Accuracy of a deep learning-based algorithm for the detection of thoracic aortic calcifications in chest computed tomography and cardiovascular surgery planning.

OBJECTIVES: To assess the accuracy of a deep learning-based algorithm for fully automated detection of thoracic aortic calcifications in chest computed tomography (CT) with a focus on the aortic clamping zone. METHODS: We retrospectively included 100 chest CT scans from 91 patients who were examined on second- or third-generation dual-source scanners. Subsamples comprised 47 scans with an ECG-gated aortic angiography and 53 unenhanced scans. A deep learning model performed aortic landmark detection and aorta segmentation to derive eight vessel segments. Associated calcifications were detected and their volumes measured using a mean-based density thresholding. Algorithm parameters (calcium cluster size threshold, aortic mask dilatation) were varied to determine optimal performance for the upper ascending aorta that encompasses the aortic clamping zone. A binary visual rating served as a reference. Standard estimates of diagnostic accuracy and inter-rater agreement using Cohen's Kappa were calculated. RESULTS: Thoracic aortic calcifications were observed in 74% of patients with a prevalence of 27% to 70% by aorta segment. Using different parameter combinations, the algorithm provided binary ratings for all scans and segments. The best-performing parameter combination for the presence of calcifications in the aortic clamping zone yielded a sensitivity of 93% and a specificity of 82% with an area under the receiver operating characteristic curve of 0.874. Using these parameters, the inter-rater agreement ranged from κ 0.66 to 0.92 per segment. CONCLUSIONS: Fully automated segmental detection of thoracic aortic calcifications in chest CT performs with high accuracy. This includes the critical preoperative assessment of the aortic clamping zone.

Radiomics workflow definition & challenges - German priority program 2177 consensus statement on clinically applied radiomics.

OBJECTIVES: Achieving a consensus on a definition for different aspects of radiomics workflows to support their translation into clinical usage. Furthermore, to assess the perspective of experts on important challenges for a successful clinical workflow implementation. MATERIALS AND METHODS: The consensus was achieved by a multi-stage process. Stage 1 comprised a definition screening, a retrospective analysis with semantic mapping of terms found in 22 workflow definitions, and the compilation of an initial baseline definition. Stages 2 and 3 consisted of a Delphi process with over 45 experts hailing from sites participating in the German Research Foundation (DFG) Priority Program 2177. Stage 2 aimed to achieve a broad consensus for a definition proposal, while stage 3 identified the importance of translational challenges. RESULTS: Workflow definitions from 22 publications (published 2012-2020) were analyzed. Sixty-nine definition terms were extracted, mapped, and semantic ambiguities (e.g., homonymous and synonymous terms) were identified and resolved. The consensus definition was developed via a Delphi process. The final definition comprising seven phases and 37 aspects reached a high overall consensus (> 89% of experts "agree" or "strongly agree"). Two aspects reached no strong consensus. In addition, the Delphi process identified and characterized from the participating experts' perspective the ten most important challenges in radiomics workflows. CONCLUSION: To overcome semantic inconsistencies between existing definitions and offer a well-defined, broad, referenceable terminology, a consensus workflow definition for radiomics-based setups and a terms mapping to existing literature was compiled. Moreover, the most relevant challenges towards clinical application were characterized. CRITICAL RELEVANCE STATEMENT: Lack of standardization represents one major obstacle to successful clinical translation of radiomics. Here, we report a consensus workflow definition on different aspects of radiomics studies and highlight important challenges to advance the clinical adoption of radiomics. KEY POINTS: Published radiomics workflow terminologies are inconsistent, hindering standardization and translation. A consensus radiomics workflow definition proposal with high agreement was developed. Publicly available result resources for further exploitation by the scientific community.

Cardioprotective effects of vaccination in hospitalized patients with COVID-19.

