Explore the vast range of titles available.

Objectives To assess the quality of simplified radiology reports generated with the large language model (LLM) ChatGPT and to discuss challenges and chances of ChatGPT-like LLMs for medical text simplification. Methods In this exploratory case study, a radiologist created three fictitious radiology reports which we simplified by prompting ChatGPT with “Explain this medical report to a child using simple language.” In a questionnaire, we tasked 15 radiologists to rate the quality of the simplified radiology reports with respect to their factual correctness, completeness, and potential harm for patients. We used Likert scale analysis and inductive free-text categorization to assess the quality of the simplified reports. Results Most radiologists agreed that the simplified reports were factually correct, complete, and not potentially harmful to the patient. Nevertheless, instances of incorrect statements, missed relevant medical information, and potentially harmful passages were reported. Conclusion While we see a need for further adaption to the medical field, the initial insights of this study indicate a tremendous potential in using LLMs like ChatGPT to improve patient-centered care in radiology and other medical domains. Clinical relevance statement Patients have started to use ChatGPT to simplify and explain their medical reports, which is expected to affect patient-doctor interaction. This phenomenon raises several opportunities and challenges for clinical routine. Key Points • Patients have started to use ChatGPT to simplify their medical reports, but their quality was unknown. • In a questionnaire, most participating radiologists overall asserted good quality to radiology reports simplified with ChatGPT. However, they also highlighted a notable presence of errors, potentially leading patients to draw harmful conclusions. • Large language models such as ChatGPT have vast potential to enhance patient-centered care in radiology and other medical domains. To realize this potential while minimizing harm, they need supervision by medical experts and adaption to the medical field. Graphical Abstract

Myeloma-associated bone disease (MBD) develops in about 80–90% of patients and severely affects their quality of life, as it accounts for the majority of mortality and morbidity. Imaging in multiple myeloma (MM) and MBD is of utmost importance in order to detect bone and bone marrow lesions as well as extraosseous soft-tissue masses and complications before the initiation of treatment. It is required for determination of the stage of disease and aids in the assessment of treatment response. Whole-body low-dose computed tomography (WBLDCT) is the key modality to establish the initial diagnosis of MM and is now recommended as reference standard procedure for the detection of lytic destruction in MBD. In contrast, whole-body magnetic resonance imaging (WBMRI) has higher sensitivity for the detection of focal and diffuse plasma cell infiltration patterns of the bone marrow and identifies them prior to osteolytic destruction. It is recommended for the evaluation of spinal and vertebral lesions, while functional, diffusion-weighted MRI (DWI-MRI) is a promising tool for the assessment of treatment response. This review addresses the current improvements and limitations of WBCT and WBMRI for diagnosis and staging in MM, underlining the fact that both modalities offer complementary information. It further summarizes the corresponding radiological findings and novel technological aspects of both modalities.

PurposeThe advent of immune checkpoint inhibitors (ICIs) has revolutionized the treatment of advanced NSCLC, leading to a string of approvals in recent years. Herein, a narrative review on the role of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) in the ever-evolving treatment landscape of advanced NSCLC is presented.MethodsThis comprehensive review will begin with an introduction into current treatment paradigms incorporating ICIs; the evolution of CT-based criteria; moving onto novel phenomena observed with ICIs and the current state of hybrid imaging for diagnosis, treatment planning, evaluation of treatment efficacy and toxicity in advanced NSCLC, also taking into consideration its limitations and future directions.ConclusionsThe advent of ICIs marks the dawn of a new era bringing forth new challenges particularly vis-à-vis treatment response assessment and observation of novel phenomena accompanied by novel systemic side effects. While FDG PET/CT is widely adopted for tumor volume delineation in locally advanced disease, response assessment to immunotherapy based on current criteria is of high clinical value but has its inherent limitations. In recent years, modifications of established (PET)/CT criteria have been proposed to provide more refined approaches towards response evaluation. Not only a comprehensive inclusion of PET-based response criteria in prospective randomized controlled trials, but also a general harmonization within the variety of PET-based response criteria is pertinent to strengthen clinical implementation and widespread use of hybrid imaging for response assessment in NSCLC.

