Detecting a fetus in ultrasound images using grad CAM and locating the fetus in the uterus

Genta Ishikawa, Rong Xu, Jun Ohya, Hiroyasu Iwata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose an automatic method for estimating fetal position based on classification and detection of different fetal parts in ultrasound images. Fine tuning is performed in the ultrasound images to be used for fetal examination using CNN, and classification of four classes "head", "body", "leg" and "other" is realized. Based on the obtained learning result, binarization that thresholds the gradient of the feature obtained by Grad Cam is performed in the image so that a bounding box of the region of interest with large gradient is extracted. The center of the bounding box is obtained from each frame so that the trajectory of the centroids is obtained; the position of the fetus is obtained as the trajectory. Experiments using 2000 images were conducted using a fetal phantom. Each recall ratiso of the four class is 99.6% for head, 99.4% for body, 99.8% for legs, 72.6% for others, respectively. The trajectories obtained from the fetus present in “left”, “center”, “right” in the images show the above-mentioned geometrical relationship. These results indicate that the estimated fetal position coincides with the actual position very well, which can be used as the first step for automatic fetal examination by robotic systems.

Original languageEnglish
Title of host publicationICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods
EditorsAna Fred, Maria De Marsico, Gabriella Sanniti di Baja
PublisherSciTePress
Pages181-189
Number of pages9
ISBN (Electronic)9789897583513
Publication statusPublished - 2019 Jan 1
Event8th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2019 - Prague, Czech Republic
Duration: 2019 Feb 192019 Feb 21

Publication series

NameICPRAM 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
CountryCzech Republic
CityPrague
Period19/2/1919/2/21

Fingerprint

Computer aided manufacturing
Ultrasonics
Trajectories
Cams
Robotics
Tuning
Experiments

Keywords

  • Deep Leaning
  • Fetal
  • Fetal Position
  • Grad_CAM
  • Ultrasound Image

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Ishikawa, G., Xu, R., Ohya, J., & Iwata, H. (2019). Detecting a fetus in ultrasound images using grad CAM and locating the fetus in the uterus. In A. Fred, M. De Marsico, & G. S. di Baja (Eds.), ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods (pp. 181-189). (ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods). SciTePress.

Detecting a fetus in ultrasound images using grad CAM and locating the fetus in the uterus. / Ishikawa, Genta; Xu, Rong; Ohya, Jun; Iwata, Hiroyasu.

ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. ed. / Ana Fred; Maria De Marsico; Gabriella Sanniti di Baja. SciTePress, 2019. p. 181-189 (ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ishikawa, G, Xu, R, Ohya, J & Iwata, H 2019, Detecting a fetus in ultrasound images using grad CAM and locating the fetus in the uterus. in A Fred, M De Marsico & GS di Baja (eds), 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. 181-189, 8th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2019, Prague, Czech Republic, 19/2/19.
Ishikawa G, Xu R, Ohya J, Iwata H. Detecting a fetus in ultrasound images using grad CAM and locating the fetus in the uterus. In Fred A, De Marsico M, di Baja GS, editors, ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. SciTePress. 2019. p. 181-189. (ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods).
Ishikawa, Genta ; Xu, Rong ; Ohya, Jun ; Iwata, Hiroyasu. / Detecting a fetus in ultrasound images using grad CAM and locating the fetus in the uterus. ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. editor / Ana Fred ; Maria De Marsico ; Gabriella Sanniti di Baja. SciTePress, 2019. pp. 181-189 (ICPRAM 2019 - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods).
@inproceedings{9329321c1cb3484eb2a7cf10d5c419fe,
title = "Detecting a fetus in ultrasound images using grad CAM and locating the fetus in the uterus",
abstract = "In this paper, we propose an automatic method for estimating fetal position based on classification and detection of different fetal parts in ultrasound images. Fine tuning is performed in the ultrasound images to be used for fetal examination using CNN, and classification of four classes {"}head{"}, {"}body{"}, {"}leg{"} and {"}other{"} is realized. Based on the obtained learning result, binarization that thresholds the gradient of the feature obtained by Grad Cam is performed in the image so that a bounding box of the region of interest with large gradient is extracted. The center of the bounding box is obtained from each frame so that the trajectory of the centroids is obtained; the position of the fetus is obtained as the trajectory. Experiments using 2000 images were conducted using a fetal phantom. Each recall ratiso of the four class is 99.6{\%} for head, 99.4{\%} for body, 99.8{\%} for legs, 72.6{\%} for others, respectively. The trajectories obtained from the fetus present in “left”, “center”, “right” in the images show the above-mentioned geometrical relationship. These results indicate that the estimated fetal position coincides with the actual position very well, which can be used as the first step for automatic fetal examination by robotic systems.",
keywords = "Deep Leaning, Fetal, Fetal Position, Grad_CAM, Ultrasound Image",
author = "Genta Ishikawa and Rong Xu and Jun Ohya and Hiroyasu Iwata",
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 = "181--189",
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 a fetus in ultrasound images using grad CAM and locating the fetus in the uterus

AU - Ishikawa, Genta

AU - Xu, Rong

AU - Ohya, Jun

AU - Iwata, Hiroyasu

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this paper, we propose an automatic method for estimating fetal position based on classification and detection of different fetal parts in ultrasound images. Fine tuning is performed in the ultrasound images to be used for fetal examination using CNN, and classification of four classes "head", "body", "leg" and "other" is realized. Based on the obtained learning result, binarization that thresholds the gradient of the feature obtained by Grad Cam is performed in the image so that a bounding box of the region of interest with large gradient is extracted. The center of the bounding box is obtained from each frame so that the trajectory of the centroids is obtained; the position of the fetus is obtained as the trajectory. Experiments using 2000 images were conducted using a fetal phantom. Each recall ratiso of the four class is 99.6% for head, 99.4% for body, 99.8% for legs, 72.6% for others, respectively. The trajectories obtained from the fetus present in “left”, “center”, “right” in the images show the above-mentioned geometrical relationship. These results indicate that the estimated fetal position coincides with the actual position very well, which can be used as the first step for automatic fetal examination by robotic systems.

AB - In this paper, we propose an automatic method for estimating fetal position based on classification and detection of different fetal parts in ultrasound images. Fine tuning is performed in the ultrasound images to be used for fetal examination using CNN, and classification of four classes "head", "body", "leg" and "other" is realized. Based on the obtained learning result, binarization that thresholds the gradient of the feature obtained by Grad Cam is performed in the image so that a bounding box of the region of interest with large gradient is extracted. The center of the bounding box is obtained from each frame so that the trajectory of the centroids is obtained; the position of the fetus is obtained as the trajectory. Experiments using 2000 images were conducted using a fetal phantom. Each recall ratiso of the four class is 99.6% for head, 99.4% for body, 99.8% for legs, 72.6% for others, respectively. The trajectories obtained from the fetus present in “left”, “center”, “right” in the images show the above-mentioned geometrical relationship. These results indicate that the estimated fetal position coincides with the actual position very well, which can be used as the first step for automatic fetal examination by robotic systems.

KW - Deep Leaning

KW - Fetal

KW - Fetal Position

KW - Grad_CAM

KW - Ultrasound Image

UR - http://www.scopus.com/inward/record.url?scp=85064628907&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064628907&partnerID=8YFLogxK

M3 - Conference contribution

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

SP - 181

EP - 189

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 -