COVID-19 vaccination has been shown to prevent and reduce the severity of COVID-19 disease. The aim of this study was to explore the cardioprotective effect of COVID-19 vaccination in hospitalized COVID-19 patients. In this retrospective, single-center cohort study, we included hospitalized COVID-19 patients with confirmed vaccination status from July 2021 to February 2022. We assessed outcomes such as acute cardiac events and cardiac biomarker levels through clinical and laboratory data. Our analysis covered 167 patients (69% male, mean age 58 years, 42% being fully vaccinated). After adjustment for confounders, vaccinated hospitalized COVID-19 patients displayed a reduced relative risk for acute cardiac events (RR: 0.33, 95% CI [0.07; 0.75]) and showed diminished troponin T levels (Cohen's d: - 0.52, 95% CI [- 1.01; - 0.14]), compared to their non-vaccinated peers. Type 2 diabetes (OR: 2.99, 95% CI [1.22; 7.35]) and existing cardiac diseases (OR: 4.31, 95% CI [1.83; 10.74]) were identified as significant risk factors for the emergence of acute cardiac events. Our findings suggest that COVID-19 vaccination may confer both direct and indirect cardioprotective effects in hospitalized COVID-19 patients.

A retrieval-augmented chatbot based on GPT-4 provides appropriate differential diagnosis in gastrointestinal radiology: a proof of concept study.

BACKGROUND: We investigated the potential of an imaging-aware GPT-4-based chatbot in providing diagnoses based on imaging descriptions of abdominal pathologies. METHODS: Utilizing zero-shot learning via the LlamaIndex framework, GPT-4 was enhanced using the 96 documents from the Radiographics Top 10 Reading List on gastrointestinal imaging, creating a gastrointestinal imaging-aware chatbot (GIA-CB). To assess its diagnostic capability, 50 cases on a variety of abdominal pathologies were created, comprising radiological findings in fluoroscopy, MRI, and CT. We compared the GIA-CB to the generic GPT-4 chatbot (g-CB) in providing the primary and 2 additional differential diagnoses, using interpretations from senior-level radiologists as ground truth. The trustworthiness of the GIA-CB was evaluated by investigating the source documents as provided by the knowledge-retrieval mechanism. Mann-Whitney U test was employed. RESULTS: The GIA-CB demonstrated a high capability to identify the most appropriate differential diagnosis in 39/50 cases (78%), significantly surpassing the g-CB in 27/50 cases (54%) (p = 0.006). Notably, the GIA-CB offered the primary differential in the top 3 differential diagnoses in 45/50 cases (90%) versus g-CB with 37/50 cases (74%) (p = 0.022) and always with appropriate explanations. The median response time was 29.8 s for GIA-CB and 15.7 s for g-CB, and the mean cost per case was $0.15 and $0.02, respectively. CONCLUSIONS: The GIA-CB not only provided an accurate diagnosis for gastrointestinal pathologies, but also direct access to source documents, providing insight into the decision-making process, a step towards trustworthy and explainable AI. Integrating context-specific data into AI models can support evidence-based clinical decision-making. RELEVANCE STATEMENT: A context-aware GPT-4 chatbot demonstrates high accuracy in providing differential diagnoses based on imaging descriptions, surpassing the generic GPT-4. It provided formulated rationale and source excerpts supporting the diagnoses, thus enhancing trustworthy decision-support. KEY POINTS: • Knowledge retrieval enhances differential diagnoses in a gastrointestinal imaging-aware chatbot (GIA-CB). • GIA-CB outperformed the generic counterpart, providing formulated rationale and source excerpts. • GIA-CB has the potential to pave the way for AI-assisted decision support systems.

Association Between Body Composition and Survival in Patients With Gastroesophageal Adenocarcinoma: An Automated Deep Learning Approach.

PURPOSE: Body composition (BC) may play a role in outcome prognostication in patients with gastroesophageal adenocarcinoma (GEAC). Artificial intelligence provides new possibilities to opportunistically quantify BC from computed tomography (CT) scans. We developed a deep learning (DL) model for fully automatic BC quantification on routine staging CTs and determined its prognostic role in a clinical cohort of patients with GEAC. MATERIALS AND METHODS: We developed and tested a DL model to quantify BC measures defined as subcutaneous and visceral adipose tissue (VAT) and skeletal muscle on routine CT and investigated their prognostic value in a cohort of patients with GEAC using baseline, 3-6-month, and 6-12-month postoperative CTs. Primary outcome was all-cause mortality, and secondary outcome was disease-free survival (DFS). Cox regression assessed the association between (1) BC at baseline and mortality and (2) the decrease in BC between baseline and follow-up scans and mortality/DFS. RESULTS: Model performance was high with Dice coefficients ≥0.94 ± 0.06. Among 299 patients with GEAC (age 63.0 ± 10.7 years; 19.4% female), 140 deaths (47%) occurred over a median follow-up of 31.3 months. At baseline, no BC measure was associated with DFS. Only a substantial decrease in VAT >70% after a 6- to 12-month follow-up was associated with mortality (hazard ratio [HR], 1.99 [95% CI, 1.18 to 3.34]; P = .009) and DFS (HR, 1.73 [95% CI, 1.01 to 2.95]; P = .045) independent of age, sex, BMI, Union for International Cancer Control stage, histologic grading, resection status, neoadjuvant therapy, and time between surgery and follow-up CT. CONCLUSION: DL enables opportunistic estimation of BC from routine staging CT to quantify prognostic information. In patients with GEAC, only a substantial decrease of VAT 6-12 months postsurgery was an independent predictor for DFS beyond traditional risk factors, which may help to identify individuals at high risk who go otherwise unnoticed.

