Classification of Surgical Devices with Artificial Neural Network Approach
Conference proceedings article
Authors/Editors
Strategic Research Themes
Publication Details
Author list: Lelachaicharoeanpan, Jaroonwit; Vongbunyong, Supachai;
Publisher: Hindawi
Publication year: 2021
Start page: 154
End page: 159
Number of pages: 6
ISBN: 9781670000000
ISSN: 0146-9428
eISSN: 1745-4557
Languages: English-Great Britain (EN-GB)
Abstract
In an operation, large number of surgical devices are generally used by surgeons. After they have been used, a special cleaning protocol is required to make sure that they will be disinfected and safe and to use in subsequent operations. In hospitals, the used devices will return to be treated at CSSD (Central Sterile Supply Department). The device needs to be classified and treated separately according to the types and models. Traditionally manual classification process has become an issue when the number of the returned devices increases. In this research, robotic and vision systems are used to classify the surgical devices. Object recognition and detection are developed with Machine Learning (ML) approach. Artificial Neural Networks, YOLO (You Only Look Once) algorithm, is applied to solve this problem. Five classes of surgical devices - i.e., scissor, blade holder, clamp, suction, retractor- are trained and demonstrated. © 2021 IEEE.
Keywords
CSSD, YOLO
Contact Information