Longitudinal cardiac dimensions in patients undergoing LVAD implantation.

BACKGROUND: In conventional left ventricular assist devices (LVAD), a separate outflow graft is sutured to the ascending aorta. Novel device designs may include a transventricular outflow cannula crossing the aortic valve (AV). While transversal ventricular dimensions are well investigated in patients with severe heart failure, little is known about the longitudinal dimensions. These dimensions are, however, particularly critical for the design and development of mechanical circulatory support (MCS) devices with transaortic outflow cannula. METHODS: In an explorative retrospective cohort study at the University Medical Center Freiburg, Germany, the longitudinal cardiac dimensions of patients undergoing computed tomography angiography (CTA) before and, if available, after LVAD implantation were analyzed. Among others, the following dimensions were assessed: (a) apex to AV, (b) apex to mitral valve, (c) AV to sinotubular junction (STJ), (d) apex to STJ, (e) apex to brachiocephalic artery (BCA), and (f) AV to BCA. RESULTS: In total, 44 LVAD patients (36 male, age 55.8 years, height 1.75 m) were included. The longitudinal cardiac dimensions were (a) 114.5 ± 12.1 mm, (b) 108.0 ± 12.4 mm, (c) 20.9 ± 2.9, (d) 135.4 ± 13.4 mm, (e) 206.0 ± 18.3, and (f) 91.5 ± 9.8 mm. Postoperatively, (a) and (b) decreased by 31.5% and 39.5%, respectively (N = 14). CONCLUSIONS: Longitudinal cardiac dimensions may be reduced by up to 40% after LVAD implantation. A better knowledge of these dimensions and their postoperative alterations in LVAD patients may improve surgical planning and help to design MCS devices with transventricular outflow cannula.

A Context-based Chatbot Surpasses Trained Radiologists and Generic ChatGPT in Following the ACR Appropriateness Guidelines.

Background Radiological imaging guidelines are crucial for accurate diagnosis and optimal patient care as they result in standardized decisions and thus reduce inappropriate imaging studies. Purpose In the present study, we investigated the potential to support clinical decision-making using an interactive chatbot designed to provide personalized imaging recommendations from American College of Radiology (ACR) appropriateness criteria documents using semantic similarity processing. Methods We utilized 209 ACR appropriateness criteria documents as specialized knowledge base and employed LlamaIndex, a framework that allows to connect large language models with external data, and the ChatGPT 3.5-Turbo to create an appropriateness criteria contexted chatbot (accGPT). Fifty clinical case files were used to compare the accGPT's performance against general radiologists at varying experience levels and to generic ChatGPT 3.5 and 4.0. Results All chatbots reached at least human performance level. For the 50 case files, the accGPT performed best in providing correct recommendations that were "usually appropriate" according to the ACR criteria and also did provide the highest proportion of consistently correct answers in comparison with generic chatbots and radiologists. Further, the chatbots provided substantial time and cost savings, with an average decision time of 5 minutes and a cost of 0.19 € for all cases, compared to 50 minutes and 29.99 € for radiologists (both p < 0.01). Conclusion ChatGPT-based algorithms have the potential to substantially improve the decision-making for clinical imaging studies in accordance with ACR guidelines. Specifically, a context-based algorithm performed superior to its generic counterpart, demonstrating the value of tailoring AI solutions to specific healthcare applications.

Deep learning segmentation results in precise delineation of the putamen in multiple system atrophy.

