scholarly journals Toward real-time endoscopically-guided robotic navigation based on a 3D virtual surgical field model

2015 ◽  
Author(s):  
Yuanzheng Gong ◽  
Danying Hu ◽  
Blake Hannaford ◽  
Eric J. Seibel
Keyword(s):  
Real Time ◽  
Field Model ◽  
Robotic Navigation ◽  
Surgical Field

scholarly journals Development of detection method for automatic hemostasis using machine learning with abdominal cavity irrigation

2020 ◽  
Vol 7 (7) ◽  
pp. 2103
Author(s):  
Yoshihisa Matsunaga ◽  
Ryoichi Nakamura
Keyword(s):  
Machine Learning ◽  
Minimally Invasive Surgery ◽  
Minimally Invasive ◽  
Real Time ◽  
Invasive Surgery ◽  
Abdominal Cavity ◽  
Training Dataset ◽  
Support Vector ◽  
Processing Cost ◽  
Surgical Field

Background: Abdominal cavity irrigation is a more minimally invasive surgery than that using a gas. Minimally invasive surgery improves the quality of life of patients; however, it demands higher skills from the doctors. Therefore, the study aimed to reduce the burden by assisting and automating the hemostatic procedure a highly frequent procedure by taking advantage of the clearness of the endoscopic images and continuous bleeding point observations in the liquid. We aimed to construct a method for detecting organs, bleeding sites, and hemostasis regions.Methods: We developed a method to perform real-time detection based on machine learning using laparoscopic videos. Our training dataset was prepared from three experiments in pigs. Linear support vector machine was applied using new color feature descriptors. In the verification of the accuracy of the classifier, we performed five-part cross-validation. Classification processing time was measured to verify the real-time property. Furthermore, we visualized the time series class change of the surgical field during the hemostatic procedure.Results: The accuracy of our classifier was 98.3% and the processing cost to perform real-time was enough. Furthermore, it was conceivable to quantitatively indicate the completion of the hemostatic procedure based on the changes in the bleeding region by ablation and the hemostasis regions by tissue coagulation.Conclusions: The organs, bleeding sites, and hemostasis regions classification was useful for assisting and automating the hemostatic procedure in the liquid. Our method can be adapted to more hemostatic procedures. 

Image-guided near-infrared fluorescent sentinel lymph node mapping in human breast cancer

2009 ◽  
Vol 27 (15_suppl) ◽  
pp. e11591-e11591
Author(s):  
S. Troyan ◽  
S. Gibbs-Strauss ◽  
S. Gioux ◽  
R. Oketokoun ◽  
F. Azar ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Optical Imaging ◽  
Real Time ◽  
Near Infrared ◽  
Imaging System ◽  
Sulfur Colloid ◽  
Guided Surgery ◽  
Image Guided ◽  
Nir Fluorescence ◽  
Surgical Field

e11591 Background: Breast cancer surgery is presently performed without real-time image-guidance. We have developed a novel optical imaging system for image-guided surgery that uses invisible near-infrared (NIR) fluorescent light to highlight structures on the surgical field with high sensitivity, specificity, and contrast. We have also performed the first human clinical trial of the imaging system in women undergoing SLN mapping for breast cancer. Methods: We used a portable imaging system with an articulating arm that has 6 degrees of freedom, high power LED light source, custom optics, custom software, and sterile drape. The imaging system provided simultaneous and real-time imaging of color video and NIR fluorescence at up to 15 frames per second. N = 6 women with biopsy- confirmed breast cancer undergoing SLN mapping gave informed consent. All subjects received conventional mapping with Tc-99m sulfur colloid using a handheld gamma probe as well as NIR fluorescence-guided SLN mapping using a mixture of indocyanine green (ICG) diluted to a final concentration of 10 μM in human serum albumin (ICG:HSA). Results: The imaging system was easy to position in the operating room, with the articulating arm providing 50” horizontal reach and 70” vertical reach. Working distance to the patient was 18”. NIR fluorescence excitation was 20 mW/cm2 at 760 nm. NIR-depleted white light was 40,000 lux. A total of 1.6 ml of ICG:HSA was injected intra-tumorally and peri-tumorally and the site massaged for 5 min. 8 of 9 SLNs identified by Tc- 99m sulfur colloid were also identified by NIR fluorescence. However, NIR fluorescence identified an SLN, confirmed to have cancer in it, that was not identified by Tc-99m sulfur colloid. These differences were consistent with asynchrony in the injection techniques. Unlike the gamma-ray probe, NIR fluorescence provided high-resolution, large area optical imaging of the surgical field, and helped guide surgical resection. Conclusions: In this 6-patient pilot study, a novel NIR fluorescence optical imaging system was used for the first time, and provided real-time image-guided surgery for SLN mapping of breast cancer. No significant financial relationships to disclose.