Objectives Diagnostic accuracy of artificial intelligence (AI) pneumothorax (PTX) detection in chest radiographs (CXR) is limited by the noisy annotation quality of public training data and confounding thoracic tubes (TT). We hypothesize that in-image annotations of the dehiscent visceral pleura for algorithm training boosts algorithm’s performance and suppresses confounders. Methods Our single-center evaluation cohort of 3062 supine CXRs includes 760 PTX-positive cases with radiological annotations of PTX size and inserted TTs. Three step-by-step improved algorithms (differing in algorithm architecture, training data from public datasets/clinical sites, and in-image annotations included in algorithm training) were characterized by area under the receiver operating characteristics (AUROC) in detailed subgroup analyses and referenced to the well-established “CheXNet” algorithm. Results Performances of established algorithms exclusively trained on publicly available data without in-image annotations are limited to AUROCs of 0.778 and strongly biased towards TTs that can completely eliminate algorithm’s discriminative power in individual subgroups. Contrarily, our final “algorithm 2” which was trained on a lower number of images but additionally with in-image annotations of the dehiscent pleura achieved an overall AUROC of 0.877 for unilateral PTX detection with a significantly reduced TT-related confounding bias. Conclusions We demonstrated strong limitations of an established PTX-detecting AI algorithm that can be significantly reduced by designing an AI system capable of learning to both classify and localize PTX. Our results are aimed at drawing attention to the necessity of high-quality in-image localization in training data to reduce the risks of unintentionally biasing the training process of pathology-detecting AI algorithms. Key Points • Established pneumothorax-detecting artificial intelligence algorithms trained on public training data are strongly limited and biased by confounding thoracic tubes. • We used high-quality in-image annotated training data to effectively boost algorithm performance and suppress the impact of confounding thoracic tubes. • Based on our results, we hypothesize that even hidden confounders might be effectively addressed by in-image annotations of pathology-related image features.

Needle artifacts pose a major limitation for MRI-guided interventions, as they impact the visually perceived needle size and needle-to-target-distance. The objective of this agar liver phantom study was to establish an experimental basis to understand and reduce needle artifact formation during MRI-guided abdominal interventions. Using a vendor-specific prototype fluoroscopic T1-weighted gradient echo sequence with real-time multiplanar acquisition at 1.5 T, the influence of 6 parameters (flip angle, bandwidth, matrix, slice thickness, read-out direction, intervention angle relative to B 0 ) on artifact formation of 4 different coaxial MR-compatible coaxial needles (Nitinol, 16G–22G) was investigated. As one parameter was modified, the others remained constant. For each individual parameter variation, 2 independent and blinded readers rated artifact diameters at 2 predefined positions (15 mm distance from the perceived needle tip and at 50% of the needle length). Differences between the experimental subgroups were assessed by Bonferroni-corrected non-parametric tests. Correlations between continuous variables were expressed by the Bravais–Pearson coefficient and interrater reliability was quantified using the intraclass classification coefficient. Needle artifact size increased gradually with increasing flip angles ( p  = 0.002) as well as increasing intervention angles ( p  < 0.001). Artifact diameters differed significantly between the chosen matrix sizes ( p  = 0.002) while modifying bandwidth, readout direction, and slice thickness showed no significant differences. Interrater reliability was high (intraclass correlation coefficient 0.776–0.910). To minimize needle artifacts in MRI-guided abdominal interventions while maintaining optimal visibility of the coaxial needle, we suggest medium-range flip angles and low intervention angles relative to B 0 .