Photon-counting detector computed tomography for metal artifact reduction: a comparative study of different artifact reduction techniques in patients with orthopedic implants.

PURPOSE: Artifacts caused by metallic implants remain a challenge in computed tomography (CT). We investigated the impact of photon-counting detector computed tomography (PCD-CT) for artifact reduction in patients with orthopedic implants with respect to image quality and diagnostic confidence using different artifact reduction approaches. MATERIAL AND METHODS: In this prospective study, consecutive patients with orthopedic implants underwent PCD-CT imaging of the implant area. Four series were reconstructed for each patient (clinical standard reconstruction [PCD-CTStd], monoenergetic images at 140 keV [PCD-CT140keV], iterative metal artifact reduction (iMAR) corrected [PCD-CTiMAR], combination of iMAR and 140 keV monoenergetic [PCD-CT140keV+iMAR]). Subsequently, three radiologists evaluated the reconstructions in a random and blinded manner for image quality, artifact severity, anatomy delineation (adjacent and distant), and diagnostic confidence using a 5-point Likert scale (5 = excellent). In addition, the coefficient of variation [CV] and the relative quantitative artifact reduction potential were obtained as objective measures. RESULTS: We enrolled 39 patients with a mean age of 67.3 ± 13.2 years (51%; n = 20 male) and a mean BMI of 26.1 ± 4 kg/m2. All image quality measures and diagnostic confidence were significantly higher for the iMAR vs. non-iMAR reconstructions (all p < 0.001). No significant effect of the different artifact reduction approaches on CV was observed (p = 0.26). The quantitative analysis indicated the most effective artifact reduction for the iMAR reconstructions, which was higher than PCD-CT140keV (p < 0.001). CONCLUSION: PCD-CT allows for effective metal artifact reduction in patients with orthopedic implants, resulting in superior image quality and diagnostic confidence with the potential to improve patient management and clinical decision making.

Ectopic pancreas tissue in the posterior mediastinum.

The occurrence of ectopic pancreas in the mediastinum is rare. Herein, we report a 22-year-old female who presented with right shoulder pain, dysphagia, fever and headaches. Chest computer tomography revealed a mass in the posterior mediastinum with accompanying signs of acute mediastinitis. Needle biopsy and fine-needle aspiration revealed ectopic gastral tissue and ectopic pancreas tissue, respectively. Surgical resection was attempted due to recurring acute pancreatitis episodes. However, due to chronic-inflammatory adhesions of the mass to the tracheal wall, en-bloc resection was not possible without major tracheal resection. Since then, recurring pancreatitis episodes have been treated conservatively with antibiotics. We report this case due to its differing clinical and radiological findings in comparison to previous case reports, none of which pertained a case of ectopic pancreas tissue in the posterior mediastinum with recurring acute pancreatitis and mediastinitis.

Photon-counting CT of degenerative changes and rupture of silicone breast implants: a pilot study.

