Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2009
Ultrasound guided robotic biopsy using augmented reality and human-robot cooperative control.
Ultrasound-guided biopsy is a proficient mininvasive approach for tumors staging but requires very long training and particular manual and 3D space perception abilities of the physician, for the planning of the needle trajectory and the execution of the procedure. In order to simplify this difficult task, we have developed an integrated system that provides the clinician two types of assistance: an augmented reality visualization allows accurate and easy planning of needle trajectory and target reaching verification; a robot arm with a six-degree-of-freedom force sensor allows the precise positioning of the needle holder and allows the clinician to adjust the planned trajectory (cooperative control) to overcome needle deflection and target motion. Preliminary tests have been executed on an ultrasound phantom showing high precision of the system in static conditions and the utility and usability of the cooperative control in simulated no-rigid conditions.
-
MR guidance of high intensity focused ultrasound is evolving with each new application. In this paper we describe ongoing research in the MR-guidance aspect of MR-guided focused ultrasound. The structure is divided into the pretreatment/setup phase of the procedure, MR thermometry for monitoring the actual treatment, and methods for assessment and follow-up.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2009
System to improve AED resuscitation using interactive CPR coaching.
A positive impact on cardiac arrest survival has been demonstrated with the substantial reduction in time to defibrillation provided by the widespread deployment of automated external defibrillators (AEDs). However, recent studies have identified the importance of performing chest compressions before defibrillation in facilitating effective recovery from long duration ventricular fibrillation (VF). Despite the importance of cardiopulmonary resuscitation (CPR), effective performance of it in the field is hampered by many problems including the dependence on rescuer technique, which is known to be variable even with trained professionals. ⋯ In general using any type of coaching provided improvements in all of the CPR performance measures excluding chest recoil where there was a slight decrease in performance. The statistical results also indicated that the audio/visual coaching conditions provided a more effective coaching condition with respect to chest compression rate. Most notably, the feedback conditions both provided a statistically significant or trends toward improving chest compression effectiveness and produced superior performance as a whole.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2009
Optimizing cardiac resuscitation outcomes using wavelet analysis.
Ventricular fibrillation (VF) is the most lethal of cardiac arrhythmias that leads to sudden cardiac death if untreated within minutes of its occurrence. Defibrillation using electric shock resets the heart to return to spontaneous circulation (ROSC) state, however the success of which depends on various factors such as the viability of myocardium and the time lag between the onset of VF to defibrillation. Recent studies have reported that performing cardio pulmonary resuscitation (CPR) procedure prior to applying shock increases the survival rate especially when VF is untreated for more than 5 minutes. ⋯ Existing works in the literature have demonstrated correlation between the characteristics of the VF waveform and the outcome (ROSC) of the defibrillation. The proposed work improves on this by attempting to arrive at a near real-time monitoring tool in aiding the EMS staff. Using data collected from 16 pigs during VF, the proposed wavelet methodology achieved an overall accuracy of 94% in successfully predicting the shock outcomes.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2009
Data mining of patients on weaning trials from mechanical ventilation using cluster analysis and neural networks.
The process of weaning from mechanical ventilation is one of the challenges in intensive care. 149 patients under extubation process (T-tube test) were studied: 88 patients with successful trials (group S), 38 patients who failed to maintain spontaneous breathing and were reconnected (group F), and 23 patients with successful test but that had to be reintubated before 48 hours (group R). Each patient was characterized using 8 time series and 6 statistics extracted from respiratory and cardiac signals. A moving window statistical analysis was applied obtaining for each patient a sequence of patterns of 48 features. ⋯ Neural networks were applied to discriminate between patients from groups S, F and R. The best performance obtained was 84.0% of well classified patients using a linear perceptron trained with a feature selection procedure (that selected 19 of the 48 features) and taking as input the main cluster centroid. However, the classification baseline 69.8% could not be improved when using the original set of patterns instead of the centroids to classify the patients.