Objectives To investigate the cost-effectiveness of supplemental short-protocol brain MRI after negative non-contrast CT for the detection of minor strokes in emergency patients with mild and unspecific neurological symptoms. Methods The economic evaluation was centered around a prospective single-center diagnostic accuracy study validating the use of short-protocol brain MRI in the emergency setting. A decision-analytic Markov model distinguished the strategies “no additional imaging” and “additional short-protocol MRI” for evaluation. Minor stroke was assumed to be missed in the initial evaluation in 40% of patients without short-protocol MRI. Specialized post-stroke care with immediate secondary prophylaxis was assumed for patients with detected minor stroke. Utilities and quality-of-life measures were estimated as quality-adjusted life years (QALYs). Input parameters were obtained from the literature. The Markov model simulated a follow-up period of up to 30 years. Willingness to pay was set to $100,000 per QALY. Cost-effectiveness was calculated and deterministic and probabilistic sensitivity analysis was performed. Results Additional short-protocol MRI was the dominant strategy with overall costs of $26,304 (CT only: $27,109). Cumulative calculated effectiveness in the CT-only group was 14.25 QALYs (short-protocol MRI group: 14.31 QALYs). In the deterministic sensitivity analysis, additional short-protocol MRI remained the dominant strategy in all investigated ranges. Probabilistic sensitivity analysis results from the base case analysis were confirmed, and additional short-protocol MRI resulted in lower costs and higher effectiveness. Conclusion Additional short-protocol MRI in emergency patients with mild and unspecific neurological symptoms enables timely secondary prophylaxis through detection of minor strokes, resulting in lower costs and higher cumulative QALYs. Key Points • Short-protocol brain MRI after negative head CT in selected emergency patients with mild and unspecific neurological symptoms allows for timely detection of minor strokes. • This strategy supports clinical decision-making with regard to immediate initiation of secondary prophylactic treatment, potentially preventing subsequent major strokes with associated high costs and reduced QALY. • According to the Markov model, additional short-protocol MRI remained the dominant strategy over wide variations of input parameters, even when assuming disproportionally high costs of the supplemental MRI scan.

IntroductionExperimental stroke studies suggest an influence of the time of day of stroke onset on infarct progression. Whether this holds true after human stroke is unknown, but would have implications for the design of randomised controlled trials, especially those on neuroprotection.MethodsWe pooled data from 583 patients with anterior large-vessel occlusion stroke from three prospectively recruited cohorts. Ischaemic core and penumbra volumes were determined with CT perfusion using automated thresholds. Core growth was calculated as the ratio of core volume and onset-to-imaging time. To determine circadian rhythmicity, we applied multivariable linear and sinusoidal regression analysis adjusting for potential baseline confounders.ResultsPatients with symptom onset at night showed larger ischaemic core volumes on admission compared with patients with onset during the day (median, 40.2 mL vs 33.8 mL), also in adjusted analyses (p=0.008). Sinusoidal analysis indicated a peak of core volumes with onset at 11pm. Core growth was faster at night compared with day onset (adjusted p=0.01), especially for shorter onset-to-imaging times. In contrast, penumbra volumes did not change across the 24-hour cycle.DiscussionThese results suggest that human infarct progression varies across the 24-hour cycle with potential implications for the design and interpretation of neuroprotection trials.

BackgroundThe PET-derived metabolic tumor volume (MTV) is an independent prognosticator in non-small cell lung cancer (NSCLC) patients. We analyzed the prognostic value of residual MTV (rMTV) after completion of chemoradiotherapy (CRT) in inoperable stage III NSCLC patients with and without immune checkpoint inhibition (ICI).MethodsFifty-six inoperable stage III NSCLC patients (16 female, median 65.0 years) underwent 18F-FDG PET/CT after completion of standard CRT. rMTV was delineated on 18F-FDG PET/CT using a standard threshold (liver SUVmean + 2 × standard deviation). 21/56 patients underwent additional ICI (CRT-IO, 21/56 patients) thereafter. Patients were divided in volumetric subgroups using median split dichotomization (MTV ≤ 4.3 ml vs. > 4.3 ml). rMTV, clinical features, and ICI-application were correlated with clinical outcome parameters (progression-free survival (PFS), local PFS (LPFS), and overall survival (OS).ResultsOverall, median follow-up was 52.0 months. Smaller rMTV was associated with longer median PFS (29.3 vs. 10.5 months, p = 0.015), LPFS (49.9 vs. 13.5 months, p = 0.001), and OS (63.0 vs. 23.0 months, p = 0.003). CRT-IO patients compared to CRT patients showed significantly longer median PFS (29.3 vs. 11.2 months, p = 0.034), LPFS (median not reached vs. 14.0 months, p = 0.016), and OS (median not reached vs. 25.2 months, p = 0.007). In the CRT subgroup, smaller rMTV was associated with longer median PFS (33.5 vs. 8.6 months, p = 0.001), LPFS (49.9 vs. 10.1 months, p = 0.001), and OS (63.0 vs. 16.3 months, p = 0.004). In the CRT-IO subgroup, neither PFS, LPFS, nor OS were associated with MTV (p > 0.05 each). The findings were confirmed in subsequent multivariate analyses.ConclusionIn stage III NSCLC, smaller rMTV is highly associated with superior clinical outcome, especially in patients undergoing CRT without ICI. Patients with CRT-IO show significantly improved outcome compared to CRT patients. Of note, clinical outcome in CRT-IO patients is independent of residual MTV. Hence, even patients with large rMTV might profit from ICI despite extensive tumor load.

