Detecting and tracking surgical tools for recognizing phases of the awake brain tumor removal surgery

Hiroki Fujie, Keiju Hirata, Takahiro Horigome, Hiroshi Nagahashi, Jun Ohya, Manabu Tamura, Ken Masamune, Yoshihiro Muragaki

研究成果: Conference contribution

抄録

In order to realize automatic recognition of surgical processes in surgical brain tumor removal using microscopic camera, we propose a method of detecting and tracking surgical tools by video analysis. The proposed method consists of a detection part and tracking part. In the detection part, object detection is performed for each frame of surgery video, and the category and bounding box are acquired frame by frame. The convolution layer strengthens the robustness using data augmentation (central cropping and random erasing). The tracking part uses SORT, which predicts and updates the acquired bounding box corrected by using Kalman Filter; next, the object ID is assigned to each corrected bounding box using the Hungarian algorithm. The accuracy of our proposed method is very high as follows. As a result of experiments on spatial detection. the mean average precision is 90.58%. the mean accuracy of frame label detection is 96.58%. These results are very promising for surgical phase recognition.

元の言語English
ホスト出版物のタイトルICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods
編集者Ana Fred, Maria De Marsico, Gabriella Sanniti di Baja
出版者SciTePress
ページ190-199
ページ数10
ISBN(電子版)9789897583513
出版物ステータスPublished - 2019 1 1
イベント8th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2019 - Prague, Czech Republic
継続期間: 2019 2 192019 2 21

出版物シリーズ

名前ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods

Conference

Conference8th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2019
Czech Republic
Prague
期間19/2/1919/2/21

Fingerprint

Convolution
Kalman filters
Surgery
Labels
Tumors
Brain
Cameras
Experiments
Object detection

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

これを引用

Fujie, H., Hirata, K., Horigome, T., Nagahashi, H., Ohya, J., Tamura, M., ... Muragaki, Y. (2019). Detecting and tracking surgical tools for recognizing phases of the awake brain tumor removal surgery. : A. Fred, M. De Marsico, & G. S. di Baja (版), ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods (pp. 190-199). (ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods). SciTePress.

Detecting and tracking surgical tools for recognizing phases of the awake brain tumor removal surgery. / Fujie, Hiroki; Hirata, Keiju; Horigome, Takahiro; Nagahashi, Hiroshi; Ohya, Jun; Tamura, Manabu; Masamune, Ken; Muragaki, Yoshihiro.

ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. 版 / Ana Fred; Maria De Marsico; Gabriella Sanniti di Baja. SciTePress, 2019. p. 190-199 (ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods).

