ABSTRACT
PURPOSE: The field of radiology is currently underestimated by undergraduate medical students. The "Hands-on Radiology" summer school was established to improve radiology knowledge and interest among undergraduates. The purpose of this questionnaire survey was to analyze whether a radiological hands-on course is an effective tool to reach and motivate undergraduate students. MATERIALS AND METHODS: The three-day course held in August 2022 included lectures, quizzes, and small group hands-on workshops focusing on practical work with simulators. All participants (n = 30) were asked to rate their knowledge and motivation to specialize in radiology at the beginning of the summer school (day 1) and the end (day 3). The questionnaires included multiple choice questions, 10-point scale questions and open comment questions. The second questionnaire (day 3) included additional questions regarding the program (topic choice, length, etc.). RESULTS: Out of 178 applicants, 30 students (16.8%) from 21 universities were selected to participate (50% female and 50% male students). All students completed both questionnaires. The overall rating was 9.47 on a 10-point scale. While the self-reported knowledge level increased from 6.47 (day 1) to 7.50 (day 3), almost all participants (96.7%, n = 29/30) mentioned an increased interest in the specialization of radiology after the event. Interestingly, most students (96.7%) preferred onsite teaching instead of online teaching and chose residents over board-certified radiologists as teachers. CONCLUSION: Intensive three-day courses are valuable tools to strengthen interest in radiology and increase knowledge among medical students. Particularly, students who already have a tendency to specialize in radiology are further motivated.
ABSTRACT
BACKGROUND: Osteoporosis causes an increased fracture risk. Clinically, osteoporosis is diagnosed late, usually after the first fracture occurs. This emphasizes the need for an early diagnosis of osteoporosis. However, computed tomography (CT) as routinely used for polytrauma scans cannot be used in the form of quantitative computed tomography (QCT) diagnosis because QCT can only be applied natively, i.e., without any contrast agent application. Here, we tested whether and how contrast agent application could be used for bone densitometry measurements. METHODS: Bone mineral density (BMD) was determined by QCT in the spine region of patients with and without the contrast agent Imeron 350. Corresponding scans were performed in the hip region to evaluate possible location-specific differences. RESULTS: Measurements with and without contrast agent administration between spine and hip bones indicate that the corresponding BMD values were reproducibly different between spine and hips, indicating that Imeron 350 application has a location-specific effect. We determined location-specific conversion factors that allow us then to determine the BMD values relevant for osteoporosis diagnosis. CONCLUSIONS: Results show that contrast administration cannot be used directly for CT diagnostics because the agent significantly alters BMD values. However, location-specific conversion factors can be established, which are likely to depend on additional parameters such as the weight and corresponding BMI of the patient.
ABSTRACT
Gleamer BoneView© is a commercially available AI algorithm for fracture detection in radiographs. We aim to test if the algorithm can assist in better sensitivity and specificity for fracture detection by residents with prospective integration into clinical workflow. Radiographs with inquiry for fracture initially reviewed by two residents were randomly assigned and included. A preliminary diagnosis of a possible fracture was made. Thereafter, the AI decision on presence and location of possible fractures was shown and changes to diagnosis could be made. Final diagnosis of fracture was made by a board-certified radiologist with over eight years of experience, or if available, cross-sectional imaging. Sensitivity and specificity of the human report, AI diagnosis, and assisted report were calculated in comparison to the final expert diagnosis. 1163 exams in 735 patients were included, with a total of 367 fractures (31.56%). Pure human sensitivity was 84.74%, and AI sensitivity was 86.92%. Thirty-five changes were made after showing AI results, 33 of which resulted in the correct diagnosis, resulting in 25 additionally found fractures. This resulted in a sensitivity of 91.28% for the assisted report. Specificity was 97.11, 84.67, and 97.36%, respectively. AI assistance showed an increase in sensitivity for both residents, without a loss of specificity.
