Automatic Smoke Classification in Endoscopic Video

Author(s):  
Andreas Leibetseder ◽  
Manfred Jürgen Primus ◽  
Klaus Schoeffmann
Keyword(s):  
2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Matthias Ivantsits ◽  
Lennart Tautz ◽  
Simon Sündermann ◽  
Isaac Wamala ◽  
Jörg Kempfert ◽  
...  

AbstractMinimally invasive surgery is increasingly utilized for mitral valve repair and replacement. The intervention is performed with an endoscopic field of view on the arrested heart. Extracting the necessary information from the live endoscopic video stream is challenging due to the moving camera position, the high variability of defects, and occlusion of structures by instruments. During such minimally invasive interventions there is no time to segment regions of interest manually. We propose a real-time-capable deep-learning-based approach to detect and segment the relevant anatomical structures and instruments. For the universal deployment of the proposed solution, we evaluate them on pixel accuracy as well as distance measurements of the detected contours. The U-Net, Google’s DeepLab v3, and the Obelisk-Net models are cross-validated, with DeepLab showing superior results in pixel accuracy and distance measurements.


Author(s):  
André R. de Geus ◽  
Marcos A. Batista ◽  
Marcos N. Rabelo ◽  
Celia Z. Barcelos ◽  
Sérgio F. da Silva

2009 ◽  
Author(s):  
Daniel Mirota ◽  
Russell H. Taylor ◽  
Masaru Ishii ◽  
Gregory D. Hager

2003 ◽  
Vol 7 (3) ◽  
pp. 141-152 ◽  
Author(s):  
S.A. Karkanis ◽  
D.K. Iakovidis ◽  
D.E. Maroulis ◽  
D.A. Karras ◽  
M. Tzivras

Author(s):  
N. C. van Dongen ◽  
F. van der Sommen ◽  
S. Zinger ◽  
E. J. Sekoon ◽  
P. H. N. de With

1998 ◽  
Vol 44 (3) ◽  
pp. 49-53 ◽  
Author(s):  
P. S. Vetshev ◽  
L. I. Ippolitov ◽  
D. I. Gabaidze

The widespread use of endoscopic surgery over the past 10 years is primarily associated with scientific and technological progress, the improvement of endoscopic video equipment, special tools necessary for ultra-precise operating techniques. Some laparoscopic surgeries have already been recognized by experts and are the method of choice in the treatment of a large number of patients, others are still at the stage of clinical trials and a set of sufficient observations to generalize [2, 10, 47].


Author(s):  
Rana F. Al Muslem ◽  
Mohammad R. Al Eid ◽  
Hussain A. Al Baharna

<p class="abstract"><strong>Background:</strong> Septoplasty is a common procedure in the field of otolaryngology for treatment of septal deviations. Intranasal splints and trans-septal quilting suture are commonly utilized to prevent post-operative complications. The silicone splint is a quick and simple technique to aid in cartilage support; however, it can cause discomfort. Trans-septal quilting suture is more available, well-tolerated and can help in mucosal tear closure, though is time-consuming. This study aimed to compare the efficacy of intranasal silicone splints versus quilting suture in the prevention of post endoscopic septoplasty complications.</p><p class="abstract"><strong>Methods:</strong> This was a retrospective COHORT study comprised of patients who underwent endoscopic septoplasty between January 2017 and December 2019 at Qatif central hospital. The patients were assigned into two groups: group S, who received intranasal splints and group Q, who received trans-septal quilting suturing. Patients’ medical records were reviewed for evaluation of post-operative visits and post-operative nasal endoscopic video recordings from the image archive software were evaluated to document complications. Statistical analysis was conducted using SPSS 23.0 software.</p><p class="abstract"><strong>Results:</strong> The study included 65 patients, of whom 41 were in group S and 24 were in group Q. None of the patients had major bleeding, local infection or mucosal synechia. There was a higher complication rate in terms of mucosal crustation, septal hematoma and perforation among group S; however, the difference was not statistically significant.</p><p class="abstract"><strong>Conclusions:</strong> We conclude that trans-septal quilting suture and intranasal silicone splints are both equally effective in preventing complications following septoplasty.</p>


Gut ◽  
2017 ◽  
Vol 68 (1) ◽  
pp. 94-100 ◽  
Author(s):  
Michael F Byrne ◽  
Nicolas Chapados ◽  
Florian Soudan ◽  
Clemens Oertel ◽  
Milagros Linares Pérez ◽  
...  

BackgroundIn general, academic but not community endoscopists have demonstrated adequate endoscopic differentiation accuracy to make the ‘resect and discard’ paradigm for diminutive colorectal polyps workable. Computer analysis of video could potentially eliminate the obstacle of interobserver variability in endoscopic polyp interpretation and enable widespread acceptance of ‘resect and discard’.Study design and methodsWe developed an artificial intelligence (AI) model for real-time assessment of endoscopic video images of colorectal polyps. A deep convolutional neural network model was used. Only narrow band imaging video frames were used, split equally between relevant multiclasses. Unaltered videos from routine exams not specifically designed or adapted for AI classification were used to train and validate the model. The model was tested on a separate series of 125 videos of consecutively encountered diminutive polyps that were proven to be adenomas or hyperplastic polyps.ResultsThe AI model works with a confidence mechanism and did not generate sufficient confidence to predict the histology of 19 polyps in the test set, representing 15% of the polyps. For the remaining 106 diminutive polyps, the accuracy of the model was 94% (95% CI 86% to 97%), the sensitivity for identification of adenomas was 98% (95% CI 92% to 100%), specificity was 83% (95% CI 67% to 93%), negative predictive value 97% and positive predictive value 90%.ConclusionsAn AI model trained on endoscopic video can differentiate diminutive adenomas from hyperplastic polyps with high accuracy. Additional study of this programme in a live patient clinical trial setting to address resect and discard is planned.


Sign in / Sign up

Export Citation Format

Share Document