Augmented Reality-Assisted Neurosurgical Drain Placement (ARANED): Technical Note.

BACKGROUND: Many surgical procedures, such as placement of intracranial drains, are currently being performed blindly, relying on anatomical landmarks. As a result, accuracy results still have room for improvement. Neuronavigation could address this issue, but its application in an urgent setting is often impractical. Augmented reality (AR) provided through a head-worn device has the potential to tackle this problem, but its implementation should meet physicians' needs. METHODS: The Surgical Augmented Reality Assistance (SARA) project aims to develop an AR solution that is suitable for preoperative planning, intraoperative visualisation and navigational support in an everyday clinical setting, using a Microsoft HoloLens. RESULTS: Proprietary hardware and software adaptations and dedicated navigation algorithms are applied to the Microsoft HoloLens to optimise it specifically for neurosurgical navigation. This includes a pipeline with an additional set of advanced, semi-automated algorithms responsible for image processing, hologram-to-patient registration and intraoperative tracking using infrared depth-sensing. A smooth and efficient workflow while maintaining high accuracy is prioritised. The AR solution provides a fully integrated and completely mobile navigation setup. Initial preclinical and clinical validation tests applying the solution to intracranial drain placement are described. CONCLUSION: AR has the potential to vastly increase accuracy of everyday procedures that are frequently performed without image guidance, but could still benefit from navigational support, such as intracranial drain placements. Technical development should go hand in hand with preclinical and clinical validation in order to demonstrate improvements in accuracy and clinical outcomes.

Automated Segmentation of Colorectal Tumor in 3D MRI Using 3D Multiscale Densely Connected Convolutional Neural Network.

The main goal of this work is to automatically segment colorectal tumors in 3D T2-weighted (T2w) MRI with reasonable accuracy. For such a purpose, a novel deep learning-based algorithm suited for volumetric colorectal tumor segmentation is proposed. The proposed CNN architecture, based on densely connected neural network, contains multiscale dense interconnectivity between layers of fine and coarse scales, thus leveraging multiscale contextual information in the network to get better flow of information throughout the network. Additionally, the 3D level-set algorithm was incorporated as a postprocessing task to refine contours of the network predicted segmentation. The method was assessed on T2-weighted 3D MRI of 43 patients diagnosed with locally advanced colorectal tumor (cT3/T4). Cross validation was performed in 100 rounds by partitioning the dataset into 30 volumes for training and 13 for testing. Three performance metrics were computed to assess the similarity between predicted segmentation and the ground truth (i.e., manual segmentation by an expert radiologist/oncologist), including Dice similarity coefficient (DSC), recall rate (RR), and average surface distance (ASD). The above performance metrics were computed in terms of mean and standard deviation (mean ± standard deviation). The DSC, RR, and ASD were 0.8406 ± 0.0191, 0.8513 ± 0.0201, and 2.6407 ± 2.7975 before postprocessing, and these performance metrics became 0.8585 ± 0.0184, 0.8719 ± 0.0195, and 2.5401 ± 2.402 after postprocessing, respectively. We compared our proposed method to other existing volumetric medical image segmentation baseline methods (particularly 3D U-net and DenseVoxNet) in our segmentation tasks. The experimental results reveal that the proposed method has achieved better performance in colorectal tumor segmentation in volumetric MRI than the other baseline techniques.

Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix Factorization.

The main goal of this work was to assess the performance of different initializations of matrix factorization algorithms for an accurate identification of muscle synergies. Currently, nonnegative matrix factorization (NNMF) is the most commonly used method to identify muscle synergies. However, it has been shown that NNMF performance might be affected by different kinds of initialization. The present study aims at optimizing the traditional NNMF initialization for data with partial or complete temporal dependencies. For this purpose, three different initializations are used: random, SVD-based, and sparse. NNMF was used to identify muscle synergies from simulated data as well as from experimental surface EMG signals. Simulated data were generated from synthetic independent and dependent synergy vectors (i.e., shared muscle components), whose activation coefficients were corrupted by simulating controlled degrees of correlation. Similarly, EMG data were artificially modified, making the extracted activation coefficients temporally dependent. By measuring the quality of identification of the original synergies underlying the data, it was possible to compare the performance of different initialization techniques. Simulation results demonstrate that sparse initialization performs significantly better than all other kinds of initialization in reconstructing muscle synergies, regardless of the correlation level in the data.