Search

Surgical smoke removal algorithms can improve the quality of intra-operative imaging and reduce hazards in image-guided surgery, a highly desirable post-process for many clinical applications. These algorithms also enable effective computer vision tasks for future robotic surgery. In this article, we present a new unsupervised learning framework for high-quality pixel-wise smoke detection and removal. One of the well recognized grand challenges in using convolutional neural networks (CNNs) for medical image processing is to obtain intra-operative medical imaging datasets for network training and validation, but availability and quality of these datasets are scarce. Our novel training framework does not require ground-truth image pairs. Instead, it learns purely from computer-generated simulation images. This approach opens up new avenues and bridges a substantial gap between conventional non-learning based methods and which requiring prior knowledge gained from extensive training datasets. Inspired by the Generative Adversarial Network (GAN), we have developed a novel generative-collaborative learning scheme that decomposes the de-smoke process into two separate tasks: smoke detection and smoke removal. The detection network is used as prior knowledge, and also as a loss function to maximize its support for training of the smoke removal network. Quantitative and qualitative studies show that the proposed training framework outperforms the state-of-the-art de-smoking approaches including the latest GAN framework (such as PIX2PIX). Although trained on synthetic images, experimental results on clinical images have proved the effectiveness of the proposed network for detecting and removing surgical smoke on both simulated and real-world laparoscopic images.

Navigating a powered wheelchair and avoiding collisions is often a daunting task for new wheelchair users. It takes time and practice to gain the coordination needed to become a competent driver and this can be even more of a challenge for someone with a disability. We present a cost-effective virtual reality (VR) application that takes advantage of consumer level VR hardware. The system can be easily deployed in an assessment centre or for home use, and does not depend on a specialized high-end virtual environment such as a Powerwall or CAVE. This paper reviews previous work that has used virtual environments technology for training tasks, particularly wheelchair simulation. We then describe the implementation of our own system and the first validation study carried out using thirty three able bodied volunteers. The study results indicate that at a significance level of 5 percent then there is an improvement in driving skills from the use of our VR system. We thus have the potential to develop the competency of a wheelchair user whilst avoiding the risks inherent to training in the real world. However, the occurrence of cybersickness is a particular problem in this application that will need to be addressed.

Applications of virtual reality (VR) and augmented reality (AR) in medicine require real-time visualization and modeling of large three-dimensional data sets. Consequently, these applications require powerful computation, extensive high-bandwidth memory, and fast communication links. In the past, the manufacturers of medical imaging equipment produced their own special-purpose proprietary hardware for image processing and solid graphics. Due to the developments in computer hardware in general and in graphics accelerators in particular, there is a trend toward replacing the proprietary hardware off-the-shelf (OTS) equipment. Computer graphics itself has advanced in its quest for realism. Generic algorithms such as shading, texture mapping, and volume rendering have been developed to meet the resultant ever increasing requirements. Advances in both the OTS CPU and graphics hardware have enabled real-time implementations of these algorithms, thereby facilitating many of the medical VR/AR applications used today. The development of graphics libraries such as OpenGL has also been an important factor. These libraries provide an underlying portable software platform that optimizes the utilization of the available graphics hardware. OpenGL has become a standard graphics application programming interface, particularly for graphics-intensive applications, and more and more OTS systems provide hardware implementations of OpenGL commands. The review paper follows the evolution of these technologies and examines their crucial role in enabling the appearance of the current VR/AR applications in medicine and provides a look at current trends and future possibilities.

jgViz uses standard grid technologies and Chromium cluster graphics software to schedule the best available distributed graphics pipeline. Visualization of large data sets using computer graphics techniques has become a mainstream requirement for many scientists and engineers. However, achieving interactive performance when rendering a complex visualization often requires high-performance computing facilities. One solution is to exploit real-time graphics accelerators, which are used in the full range of computing devices from games consoles and set-top boxes to supercomputers and advanced training simulators. At the same time, the service infrastructure for distributed networks has produced the third generation of the connected world: the grid. jgViz, our Java-implemented grid visualization system, uses grid functionality to enable transparent access to reliable parallel graphics pipelines. Lightweight and highly portable, jgViz aims to be plug-and-play for the existing grid resource allocation mechanism