OBJECTIVES: The precise segmentation of atrophic structures remains challenging in neurodegenerative diseases. We determined the performance of a Deep Neural Patchwork (DNP) in comparison to established segmentation algorithms regarding the ability to delineate the putamen in multiple system atrophy (MSA), Parkinson's disease (PD), and healthy controls. METHODS: We retrospectively included patients with MSA and PD as well as healthy controls. A DNP was trained on manual segmentations of the putamen as ground truth. For this, the cohort was randomly split into a training (N = 131) and test set (N = 120). The DNP's performance was compared with putaminal segmentations as derived by Automatic Anatomic Labelling, Freesurfer and Fastsurfer. For validation, we assessed the diagnostic accuracy of the resulting segmentations in the delineation of MSA vs. PD and healthy controls. RESULTS: A total of 251 subjects (61 patients with MSA, 158 patients with PD, and 32 healthy controls; mean age of 61.5 ± 8.8 years) were included. Compared to the dice-coefficient of the DNP (0.96), we noted significantly weaker performance for AAL3 (0.72; p < .001), Freesurfer (0.82; p < .001), and Fastsurfer (0.84, p < .001). This was corroborated by the superior diagnostic performance of MSA vs. PD and HC of the DNP (AUC 0.93) versus the AUC of 0.88 for AAL3 (p = 0.02), 0.86 for Freesurfer (p = 0.048), and 0.85 for Fastsurfer (p = 0.04). CONCLUSION: By utilization of a DNP, accurate segmentations of the putamen can be obtained even if substantial atrophy is present. This allows for more precise extraction of imaging parameters or shape features from the putamen in relevant patient cohorts. CLINICAL RELEVANCE STATEMENT: Deep learning-based segmentation of the putamen was superior to currently available algorithms and is beneficial for the diagnosis of multiple system atrophy. KEY POINTS: • A Deep Neural Patchwork precisely delineates the putamen and performs equal to human labeling in multiple system atrophy, even when pronounced putaminal volume loss is present. • The Deep Neural Patchwork-based segmentation was more capable to differentiate between multiple system atrophy and Parkinson's disease than the AAL3 atlas, Freesurfer, or Fastsurfer.

RF-induced heating of interventional devices at 23.66 MHz.

OBJECTIVE: Low-field MRI systems are expected to cause less RF heating in conventional interventional devices due to lower Larmor frequency. We systematically evaluate RF-induced heating of commonly used intravascular devices at the Larmor frequency of a 0.55 T system (23.66 MHz) with a focus on the effect of patient size, target organ, and device position on maximum temperature rise. MATERIALS AND METHODS: To assess RF-induced heating, high-resolution measurements of the electric field, temperature, and transfer function were combined. Realistic device trajectories were derived from vascular models to evaluate the variation of the temperature increase as a function of the device trajectory. At a low-field RF test bench, the effects of patient size and positioning, target organ (liver and heart) and body coil type were measured for six commonly used interventional devices (two guidewires, two catheters, an applicator and a biopsy needle). RESULTS: Electric field mapping shows that the hotspots are not necessarily localized at the device tip. Of all procedures, the liver catheterizations showed the lowest heating, and a modification of the transmit body coil could further reduce the temperature increase. For common commercial needles no significant heating was measured at the needle tip. Comparable local SAR values were found in the temperature measurements and the TF-based calculations. CONCLUSION: At low fields, interventions with shorter insertion lengths such as hepatic catheterizations result in less RF-induced heating than coronary interventions. The maximum temperature increase depends on body coil design.

Where Position Matters-Deep-Learning-Driven Normalization and Coregistration of Computed Tomography in the Postoperative Analysis of Deep Brain Stimulation.

INTRODUCTION: Recent developments in the postoperative evaluation of deep brain stimulation surgery on the group level warrant the detection of achieved electrode positions based on postoperative imaging. Computed tomography (CT) is a frequently used imaging modality, but because of its idiosyncrasies (high spatial accuracy at low soft tissue resolution), it has not been sufficient for the parallel determination of electrode position and details of the surrounding brain anatomy (nuclei). The common solution is rigid fusion of CT images and magnetic resonance (MR) images, which have much better soft tissue contrast and allow accurate normalization into template spaces. Here, we explored a deep-learning approach to directly relate positions (usually the lead position) in postoperative CT images to the native anatomy of the midbrain and group space. MATERIALS AND METHODS: Deep learning is used to create derived tissue contrasts (white matter, gray matter, cerebrospinal fluid, brainstem nuclei) based on the CT image; that is, a convolution neural network (CNN) takes solely the raw CT image as input and outputs several tissue probability maps. The ground truth is based on coregistrations with MR contrasts. The tissue probability maps are then used to either rigidly coregister or normalize the CT image in a deformable way to group space. The CNN was trained in 220 patients and tested in a set of 80 patients. RESULTS: Rigorous validation of such an approach is difficult because of the lack of ground truth. We examined the agreements between the classical and proposed approaches and considered the spread of implantation locations across a group of identically implanted subjects, which serves as an indicator of the accuracy of the lead localization procedure. The proposed procedure agrees well with current magnetic resonance imaging-based techniques, and the spread is comparable or even lower. CONCLUSIONS: Postoperative CT imaging alone is sufficient for accurate localization of the midbrain nuclei and normalization to the group space. In the context of group analysis, it seems sufficient to have a single postoperative CT image of good quality for inclusion. The proposed approach will allow researchers and clinicians to include cases that were not previously suitable for analysis.

