Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan

Ryo Furukawa, Genki Nagamatsu, Shiro Oka, Takahiro Kotachi, Yuki Okamoto, Shinji Tanaka, Hiroshi Kawasaki

Research output: Contribution to journalArticle

Abstract

For effective in situ endoscopic diagnosis and treatment, measurement of polyp sizes is important. For this purpose, 3D endoscopic systems have been researched. Among such systems, an active stereo technique, which projects a special pattern wherein each feature is coded, is a promising approach because of simplicity and high precision. However, previous works of this approach have problems. First, the quality of 3D reconstruction depended on the stabilities of feature extraction from the images captured by the endoscope camera. Second, due to the limited pattern projection area, the reconstructed region was relatively small. In this Letter, the authors propose a learning-based technique using convolutional neural networks to solve the first problem and an extended bundle adjustment technique, which integrates multiple shapes into a consistent single shape, to address the second. The effectiveness of the proposed techniques compared to previous techniques was evaluated experimentally.

Original languageEnglish
Pages (from-to)249-254
Number of pages6
JournalHealthcare Technology Letters
Volume6
Issue number6
DOIs
Publication statusPublished - Jan 1 2019

Fingerprint

Social Adjustment
Endoscopes
Polyps
Learning

All Science Journal Classification (ASJC) codes

  • Health Informatics
  • Health Information Management

Cite this

Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan. / Furukawa, Ryo; Nagamatsu, Genki; Oka, Shiro; Kotachi, Takahiro; Okamoto, Yuki; Tanaka, Shinji; Kawasaki, Hiroshi.

In: Healthcare Technology Letters, Vol. 6, No. 6, 01.01.2019, p. 249-254.

Research output: Contribution to journalArticle

Furukawa, Ryo ; Nagamatsu, Genki ; Oka, Shiro ; Kotachi, Takahiro ; Okamoto, Yuki ; Tanaka, Shinji ; Kawasaki, Hiroshi. / Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan. In: Healthcare Technology Letters. 2019 ; Vol. 6, No. 6. pp. 249-254.
@article{dbb9b169d33f4b7ebd2c6802a0f837d5,
title = "Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan",
abstract = "For effective in situ endoscopic diagnosis and treatment, measurement of polyp sizes is important. For this purpose, 3D endoscopic systems have been researched. Among such systems, an active stereo technique, which projects a special pattern wherein each feature is coded, is a promising approach because of simplicity and high precision. However, previous works of this approach have problems. First, the quality of 3D reconstruction depended on the stabilities of feature extraction from the images captured by the endoscope camera. Second, due to the limited pattern projection area, the reconstructed region was relatively small. In this Letter, the authors propose a learning-based technique using convolutional neural networks to solve the first problem and an extended bundle adjustment technique, which integrates multiple shapes into a consistent single shape, to address the second. The effectiveness of the proposed techniques compared to previous techniques was evaluated experimentally.",
author = "Ryo Furukawa and Genki Nagamatsu and Shiro Oka and Takahiro Kotachi and Yuki Okamoto and Shinji Tanaka and Hiroshi Kawasaki",
year = "2019",
month = "1",
day = "1",
doi = "10.1049/htl.2019.0070",
language = "English",
volume = "6",
pages = "249--254",
journal = "Healthcare Technology Letters",
issn = "2053-3713",
publisher = "Institution of Engineering and Technology",
number = "6",

}

TY - JOUR

T1 - Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan

AU - Furukawa, Ryo

AU - Nagamatsu, Genki

AU - Oka, Shiro

AU - Kotachi, Takahiro

AU - Okamoto, Yuki

AU - Tanaka, Shinji

AU - Kawasaki, Hiroshi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - For effective in situ endoscopic diagnosis and treatment, measurement of polyp sizes is important. For this purpose, 3D endoscopic systems have been researched. Among such systems, an active stereo technique, which projects a special pattern wherein each feature is coded, is a promising approach because of simplicity and high precision. However, previous works of this approach have problems. First, the quality of 3D reconstruction depended on the stabilities of feature extraction from the images captured by the endoscope camera. Second, due to the limited pattern projection area, the reconstructed region was relatively small. In this Letter, the authors propose a learning-based technique using convolutional neural networks to solve the first problem and an extended bundle adjustment technique, which integrates multiple shapes into a consistent single shape, to address the second. The effectiveness of the proposed techniques compared to previous techniques was evaluated experimentally.

AB - For effective in situ endoscopic diagnosis and treatment, measurement of polyp sizes is important. For this purpose, 3D endoscopic systems have been researched. Among such systems, an active stereo technique, which projects a special pattern wherein each feature is coded, is a promising approach because of simplicity and high precision. However, previous works of this approach have problems. First, the quality of 3D reconstruction depended on the stabilities of feature extraction from the images captured by the endoscope camera. Second, due to the limited pattern projection area, the reconstructed region was relatively small. In this Letter, the authors propose a learning-based technique using convolutional neural networks to solve the first problem and an extended bundle adjustment technique, which integrates multiple shapes into a consistent single shape, to address the second. The effectiveness of the proposed techniques compared to previous techniques was evaluated experimentally.

UR - http://www.scopus.com/inward/record.url?scp=85077517032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077517032&partnerID=8YFLogxK

U2 - 10.1049/htl.2019.0070

DO - 10.1049/htl.2019.0070

M3 - Article

AN - SCOPUS:85077517032

VL - 6

SP - 249

EP - 254

JO - Healthcare Technology Letters

JF - Healthcare Technology Letters

SN - 2053-3713

IS - 6

ER -