Off-Label use of Woven EndoBridge device for intracranial brain aneurysm treatment: Modeling of occlusion outcome.

INTRODUCTION: The Woven EndoBridge (WEB) device is emerging as a novel therapy for intracranial aneurysms, but its use for off-label indications requires further study. Using machine learning, we aimed to develop predictive models for complete occlusion after off-label WEB treatment and to identify factors associated with occlusion outcomes. METHODS: This multicenter, retrospective study included 162 patients who underwent off-label WEB treatment for intracranial aneurysms. Baseline, morphological, and procedural variables were utilized to develop machine-learning models predicting complete occlusion. Model interpretation was performed to determine significant predictors. Ordinal regression was also performed with occlusion status as an ordinal outcome from better (Raymond Roy Occlusion Classification [RROC] grade 1) to worse (RROC grade 3) status. Odds ratios (OR) with 95 % confidence intervals (CI) were reported. RESULTS: The best performing model achieved an AUROC of 0.8 for predicting complete occlusion. Larger neck diameter and daughter sac were significant independent predictors of incomplete occlusion. On multivariable ordinal regression, higher RROC grades (OR 1.86, 95 % CI 1.25-2.82), larger neck diameter (OR 1.69, 95 % CI 1.09-2.65), and presence of daughter sacs (OR 2.26, 95 % CI 0.99-5.15) were associated with worse aneurysm occlusion after WEB treatment, independent of other factors. CONCLUSION: This study found that larger neck diameter and daughter sacs were associated with worse occlusion after WEB therapy for aneurysms. The machine learning approach identified anatomical factors related to occlusion outcomes that may help guide patient selection and monitoring with this technology. Further validation is needed.

Optimizing Diagnostic Performance of ChatGPT: The Impact of Prompt Engineering on Thoracic Radiology Cases.

Background Recent studies have highlighted the diagnostic performance of ChatGPT 3.5 and GPT-4 in a text-based format, demonstrating their radiological knowledge across different areas. Our objective is to investigate the impact of prompt engineering on the diagnostic performance of ChatGPT 3.5 and GPT-4 in diagnosing thoracic radiology cases, highlighting how the complexity of prompts influences model performance. Methodology We conducted a retrospective cross-sectional study using 124 publicly available Case of the Month examples from the Thoracic Society of Radiology website. We initially input the cases into the ChatGPT versions without prompting. Then, we employed five different prompts, ranging from basic task-oriented to complex role-specific formulations to measure the diagnostic accuracy of ChatGPT versions. The differential diagnosis lists generated by the models were compared against the radiological diagnoses listed on the Thoracic Society of Radiology website, with a scoring system in place to comprehensively assess the accuracy. Diagnostic accuracy and differential diagnosis scores were analyzed using the McNemar, Chi-square, Kruskal-Wallis, and Mann-Whitney U tests. Results Without any prompts, ChatGPT 3.5's accuracy was 25% (31/124), which increased to 56.5% (70/124) with the most complex prompt (P < 0.001). GPT-4 showed a high baseline accuracy at 53.2% (66/124) without prompting. This accuracy increased to 59.7% (74/124) with complex prompts (P = 0.09). Notably, there was no statistical difference in peak performance between ChatGPT 3.5 (70/124) and GPT-4 (74/124) (P = 0.55). Conclusions This study emphasizes the critical influence of prompt engineering on enhancing the diagnostic performance of ChatGPT versions, especially ChatGPT 3.5.

Can large language models be new supportive tools in coronary computed tomography angiography reporting?

The advent of large language models (LLMs) marks a transformative leap in natural language processing, offering unprecedented potential in radiology, particularly in enhancing the accuracy and efficiency of coronary artery disease (CAD) diagnosis. While previous studies have explored the capabilities of specific LLMs like ChatGPT in cardiac imaging, a comprehensive evaluation comparing multiple LLMs in the context of CAD-RADS 2.0 has been lacking. This study addresses this gap by assessing the performance of various LLMs, including ChatGPT 4, ChatGPT 4o, Claude 3 Opus, Gemini 1.5 Pro, Mistral Large, Meta Llama 3 70B, and Perplexity Pro, in answering 30 multiple-choice questions derived from the CAD-RADS 2.0 guidelines. Our findings reveal that ChatGPT 4o achieved the highest accuracy at 100 %, with ChatGPT 4 and Claude 3 Opus closely following at 96.6 %. Other models, including Mistral Large, Perplexity Pro, Meta Llama 3 70B, and Gemini 1.5 Pro, also demonstrated commendable performance, though with slightly lower accuracy ranging from 90 % to 93.3 %. This study underscores the proficiency of current LLMs in understanding and applying CAD-RADS 2.0, suggesting their potential to significantly enhance radiological reporting and patient care in coronary artery disease. The variations in model performance highlight the need for further research, particularly in evaluating the visual diagnostic capabilities of LLMs-a critical component of radiology practice. This study provides a foundational comparison of LLMs in CAD-RADS 2.0 and sets the stage for future investigations into their broader applications in radiology, emphasizing the importance of integrating both text-based and visual knowledge for optimal clinical outcomes.