Development and evaluation of machine learning models based on X-ray radiomics for the classification and differentiation of malignant and benign bone tumors.

OBJECTIVES: To develop and validate machine learning models to distinguish between benign and malignant bone lesions and compare the performance to radiologists. METHODS: In 880 patients (age 33.1 ± 19.4 years, 395 women) diagnosed with malignant (n = 213, 24.2%) or benign (n = 667, 75.8%) primary bone tumors, preoperative radiographs were obtained, and the diagnosis was established using histopathology. Data was split 70%/15%/15% for training, validation, and internal testing. Additionally, 96 patients from another institution were obtained for external testing. Machine learning models were developed and validated using radiomic features and demographic information. The performance of each model was evaluated on the test sets for accuracy, area under the curve (AUC) from receiver operating characteristics, sensitivity, and specificity. For comparison, the external test set was evaluated by two radiology residents and two radiologists who specialized in musculoskeletal tumor imaging. RESULTS: The best machine learning model was based on an artificial neural network (ANN) combining both radiomic and demographic information achieving 80% and 75% accuracy at 75% and 90% sensitivity with 0.79 and 0.90 AUC on the internal and external test set, respectively. In comparison, the radiology residents achieved 71% and 65% accuracy at 61% and 35% sensitivity while the radiologists specialized in musculoskeletal tumor imaging achieved an 84% and 83% accuracy at 90% and 81% sensitivity, respectively. CONCLUSIONS: An ANN combining radiomic features and demographic information showed the best performance in distinguishing between benign and malignant bone lesions. The model showed lower accuracy compared to specialized radiologists, while accuracy was higher or similar compared to residents. KEY POINTS: • The developed machine learning model could differentiate benign from malignant bone tumors using radiography with an AUC of 0.90 on the external test set. • Machine learning models that used radiomic features or demographic information alone performed worse than those that used both radiomic features and demographic information as input, highlighting the importance of building comprehensive machine learning models. • An artificial neural network that combined both radiomic and demographic information achieved the best performance and its performance was compared to radiology readers on an external test set.

Impact of radiographic field-of-view volume on alignment accuracy during virtual implant planning: A noninterventional retrospective pilot study.

OBJECTIVE: To evaluate the impact of reducing the radiographic field of view (FOV) on the trueness and precision of the alignment between cone beam computed tomography (CBCT) and intraoral scanning data for implant planning. MATERIALS AND METHODS: Fifteen participants presenting with one of three clinical scenarios: single tooth loss (ST, n = 5), multiple missing teeth (MT, n = 5) and presence of radiographic artifacts (AR, n = 5) were included. CBCT volumes covering the full arch (FA) were reduced to the quadrant (Q) or the adjacent tooth/teeth (A). Two operators, an expert (exp) in virtual implant planning and an inexperienced clinician, performed multiple superimpositions, with FA-exp serving as a reference. The deviations were calculated at the implant apex and shoulder levels. Thereafter, linear mixed models were adapted to investigate the influence of FOV on discrepancies. RESULTS: Evaluation of trueness compared to FA-exp resulted in the largest mean (AR-A: 0.10 ± 0.33 mm) and single maximum discrepancy (AR-Q: 1.44 mm) in the presence of artifacts. Furthermore, for the ST group, the largest mean error (-0.06 ± 0.2 mm, shoulder) was calculated with the FA-FOV, while for MT, with the intermediate volume (-0.07 ± 0.24 mm, Q). In terms of precision, the mean SD intervals were ≤0.25 mm (A-exp). Precision was influenced by FOV volume (FA < Q < A) but not by operator expertise. CONCLUSIONS: For single posterior missing teeth, an extended FOV does not improve registration accuracy. However, in the presence of artifacts or multiple missing posterior teeth, caution is recommended when reducing FOV.

Multitask Deep Learning for Segmentation and Classification of Primary Bone Tumors on Radiographs.

