnostics and to assess the sociodemographic factors associated with patient attitudes.

Design, Setting, And Participants: This cross-sectional study developed and implemented an anonymous quantitative survey between February 1 and November 1, 2023, using a nonprobability sample at 74 hospitals in 43 countries.

Intermuscular adipose tissue and lean muscle mass assessed with MRI in people with chronic back pain in Germany: a retrospective observational study.

Background: Chronic back pain (CBP) affects over 80 million people in Europe, contributing to substantial healthcare costs and disability. Understanding modifiable risk factors, such as muscle composition, may aid in prevention and treatment. This study investigates the association between lean muscle mass (LMM) and intermuscular adipose tissue (InterMAT) with CBP using noninvasive whole-body magnetic resonance imaging (MRI).

Prostate Cancer Detection in Younger Men: A Comparative Analysis of Systematic and Magnetic Resonance Imaging-targeted Biopsy in the PROBASE Trial.

The optimal approach for prostate cancer (PC) screening, including the ideal starting age and most effective diagnostic method, remains under investigation. We evaluated the diagnostic performance of magnetic resonance imaging (MRI)-targeted biopsy (TBx) and systematic biopsy (SBx) in detecting clinically significant PC (csPC) in men aged 45-50 yr in PROBASE, a prospective, randomized trial of a risk-adapted screening strategy. A total of 525 participants with elevated prostate-specific antigen (≥3 ng/ml) underwent MRI followed by biopsy.

Deep learning-based acceleration of high-resolution compressed sense MR imaging of the hip.

Purpose: To evaluate a Compressed Sense Artificial Intelligence framework (CSAI) incorporating parallel imaging, compressed sense (CS), and deep learning for high-resolution MRI of the hip, comparing it with standard-resolution CS imaging.

Methods: Thirty-two patients with femoroacetabular impingement syndrome underwent 3 T MRI scans. Coronal and sagittal intermediate-weighted TSE sequences with fat saturation were acquired using CS (0.

Lung volume assessment for mean dark-field coefficient calculation using different determination methods.

Background: Accurate lung volume determination is crucial for reliable dark-field imaging. We compared different approaches for the determination of lung volume in mean dark-field coefficient calculation.

Methods: In this retrospective analysis of data prospectively acquired between October 2018 and October 2020, patients at least 18 years of age who underwent chest computed tomography (CT) were screened for study participation.

Deep learning and conventional hip MRI for the detection of labral and cartilage abnormalities using arthroscopy as standard of reference.

Objectives: To evaluate the performance of high-resolution deep learning-based hip MR imaging (CSAI) compared to standard-resolution compressed sense (CS) sequences using hip arthroscopy as standard of reference.

Methods: Thirty-two patients (mean age, 37.5 years (± 11.

Evaluating the effectiveness of biomedical fine-tuning for large language models on clinical tasks.

Objectives: Large language models (LLMs) have shown potential in biomedical applications, leading to efforts to fine-tune them on domain-specific data. However, the effectiveness of this approach remains unclear. This study aims to critically evaluate the performance of biomedically fine-tuned LLMs against their general-purpose counterparts across a range of clinical tasks.

Dark-field chest radiography signal characteristics in inspiration and expiration in healthy and emphysematous subjects.

Background: Dark-field chest radiography is sensitive to the lung alveolar structure. We evaluated the change of dark-field signal between inspiration and expiration.

Methods: From 2018 to 2020, patients who underwent chest computed tomography (CT) were prospectively enrolled, excluding those with any lung condition besides emphysema visible on CT.

Evaluation of a Retrieval-Augmented Generation-Powered Chatbot for Pre-CT Informed Consent: a Prospective Comparative Study.

This study aims to investigate the feasibility, usability, and effectiveness of a Retrieval-Augmented Generation (RAG)-powered Patient Information Assistant (PIA) chatbot for pre-CT information counseling compared to the standard physician consultation and informed consent process. This prospective comparative study included 86 patients scheduled for CT imaging between November and December 2024. Patients were randomly assigned to either the PIA group (n = 43), who received pre-CT information via the PIA chat app, or the control group (n = 43), with standard doctor-led consultation.

Longitudinal assessment of changes in muscle composition using proton density fat fraction and T2* in patients with and without incidental vertebral compression fractures.

Objective: Chemical shift encoded-based water-fat separation magnetic resonance imaging (CSE-MRI) is an emerging noninvasive tool for the assessment of bone and muscle composition. This study aims to examine both the predictive value and the longitudinal change of proton density fat fraction (PDFF) and T2* in the paraspinal muscles (PSM) in patients with and without the development of an incidental vertebral compression fracture (VCFs) after 6 months of follow-up.

Methods: Patients (N=56) with CT and 3T CSE-MRI of the lumbar spine at baseline and CSE-MRI at 6 months follow-up were included in this retrospective study.

Whole pancreas water T mapping at 3 Tesla.

Purpose: A fast T mapping method of the whole pancreas remains a challenge, due to the complex anatomy of the organ. In addition, a technique for pancreas water T mapping is needed, since the T is biased in the presence of fat. The purpose of this work is to accelerate the acquisition of water selective T (wT) mapping for the whole pancreas at 3 T.

Automated CT Measurement of Total Kidney Volume for Predicting Renal Function Decline after Lu Prostate-specific Membrane Antigen-I&T Radioligand Therapy.

Background Lutetium 177 (Lu) prostate-specific membrane antigen (PSMA) radioligand therapy is a novel treatment option for metastatic castration-resistant prostate cancer. Evidence suggests nephrotoxicity is a delayed adverse effect in a considerable proportion of patients. Purpose To identify predictive markers for clinically significant deterioration of renal function in patients undergoing Lu-PSMA-I&T radioligand therapy.

Comparison of dark-field chest radiography and CT for the assessment of COVID-19 pneumonia.

Background: Dark-field chest radiography allows the assessment of the structural integrity of the alveoli by exploiting the wave properties of x-rays.

Purpose: To compare the qualitative and quantitative features of dark-field chest radiography in patients with COVID-19 pneumonia with conventional CT imaging.

Materials And Methods: In this prospective study conducted from May 2020 to December 2020, patients aged at least 18 years who underwent chest CT for clinically suspected COVID-19 infection were screened for participation.

Current applications and challenges in large language models for patient care: a systematic review.

Background: The introduction of large language models (LLMs) into clinical practice promises to improve patient education and empowerment, thereby personalizing medical care and broadening access to medical knowledge. Despite the popularity of LLMs, there is a significant gap in systematized information on their use in patient care. Therefore, this systematic review aims to synthesize current applications and limitations of LLMs in patient care.