Introduction: Zygomatic fractures can be diagnosed with either computed tomography (CT) or direct digital radiography (DR). The aim of the present study was to assess the effect of CT dose reduction on the preference for facial CT versus DR for accurate diagnosis of isolated zygomatic fractures. Materials and methods: Eight zygomatic fractures were inflicted on four human cadavers with a free fall impactor technique. The cadavers were scanned using eight CT protocols, which were identical except for a systematic decrease in radiation dose per protocol, and one DR protocol. Single axial CT images were displayed alongside a DR image of the same fracture creating a total of 64 dual images for comparison. A total of 54 observers, including radiologists, radiographers and oral and maxillofacial surgeons, made a forced choice for either CT or DR. Results: Forty out of 54 observers (74%) preferred CT over DR (all with P < 0.05). Preference for CT was maintained even when radiation dose reduced from 147.4 mSv to 46.4 mSv (DR dose was 6.9 mSv). Only a single out of all raters preferred DR (P ¼ 0.0003). The remaining 13 observers had no significant preference. Conclusion: This study demonstrates that preference for axial CT over DR is not affected by substantial (~70%) CT dose reduction for the assessment of zygomatico-orbital fractures.
MULTIFILE
Muziek kan een drager zijn van herinneringen en emoties. In onze jeugd en vroege volwassenheid ontwikkelen we onze persoonlijke muzieksmaak. Voor mensen met dementie, meestal 80-plussers, is dat ruim zestig jaar geleden. Voor hen is er nu een online muziekstation dat muziek uit die periode draait: Radio Remember.
From diagnosis to patient scheduling, AI is increasingly being considered across different clinical applications. Despite increasingly powerful clinical AI, uptake into actual clinical workflows remains limited. One of the major challenges is developing appropriate trust with clinicians. In this paper, we investigate trust in clinical AI in a wider perspective beyond user interactions with the AI. We offer several points in the clinical AI development, usage, and monitoring process that can have a significant impact on trust. We argue that the calibration of trust in AI should go beyond explainable AI and focus on the entire process of clinical AI deployment. We illustrate our argument with case studies from practitioners implementing clinical AI in practice to show how trust can be affected by different stages in the deployment cycle.