Background An artificial intelligence model that assesses primary bone tumors on radiographs may assist in the diagnostic workflow. Purpose To develop a multitask deep learning (DL) model for simultaneous bounding box placement, segmentation, and classification of primary bone tumors on radiographs. Materials and Methods This retrospective study analyzed bone tumors on radiographs acquired prior to treatment and obtained from patient data from January 2000 to June 2020. Benign or malignant bone tumors were diagnosed in all patients by using the histopathologic findings as the reference standard. By using split-sample validation, 70% of the patients were assigned to the training set, 15% were assigned to the validation set, and 15% were assigned to the test set. The final performance was evaluated on an external test set by using geographic validation, with accuracy, sensitivity, specificity, and 95% CIs being used for classification, the intersection over union (IoU) being used for bounding box placements, and the Dice score being used for segmentations. Results Radiographs from 934 patients (mean age, 33 years ± 19 [standard deviation]; 419 women) were evaluated in the internal data set, which included 667 benign bone tumors and 267 malignant bone tumors. Six hundred fifty-four patients were in the training set, 140 were in the validation set, and 140 were in the test set. One hundred eleven patients were in the external test set. The multitask DL model achieved 80.2% (89 of 111; 95% CI: 72.8, 87.6) accuracy, 62.9% (22 of 35; 95% CI: 47, 79) sensitivity, and 88.2% (67 of 76; CI: 81, 96) specificity in the classification of bone tumors as malignant or benign. The model achieved an IoU of 0.52 ± 0.34 for bounding box placements and a mean Dice score of 0.60 ± 0.37 for segmentations. The model accuracy was higher than that of two radiologic residents (71.2% and 64.9%; P = .002 and P < .001, respectively) and was comparable with that of two musculoskeletal fellowship-trained radiologists (83.8% and 82.9%; P = .13 and P = .25, respectively) in classifying a tumor as malignant or benign. Conclusion The developed multitask deep learning model allowed for accurate and simultaneous bounding box placement, segmentation, and classification of primary bone tumors on radiographs. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Carrino in this issue.

Determination of local flow ratios and velocities in a femoral venous cannula with computational fluid dynamics and 4D flow-sensitive magnetic resonance imaging: A method validation.

Cannulas with multi-staged side holes are the method of choice for femoral cannulation in extracorporeal therapies today. A variety of differently designed products is available on the market. While the preferred tool for the performance assessment of such cannulas are pressure-flow curves, little is known about the flow and velocity distribution. Within this work flow and velocity patterns of a femoral venous cannula with multi-staged side holes were investigated. A mock circulation loop for cannula performance evaluation was built and reproduced using a computer-aided design system. With computational fluid dynamics, volume flows and fluid velocities were determined quantitatively and visually with hole-based precision. In order to ensure the correctness of the flow simulation, the results were subsequently validated by determining the same parameters with four-dimensional flow-sensitive magnetic resonance imaging. Measurement data and numerical solution differed 7% on average throughout the data set for the examined parameters. The highest inflow and velocity were detected at the most proximal holes, where half of the total volume flow enters the cannula. At every hole stage a Y-shaped inflow profile was detected, forming a centered stream in the middle of the cannula. Simultaneously, flow separation creates zones with significant lower flow velocities. Numerical simulation, validated with four-dimensional flow-sensitive magnetic resonance imaging, is a valuable tool to examine flow and velocity distributions of femoral venous cannulas with hole-based accuracy. Flow and velocity distribution in such cannulas are not ideal. Based on this work future cannulas can be effectively optimized.

Evaluation of computed tomography settings in the context of visualization and discrimination of low dose injections of a novel liquid soft tissue fiducial marker in head and neck imaging.