Engineering Three-Dimensional Digital Modeling Technology Based on the OGRE Graphics Engine

2012 ◽  
Vol 263-266 ◽  
pp. 1407-1413
Author(s):  
Lu Shuang Wei ◽  
Ying Wang
Keyword(s):  
Real Time ◽  
Data Model ◽  
Field Model ◽  
Three Dimensional ◽  
Time Model ◽  
Modeling Technology ◽  
Time Simulation ◽  
Digital Modeling ◽  
Graphic Construction ◽  
Graphics Engine

In order to solve the problem that the engineering three-dimensional data field model in the virtual reality environment cannot be modified in real time and cannot carry out dynamic simulation, this paper proposes the skeleton grid modeling technology and establishes an engineering three-dimensional data model based on the OGRE graphics engine, which achieves a data-driven dynamic three-dimensional graphic construction. The technology has the ability to modify the real-time model grid geometry and topological characteristics, and provides the possibility of real-time simulation for large projects.

scholarly journals Recognition and Location Estimation for Multiple Indoor Static Objects

2019 ◽  
Vol 8 (2) ◽  
pp. 5152-5156
Keyword(s):  
Support Vector Machine ◽  
Real Time ◽  
Visually Impaired ◽  
Location Estimation ◽  
Support Vector ◽  
Robotic Navigation ◽  
Image Objects ◽  
Sift Features ◽  
Adaboost Classifier ◽  
Visually Impaired Persons

Locating objects in an image is a very useful task for robotic navigation and visually impaired persons. The ultimate goal of my work is to position the recognized objects in the image. Objects are detected using Adaboost techniques and also recognized from the real-time images. Objects are detected using AdaBoost classifier. SIFT features are extracted from the objects found in the image and classified using Support Vector Machine, and the position of an objects are estimated. We proposed IOLE algorithm to estimate the location of object in an image

scholarly journals Modern intraoperative imaging modalities for the vascular neurosurgeon treating intracerebral hemorrhage

2013 ◽  
Vol 34 (5) ◽  
pp. E2 ◽  
Author(s):  
Oded Goren ◽  
Stephen J. Monteith ◽  
Moshe Hadani ◽  
Mati Bakon ◽  
Sagi Harnof
Keyword(s):  
Intracerebral Hemorrhage ◽  
Real Time ◽  
Intraoperative Imaging ◽  
Imaging Modalities ◽  
Reliable Technique ◽  
Hematoma Evacuation ◽  
Image Guided ◽  
Surgical Field ◽  
Real Time Information ◽  
Time Information

This paper reviews the current intraoperative imaging tools that are available to assist neurosurgeons in the treatment of intracerebral hemorrhage (ICH). This review shares the authors' experience with each modality and discusses the advantages, potential limitations, and disadvantages of each. Surgery for ICH is directed at blood clot removal, reduction of intracranial pressure, and minimization of secondary damage associated with hematoma breakdown products. For effective occlusion and safe obliteration of vascular anomalies associated with ICH, vascular neurosurgeons today require a thorough understanding of the various intraoperative imaging modalities available for obtaining real-time information. Use of one or more of these modalities may improve the surgeon's confidence during the procedure, the patient's safety during surgery, and surgical outcome. The modern techniques discussed include 1) indocyanine green–based video angiography, which provides real-time information based on high-quality images showing the residual filling of vascular pathological entities and the patency of blood vessels of any size in the surgical field; and 2) intraoperative angiography, which remains the gold standard intraoperative diagnostic test in the surgical management of cerebral aneurysms and arteriovenous malformations. Hybrid procedures, providing multimodality image-guided surgeries and combining endovascular with microsurgical strategies within the same surgical session, have become feasible and safe. Microdoppler is a safe, noninvasive, and reliable technique for evaluation of hemodynamics of vessels in the surgical field, with the advantage of ease of use. Intraoperative MRI provides an effective navigation tool for cavernoma surgery, in addition to assessing the extent of resection during the procedure. Intraoperative CT scanning has the advantage of very high sensitivity to acute bleeding, thereby assisting in the confirmation of the extent of hematoma evacuation and the extent of vascular anomaly resection. Intraoperative ultrasound aids navigation and evacuation assessment during intracerebral hematoma evacuation surgeries. It supports the concept of minimally invasive surgery and has undergone extensive development in recent years, with the quality of ultrasound imaging having improved considerably. Image-guided therapy, combined with modern intraoperative imaging modalities, has changed the fundamentals of conventional vascular neurosurgery by presenting real-time visualization of both normal tissue and pathological entities. These imaging techniques are important adjuncts to the surgeon's standard surgical armamentarium. Familiarity with these imaging modalities may help the surgeon complete procedures with improved safety, efficiency, and clinical outcome.