Comparison of Performance of Large Language Models on Lung-RADS Related Questions.

This study evaluates LLM integration in interpreting Lung-RADS for lung cancer screening, highlighting their innovative role in enhancing radiological practice. Our findings reveal that Claude 3 Opus and Perplexity achieved a 96% accuracy rate, outperforming other models.

Evaluating text and visual diagnostic capabilities of large language models on questions related to the Breast Imaging Reporting and Data System Atlas 5th edition.

PURPOSE: This study aimed to evaluate the performance of large language models (LLMs) and multimodal LLMs in interpreting the Breast Imaging Reporting and Data System (BI-RADS) categories and providing clinical management recommendations for breast radiology in text-based and visual questions. METHODS: This cross-sectional observational study involved two steps. In the first step, we compared ten LLMs (namely ChatGPT 4o, ChatGPT 4, ChatGPT 3.5, Google Gemini 1.5 Pro, Google Gemini 1.0, Microsoft Copilot, Perplexity, Claude 3.5 Sonnet, Claude 3 Opus, and Claude 3 Opus 200K), general radiologists, and a breast radiologist using 100 text-based multiple-choice questions (MCQs) related to the BI-RADS Atlas 5th edition. In the second step, we assessed the performance of five multimodal LLMs (ChatGPT 4o, ChatGPT 4V, Claude 3.5 Sonnet, Claude 3 Opus, and Google Gemini 1.5 Pro) in assigning BI-RADS categories and providing clinical management recommendations on 100 breast ultrasound images. The comparison of correct answers and accuracy by question types was analyzed using McNemar's and chi-squared tests. Management scores were analyzed using the Kruskal- Wallis and Wilcoxon tests. RESULTS: Claude 3.5 Sonnet achieved the highest accuracy in text-based MCQs (90%), followed by ChatGPT 4o (89%), outperforming all other LLMs and general radiologists (78% and 76%) (P < 0.05), except for the Claude 3 Opus models and the breast radiologist (82%) (P > 0.05). Lower-performing LLMs included Google Gemini 1.0 (61%) and ChatGPT 3.5 (60%). Performance across different categories of showed no significant variation among LLMs or radiologists (P > 0.05). For breast ultrasound images, Claude 3.5 Sonnet achieved 59% accuracy, significantly higher than other multimodal LLMs (P < 0.05). Management recommendations were evaluated using a 3-point Likert scale, with Claude 3.5 Sonnet scoring the highest (mean: 2.12 ± 0.97) (P < 0.05). Accuracy varied significantly across BI-RADS categories, except Claude 3 Opus (P < 0.05). Gemini 1.5 Pro failed to answer any BI-RADS 5 questions correctly. Similarly, ChatGPT 4V failed to answer any BI-RADS 1 questions correctly, making them the least accurate in these categories (P < 0.05). CONCLUSION: Although LLMs such as Claude 3.5 Sonnet and ChatGPT 4o show promise in text-based BI-RADS assessments, their limitations in visual diagnostics suggest they should be used cautiously and under radiologists' supervision to avoid misdiagnoses. CLINICAL SIGNIFICANCE: This study demonstrates that while LLMs exhibit strong capabilities in text-based BI-RADS assessments, their visual diagnostic abilities are currently limited, necessitating further development and cautious application in clinical practice.

The Relationship Between Intramural Fat Accumulation and Sarcopenia on MR Enterography Exams in Patients with Crohn's Disease.