BACKGROUND: Intraoperative incorporation of radiopaque fiducial markers at the tumor resection surface can provide useful assistance in identifying the tumor bed in postoperative imaging for RT planning and radiological follow-up. Besides titanium clips, iodine containing injectable liquid fiducial markers represent an option that has emerged more recently for this purpose. In this study, marking oral soft tissue resection surfaces, applying low dose injections of a novel Conformité Européenne (CE)-marked liquid fiducial marker based on sucrose acetoisobutyrate (SAIB) and iodinated SAIB (x-SAIB) was investigated. METHODS: Visibility and discriminability of low dose injections of SAIB/x-SAIB (10 µl, 20 µl, 30 µl) were systematically studied at different kV settings used in clinical routine in an ex-vivo porcine mandible model. Transferability of the preclinical results into the clinical setting and applicability of DE-CT were investigated in initial patients. RESULTS: Markers created by injection volumes as low as 10 µl were visible in CT imaging at all kV settings applied in clinical routine (70-120 kV). An injection volume of 30 µl allowed differentiation from an injection volume of 10 µl. In a total of 118 injections performed in two head and neck cancer patients, markers were clearly visible in 83% and 86% of injections. DE-CT allowed for differentiation between SAIB/x-SAIB markers and other hyperdense structures. CONCLUSIONS: Injection of low doses of SAIB/x-SAIB was found to be a feasible approach to mark oral soft tissue resection surfaces, with injection volumes as low as 10 µl found to be visible at all kV settings applied in clinical routine. With the application of SAIB/x-SAIB reported for tumors of different organs already, mostly applying relatively large volumes for IGRT, this study adds information on the applicability of low dose injections to facilitate identification of the tumor bed in postoperative CT and on performance of the marker at different kV settings used in clinical routine.

K-t GRAPPA-accelerated 4D flow MRI of liver hemodynamics: influence of different acceleration factors on qualitative and quantitative assessment of blood flow.

OBJECTIVE: We sought to evaluate the feasibility of k-t parallel imaging for accelerated 4D flow MRI in the hepatic vascular system by investigating the impact of different acceleration factors. MATERIALS AND METHODS: k-t GRAPPA accelerated 4D flow MRI of the liver vasculature was evaluated in 16 healthy volunteers at 3T with acceleration factors R = 3, R = 5, and R = 8 (2.0 × 2.5 × 2.4 mm(3), TR = 82 ms), and R = 5 (TR = 41 ms); GRAPPA R = 2 was used as the reference standard. Qualitative flow analysis included grading of 3D streamlines and time-resolved particle traces. Quantitative evaluation assessed velocities, net flow, and wall shear stress (WSS). RESULTS: Significant scan time savings were realized for all acceleration factors compared to standard GRAPPA R = 2 (21-71 %) (p < 0.001). Quantification of velocities and net flow offered similar results between k-t GRAPPA R = 3 and R = 5 compared to standard GRAPPA R = 2. Significantly increased leakage artifacts and noise were seen between standard GRAPPA R = 2 and k-t GRAPPA R = 8 (p < 0.001) with significant underestimation of peak velocities and WSS of up to 31 % in the hepatic arterial system (p <0.05). WSS was significantly underestimated up to 13 % in all vessels of the portal venous system for k-t GRAPPA R = 5, while significantly higher values were observed for the same acceleration with higher temporal resolution in two veins (p < 0.05). CONCLUSION: k-t acceleration of 4D flow MRI is feasible for liver hemodynamic assessment with acceleration factors R = 3 and R = 5 resulting in a scan time reduction of at least 40 % with similar quantitation of liver hemodynamics compared with GRAPPA R = 2.

Reproducibility study of four-dimensional flow MRI of arterial and portal venous liver hemodynamics: influence of spatio-temporal resolution.

PURPOSE: To evaluate influence of variation in spatio-temporal resolution and scan-rescan reproducibility on three-dimensional (3D) visualization and quantification of arterial and portal venous (PV) liver hemodynamics at four-dimensional (4D) flow MRI. METHODS: Scan-rescan reproducibility of 3D hemodynamic analysis of the liver was evaluated in 10 healthy volunteers using 4D flow MRI at 3T with three different spatio-temporal resolutions (2.4 × 2.0 × 2.4 mm(3), 61.2 ms; 2.5 × 2.0 × 2.4 mm(3), 81.6 ms; 2.6 × 2.5 × 2.6 mm(3), 80 ms) and thus different total scan times. Qualitative flow analysis used 3D streamlines and time-resolved particle traces. Quantitative evaluation was based on maximum and mean velocities, flow volume, and vessel lumen area in the hepatic arterial and PV systems. RESULTS: 4D flow MRI showed good interobserver variability for assessment of arterial and PV liver hemodynamics. 3D flow visualization revealed limitations for the left intrahepatic PV branch. Lower spatio-temporal resolution resulted in underestimation of arterial velocities (mean 15%, P < 0.05). For the PV system, hemodynamic analyses showed significant differences in the velocities for intrahepatic portal vein vessels (P < 0.05). Scan-rescan reproducibility was good except for flow volumes in the arterial system. CONCLUSION: 4D flow MRI for assessment of liver hemodynamics can be performed with low interobserver variability and good reproducibility. Higher spatio-temporal resolution is necessary for complete assessment of the hepatic blood flow required for clinical applications.

