Paper Info
Title
Surgical Process Identification System using Machine Learning in Awake Surgery for Brain Tumor
Abstract
During surgery for brain tumor, expert surgeons consider maximum brain tumor removal and minimum postoperative neuroglial complications. At this brain tumor resection, the surgeon resects based on his knowledge and experience, the surgical process, work contents, and duration of surgery vary by cases. It is difficult for the young surgeons and surgical staffs to understand the surgical process involved. Visualization of the surgical process is an effective tool for aiding the understanding among the surgical staff. This paper presents a surgical identification system using intra-operative information and machine learning. We extract surgical process features using navigation system's log, MR images and microscope video. Then, the surgical processes are identified using Hierarchical Hidden Markov Model. The method has been evaluated using past log data (navigation system's log, MR images and microscope video). The accuracy of the identified surgical processes was 84% in 12 processes. This result indicated that the surgical process identification error is a few minutes, high revel accuracy. In addition, this result is a possibility to support understanding of surgical processes for young surgeons and surgical staffs.
Year
DOI
Venue
2019
10.1109/LifeTech.2019.8884047
2019 IEEE 1st Global Conference on Life Sciences and Technologies (LifeTech)
Keywords
Field
DocType
machine learning,surgical process,glioma
Hierarchical hidden Markov model,Visualization,Computer science,Navigation system,Identification system,Brain tumor,Feature extraction,Artificial intelligence,Hidden Markov model,Surgery,Process identification,Machine learning
Conference
ISBN
Citations 
PageRank 
978-1-7281-0544-4
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Tomohiro Nagai100.34
Ikuma Sato200.34
Yuichi Fujino300.34
Manabu Tamura431.88
Yoshihiro Muragaki52912.81
Ken Masamune625348.57