Saved in:
Bibliographic Details
Main Authors: Peng, Haonan, Lin, Shan, King, Daniel, Su, Yun-Hsuan, Bly, Randall A., Moe, Kris S., Hannaford, Blake
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2108.03534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929402292469760
author Peng, Haonan
Lin, Shan
King, Daniel
Su, Yun-Hsuan
Bly, Randall A.
Moe, Kris S.
Hannaford, Blake
author_facet Peng, Haonan
Lin, Shan
King, Daniel
Su, Yun-Hsuan
Bly, Randall A.
Moe, Kris S.
Hannaford, Blake
contents Accurate instrument segmentation in endoscopic vision of robot-assisted surgery is challenging due to reflection on the instruments and frequent contacts with tissue. Deep neural networks (DNN) show competitive performance and are in favor in recent years. However, the hunger of DNN for labeled data poses a huge workload of annotation. Motivated by alleviating this workload, we propose a general embeddable method to decrease the usage of labeled real images, using active generated synthetic images. In each active learning iteration, the most informative unlabeled images are first queried by active learning and then labeled. Next, synthetic images are generated based on these selected images. The instruments and backgrounds are cropped out and randomly combined with each other with blending and fusion near the boundary. The effectiveness of the proposed method is validated on 2 sinus surgery datasets and 1 intraabdominal surgery dataset. The results indicate a considerable improvement in performance, especially when the budget for annotation is small. The effectiveness of different types of synthetic images, blending methods, and external background are also studied. All the code is open-sourced at: https://github.com/HaonanPeng/active_syn_generator.
format Preprint
id arxiv_https___arxiv_org_abs_2108_03534
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Reducing Annotating Load: Active Learning with Synthetic Images in Surgical Instrument Segmentation
Peng, Haonan
Lin, Shan
King, Daniel
Su, Yun-Hsuan
Bly, Randall A.
Moe, Kris S.
Hannaford, Blake
Computer Vision and Pattern Recognition
Accurate instrument segmentation in endoscopic vision of robot-assisted surgery is challenging due to reflection on the instruments and frequent contacts with tissue. Deep neural networks (DNN) show competitive performance and are in favor in recent years. However, the hunger of DNN for labeled data poses a huge workload of annotation. Motivated by alleviating this workload, we propose a general embeddable method to decrease the usage of labeled real images, using active generated synthetic images. In each active learning iteration, the most informative unlabeled images are first queried by active learning and then labeled. Next, synthetic images are generated based on these selected images. The instruments and backgrounds are cropped out and randomly combined with each other with blending and fusion near the boundary. The effectiveness of the proposed method is validated on 2 sinus surgery datasets and 1 intraabdominal surgery dataset. The results indicate a considerable improvement in performance, especially when the budget for annotation is small. The effectiveness of different types of synthetic images, blending methods, and external background are also studied. All the code is open-sourced at: https://github.com/HaonanPeng/active_syn_generator.
title Reducing Annotating Load: Active Learning with Synthetic Images in Surgical Instrument Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2108.03534