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..

Enhancing chatbot performance for imaging recommendations: Leveraging GPT-4 and context-awareness for trustworthy clinical guidance.

PURPOSE: To investigate if GPT-4 improves the accuracy, consistency, and trustworthiness of a context-aware chatbot to provide personalized imaging recommendations from American College of Radiology (ACR) appropriateness criteria documents using semantic similarity processing: In addition, we sought to enable auditability of the output by revealing the information source the decision relies on. MATERIAL AND METHODS: We refined an existing chatbot that incorporated specialized knowledge of the ACR guidelines by upgrading GPT-3.5-Turbo to its successor GPT-4 by OpenAI, using the latest version of LlamaIndex, and improving the prompting strategy. This chatbot was compared to the previous version, generic GPT-3.5-Turbo and GPT-4, and general radiologists regarding the performance in applying the ACR appropriateness guidelines. RESULTS: The refined context-aware chatbot performed superior to the previous version using GPT-3.5-Turbo, generic chatbots GPT-3.5-Turbo and GPT-4, and general radiologists in providing "usually or may be appropriate" recommendations according to the ACR guidelines (all p < 0.001). It also outperformed GPT-3.5-Turbo and general radiologists in respect to "usually appropriate" recommendations (both p < 0.001). Moreover, the consistency in correct answers was higher with 78 % consistent correct "usually appropriate" answers and 94 % for "usually or may be appropriate" recommendations. In all cases, the same source documents were chosen, ensuring transparency. CONCLUSION: Our study demonstrates the significance of context awareness in ensuring the use of appropriate knowledge and proposes a strategy to enhance trust in chatbot-based outputs to provide transparency. The improvements in accuracy, consistency, and source transparency address trust issues and enhance the clinical decision support process. ABBREVIATIONS: ACR, American College of Radiology; accGPT, appropriateness criteria context aware GPT; accGPT-4, appropriateness criteria context aware GPT using GPT-4; GPT, generative pre-trained transformer; LLM, Large Language Model.

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.

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.

AI-based X-ray fracture analysis of the distal radius: accuracy between representative classification, detection and segmentation deep learning models for clinical practice.

OBJECTIVES: To aid in selecting the optimal artificial intelligence (AI) solution for clinical application, we directly compared performances of selected representative custom-trained or commercial classification, detection and segmentation models for fracture detection on musculoskeletal radiographs of the distal radius by aligning their outputs. DESIGN AND SETTING: This single-centre retrospective study was conducted on a random subset of emergency department radiographs from 2008 to 2018 of the distal radius in Germany. MATERIALS AND METHODS: An image set was created to be compatible with training and testing classification and segmentation models by annotating examinations for fractures and overlaying fracture masks, if applicable. Representative classification and segmentation models were trained on 80% of the data. After output binarisation, their derived fracture detection performances as well as that of a standard commercially available solution were compared on the remaining X-rays (20%) using mainly accuracy and area under the receiver operating characteristic (AUROC). RESULTS: A total of 2856 examinations with 712 (24.9%) fractures were included in the analysis. Accuracies reached up to 0.97 for the classification model, 0.94 for the segmentation model and 0.95 for BoneView. Cohen's kappa was at least 0.80 in pairwise comparisons, while Fleiss' kappa was 0.83 for all models. Fracture predictions were visualised with all three methods at different levels of detail, ranking from downsampled image region for classification over bounding box for detection to single pixel-level delineation for segmentation. CONCLUSIONS: All three investigated approaches reached high performances for detection of distal radius fractures with simple preprocessing and postprocessing protocols on the custom-trained models. Despite their underlying structural differences, selection of one's fracture analysis AI tool in the frame of this study reduces to the desired flavour of automation: automated classification, AI-assisted manual fracture reading or minimised false negatives.