Research on magnetic resonance enterography (MRE) and sarcopenia for assessing Crohn's disease (CD) is growing. Our study examined the connections between the presence of sarcopenia, intramural fat accumulation (IFA), and clinical, laboratory, and MRE findings.This retrospective study was conducted on 112 patients with suspected or diagnosed CD who underwent 3-tesla MRE. The study examined the correlation between sarcopenia-related parameters and MRE findings. Results of MRE exams and clinical and laboratory results were statistically analyzed. The Kruskal-Wallis, Pearson chi-square, and Fisher-Freeman-Halton tests were used for comparison.It was determined that patients with active inflammation on a chronic basis had more IFA than the others (p<0.001). There were positive relationships between IFA and intramural edema (p<0.001). There were positive correlations between IFA and high b-values and negative correlations with apparent diffusion coefficient values (p<0.05). Positively significant relationships were found between IFA and wall thickness, affected segment length, disease duration, and sedimentation values (p<0.05). Strong correlations were found between sarcopenia and the CD activity index as well as wall thickness (p<0.001/p=0.003). There was no significant relationship between steroid usage and other variables.The presence of IFA is associated with chronic inflammation. There was no clear relationship between steroid use and IFA. Our findings support the idea that sarcopenia is related to the activity of CD. Further comprehensive research is required on these subjects. · The usage of MR enterography for the management of CD is increasing day by day due to its advantages.. · There is a paucity of evidence regarding the relationship between sarcopenia and MR enterography findings in patients with CD.. · Intramural fat accumulation (IFA) is a sign of chronicity in patients with CD.. · The presence of IFA seems to be associated with active inflammation on a chronic basis.. · There was no clear relationship between steroid use and IFA.. · Algin O, Günes YC, Cankurtaran RE et al. The Relationship Between Intramural Fat Accumulation and Sarcopenia on MR Enterography Exams in Patients with Crohn's Disease. Fortschr Röntgenstr 2024; DOI 10.1055/a-2330-8148.

Computed tomography findings in COVID-19 and atypical pneumonia: a comparative study.

INTRODUCTION: Computed tomography (CT) has an important role in the rapid diagnosis, treatment, and management of lower respiratory tract infections. This study aimed to explore different imaging characteristics between Coronavirus disease 2019 (COVID-19) and atypical pneumonia (non-COVID-19) on chest CT of patients admitted to the emergency department. METHODOLOGY: CT features of 120 patients with positive Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) by reverse transcriptase-polymerase chain reaction (RT-PCR) and 83 patients with negative SARS-CoV-2 by RT-PCR but positive respiratory tract sample test results for other respiratory pathogens were retrospectively evaluated, findings were recorded and compared between the two groups. RESULTS: Compared to non-COVID-19, COVID-19 patients were more likely to have a peripheral (60.5% vs. 23.8%, p < 0.001) and bilateral distribution (72.3% vs. 41.3%, p < 0.001), patchy consolidations (45% vs. 28.9%, p = 0.021), ground glass opacity (GGO) (94.2% vs. 83.1%, p = 0.011), crazy paving patterns (55% vs. 31.3%, p < 0.001); but less likely to have centrilobular nodules (15% vs. 62.7%, p < 0.001), pleural effusion (3.3% vs. 10.8%, p = 0.032), multifocal consolidations (7.5% vs. 21.7%, p = 0.003), and random distribution (1.7% vs. 46.3%, p < 0.001). CONCLUSIONS: There were significant differences between the CT patterns of patients with COVID-19 and other atypical pneumonia. The presence of patchy consolidations, GGO, crazy paving patterns with typical peripheral, bilateral distribution, and absence of centrilobular nodules, pleural effusion, and multifocal consolidations may help to differentiate COVID-19 from atypical pneumonia.

Sarcopenia and Myosteatosis Assessed by Magnetic Resonance Enterography May Predict Negative Outcomes in Patients with Crohn's Disease.

BACKGROUND: Limited research has examined the clinical consequences of sarcopenia and myosteatosis in Crohn's disease. This study aimed to determine the prevalence, risk factors, and effects of sarcopenia and myosteatosis on prognostic outcomes in Crohn's disease patients who underwent magnetic resonance enterography. MATERIALS AND METHODS: This retrospective observational study included 116 Crohn's disease patients who underwent magnetic resonance enterography between January 2015 and August 2021. Skeletal muscle index was the ratio of the cross-sectional area of skeletal muscles at the L3 vertebral level to the square of the neck in cross-sectional imaging. Sarcopenia was defined as skeletal muscle index <38.5 cm2/m2 in women and <52.4 cm2/m2 in men. Myosteatosis was considered positive if the ratio of the mean signal intensity of the psoas muscle to the mean signal intensity of the cerebrospinal fluid was above 0.107. RESULTS: Among the negative results in the post-procedure follow-up of the patients, a significant increase was observed in the sarcopenia group regarding abscess and the need for surgery (P < .05). Anti-tumor necrosis factor initiation was found to be significantly higher in the follow-up than in patients without myosteatosis (P = .029). In the multivariate model established with these variables, the presence of sarcopenia in the surgical follow-up was odds ratio = 5.34 (CI: 1.02-28.03, P = .047) and was found to be significantly associated with the increased risk. CONCLUSIONS: The presence of myosteatosis and sarcopenia detected in magnetic resonance enterography may be a harbinger of negative outcomes in Crohn's disease patients. Nutritional support should be provided to these patients with the potential to alter the course of the disease.

