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.

The aim of this study was to evaluate and compare the diagnostic accuracy, the inter-rater agreement and raters’ certainty of cone beam computed tomography (CBCT) and radiography for the detection of scaphoid fractures. Our hypothesis is that the CBCT has a higher diagnostic accuracy for scaphoid fractures than radiography. We retrospectively analysed patients who underwent both radiography and CBCT examinations within 4 days to rule out a scaphoid fracture over a 2-year period in our institution. 4 blinded radiologists and orthopaedic surgeons independently rated the images regarding the presence of a scaphoid fracture. The reference standard was evaluated by two radiologists in a consensus reading. Inter-rater correlation was evaluated, pooled sensitivity, specificity, positive and negative predictive values were calculated and compared. 102 patients met the inclusion criteria. 52% of them had a scaphoid fracture. The inter-rater correlation was higher in the CBCT compared to radiography (P < 0.001). Sensitivity, specificity, positive and negative predictive values were higher for CBCT than for radiography (P < 0.019). Observers’ fracture classifications showed a higher correlation with the reference standard in the CBCT. Observers’ certainty for fracture detection and classification were higher in the CBCT. CBCT shows a higher diagnostic accuracy for scaphoid fractures than radiography.

To compare the diagnostic accuracy of radiography, to radiography equivalent dose multidetector computed tomography (RED-MDCT) and to radiography equivalent dose cone beam computed tomography (RED-CBCT) for wrist fractures. As study subjects we obtained 10 cadaveric human hands from body donors. Distal radius, distal ulna and carpal bones (n = 100) were artificially fractured in random order in a controlled experimental setting. We performed radiation dose equivalent radiography (settings as in standard clinical care), RED-MDCT in a 320 row MDCT with single shot mode and RED-CBCT in a device dedicated to musculoskeletal imaging. Three raters independently evaluated the resulting images for fractures and the level of confidence for each finding. Gold standard was evaluated by consensus reading of a high-dose MDCT. Pooled sensitivity was higher in RED-MDCT with 0.89 and RED-MDCT with 0.81 compared to radiography with 0.54 (P = < .004). No significant differences were detected concerning the modalities’ specificities (with values between P = .98). Raters' confidence was higher in RED-MDCT and RED-CBCT compared to radiography (P < .001). The diagnostic accuracy of RED-MDCT and RED-CBCT for wrist fractures proved to be similar and in some parts even higher compared to radiography. Readers are more confident in their reporting with the cross sectional modalities. Dose equivalent cross sectional computed tomography of the wrist could replace plain radiography for fracture diagnosis in the long run.

Background Photon-counting detector computed tomography (PCD-CT) is a promising new technology with the potential to fundamentally change workflows in the daily routine and provide new quantitative imaging information to improve clinical decision-making and patient management. Method The contents of this review are based on an unrestricted literature search of PubMed and Google Scholar using the search terms “photon-counting CT”, “photon-counting detector”, “spectral CT”, “computed tomography” as well as on the authors’ own experience. Results The fundamental difference with respect to the currently established energy-integrating CT detectors is that PCD-CT allows for the counting of every single photon at the detector level. Based on the identified literature, PCD-CT phantom measurements and initial clinical studies have demonstrated that the new technology allows for improved spatial resolution, reduced image noise, and new possibilities for advanced quantitative image postprocessing. Conclusion For clinical practice, the potential benefits include fewer beam hardening artifacts, a radiation dose reduction, and the use of new or combinations of contrast agents. In particular, critical patient groups such as oncological, cardiovascular, lung, and head & neck as well as pediatric patient collectives benefit from the clinical advantages. Key Points: Citation Format

Purpose: Comparison of radiation dose of cone beam computed tomography (CBCT) and multidetector computed tomography (MDCT) in examinations of the hand. Materials and Methods: Dose calculations were carried out by means of Monte Carlo simulations in MDCT and CBCT. A corpse hand was examined in a 320-row MDCT scanner and a dedicated extremities CBCT scanner with standard protocols and multiple low-dose protocols. The image quality of the examinations was evaluated by 5 investigators using a Likert scale from 1 (very good) to 5 (very poor) regarding depiction of cortical bone, cancellous bone, joint surfaces, soft tissues and artifacts. For a sum of ratings of all structures < 50 a good overall image quality was expected. The studies with at least good overall image quality were compared with respect to the dose. Results: The dose of the standard examination was 13.21 (12.96 to 13.46 CI) mGy in MDCT and 7.15 (6.99 to 7.30 CI) mGy in CBCT. The lowest dose in a study with good overall image quality was 4.54 (4.43 to 4.64 CI) mGy in MDCT and 5.72 (5.59 to 5.85 CI) mGy in CBCT. Conclusion: Although the dose of the standard protocols in the CBCT is lower than in the MDCT, the MDCT can realize a good overall image quality at a lower dose than the CBCT. Dose optimization of CT examination protocols for the hand is useful in both modalities, the MDCT has an even greater potential for optimization. Key points: • Low dose examinations of the hand are feasible in CBCT and MDCT. • In default settings CBCT has a lower dose than MDCT. • MDCT enables a good image quality at a lower dose than CBCT. Citation Format: • Neubauer J, Neubauer C, Gerstmair A et al. Comparison of the Radiation Dose from Cone Beam Computed Tomography and Multidetector Computed Tomography in Examinations of the Hand. Fortschr Röntgenstr 2016; 188: 488 – 493 Ziel: Vergleich der Strahlendosis von Cone-Beam Computertomografie (CBCT) und Multidetektor-Computertomografie (MDCT) bei Untersuchungen der Hand. Material und Methoden: Dosisbestimmungen wurden mittels Monte Carlo-Simulationen an MDCT und CBCT durchgeführt. Eine Leichenhand wurde in einem 320-Zeilen MDCT-Scanner und einem für die Bildgebung der Extremitäten ausgerichteten CBCT-Scanner mit Standardprotokollen und multiplen Niedrigdosisprotokollen untersucht. Die Bildqualität der Untersuchungen wurde von 5 Untersuchern mittels einer Likert-Skala von 1 (sehr gut) bis 5 (sehr schlecht) bezüglich der Abbildung von Kortikalis, Spongiosa, Gelenkflächen, Weichteilen und Artefakten beurteilt. Bei einer Summe der Bewertungen aller Strukturen < 50 wurde eine gute Gesamtbildqualität angenommen. Die Untersuchungen mit mindestens guter Gesamtbildqualität wurden bezüglich der Dosis verglichen. Ergebnisse: Die Dosis der Standarduntersuchung war 13,21 (KI 12,96 – 13,46) mGy im MDCT und 7,15 (KI 6,99 – 7,30) mGy im CBCT. Die niedrigste Dosis in einer Untersuchung mit guter Gesamtbildqualität war 4,54 (KI 4,43 – 4,64) mGy im MDCT und 5,72 (KI 5,59 – 5,85) mGy im CBCT. Schlussfolgerung: Obwohl die Dosis der Standardprotokolle in der CBCT niedriger ist als in der MDCT, kann die MDCT eine gute Gesamtbildqualität bei geringerer Dosis als die CBCT realisieren. Die Dosisoptimierung der CT-Untersuchungsprotokolle für die Hand ist in beiden Modalitäten sinnvoll, wobei die MDCT ein größeres Optimierungspotenzial aufweist.