Unsupervised Learning of Surgical Smoke Removal from Simulation
Authors: Chen, L., Tang, W. and John, W.N.
Conference: The 11th Hamlyn Symposium on Medical Robotics
Dates: 24-27 June 2018
Abstract:The surgical smoke produced during minimally invasive surgery can not only reduce the visibility of the surgeons, but also severally affect the performance of image processing algorithms used for image guided surgery such as image tracking, segmentation, detection and retrieval. Besides from physical smoke evacuation devices, many research works address this issue by using vision-based methods to filter out the smoke and try to recover the clear images. More recently, end-to-end deep learning approaches have been introduced to solve the de-hazing and de-smoking problems. However, it is extremely difficult to collect large amounts of data for the effective learning of the implicit de-smoking function, especially for surgical scenes. In this paper, we propose a computational framework for unsupervised learning of smoke removal from rendering smoke on laparoscopic video. Compared to conventional image processing approaches, our proposed framework is able to remove local smoke and recover more realistic tissue colour but will not affect the areas without smoke. Although trained on synthetic images, the experimental results show that our network is able to effectively remove smoke on laparoscopic images with real surgical smoke.
https://eprints.bournemouth.ac.uk/31189/
Source: Manual
Unsupervised Learning of Surgical Smoke Removal from Simulation
Authors: Chen, L., Tang, W. and John, W.N.
Conference: The 11th Hamlyn Symposium on Medical Robotics
Abstract:The surgical smoke produced during minimally invasive surgery can not only reduce the visibility of the surgeons, but also severally affect the performance of image processing algorithms used for image guided surgery such as image tracking, segmentation, detection and retrieval. Besides from physical smoke evacuation devices, many research works address this issue by using vision-based methods to filter out the smoke and try to recover the clear images. More recently, end-to-end deep learning approaches have been introduced to solve the de-hazing and de-smoking problems. However, it is extremely difficult to collect large amounts of data for the effective learning of the implicit de-smoking function, especially for surgical scenes. In this paper, we propose a computational framework for unsupervised learning of smoke removal from rendering smoke on laparoscopic video. Compared to conventional image processing approaches, our proposed framework is able to remove local smoke and recover more realistic tissue colour but will not affect the areas without smoke. Although trained on synthetic images, the experimental results show that our network is able to effectively remove smoke on laparoscopic images with real surgical smoke.
https://eprints.bournemouth.ac.uk/31189/
http://concepts.m-w.co.uk/viewscreen.aspx?concept_id=10079&project_id=0&screen_id=19180
Source: BURO EPrints