BACKGROUND: Accurate assessment of breast implants is important for appropriate clinical management. We evaluated silicone properties and diagnostic accuracy for characterizing silicone implants and detecting degenerative changes including rupture in photon-counting computed tomography (PCCT). METHODS: Over 16 months, we prospectively included patients with silicone implants and available breast magnetic resonance imaging (MRI) who received thoracic PCCT performed in prone position. Consensus reading of all available imaging studies including MRI served as reference standard. Two readers evaluated all implants in PCCT reconstructions for degenerative changes. In a subgroup of implants, mean density of silicone, adjacent muscle, and fat were measured on PCCT reconstructions. Contrast-to-noise ratios (CNRs) were calculated for implant-to-muscle and implant-to-fat. RESULTS: Among 21 subjects, aged 60 ± 13.1 years (mean ± standard deviation) with 29 implants PCCT showed the following: high accuracy for linguine sign, intraimplant fluid (all > 0.99), peri-implant silicone (0.95), keyhole sign (0.90), and folds of the membrane (0.81); high specificity for linguine sign, intraimplant fluid, keyhole sign, folds of the membrane (all > 0.99), and peri-implant silicone (0.98); and high sensitivity for linguine sign and intraimplant fluid (all > 0.99). In a subgroup of 12 implants, the highest CNR for implant-to-muscle was observed on virtual unenhanced reconstructions (20.9) and iodine maps (22.9), for implant-to-fat on iodine maps (27.7) and monoenergetic reconstructions (31.8). CONCLUSIONS: Our findings demonstrate that silicone breast implants exhibit distinct contrast properties at PCCT, which may provide incremental information for detection of degenerative changes and rupture of implants. RELEVANCE STATEMENT: Thoracic photon-counting computed tomography is a promising modality for the diagnostic assessment of silicone breast implants. KEY POINTS: • Thoracic photon-counting computed tomography demonstrates unique contrast properties of silicone breast implants. • Iodine map reconstructions reveal strong contrast-to-noise ratios for implant-to-muscle and implant-to-fat. • Thoracic photon-counting computed tomography shows high diagnostic accuracy in detecting implant degeneration and rupture. TRIAL REGISTRATION: German Clinical Trials Register number DRKS00028997, date of registration 2022-08-08, retrospectively registered.

Impact of temporal resolution on perfusion metrics, therapy decision, and radiation dose reduction in brain CT perfusion in patients with suspected stroke.

PURPOSE: CT perfusion of the brain is a powerful tool in stroke imaging, though the radiation dose is rather high. Several strategies for dose reduction have been proposed, including increasing the intervals between the dynamic scans. We determined the impact of temporal resolution on perfusion metrics, therapy decision, and radiation dose reduction in brain CT perfusion from a large dataset of patients with suspected stroke. METHODS: We retrospectively included 3555 perfusion scans from our clinical routine dataset. All cases were processed using the perfusion software VEOcore with a standard sampling of 1.5 s, as well as simulated reduced temporal resolution of 3.0, 4.5, and 6.0 s by leaving out respective time points. The resulting perfusion maps and calculated volumes of infarct core and mismatch were compared quantitatively. Finally, hypothetical decisions for mechanical thrombectomy following the DEFUSE-3 criteria were compared. RESULTS: The agreement between calculated volumes for core (ICC = 0.99, 0.99, and 0.98) and hypoperfusion (ICC = 0.99, 0.99, and 0.97) was excellent for all temporal sampling schemes. Of the 1226 cases with vascular occlusion, 14 (1%) for 3.0 s sampling, 23 (2%) for 4.5 s sampling, and 63 (5%) for 6.0 s sampling would have been treated differently if the DEFUSE-3 criteria had been applied. Reduction of temporal resolution to 3.0 s, 4.5 s, and 6.0 s reduced the radiation dose by a factor of 2, 3, or 4. CONCLUSION: Reducing the temporal sampling of brain perfusion CT has only a minor impact on image quality and treatment decision, but significantly reduces the radiation dose to that of standard non-contrast CT.

Value of virtual non-contrast images to identify uncomplicated cystic renal lesions: photon-counting detector CT vs. dual-energy integrating detector CT.

PURPOSE: To investigate the value of photon-counting detector CT (PCD-CT) derived virtual non-contrast (VNC) reconstructions to identify renal cysts in comparison with conventional dual-energy integrating detector (DE EID) CT-derived VNC reconstructions. MATERIAL AND METHODS: We prospectively enrolled consecutive patients with simple renal cysts (Bosniak classification-Version 2019, density ≤ 20 HU and/or enhancement ≤ 20 HU) who underwent multiphase (non-contrast, arterial, portal venous phase) PCD-CT and for whom non-contrast and portal venous phase DE EID-CT was available. Subsequently, VNC reconstructions were calculated for all contrast phases and density as well as contrast enhancement within the cysts were measured and compared. MRI and/or ultrasound served as reference standards for lesion classification. RESULTS: 19 patients (1 cyst per patient; age 69.5 ± 10.7 years; 17 [89.5%] male) were included. Density measurements on PCD-CT non-contrast and VNC reconstructions (arterial and portal venous phase) revealed no significant effect on HU values (p = 0.301). In contrast, a significant difference between non-contrast vs. VNC images was found for DE EID-CT (p = 0.02). For PCD-CT, enhancement for VNC reconstructions was < 20 HU for all evaluated cysts. DE EID-CT measurements revealed an enhancement of > 20 HU in five lesions (26.3%) using the VNC reconstructions, which was not seen with the non-contrast images. CONCLUSION: PCD-CT-derived VNC images allow for reliable and accurate characterization of simple cystic renal lesions similar to non-contrast scans whereas VNC images calculated from DE EID-CT resulted in substantial false characterization. Thus, PCD-CT-derived VNC images may substitute for non-contrast images and reduce radiation dose and follow-up imaging.