The brainstem connections of the supplementary motor area and its relations to the corticospinal tract: Experimental rat and human 3-tesla tractography study.

Although the supplementary motor area (SMA) is a large region on the medial surface of the frontal lobe of the brain, little is known about its function. The current study uses 3-tesla high-resolution diffusion tensor tractography (DTI) in healthy individuals and biotinylated dextran amine (BDA) and fluoro-gold (FG) tracer in rats to demonstrate the afferent and efferent connections of the SMA with brainstem structures. It also aims to clarify how SMA fibers relate to the corticospinal tract (CST). The BDA (n = 6) and FG (n = 8) tracers were pressure-injected into the SMA of 14 Wistar albino rats. Light and fluorescence microscopy was used to capture images of the FG and BDA-labeled cells and axons. High-resolution 3-tesla DTI data were acquired from the Human Connectome Project database. Tracts between the SMA and brainstem structures were analyzed using diffusion spectrum imaging (DSI) studio software. The FG injections into the SMA showed afferent projections from mesencephalic (periaqueductal gray matter, substantia nigra pars reticulata, ventral tegmental area, inferior colliculus, mesencephalic reticular, tegmental, and raphe nuclei), pontine (locus coeruleus, pontine reticular and vestibular nuclei), and medullary (area postrema, parabrachial, and medullary reticular nuclei) structures. The anterograde tracer BDA injections into the SMA showed efferent connections with mesencephalic (periaqueductal gray, substantia nigra pars compacta, dorsal raphe, trigeminal motor mesencephalic, and mesencephalic reticular nuclei), pontine (locus coeruleus, nucleus of the lateral lemniscus, vestibular, cochlear, and pontine reticular nuclei), and medullary (area postrema, medullary reticular, olivary, and parabrachial nuclei) structures. The SMA had efferent but no afferent connections with the cerebellar nuclei. The DTI results in healthy human subjects highly corresponded with the experimental results. Further, the DTI results showed a distinct bundle that descended to spinal levels closely related to the CST. Understanding SMA's afferent and efferent connections will enrich our knowledge of its contribution to various brainstem networks and may provide new perspectives for understanding its motor and non-motor functions.

Connections of the Dentate Nucleus with the Amygdala: Experimental Rat and Human 3-Tesla Tractography Study.

Background: The role of the cerebellum in motor function is well recognized. However, its role in higher nervous system activities such as cognition, emotion, endocrine, and autonomic activities is less known. The present study aims to show direct dento-amygdala projections using a biotinylated dextran amine (BDA) tracer in rats and 3-tesla (T) high-resolution diffusion tensor imaging (DTI)-based tractography in humans. Materials and Methods: The BDA tracer was pressure injected into the dentate nucleus of the cerebellum of Wistar albino rats. Labeled cells and axons were documented. High-resolution 3-T tractography data were obtained from the Human Connectome Project database. Dento-amygdala tracts were analyzed using diffusion spectrum imaging (DSI) Studio software. Results: The experimental study showed bilateral projections between the dentate nucleus and the central and basal nuclei and ipsilateral projections between lateral nuclei of the amygdala. The fibers from the dentate nucleus reached the amygdala through the superior cerebellar peduncle (SCP), and the contralateral fibers crossed in the decussation of SCP at the midbrain. The dento-amygdala results of the experimental study corresponded with the 3-T tractography findings on humans. Additionally, DTI findings showed that most of the dentate fibers passed through the hypothalamus before reaching the amygdala, and the amygdalae of the two sides are connected through the anterior commissure. Discussion: The 3-T DTI data of adult humans showed both direct dento-amygdala and indirect dento-hypothalamo-amygdala projections. Thus, this may indicate cerebellar contribution in modulation of emotional and autonomic functions. Furthermore, this can explain the emotional and cognitive deficits that occur in patients with cerebellar or SCP damage. Impact statement The present study showed direct dento-amygdala connections in the rat brain and human brain, which may provide evidence for cerebellar contribution in modulation of emotional and autonomic functions.