Purpose: To assess current perceptions, practices and education needs pertaining to artificial intelligence (AI) in the medical physics field.Methods: A web-based survey was distributed to the... Show morePurpose: To assess current perceptions, practices and education needs pertaining to artificial intelligence (AI) in the medical physics field.Methods: A web-based survey was distributed to the European Federation of Organizations for Medical Physics (EFOMP) through social media and email membership list. The survey included questions about education, personal knowledge, needs, research and professionalism around AI in medical physics. Demographics information were also collected. Responses were stratified and analysed by gender, type of institution and years of experience in medical physics. Statistical significance (p < 0.05) was assessed using paired t-test.Results: 219 people from 31 countries took part in the survey. 81% (n = 177) of participants agreed that AI will improve the daily work of Medical Physics Experts (MPEs) and 88% (n = 193) of respondents expressed the need for MPEs of specific training on AI. The average level of AI knowledge among participants was 2.3 +/- 1.0 (mean +/- standard deviation) in a 1-to-5 scale and 96% (n = 210) of participants showed interest in improving their AI skills. A significantly lower AI knowledge was observed for female participants (2.0 +/- 1.0), compared to male responders (2.4 +/- 1.0). 64% of participants indicated that they are not involved in AI projects. The percentage of female leading AI projects was significantly lower than the male counterparts (3% vs 19%).Conclusions: AI was perceived as a positive resource to support MPEs in their daily tasks. Participants demonstrated a strong interest in improving their current AI-related skills, enhancing the need for dedicated training for MPEs. Show less
Speelman, E.S.; Brocx, B.; Wilbers, J.E.; Bie, M.J. de; Ivashchenko, O.; Tank, Y.; Molen, A.J. van der 2019
Purpose Whole-body computed tomography (WBCT) is the standard diagnostic method for evaluating polytrauma patients. When patients are unable to elevate their arms, the arms are placed along the... Show morePurpose Whole-body computed tomography (WBCT) is the standard diagnostic method for evaluating polytrauma patients. When patients are unable to elevate their arms, the arms are placed along the body, which affects the image quality negatively. Aim of this systematic review is to evaluate the influence of below the shoulder arm positions on image quality of WBCT. Methods Literature in PubMed and Scopus databases was systematically searched. Results of the papers were stratified into 4 categories: arms elevated, 1 arm up 1 arm down, arms ventrally supported, arms along the body. A qualitative analysis was performed on subjective image quality and a quantitative analysis on objective quality (image noise). Results Eight studies were included with 1421 participants. Various studies reported significantly higher quality scores with arms elevated, compared to arms along the body. Significant differences in objective image quality were found between the arms elevated and the arms ventrally on support group. The arms ventrally supported group had a significantly higher image quality than the arms along the body group. A statistically significant difference was found in objective image quality between the 1 arm up 1 arm down and arms along the body group. No preferential below the shoulders position could be identified. Conclusion Positioning the arms alongside the body results in a poor image quality. Placing the arms on a pillow ventrally to the chest improves image quality. Interestingly, asymmetrical arm positioning has potential to improve the image quality for patients that are unable to elevate the arms. Show less
Resection of maxillary cancer often results in incomplete excision because of the tumour's proximity to important structures such as the orbit. To deal with this problem we prospectively... Show moreResection of maxillary cancer often results in incomplete excision because of the tumour's proximity to important structures such as the orbit. To deal with this problem we prospectively investigated the feasibility of intraoperative imaging during maxillectomy to verify the planned resection margins. In total, six patients diagnosed with maxillary cancer listed for maxillectomy were included, irrespective of the histological type of tumour. Before resection, an accurate intended resection volume was delineated on diagnostic images. At the end of the operation we took a cone-beam computed tomographic (CT) scan of the treated maxilla, after which the accuracy of the resection was quantitatively evaluated by comparing the preoperative resection plan and the images acquired intraoperatively, based on the anatomy. Further resection was then done if necessary and quantitatively evaluated with a second cone-beam CT scan. Postoperatively we compared the results of the scan with those of the histological examination. Of the six, two resections were reported pathologically as less than radical, each of which was detected by intraoperative CT and resulted in extensions of the original resections. The mean (SD) distance between the planned and the actual resection was 1.49 (2.78) mm This suggests that intraoperative cone-beam CT imaging is a promising way to make an adequate intraoperative assessment of planned surgical margins of maxillary tumours. This allows for intraoperative resection margins to be improved, possibly leading to a better prognosis for the patient. (C) 2019 The British Association of Oral and Maxillofacial Surgeons. Published by Elsevier Ltd. All rights reserved. Show less