https://scholars.lib.ntu.edu.tw/handle/123456789/599039
Title: | Semi-Automated Extraction of Lens Fragments Via a Surgical Robot Using Semantic Segmentation of OCT Images with Deep Learning-Experimental Results in Ex Vivo Animal Model | Authors: | Shin C Gerber M Lee Y.-H Rodriguez M Aghajani Pedram S Hubschman J.-P Tsao T.-C Rosen J. YU-HSIU LEE |
Keywords: | Cataract surgery;computer vision for medical robotics;deep learning;medical robots and systems;surgical robotics: planning;Agricultural robots;Convolutional neural networks;Deep learning;Extraction;Lenses;Mammals;Optical tomography;Robotic surgery;Robotics;Robots;Semantics;Surgery;Automated extraction;Interventional;Lens materials;Robotic systems;Segmentation algorithms;Semantic segmentation;Semi-automated detection;Surgical systems;Image segmentation | Issue Date: | 2021 | Journal Volume: | 6 | Journal Issue: | 3 | Start page/Pages: | 5261-5268 | Source: | IEEE Robotics and Automation Letters | Abstract: | The overarching goal of this letter is to demonstrate the feasibility of using optical coherence tomography (OCT) to guide a robotic system to extract lens fragments from ex vivo pig eyes. A convolutional neural network (CNN) was developed to semantically segment four intraocular structures (lens material, capsule, cornea, and iris) from OCT images. The neural network was trained on images from ten pig eyes, validated on images from eight different eyes, and tested on images from another ten eyes. This segmentation algorithm was incorporated into the Intraocular Robotic Interventional Surgical System (IRISS) to realize semi-automated detection and extraction of lens material. To demonstrate the system, the semi-automated detection and extraction task was performed on seven separate ex vivo pig eyes. The developed neural network exhibited 78.20% for the validation set and 83.89% for the test set in mean intersection over union metrics. Successful implementation and efficacy of the developed method were confirmed by comparing the preoperative and postoperative OCT volume scans from the seven experiments. ? 2016 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104264556&doi=10.1109%2fLRA.2021.3072574&partnerID=40&md5=9cb8cb36d339a13d86562cea683465c1 https://scholars.lib.ntu.edu.tw/handle/123456789/599039 |
ISSN: | 23773766 | DOI: | 10.1109/LRA.2021.3072574 |
Appears in Collections: | 機械工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.