Cervical spine fracture detection in computed tomography using convolutional neural networks.

Objective.In the context of primary in-hospital trauma management timely reading of computed tomography (CT) images is critical. However, assessment of the spine is time consuming, fractures can be very subtle, and the potential for under-diagnosis or delayed diagnosis is relevant. Artificial intelligence is increasingly employed to assist radiologists with the detection of spinal fractures and prioritization of cases. Currently, algorithms focusing on the cervical spine are commercially available. A common approach is the vertebra-wise classification. Instead of a classification task, we formulate fracture detection as a segmentation task aiming to find and display all individual fracture locations presented in the image.Approach.Based on 195 CT examinations, 454 cervical spine fractures were identified and annotated by radiologists at a tertiary trauma center. We trained for the detection a U-Net via four-fold-cross validation to segment spine fractures and the spine via a multi-task loss. We further compared advantages of two image reformation approaches-straightened curved planar reformatted (CPR) around the spine and spinal canal aligned volumes of interest (VOI)-to achieve a unified vertebral alignment in comparison to processing the Cartesian data directly.Main results.Of the three data versions (Cartesian, reformatted, VOI) the VOI approach showed the best detection rate and a reduced computation time. The proposed algorithm was able to detect 87.2% of cervical spine fractures at an average number of false positives of 3.5 per case. Evaluation of the method on a public spine dataset resulted in 0.9 false positive detections per cervical spine case.Significance.The display of individual fracture locations as provided with high sensitivity by the proposed voxel classification based fracture detection has the potential to support the trauma CT reading workflow by reducing missed findings.

Insertional depth-dependent intracochlear pressure changes in a model of cochlear implantation.

CONCLUSION: Over time, a homogenous increase in intracochlear pressure was seen in every experiment. Significant reductions in terms of amplitude variation and insertion depth were observed over time, using the one-point-supported insertion method. The frequency of peaks between the thirds was significantly lower when using the two-points-supported insertion method. OBJECTIVES: The preservation of residual hearing and minimization of intracochlear trauma are two of the major goals in modern cochlear implantation (CI) surgery. It is assumed that intracochlear pressure measurements yield information about the intracochlear behavior of the electrode itself in the cochlea. The aim of this study was to investigate temporal intracochlear fluid pressure changes using two different kinds of insertion conditions. METHOD: Cochlear implantations with the Advanced Bionics IJ® electrode were performed in an artificial cochlear model with a constant insertional speed of 0.5 mm/s provided by a linear actor. Amplitude pressure changes and number of pressure peaks were evaluated for every part. RESULT: Intracochlear fluid pressure changes are assumed to affect the preservation of residual hearing and should be minimized. The stability and reduction of movement of a lateral wall IJ® electrode increase at deeper insertion and affect intracochlear fluid pressure amplitude.

Comparison of the effects of four different cochlear implant electrodes on intra-cochlear pressure in a model.

CONCLUSION: Based on this model experiment, a small tip and low volume electrode show lowest intra-cochlear pressure values. Insertional support by a tool minimizes fast pressure changes. Higher electrodes volumes affect slow and fast pressure changes as well. OBJECTIVE: Insertion causing low intra-cochlear pressure is assumed to be important for atraumatic cochlear implant surgery to preserve residual hearing. Cochlear implant electrodes differ in terms of parameters like tip size, length, volume, and technique of insertion. The aim of this study was to observe the effect of different cochlear implant electrodes on insertional intra-cochlear pressure in a cochlear model. MATERIALS AND METHODS: Cochlear implant electrode insertions were performed in an artificial cochlear model and intra-cochlear pressure changes were recorded in parallel with a micro-pressure sensor positioned in the apical region of the cochlear model to follow the maximum values, temporal changes, maximum amplitude, and frequency of changes in intra-cochlear pressure. Insertions were performed with four different electrodes (Advanced Bionics 1j, Helix, HFMS, and LW23). RESULTS: This study found statistically significant differences in the occurrence of initial maximum pressure values correlating with the electrode tip size. The different electrodes and the technique of insertion significantly affected the occurrence of maximum value, amplitude, and frequency of intra-cochlear pressure occurrence.

Intracochlear Pressure Changes due to 2 Electrode Types: An Artificial Model Experiment.

Objective To preserve residual hearing in cochlear implant surgery, the electrode design has been refined, and an atraumatic insertion has become one aspect of cochlear implant research. Previous studies have described the effect of insertion speed and opening of the round window membrane on intracochlear pressure changes. The aim of our current study was to observe intracochlear pressure changes due to different cochlear implant electrodes in an artificial cochlear model with stable surrounding factors. Study Design Prospective controlled study. Setting Tertiary referral center. Subjects and Methods The experiments were performed in an artificial cochlear model with a pressure sensor in the apical area. With straight and perimodiolar electrode arrays, 5 insertions with the same insertion speed and 5 insertions over the same time were performed. Results With the perimodiolar high-volume electrode, significantly greater intracochlear fluid pressure changes were observed than with the straight electrode. Compared with the straight electrode, the perimodiolar electrode induces significantly higher pressure peaks (1.12 ± 0.15 vs 0.86 ± 0.05 mm Hg, P = .006) and significantly higher amplitudes (0.38 ± 0.07 vs 0.09 ± 0.07 mm Hg, P < .001). Conclusion The reliable preservation of residual hearing is an important multifactorial challenge in modern cochlear implant surgery. Insertion speed, handling, and electrode design are known to influence the preservation of residual hearing. In our artificial model experiments, we could prove objectively that the volume of the electrodes has a significant influence on the intracochlear pressure changes during cochlear implantation.