1
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Artificial Intelligence-enabled, Real-time Intraoperative Ultrasound Imaging of Neural Structures Within the Psoas : Validation in a Porcine Spine Model

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          A porcine model was used to evaluate an Artificial Intelligence (AI)-enabled ultrasound imaging system. Image processing and machine learning algorithms were developed to enable intraoperative ultrasonic detection, segmentation, classification, and display of neural structures within the psoas. The imaging system's performance was assessed with tissue dissection and Dice coefficient calculation.

          Abstract

          Study Design.

          Experimental in-vivo animal study.

          Objective.

          The aim of this study was to evaluate an Artificial Intelligence (AI)-enabled ultrasound imaging system's ability to detect, segment, classify, and display neural and other structures during trans-psoas spine surgery.

          Summary of Background Data.

          Current methodologies for intraoperatively localizing and visualizing neural structures within the psoas are limited and can impact the safety of lateral lumbar interbody fusion (LLIF). Ultrasound technology, enhanced with AI-derived neural detection algorithms, could prove useful for this task.

          Methods.

          The study was conducted using an in vivo porcine model (50 subjects). Image processing and machine learning algorithms were developed to detect neural and other anatomic structures within and adjacent to the psoas muscle while using an ultrasound imaging system during lateral lumbar spine surgery (SonoVision,™ Tissue Differentiation Intelligence, USA). The imaging system's ability to detect and classify the anatomic structures was assessed with subsequent tissue dissection. Dice coefficients were calculated to quantify the performance of the image segmentation.

          Results.

          The AI-trained ultrasound system detected, segmented, classified, and displayed nerve, psoas muscle, and vertebral body surface with high sensitivity and specificity. The mean Dice coefficient score for each tissue type was >80%, indicating that the detected region and ground truth were >80% similar to each other. The mean specificity of nerve detection was 92%; for bone and muscle, it was >95%. The accuracy of nerve detection was >95%.

          Conclusion.

          This study demonstrates that a combination of AI-derived image processing and machine learning algorithms can be developed to enable real-time ultrasonic detection, segmentation, classification, and display of critical anatomic structures, including neural tissue, during spine surgery. AI-enhanced ultrasound imaging can provide a visual map of important anatomy in and adjacent to the psoas, thereby providing the surgeon with critical information intended to increase the safety of LLIF surgery.

          Level of Evidence: N/A

          Related collections

          Most cited references45

          • Record: found
          • Abstract: found
          • Article: not found

          Fully Convolutional Networks for Semantic Segmentation.

          Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional networks achieve improved segmentation of PASCAL VOC (30% relative improvement to 67.2% mean IU on 2012), NYUDv2, SIFT Flow, and PASCAL-Context, while inference takes one tenth of a second for a typical image.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI

            Deep learning is a branch of artificial intelligence where networks of simple interconnected units are used to extract patterns from data in order to solve complex problems. Deep-learning algorithms have shown groundbreaking performance in a variety of sophisticated tasks, especially those related to images. They have often matched or exceeded human performance. Since the medical field of radiology mainly relies on extracting useful information from images, it is a very natural application area for deep learning, and research in this area has rapidly grown in recent years. In this article, we discuss the general context of radiology and opportunities for application of deep-learning algorithms. We also introduce basic concepts of deep learning, including convolutional neural networks. Then, we present a survey of the research in deep learning applied to radiology. We organize the studies by the types of specific tasks that they attempt to solve and review a broad range of deep-learning algorithms being utilized. Finally, we briefly discuss opportunities and challenges for incorporating deep learning in the radiology practice of the future. Level of Evidence: 3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;49:939-954.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Intraoperative and early postoperative complications in extreme lateral interbody fusion: an analysis of 600 cases.