ObjectiveThe aims of our study were to analyze agreement among readers with different levels of expertise and diagnostic performance of individual and combined imaging signs for the diagnosis of adhesive capsulitis of the shoulder.MethodsIn a retrospective study, contrast-enhanced shoulder MRIs of 60 patients with and 120 without clinically diagnosed adhesive capsulitis were evaluated by three readers independently. As non-enhanced imaging signs, readers evaluated signal intensity and thickness of the axillary recess capsule, thickness of the rotator interval capsule and the coracohumeral ligament as well as obliteration of subcoracoid fat. Furthermore, contrast enhancement of axillary recess and rotator interval capsule were evaluated. Data analysis included interreader reliability, ROC analysis, and logistic regression (p < 0.05).ResultsContrast-enhanced parameters showed substantially higher agreement among readers (ICC 0.79–0.80) than non-enhanced parameters (0.37–0.45). AUCs of contrast-enhanced signs (95.1–96.6%) were significantly higher (p < 0.01) than of non-enhanced imaging signs (61.5–85.9%) when considered individually. Combined evaluation of axillary recess signal intensity and thicknesses of axillary recess or rotator interval—when at least one of two signs was rated positive—increased accuracy compared to individual imaging signs, however not statistically significant.ConclusionContrast-enhanced imaging signs show both distinctly higher agreement among readers and distinctly higher diagnostic performance compared to non-enhanced imaging signs based on the imaging protocol used in this study. Combined evaluation of parameters showed a tendency to increase discrimination; however, the effect on diagnosis of ACS was not statistically significant.

Objectives The EOS imaging system allows for the acquirement of long-leg radiographic images in a standing position without stitching artifacts or projection bias and at a comparatively low-radiation-dose exposure. The aim of our study was to compare the accuracy of EOS images of the lower limb to conventional radiographs (CR) of the knee in a.p. view for the grading of osteoarthritis (OA). Methods One hundred forty-two patients who had undergone EOS of the lower limb and radiography of the knee on the same day were included. For the grading of OA, the Kellgren and Lawrence score (KL) score and the Osteoarthritis Research Society International (OARSI) system were used. Additionally, the joint space was measured and compared between the two techniques. EOS images were compared to conventional anteroposterior radiographs of the knee which constitute the gold standard. Results Measurements of the joint space showed very good intra-class correlation. The calculated weighted kappa for the KL score of EOS versus CR was excellent. The comparison of the different parameters of the OARSI score showed superb weighted kappa scores between 0.9 and 0.96 (α < 0.001) for the parameters osteophytes and joint space narrowing. The parameter deformity showed a good agreement between EOS and radiographs (sensitivity 93.6%; specificity 100%). For the sclerosis parameter, an overall sensitivity of 71.3% and a specificity of 99.3% were calculated. Conclusions The grading of OA using the KL score as well as the quantitative assessment of joint space width can be performed on EOS images in a.p. view as reliably as on CR. Subchondral sclerosis of the lateral and medial femur condyle or tibia is sometimes not as evident on EOS images. Key Points • Grading of OA may be performed as reliably with EOS images in a.p. view as with conventional radiographs in a.p. view. • EOS can be safely used for primary assessment of osteoarthritis of the knee. • In the preoperative setting for knee replacement surgery, conventional radiographs in two or three planes of the knee should still be acquired in addition to long-leg EOS images.