Imaging Markers Derived From MRI-Based Automated Kidney Segmentation­an Analysis of Data From the German National Cohort (NAKO Gesundheitsstudie)

BACKGROUND: Population-wide research on potential new imaging biomarkers of the kidney depends on accurate automated segmentation of the kidney and its compartments (cortex, medulla, and sinus). METHODS: We developed a robust deep-learning framework for kidney (sub-)segmentation based on a hierarchical, three-dimensional convolutional neural network (CNN) that was optimized for multi-scale problems of combined localization and segmentation. We applied the CNN to abdominal magnetic resonance images from the population-based German National Cohort (NAKO) study. RESULTS: There was good to excellent agreement between the model predictions and manual segmentations. The median values for the body-surface normalized total kidney, cortex, medulla, and sinus volumes of 9934 persons were 158, 115, 43, and 24 mL/m2. Distributions of these markers are provided both for the overall study population and for a subgroup of persons without kidney disease or any associated conditions. Multivariable adjusted regression analyses revealed that diabetes, male sex, and a higher estimated glomerular filtration rate (eGFR) are important predictors of higher total and cortical volumes. Each increase of eGFR by one unit (i.e., 1 mL/min per 1.73 m2 body surface area) was associated with a 0.98 mL/m2 increase in total kidney volume, and this association was significant. Volumes were lower in persons with eGFR-defined chronic kidney disease. CONCLUSION: The extraction of image-based biomarkers through CNN-based renal sub-segmentation using data from a population-based study yields reliable results, forming a solid foundation for future investigations.

Serum metabolite signatures of cardiac function and morphology in individuals from a population-based cohort.

BACKGROUND: Changes in serum metabolites in individuals with altered cardiac function and morphology may exhibit information about cardiovascular disease (CVD) pathway dysregulations and potential CVD risk factors. We aimed to explore associations of cardiac function and morphology, evaluated using magnetic resonance imaging (MRI) with a large panel of serum metabolites. METHODS: Cross-sectional data from CVD-free individuals from the population-based KORA cohort were analyzed. Associations between 3T-MRI-derived left ventricular (LV) function and morphology parameters (e.g., volumes, filling rates, wall thickness) and markers of carotid plaque with metabolite profile clusters and single metabolites as outcomes were assessed by adjusted multinomial logistic regression and linear regression models. RESULTS: In 360 individuals (mean age 56.3 years; 41.9% female), 146 serum metabolites clustered into three distinct profiles that reflected high-, intermediate- and low-CVD risk. Higher stroke volume (relative risk ratio (RRR): 0.53, 95%-CI [0.37; 0.76], p-value < 0.001) and early diastolic filling rate (RRR: 0.51, 95%-CI [0.37; 0.71], p-value < 0.001) were most strongly protectively associated against the high-risk profile compared to the low-risk profile after adjusting for traditional CVD risk factors. Moreover, imaging markers were associated with 10 metabolites in linear regression. Notably, negative associations of stroke volume and early diastolic filling rate with acylcarnitine C5, and positive association of function parameters with lysophosphatidylcholines, diacylphosphatidylcholines, and acylalkylphosphatidylcholines were observed. Furthermore, there was a negative association of LV wall thickness with alanine, creatinine, and symmetric dimethylarginine. We found no significant associations with carotid plaque. CONCLUSIONS: Serum metabolite signatures are associated with cardiac function and morphology even in individuals without a clinical indication of CVD.

Photon-counting CT-angiography in pre-TAVR aortic annulus assessment: effects of retrospective vs. prospective ECG-synchronization on prosthesis valve selection.