GPU-based implementation of a diagnostic wind field model used in real-time prediction of atmospheric dispersion of radionuclides

2017 ◽  
Vol 100 ◽  
pp. 146-163 ◽  
Author(s):  
Andre Pinheiro ◽  
Filipe Desterro ◽  
Marcelo C. Santos ◽  
Claudio M.N.A. Pereira ◽  
Roberto Schirru
Keyword(s):  
Real Time ◽  
Wind Field ◽  
Field Model ◽  
Atmospheric Dispersion ◽  
Wind Field Model ◽  
Time Prediction

scholarly journals Avoidance of ischemic complications after resection of a brain lesion based on intraoperative real-time recognition of the vasculature using laser speckle flow imaging

2017 ◽  
Vol 126 (1) ◽  
pp. 274-280 ◽  
Author(s):  
Makoto Ideguchi ◽  
Koji Kajiwara ◽  
Koichi Yoshikawa ◽  
Hisaharu Goto ◽  
Kazutaka Sugimoto ◽  
...  
Keyword(s):  
Arteriovenous Malformation ◽  
Real Time ◽  
Regions Of Interest ◽  
Laser Speckle ◽  
Mass Lesion ◽  
Flow Imaging ◽  
Surrounding Area ◽  
Spatiotemporal Resolution ◽  
Ischemic Complications ◽  
Surgical Field

OBJECTIVE To avoid ischemic complications, it is important to consider the arteries in resection planning for lesions such as a vascular intraparenchymal tumor and arteriovenous malformation. Here, the clinical application of laser speckle flow imaging (LSFI) as a complementary method for the management of mass lesion–related arteries during surgery was evaluated. METHODS LSFI was performed in 12 patients with mass lesion–related arteries and brain tumor or arteriovenous malformation. The portable LSFI device was centered over the surgical field, and the relative cerebral blood flow (CBF) before and after the temporary interruption of the arteries was measured through continuous recording. CBF fluctuations permitted the classification of 3 kinds of artery—a feeding artery (FA), a “passing through” artery (PA), and a combined FA and PA (FA+PA)—based on decreased relative CBF in the inner resection area and unchanged CBF in the surrounding area (FA), unchanged CBF in the inner area and decreased CBF in the surrounding area (PA), or decreased CBF in both areas (FA+PA). This information allowed the appropriate management of these arteries and avoidance of postoperative ischemic complications. RESULTS Good visualization of CBF in the surgical field and relative CBF measurements in the regions of interest were achieved in real time with excellent spatiotemporal resolution. In 11 patients (92%) and 20 regions of interest, a decline in CBF was observed after temporary interruption of the FA (n = 8), PA (n = 2), and FA+PA (n = 2) types. There was a significant average reduction in CBF of 15.3% ± 29.0%. There were no ischemic complications, and only 1 patient had a postoperative ischemic lesion caused by resection through an artery that could not be viewed by LSFI due to a positional problem. CONCLUSIONS LSFI permits noninvasive and rapid intraoperative real-time recognition of mass lesion–related vasculature. This information can be used to avoid ischemic complications as a procedure complementary to neurophysiological monitoring.

Sign in / Sign up

Export Citation Format

Share Document