Multiple Device Segmentation for Fluoroscopic Imaging Using Multi-task Learning

Author(s):  
Katharina Breininger ◽  
Tobias Würfl ◽  
Tanja Kurzendorfer ◽  
Shadi Albarqouni ◽  
Marcus Pfister ◽  
...  
2013 ◽  
Author(s):  
Peter S. Schaefer ◽  
Clinton R. Irvin ◽  
Paul N. Blankenbeckler ◽  
C. J. Brogdon
Keyword(s):  

Author(s):  
Van Hai Do ◽  
Nancy F. Chen ◽  
Boon Pang Lim ◽  
Mark Hasegawa-Johnson

2020 ◽  
Author(s):  
Ana Montalvo ◽  
Jose R. Calvo ◽  
Jean-François Bonastre
Keyword(s):  

2020 ◽  
Author(s):  
Wei Xue ◽  
Ying Tong ◽  
Chao Zhang ◽  
Guohong Ding ◽  
Xiaodong He ◽  
...  

Author(s):  
Lucy Clare Maling ◽  
John Martin Lynch ◽  
Robert William Walker ◽  
Mark Ross Norton ◽  
Rory George Middleton

Abstract Purpose Hip hemiarthroplasty (HA) is a commonly performed operation. A post-operative radiograph forms part of the routine hip fracture pathway, although patients are often mobilised prior to this investigation. This study seeks to provide evidence for a pragmatic clinical change to optimise patient safety and allocate limited resources within the National Health Service (NHS). Methods We undertook a retrospective database review of 1563 HA procedures to assess whether the routine ordering of check radiographs played an important role in a patient’s post-operative care. Results 18 (1.2%) mechanical complications led to a return to theatre within 6 weeks of the index procedure. All were dislocations. Ten had a normal post-operative radiograph and five had documented suspicion of dislocation prior to radiography. The post-operative check radiograph was the sole identifier of dislocation in only three patients (0.2%). All three of these patients were pre-morbidly bed bound and non-communicative due to cognitive impairment (AMTS 0/10). Conclusion Unless a patient is pre-morbidly bed bound and cognitively impaired, routine post-operative radiography following HA surgery is of little clinical benefit, yet may carry considerable risk to the patient and cost to the NHS. A pragmatic compromise is to perform intra-operative fluoroscopic imaging.


NeuroImage ◽  
2021 ◽  
pp. 118373
Author(s):  
Joris van der Cruijsen ◽  
Mana Manoochehri ◽  
Zeb D. Jonker ◽  
Eleni-Rosalina Andrinopoulou ◽  
Maarten A. Frens ◽  
...  
Keyword(s):  

2021 ◽  
pp. 216770262095934
Author(s):  
Julia M. Sheffield ◽  
Holger Mohr ◽  
Hannes Ruge ◽  
Deanna M. Barch

Rapid instructed task learning (RITL) is the uniquely human ability to transform task information into goal-directed behavior without relying on trial-and-error learning. RITL is a core cognitive process supported by functional brain networks. In patients with schizophrenia, RITL ability is impaired, but the role of functional network connectivity in these RITL deficits is unknown. We investigated task-based connectivity of eight a priori network pairs in participants with schizophrenia ( n = 29) and control participants ( n = 31) during the performance of an RITL task. Multivariate pattern analysis was used to determine which network connectivity patterns predicted diagnostic group. Of all network pairs, only the connectivity between the cingulo-opercular network (CON) and salience network (SAN) during learning classified patients and control participants with significant accuracy (80%). CON-SAN connectivity during learning was significantly associated with task performance in participants with schizophrenia. These findings suggest that impaired interactions between identification of salient stimuli and maintenance of task goals contributes to RITL deficits in participants with schizophrenia.


Sign in / Sign up

Export Citation Format

Share Document