To compare the diagnostic value of ultrahigh-resolution CT-angiography (UHR-CTA) compared with high-pitch spiral CTA (HPS-CTA) using a first-generation, dual-source photon-counting CT (PCD-CT) scanner for preprocedural planning of transcatheter aortic valve replacement (TAVR). Clinically referred patients with severe aortic valve stenosis underwent both, retrospective ECG-gated cardiac UHR-CTA (collimation: 120 × 0.2 mm) and prospective ECG-triggered aortoiliac HPS-CTA (collimation: 144 × 0.4 mm, full spectral capabilities) for TAVR planning from August 2022 to March 2023. Radiation dose was extracted from the CT reports, and the effective dose was calculated. Two radiologists analyzed UHR-CTA and HPS-CTA datasets, assessing the image quality of the aortic annulus, with regard to the lumen visibility and margin delineation using a 4-point visual-grading scale (ranges: 4 = "excellent" to 1 = "poor"). Aortic annulus area (AAA) measurements were taken for valve prosthesis sizing, with retrospective UHR-CTA serving as reference standard. A total of 64 patients were included (mean age, 81 years ± 7 SD; 28 women) in this retrospective study. HPS-CTA showed a lower radiation dose, 4.1 mSv vs. 12.6 mSv (p < 0.001). UHR-CTA demonstrated higher image quality to HPS-CTA (median score, 4 [IQR, 3-4] vs. 3 [IQR, 2-3]; p < 0.001). Quantitative assessments of AAA from both CTA datasets were strongly positively correlated (mean 477.4 ± 91.1 mm2 on UHR-CTA and mean 476.5 ± 90.4 mm2 on HPS-CTA, Pearson r2 = 0.857, p < 0.001) with a mean error of 22.3 ± 24.6 mm2 and resulted in identical valve prosthesis sizing in the majority of patients (91%). Patients with lower image quality on HPS-CTA (score value 1 or 2, n = 28) were more likely to receive different sizing recommendations (82%). Both UHR-CTA and HPS-CTA acquisitions using photon-counting CT technology provided reliable aortic annular assessments for TAVR planning. While UHR-CTA offers superior image quality, HPS-CTA is associated with lower radiation exposure. However, severely impaired image quality on HPS-CTA may impact on prosthesis sizing, suggesting that immediate post-scan image evaluations may require complementary UHR-CTA scanning.

A deep learning approach for projection and body-side classification in musculoskeletal radiographs.

BACKGROUND: The growing prevalence of musculoskeletal diseases increases radiologic workload, highlighting the need for optimized workflow management and automated metadata classification systems. We developed a large-scale, well-characterized dataset of musculoskeletal radiographs and trained deep learning neural networks to classify radiographic projection and body side. METHODS: In this IRB-approved retrospective single-center study, a dataset of musculoskeletal radiographs from 2011 to 2019 was retrieved and manually labeled for one of 45 possible radiographic projections and the depicted body side. Two classification networks were trained for the respective tasks using the Xception architecture with a custom network top and pretrained weights. Performance was evaluated on a hold-out test sample, and gradient-weighted class activation mapping (Grad-CAM) heatmaps were computed to visualize the influential image regions for network predictions. RESULTS: A total of 13,098 studies comprising 23,663 radiographs were included with a patient-level dataset split, resulting in 19,183 training, 2,145 validation, and 2,335 test images. Focusing on paired body regions, training for side detection included 16,319 radiographs (13,284 training, 1,443 validation, and 1,592 test images). The models achieved an overall accuracy of 0.975 for projection and 0.976 for body-side classification on the respective hold-out test sample. Errors were primarily observed in projections with seamless anatomical transitions or non-orthograde adjustment techniques. CONCLUSIONS: The deep learning neural networks demonstrated excellent performance in classifying radiographic projection and body side across a wide range of musculoskeletal radiographs. These networks have the potential to serve as presorting algorithms, optimizing radiologic workflow and enhancing patient care. RELEVANCE STATEMENT: The developed networks excel at classifying musculoskeletal radiographs, providing valuable tools for research data extraction, standardized image sorting, and minimizing misclassifications in artificial intelligence systems, ultimately enhancing radiology workflow efficiency and patient care. KEY POINTS: • A large-scale, well-characterized dataset was developed, covering a broad spectrum of musculoskeletal radiographs. • Deep learning neural networks achieved high accuracy in classifying radiographic projection and body side. • Grad-CAM heatmaps provided insight into network decisions, contributing to their interpretability and trustworthiness. • The trained models can help optimize radiologic workflow and manage large amounts of data.

