Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice.

Purpose Clinical outcome of stroke patients is usually classified into favorable (modified Rankin scale (mRS) 0–2) and unfavorable (mRS 3–5) outcome according to the modified Rankin scale. We took a closer look at the clinical course of thrombectomy stroke patients with formal unfavorable outcome and assessed whether we could achieve our treatment goals and/or neurological improvement in these patients. Methods We studied 107 patients with occlusions in the terminal carotid artery or the M1 segment of the middle cerebral artery, in whom complete recanalization (eTICI 3) could be achieved, and who had an mRS of 3–5 at 90 days. We analyzed whether an individual treatment goal (i.e., preventing aphasia) and neurological improvement (NIHSS) could be achieved. In addition, we examined whether there was clinical improvement on the mRS. Results The treatment goal was achieved in 52% (53/103) and neurological improvement in 65% (67/103). mRS 90 days post-stroke was better than mRS upon admission in 36% (38/107) and better than or equal to mRS upon admission in 80% (86/107). Of the 93 patients with known pre-stroke mRS, 18% (17/93) already had an mRS ≥ 3, with 15 of these 17 patients having a worse mRS on admission than before. Of these 17 patients, 18% regained baseline, and 24% improved from admission. Conclusion Dichotomizing the mRS into favorable and unfavorable outcome does not do justice to the full spectrum of stroke. Patients with formal unfavorable outcome after mRS can improve neurologically, achieve treatment goals, and even regain their admission or pre-stroke mRS.

Background and purpose During a period of 6 months, we provided our entire neuroradiological staff including physicians, radiographers, and researchers with systematic feedback via email on the further clinical course of stroke patients who underwent mechanical thrombectomy. We analyzed the effects of this feedback on work satisfaction, work meaningfulness and valuation of the therapy among our staff. Methods Our staff completed two self-reported questionnaires before and after the period of six months with systematic feedback. Results Employees with higher work meaningfulness and higher work satisfaction valuated endovascular stroke therapy as more useful (p<0.001). A good clinical outcome was regarded more motivating than a good interventional outcome (p<0.001). Receiving systematic feedback did not increase work satisfaction (p = 0.318) or work meaningfulness (p = 0.178). Radiographers valuated the usefulness of interventional therapy the worst of all employees (p≤ 0.017). After the feedback period, 75% of radiographers estimated stroke as a more severe disease than before. Also, their desire for feedback decreased significantly (p = 0.007). Primarily patient cases with unfavorable outcomes were remembered by the staff. Conclusions Systematic email feedback does not per se enhance work satisfaction or work meaningfulness among employees. However, receiving feedback is educative for the staff. Evaluating work satisfaction and the perception of treatment may help to identify unexpected issues and may therefore help to find specific measures that increase work satisfaction and motivation.

No abstract