Effective management of recurrent Doege-Potter syndrome with somatostatin-analogues: A case report.

BACKGROUND: Doege-Potter syndrome is defined as paraneoplastic hypoinsulinemic hypoglycemia associated with a benign or malignant solitary fibrous tumor frequently located in pleural, but also extrapleural sites. Hypoglycemia can be attributed to paraneoplastic secretion of "Big-IGF-II," a precursor of Insulin-like growth factor-II. This prohormone aberrantly binds to and activates insulin receptors, with consecutive initiation of common insulin actions such as inhibition of gluconeogenesis, activation of glycolysis and stimulation of cellular glucose uptake culminating in recurrent tumor-induced hypoglycemic episodes. Complete tumor resection or debulking surgery is considered the most promising treatment for DPS. CASE: Here, we report a rare case of a recurrent Doege-Poter Syndrome with atypical gelatinous tumor lesions of the lung, pleura and pericardial fat tissue in an 87-year-old woman. Although previously described as ineffective, we propose that adjuvant treatment with Octreotide in conjunction with intravenous glucose helped to maintain tolerable blood glucose levels before tumor resection. The somatostatin-analogue Lanreotide was successfully used after tumor debulking surgery (R2-resection) to maintain adequate blood glucose control. CONCLUSION: We conclude that somatostatin-analogues bear the potential of being effective in conjunction with limited surgical approaches for the treatment of hypoglycemia in recurrent or non-totally resectable SFT entities underlying DPS.

Deep learning reconstructed T2-weighted Dixon imaging of the spine: Impact on acquisition time and image quality.

PURPOSE: To assess the image quality and impact on acquisition time of a novel deep learning based T2 Dixon sequence (T2DL) of the spine. METHODS: This prospective, single center study included n = 44 consecutive patients with a clinical indication for lumbar MRI at our university radiology department between September 2022 and March 2023. MRI examinations were performed on 1.5-T and 3-T scanners (MAGNETOM Aera and Vida; Siemens Healthineers, Erlangen, Germany) using dedicated spine coils. The MR study protocol consisted of our standard clinical protocol, including a T2 weighted standard Dixon sequence (T2std) and an additional T2DL acquisition. The latter used a conventional sampling pattern with a higher parallel acceleration factor. The individual contrasts acquired for Dixon water-fat separation were then reconstructed using a dedicated research application. After reconstruction of the contrast images from k-space data, a conventional water-fat separation was performed to provide derived water images. Two readers with 6 and 4 years of experience in interpreting MSK imaging, respectively, analyzed the images in a randomized fashion. Regarding overall image quality, banding artifacts, artifacts, sharpness, noise, and diagnostic confidence were analyzed using a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent image quality). Statistical analyses included the Wilcoxon signed-rank test and weighted Cohen's kappa statistics. RESULTS: Forty-four patients (mean age 53 years (±18), male sex: 39 %) were prospectively included. Thirty-one examinations were performed on 1.5 T and 13 examinations on 3 T scanners. A sequence was successfully acquired in all patients. The total acquisition time of T2DL was 93 s at 1.5-T and 86 s at 3-T, compared to 235 s, and 257 s, respectively for T2std (reduction of acquisition time: 60.4 % at 1.5-T, and 66.5 % at 3-T; p < 0.01). Overall image quality was rated equal for both sequences (median T2DL: 5[3 -5], and median T2std: 5 [2 -5]; p = 0.57). T2DL showed significantly reduced noise levels compared to T2std (5 [4 -5] versus 4 [3 -4]; p < 0.001). In addition, sharpness was rated to be significantly higher in T2DL (5 [4 -5] versus 4 [3 -5]; p < 0.001). Although T2DL displayed significantly more banding artifacts (5 [2 -5] versus 5 [4 -5]; p < 0.001), no significant impact on readers diagnostic confidence between sequences was noted (T2std: 5 [2 -5], and T2DL: 5 [3 -5]; p = 0.61). Substantial inter-reader and intrareader agreement was observed for T2DL overall image quality (κ: 0.77, and κ: 0.8, respectively). CONCLUSION: T2DL is feasible, yields an image quality comparable to the reference standard while substantially reducing the acquisition time.

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.