Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation

被引:13
|
作者
Karaoglu, Mert Asim [1 ,2 ]
Brasch, Nikolas [2 ]
Stollenga, Marijn [1 ]
Wein, Wolfgang [1 ]
Navab, Nassir [2 ,3 ]
Tombari, Federico [2 ,4 ]
Ladikos, Alexander [1 ]
机构
[1] ImFus GmbH, Munich, Germany
[2] Tech Univ Munich, Comp Aided Med Procedures, Munich, Germany
[3] Johns Hopkins Univ, Comp Aided Med Procedures, Baltimore, MD USA
[4] Google, Zurich, Switzerland
关键词
Bronchoscopy; Depth estimation; Domain adaptation; RECONSTRUCTION; NAVIGATION; CT;
D O I
10.1007/978-3-030-87202-1_29
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Depth estimation from monocular images is an important task in localization and 3D reconstruction pipelines for bronchoscopic navigation. Various supervised and self-supervised deep learning-based approaches have proven themselves on this task for natural images. However, the lack of labeled data and the bronchial tissue's feature-scarce texture make the utilization of these methods ineffective on bronchoscopic scenes. In this work, we propose an alternative domain-adaptive approach. Our novel two-step structure first trains a depth estimation network with labeled synthetic images in a supervised manner; then adopts an unsupervised adversarial domain feature adaptation scheme to improve the performance on real images. The results of our experiments show that the proposed method improves the network's performance on real images by a considerable margin and can be employed in 3D reconstruction pipelines.
引用
收藏
页码:300 / 310
页数:11
相关论文
共 50 条
  • [1] Adversarial Diffusion Model for Domain-Adaptive Depth Estimation in Bronchoscopic Navigation
    Yang, Yiguang
    Ning, Guochen
    Zhong, Changhao
    Liao, Hongen
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2024, PT VI, 2024, 15006 : 46 - 56
  • [2] Cystoscopic depth estimation using gated adversarial domain adaptation
    Somers, Peter
    Holdenried-Krafft, Simon
    Zahn, Johannes
    Schuele, Johannes
    Veil, Carina
    Harland, Niklas
    Walz, Simon
    Stenzl, Arnulf
    Sawodny, Oliver
    Tarin, Cristina
    Lensch, Hendrik P. A.
    BIOMEDICAL ENGINEERING LETTERS, 2023, 13 (02) : 141 - 151
  • [3] Cystoscopic depth estimation using gated adversarial domain adaptation
    Peter Somers
    Simon Holdenried-Krafft
    Johannes Zahn
    Johannes Schüle
    Carina Veil
    Niklas Harland
    Simon Walz
    Arnulf Stenzl
    Oliver Sawodny
    Cristina Tarín
    Hendrik P. A. Lensch
    Biomedical Engineering Letters, 2023, 13 : 141 - 151
  • [4] Feature concatenation for adversarial domain adaptation
    Li, Jingyao
    Li, Zhanshan
    Lu, Shuai
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 169
  • [5] Domain adaptation with feature and label adversarial networks
    Zhao, Peng
    Zang, Wenhua
    Liu, Bin
    Kang, Zhao
    Bai, Kun
    Huang, Kaizhu
    Xu, Zenglin
    NEUROCOMPUTING, 2021, 439 (439) : 294 - 301
  • [6] Adversarial Feature Augmentation for Unsupervised Domain Adaptation
    Volpi, Riccardo
    Morerio, Pietro
    Savarese, Silvio
    Murino, Vittorio
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 5495 - 5504
  • [7] An Adversarial Training based Framework for Depth Domain Adaptation
    Katrolia, Jigyasa Singh
    Kraemer, Lars
    Rambach, Jason
    Mirbach, Bruno
    Stricker, Didier
    VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 4: VISAPP, 2021, : 353 - 361
  • [8] Multimodal Vigilance Estimation with Adversarial Domain Adaptation Networks
    Li, He
    Zheng, Wei-Long
    Lu, Bao-Liang
    2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
  • [9] Feature Constrained by Pixel: Hierarchical Adversarial Deep Domain Adaptation
    Shao, Rui
    Lan, Xiangyuan
    Yuen, Pong C.
    PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, : 220 - 228
  • [10] Bronchial orifice segmentation on bronchoscopic video frames based on generative adversarial depth estimation
    Wang, Cheng
    Hayashi, Yuichiro
    Oda, Masahiro
    Kitasaka, Takayuki
    Honma, Hirotoshi
    Takabatake, Hirotsugu
    Mori, Masaki
    Natori, Hiroshi
    Mori, Kensaku
    MEDICAL IMAGING 2021: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING, 2021, 11598