Improving the use of LLMs in radiology through prompt engineering: from precision prompts to zero-shot learning.

PURPOSE: Large language models (LLMs) such as ChatGPT have shown significant potential in radiology. Their effectiveness often depends on prompt engineering, which optimizes the interaction with the chatbot for accurate results. Here, we highlight the critical role of prompt engineering in tailoring the LLMs' responses to specific medical tasks. MATERIALS AND METHODS: Using a clinical case, we elucidate different prompting strategies to adapt the LLM ChatGPT using GPT4 to new tasks without additional training of the base model. These approaches range from precision prompts to advanced in-context methods such as few-shot and zero-shot learning. Additionally, the significance of embeddings, which serve as a data representation technique, is discussed. RESULTS: Prompt engineering substantially improved and focused the chatbot's output. Moreover, embedding of specialized knowledge allows for more transparent insight into the model's decision-making and thus enhances trust. CONCLUSION: Despite certain challenges, prompt engineering plays a pivotal role in harnessing the potential of LLMs for specialized tasks in the medical domain, particularly radiology. As LLMs continue to evolve, techniques like few-shot learning, zero-shot learning, and embedding-based retrieval mechanisms will become indispensable in delivering tailored outputs. KEY POINTS: · Large language models might impact radiological practice and decision-masking.. · However, implementation and performance are dependent on the assigned task.. · Optimization of prompting strategies can substantially improve model performance.. · Strategies for prompt engineering range from precision prompts to zero-shot learning..

Ultrashort VIBE-Dixon versus Cine and late gadolinium enhancement MRI sequences for cardiac thrombus detection.

PURPOSE: To determine the diagnostic accuracy of volumetric interpolated breath-hold examination sequences with fat suppression in Dixon technique (VIBE-Dixon) for cardiac thrombus detection. METHOD: From our clinical database, we retrospectively identified consecutive patients between 2014 and 2022 who had definite diagnosis or exclusion of cardiac thrombus confirmed by an independent adjudication committee, serving as the reference standard. All patients received 2D-Cine plus 2D-Late-Gadolinium-Enhancement (Cine + LGE) and VIBE-Dixon sequences. Two blinded readers assessed all images for the presence of cardiac thrombus. The diagnostic accuracy of Cine + LGE and VIBE-Dixon was determined and compared. RESULTS: Among 141 MRI studies (116 male, mean age: 61 years) mean image examination time was 28.8 ± 3.1 s for VIBE-Dixon and 23.3 ± 2.5 min for Cine + LGE. Cardiac thrombus was present in 49 patients (prevalence: 35 %). For both readers sensitivity for thrombus detection was significantly higher in VIBE-Dixon compared with Cine + LGE (Reader 1: 96 % vs.73 %, Reader 2: 96 % vs. 78 %, p < 0.01 for both readers), whereas specificity did not differ significantly (Reader 1: 96 % vs. 98 %, Reader 2: 92 % vs. 93 %, p > 0.1). Overall diagnostic accuracy of VIBE-Dixon was higher than for Cine + LGE (95 % vs. 89 %, p = 0.02) and was non-inferior to the reference standard (Delta ≤ 5 % with probability > 95 %). CONCLUSIONS: Biplanar VIBE-Dixon sequences, acquired within a few seconds, provided a very high diagnostic accuracy for cardiac thrombus detection. They could be used as stand-alone sequences to rapidly screen for cardiac thrombus in patients not amenable to lengthy acquisition times.

A content-aware chatbot based on GPT 4 provides trustworthy recommendations for Cone-Beam CT guidelines in dental imaging.