研究成果: Conference contribution

Fujie, H, Hirata, K, Horigome, T, Nagahashi, H, Ohya, J, Tamura, M, Masamune, K & Muragaki, Y 2019, Detecting and tracking surgical tools for recognizing phases of the awake brain tumor removal surgery. : A Fred, M De Marsico & GS di Baja (版), ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods, SciTePress, pp. 190-199, 8th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2019, Prague, Czech Republic, 19/2/19.
Fujie H, Hirata K, Horigome T, Nagahashi H, Ohya J, Tamura M その他. Detecting and tracking surgical tools for recognizing phases of the awake brain tumor removal surgery. : Fred A, De Marsico M, di Baja GS, 編集者, ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. SciTePress. 2019. p. 190-199. (ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods).
Fujie, Hiroki ; Hirata, Keiju ; Horigome, Takahiro ; Nagahashi, Hiroshi ; Ohya, Jun ; Tamura, Manabu ; Masamune, Ken ; Muragaki, Yoshihiro. / Detecting and tracking surgical tools for recognizing phases of the awake brain tumor removal surgery. ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. 編集者 / Ana Fred ; Maria De Marsico ; Gabriella Sanniti di Baja. SciTePress, 2019. pp. 190-199 (ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods).
@inproceedings{5e6bfc430a7b45d2ab0ec23bf075524b,
title = "Detecting and tracking surgical tools for recognizing phases of the awake brain tumor removal surgery",
abstract = "In order to realize automatic recognition of surgical processes in surgical brain tumor removal using microscopic camera, we propose a method of detecting and tracking surgical tools by video analysis. The proposed method consists of a detection part and tracking part. In the detection part, object detection is performed for each frame of surgery video, and the category and bounding box are acquired frame by frame. The convolution layer strengthens the robustness using data augmentation (central cropping and random erasing). The tracking part uses SORT, which predicts and updates the acquired bounding box corrected by using Kalman Filter; next, the object ID is assigned to each corrected bounding box using the Hungarian algorithm. The accuracy of our proposed method is very high as follows. As a result of experiments on spatial detection. the mean average precision is 90.58{\%}. the mean accuracy of frame label detection is 96.58{\%}. These results are very promising for surgical phase recognition.",
keywords = "Awake Brain Tumor Removal Surgery, Computer Vision, Convolutional Neural Network, Data Association, Data Augmentation, Detection, Multiple Object Tracking",
author = "Hiroki Fujie and Keiju Hirata and Takahiro Horigome and Hiroshi Nagahashi and Jun Ohya and Manabu Tamura and Ken Masamune and Yoshihiro Muragaki",
year = "2019",
month = "1",
day = "1",
language = "English",
series = "ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods",
publisher = "SciTePress",
pages = "190--199",
editor = "Ana Fred and {De Marsico}, Maria and {di Baja}, {Gabriella Sanniti}",
booktitle = "ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods",

}

TY - GEN

T1 - Detecting and tracking surgical tools for recognizing phases of the awake brain tumor removal surgery

AU - Fujie, Hiroki

AU - Hirata, Keiju

AU - Horigome, Takahiro

AU - Nagahashi, Hiroshi

AU - Ohya, Jun

AU - Tamura, Manabu

AU - Masamune, Ken

AU - Muragaki, Yoshihiro

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In order to realize automatic recognition of surgical processes in surgical brain tumor removal using microscopic camera, we propose a method of detecting and tracking surgical tools by video analysis. The proposed method consists of a detection part and tracking part. In the detection part, object detection is performed for each frame of surgery video, and the category and bounding box are acquired frame by frame. The convolution layer strengthens the robustness using data augmentation (central cropping and random erasing). The tracking part uses SORT, which predicts and updates the acquired bounding box corrected by using Kalman Filter; next, the object ID is assigned to each corrected bounding box using the Hungarian algorithm. The accuracy of our proposed method is very high as follows. As a result of experiments on spatial detection. the mean average precision is 90.58%. the mean accuracy of frame label detection is 96.58%. These results are very promising for surgical phase recognition.

AB - In order to realize automatic recognition of surgical processes in surgical brain tumor removal using microscopic camera, we propose a method of detecting and tracking surgical tools by video analysis. The proposed method consists of a detection part and tracking part. In the detection part, object detection is performed for each frame of surgery video, and the category and bounding box are acquired frame by frame. The convolution layer strengthens the robustness using data augmentation (central cropping and random erasing). The tracking part uses SORT, which predicts and updates the acquired bounding box corrected by using Kalman Filter; next, the object ID is assigned to each corrected bounding box using the Hungarian algorithm. The accuracy of our proposed method is very high as follows. As a result of experiments on spatial detection. the mean average precision is 90.58%. the mean accuracy of frame label detection is 96.58%. These results are very promising for surgical phase recognition.

KW - Awake Brain Tumor Removal Surgery

KW - Computer Vision

KW - Convolutional Neural Network

KW - Data Association

KW - Data Augmentation

KW - Detection

KW - Multiple Object Tracking

UR - http://www.scopus.com/inward/record.url?scp=85064675027&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064675027&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85064675027

T3 - ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods

SP - 190

EP - 199

BT - ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods

A2 - Fred, Ana

A2 - De Marsico, Maria

A2 - di Baja, Gabriella Sanniti

PB - SciTePress

ER -