Arthroscopically Assisted Treatment of Volar Rim Fractures

Background Arthroscopically-assisted reduction and internal fixation (AARIF) for distal radius fractures (DRF) has been extensively described. Little information is available about AARIF in AO “B3” and “C” DRF with displaced lunate facet volar rim fragment (VRF) and volar carpal subluxation. However, lunate volar rim fragment (LVRF) may be very difficult to reduce and fix under arthroscopic control using the flexor carpi radialis (FCR) or FCR extended approaches while traction is applied. Purposes The aims were to describe our surgical technique of AARIF of partial or complete DRF with VRF and provide information about how often this technique may be necessary, based on a large DRF database. Methods The dual-window volar approach for complete articular AO C DRF with volar medial fragment was described in 2012 for performing open reduction internal fixation (ORIF). Since 2015, we have used the dual-window approach for AARIF of “B3” or “C” DRF with volar carpal subluxation. We analyzed our PAF database, searching for patients treated with AARIF in “B3” and “C” fractures. Results The dual-window volar approach is very useful when using AARIF for AO “B3” and “C” DRF with displaced VRF and volar carpal subluxation. The anteromedial part of the exposure allows a direct access to reduction and fixation of the LVRF under traction and arthroscopic control. Overall, 1% of all articular DRF in this series showed a displaced LVRF amenable to the dual-window volar approach. Conclusion It is almost impossible to access and properly fix a VRF using traction and arthroscopic control through the FCR or FCR extended FCR approach because of the stretched flexor tendon mass. The use of the dual-window approach during AARIF of AO “B3” or “C” DRF has not previously been reported. Displaced VRF are rare whether they were part of “B3” or “C” fractures. If AARIF is chosen, we strongly recommend the use of the dual-window volar approach for AO “B3” and “C” fractures with VRF. A single anteromedial approach can also be used for isolated “B3” anteromedial DRF.

DWNet: Dual-Window Deep Neural Network for Time Series Prediction

Multivariate time series prediction is a very important task, which plays a huge role in climate, economy, and other fields. We usually use an Attention-based Encoder-Decoder network to deal with multivariate time series prediction because the attention mechanism makes it easier for the model to focus on the really important attributes. However, the Encoder-Decoder network has the problem that the longer the length of the sequence is, the worse the prediction accuracy is, which means that the Encoder-Decoder network cannot process long series and therefore cannot obtain detailed historical information. In this paper, we propose a dual-window deep neural network (DWNet) to predict time series. The dual-window mechanism allows the model to mine multigranularity dependencies of time series, such as local information obtained from a short sequence and global information obtained from a long sequence. Our model outperforms nine baseline methods in four different datasets.

A Spectrum Correction Algorithm Based on Beat Signal of FMCW Laser Ranging System

The accuracy of target distance obtained by a frequency modulated continuous wave (FMCW) laser ranging system is often affected by factors such as white Gaussian noise (WGN), spectrum leakage, and the picket fence effect. There are some traditional spectrum correction algorithms to solve the problem above, but the results are unsatisfactory. In this article, a decomposition filtering-based dual-window correction (DFBDWC) algorithm is proposed to alleviate the problem caused by these factors. This algorithm reduces the influence of these factors by utilizing a decomposition filtering, dual-window in time domain and two phase values of spectral peak in the frequency domain, respectively. With the comparison of DFBDWC and these traditional algorithms in simulation and experiment on a built platform, the results show a superior performance of DFBDWC based on this platform. The maximum absolute error of target distance calculated by this algorithm is reduced from 0.7937 m of discrete Fourier transform (DFT) algorithm to 0.0407 m, which is the best among all mentioned spectrum correction algorithms. A high performance FMCW laser ranging system can be realized with the proposed algorithm, which has attractive potential in a wide scope of applications.

Single Incision, Dual Window Approach for a Comminuted Distal Radius Fracture

Introduction Complex distal radius fractures often involve a fragment of the volar-ulnar articular surface and the radial styloid. The volar ulnar corner of the distal radius is an important constraint to volar translation of the carpus and thus requires stable fixation to prevent wrist displacement. The traditional volar Henry approach often requires undue tension on the median nerve while retracting for access to the ulnar aspect of the radius. To protect the median nerve from iatrogenic injury and to improve exposure of the surgical site, we propose a single incision, dual window approach to the distal radius for complex bi-columnar fractures. Methods This technique combines the trans-Flexor Carpi Radialis (FCR) approach with a subcutaneous dissection to the ulnar aspect of the wrist. This window utilizes the interval between the ulnar neurovascular bundle and the carpal tunnel contents. Results This technique allows the surgeon to work through either window and thus visualize and directly fixate the various fracture fragments. We have treated complex articular distal radius fractures associated with ulnar communition with this novel technique and it has provided direct reduction with improved fragment access. The surgical technique, a case presentation and results are detailed in this report. Conclusion This case report has demonstrated that complex bi-columnar fractures of the distal radius can be effectively approached and fixated with a single incision dual window approach.

Dual-Window Superpixel Data Augmentation for Hyperspectral Image Classification

Deep learning (DL) has been shown to obtain superior results for classification tasks in the field of remote sensing hyperspectral imaging. Superpixel-based techniques can be applied to DL, significantly decreasing training and prediction times, but the results are usually far from satisfactory due to overfitting. Data augmentation techniques alleviate the problem by synthetically generating new samples from an existing dataset in order to improve the generalization capabilities of the classification model. In this paper we propose a novel data augmentation framework in the context of superpixel-based DL called dual-window superpixel (DWS). With DWS, data augmentation is performed over patches centered on the superpixels obtained by the application of simple linear iterative clustering (SLIC) superpixel segmentation. DWS is based on dividing the input patches extracted from the superpixels into two regions and independently applying transformations over them. As a result, four different data augmentation techniques are proposed that can be applied to a superpixel-based CNN classification scheme. An extensive comparison in terms of classification accuracy with other data augmentation techniques from the literature using two datasets is also shown. One of the datasets consists of small hyperspectral small scenes commonly found in the literature. The other consists of large multispectral vegetation scenes of river basins. The experimental results show that the proposed approach increases the overall classification accuracy for the selected datasets. In particular, two of the data augmentation techniques introduced, namely, dual-flip and dual-rotate, obtained the best results.