OBJECTIVES: To develop a content-aware chatbot based on GPT-3.5-Turbo and GPT-4 with specialized knowledge on the German S2 Cone-Beam CT (CBCT) dental imaging guideline and to compare the performance against humans. METHODS: The LlamaIndex software library was used to integrate the guideline context into the chatbots. Based on the CBCT S2 guideline, 40 questions were posed to content-aware chatbots and early career and senior practitioners with different levels of experience served as reference. The chatbots' performance was compared in terms of recommendation accuracy and explanation quality. Chi-square test and one-tailed Wilcoxon signed rank test evaluated accuracy and explanation quality, respectively. RESULTS: The GPT-4 based chatbot provided 100% correct recommendations and superior explanation quality compared to the one based on GPT3.5-Turbo (87.5% vs. 57.5% for GPT-3.5-Turbo; P = .003). Moreover, it outperformed early career practitioners in correct answers (P = .002 and P = .032) and earned higher trust than the chatbot using GPT-3.5-Turbo (P = 0.006). CONCLUSIONS: A content-aware chatbot using GPT-4 reliably provided recommendations according to current consensus guidelines. The responses were deemed trustworthy and transparent, and therefore facilitate the integration of artificial intelligence into clinical decision-making.

Vaccination protects against acute respiratory distress syndrome (ARDS) in hospitalized patients with COVID-19.

This study aimed to analyze the effect of COVID-19 vaccination on the occurrence of ARDS in hospitalized COVID-19 patients. The study population of this retrospective, single-center cohort study consisted of hospitalized COVID-19 patients with known vaccination status and chest computed tomography imaging between July 2021 and February 2022. The impact of vaccination on ARDS in COVID-19 patients was assessed through logistic regression adjusting for demographic differences and confounding factors with statistical differences determined using confidence intervals and effect sizes. A total of 167 patients (69% male, average age 58 years, 95% CI [55; 60], 42% fully vaccinated) were included in the data analysis. Vaccinated COVID-19 patients had a reduced relative risk (RR) of developing ARDS (RR: 0.40, 95% CI [0.21; 0.62]). Consequently, non-vaccinated hospitalized patients had a 2.5-fold higher probability of developing ARDS. This risk reduction persisted after adjusting for several confounding variables (RR: 0.64, 95% CI [0.29; 0.94]) in multivariate analysis. The protective effect of COVID-19 vaccination increased with ARDS severity (RR: 0.61, 95% CI [0.37; 0.92]). Particularly, patients under 60 years old were at risk for ARDS onset and seemed to benefit from COVID-19 vaccination (RR: 0.51, 95% CI [0.20; 0.90]). COVID-19 vaccination showed to reduce the risk of ARDS occurrence in hospitalized COVID-19 patients, with a particularly strong effect in patients under 60 years old and those with more severe ARDS.

MR imaging after patellar MACI and MPFL reconstruction: a comparison of isolated versus combined procedures.

OBJECTIVE: To qualitatively and quantitatively evaluate the 2.5-year MRI outcome after Matrix-associated autologous chondrocyte implantation (MACI) at the patella, reconstruction of the medial patellofemoral ligament (MPFL), and combined procedures. METHODS: In 66 consecutive patients (age 22.8 ± 6.4years) with MACI at the patella (n = 16), MPFL reconstruction (MPFL; n = 31), or combined procedures (n = 19) 3T MRI was performed 2.5 years after surgery. For morphological MRI evaluation WORMS and MOCART scores were obtained. In addition quantitative cartilage T2 and T1rho relaxation times were acquired. Several clinical scores were obtained. Statistical analyses included descriptive statistics, Mann-Whitney-U-tests and Pearson correlations. RESULTS: WORMS scores at follow-up (FU) were significantly worse after combined procedures (8.7 ± 4.9) than after isolated MACI (4.3 ± 3.6, P = 0.005) and after isolated MPFL reconstruction (5.3 ± 5.7, P = 0.004). Bone marrow edema at the patella in the combined group was the only (non-significantly) worsening WORMS parameter from pre- to postoperatively. MOCART scores were significantly worse in the combined group than in the isolated MACI group (57 ± 3 vs 88 ± 9, P < 0.001). Perfect defect filling was achieved in 26% and 69% of cases in the combined and MACI group, respectively (P = 0.031). Global and patellar T2 values were higher in the combined group (Global T2: 34.0 ± 2.8ms) and MACI group (35.5 ± 3.1ms) as compared to the MPFL group (31.1 ± 3.2ms, P < 0.05). T2 values correlated significantly with clinical scores (P < 0.005). Clinical Cincinnati scores were significantly worse in the combined group (P < 0.05). CONCLUSION: After combined surgery with patellar MACI and MPFL reconstruction inferior MRI outcomes were observed than after isolated procedures. Therefore, patients with need for combined surgery may be at particular risk for osteoarthritis.