              Prospective analysis of 600 extreme lateral interbody fusion (XLIF) approach procedures for intraoperative and perioperative complications. To delineate and describe complications in a large, prospective series of minimally invasive lateral lumbar fusion procedures (XLIF). While some small series of lateral lumbar fusion have discussed complications, no results from large studies have been reported. A total of 600 patients were treated with a lateral approach to fusion (XLIF) for degenerative spinal conditions. Data were collected prospectively on all patients and analyzed for demographic, diagnostic, and hospitalization information to identify operative and early postoperative complications. Documented complication types and rates in this large series were compared with smaller prior reports on lateral approach fusions, as well as other minimally invasive (mini-anterior lumbar interbody fusion and minimally invasive surgical [MIS] transforaminal lumbar interbody fusion) and more traditional fusion approaches (posterior intertransverse fusion, anterior lumbar interbody fusion, posterior lumbar interbody fusion, transforaminal lumbar interbody fusion). Seven hundred forty-one levels were treated, 80.8% single level, 15.0% 2 level, 4.0% 3 level, 0.2% 4 level; 59.3%, including the L4 to L5 levels. A total of 99.2% included supplemental internal fixation; 83.2% included pedicle screw fixation (predominantly unilateral). Hemoglobin change from pre- to postoperation averaged 1.38. Hospital stay averaged 1.21 days. The overall incidence of perioperative complications (intraoperation and out to 6 weeks postoperation) was 6.2%: 9 (1.5%) in-hospital surgery-related events, 17 (2.8%) in-hospital medical events, 6 (1.0%) out-of-hospital surgery-related events, and 5 (0.8%) out-of-hospital medical events. There were no wound infections, no vascular injuries, no intraoperative visceral injuries, and 4 (0.7%) transient postoperative neurologic deficits. Eleven events (1.8%) resulted in additional procedures/reoperation. Compared with traditional open approaches, the MIS lateral approach to fusion by using the XLIF technique resulted in a lower incidence of infection, visceral and neurologic injury, and transfusion as well as markedly shorter hospitalization. Complications in MIS XLIF compare favorably with those from other MIS fusion procedures; duration of hospitalization is shorter than with any previously reported technique.
                Bookmark

                Author and article information

                Journal
                Spine (Phila Pa 1976)
                Spine (Phila Pa 1976)
                BRS
                Spine
                Lippincott Williams & Wilkins (Hagerstown, MD )
                0362-2436
                1528-1159
                1 February 2021
                05 October 2020
                : 46
                : 3
                : E146-E152
                Affiliations
                [a ]NeuroSpine Institute, Palmdale, CA
                [b ]Riverside University Health System, Department of Neurosurgery, Moreno Valley, CA
                [c ]Tissue Differentiation Intelligence, Delray Beach, FL
                [d ]University of San Diego, San Diego, CA
                [e ]Cephasonics Ultrasound Solutions, Santa Clara, CA
                [f ]OrthoIndy, Indianapolis, IN
                [g ]Semmes-Murphey Clinic & Department of Neurosurgery, University of Tennessee Health Science Center, Memphis, TN.
                Author notes
                Address correspondence and reprint requests to Kevin T. Foley, MD, Semmes-Murphey Clinic & Department of Neurosurgery, University of Tennessee Health Science Center, 6325 Humphreys Blvd, Memphis, TN 38120; E-mail: kfoley@ 123456usit.net
                Article
                SPINE161561 00004
                10.1097/BRS.0000000000003704
                7787186
                33399436
                3c88410b-b82c-462c-8f2e-29b816d65b4e
                Copyright © 2020 The Author(s). Published by Wolters Kluwer Health, Inc.

                This is an open access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License 4.0 (CCBY-NC-ND), where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal. http://creativecommons.org/licenses/by-nc-nd/4.0

                History
                : 27 May 2020
                : 28 June 2020
                : 13 August 2020
                Categories
                Basic Science
                Custom metadata
                TRUE
                ONLINE-ONLY

                artificial intelligence,image guidance,lateral spine surgery,neural anatomy,porcine model,psoas muscle,ultrasound

                Comments

                Comment on this article