Cargando…

Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information

Image segmentation is the pixel-by-pixel detection of objects, which is the most challenging but informative in the fundamental tasks of machine learning including image classification and object detection. Pixel-by-pixel segmentation is required to apply machine learning to support fetal cardiac ul...

Descripción completa

Detalles Bibliográficos
Autores principales: Dozen, Ai, Komatsu, Masaaki, Sakai, Akira, Komatsu, Reina, Shozu, Kanto, Machino, Hidenori, Yasutomi, Suguru, Arakaki, Tatsuya, Asada, Ken, Kaneko, Syuzo, Matsuoka, Ryu, Aoki, Daisuke, Sekizawa, Akihiko, Hamamoto, Ryuji
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7695246/
https://www.ncbi.nlm.nih.gov/pubmed/33171658
http://dx.doi.org/10.3390/biom10111526
_version_ 1783615144335507456
author Dozen, Ai
Komatsu, Masaaki
Sakai, Akira
Komatsu, Reina
Shozu, Kanto
Machino, Hidenori
Yasutomi, Suguru
Arakaki, Tatsuya
Asada, Ken
Kaneko, Syuzo
Matsuoka, Ryu
Aoki, Daisuke
Sekizawa, Akihiko
Hamamoto, Ryuji
author_facet Dozen, Ai
Komatsu, Masaaki
Sakai, Akira
Komatsu, Reina
Shozu, Kanto
Machino, Hidenori
Yasutomi, Suguru
Arakaki, Tatsuya
Asada, Ken
Kaneko, Syuzo
Matsuoka, Ryu
Aoki, Daisuke
Sekizawa, Akihiko
Hamamoto, Ryuji
author_sort Dozen, Ai
collection PubMed
description Image segmentation is the pixel-by-pixel detection of objects, which is the most challenging but informative in the fundamental tasks of machine learning including image classification and object detection. Pixel-by-pixel segmentation is required to apply machine learning to support fetal cardiac ultrasound screening; we have to detect cardiac substructures precisely which are small and change shapes dynamically with fetal heartbeats, such as the ventricular septum. This task is difficult for general segmentation methods such as DeepLab v3+, and U-net. Hence, here we proposed a novel segmentation method named Cropping-Segmentation-Calibration (CSC) that is specific to the ventricular septum in ultrasound videos in this study. CSC employs the time-series information of videos and specific section information to calibrate the output of U-net. The actual sections of the ventricular septum were annotated in 615 frames from 421 normal fetal cardiac ultrasound videos of 211 pregnant women who were screened. The dataset was assigned a ratio of 2:1, which corresponded to a ratio of the training to test data, and three-fold cross-validation was conducted. The segmentation results of DeepLab v3+, U-net, and CSC were evaluated using the values of the mean intersection over union (mIoU), which were 0.0224, 0.1519, and 0.5543, respectively. The results reveal the superior performance of CSC.
format Online
Article
Text
id pubmed-7695246
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-76952462020-11-28 Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information Dozen, Ai Komatsu, Masaaki Sakai, Akira Komatsu, Reina Shozu, Kanto Machino, Hidenori Yasutomi, Suguru Arakaki, Tatsuya Asada, Ken Kaneko, Syuzo Matsuoka, Ryu Aoki, Daisuke Sekizawa, Akihiko Hamamoto, Ryuji Biomolecules Article Image segmentation is the pixel-by-pixel detection of objects, which is the most challenging but informative in the fundamental tasks of machine learning including image classification and object detection. Pixel-by-pixel segmentation is required to apply machine learning to support fetal cardiac ultrasound screening; we have to detect cardiac substructures precisely which are small and change shapes dynamically with fetal heartbeats, such as the ventricular septum. This task is difficult for general segmentation methods such as DeepLab v3+, and U-net. Hence, here we proposed a novel segmentation method named Cropping-Segmentation-Calibration (CSC) that is specific to the ventricular septum in ultrasound videos in this study. CSC employs the time-series information of videos and specific section information to calibrate the output of U-net. The actual sections of the ventricular septum were annotated in 615 frames from 421 normal fetal cardiac ultrasound videos of 211 pregnant women who were screened. The dataset was assigned a ratio of 2:1, which corresponded to a ratio of the training to test data, and three-fold cross-validation was conducted. The segmentation results of DeepLab v3+, U-net, and CSC were evaluated using the values of the mean intersection over union (mIoU), which were 0.0224, 0.1519, and 0.5543, respectively. The results reveal the superior performance of CSC. MDPI 2020-11-08 /pmc/articles/PMC7695246/ /pubmed/33171658 http://dx.doi.org/10.3390/biom10111526 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Dozen, Ai
Komatsu, Masaaki
Sakai, Akira
Komatsu, Reina
Shozu, Kanto
Machino, Hidenori
Yasutomi, Suguru
Arakaki, Tatsuya
Asada, Ken
Kaneko, Syuzo
Matsuoka, Ryu
Aoki, Daisuke
Sekizawa, Akihiko
Hamamoto, Ryuji
Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information
title Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information
title_full Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information
title_fullStr Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information
title_full_unstemmed Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information
title_short Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information
title_sort image segmentation of the ventricular septum in fetal cardiac ultrasound videos based on deep learning using time-series information
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7695246/
https://www.ncbi.nlm.nih.gov/pubmed/33171658
http://dx.doi.org/10.3390/biom10111526
work_keys_str_mv AT dozenai imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT komatsumasaaki imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT sakaiakira imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT komatsureina imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT shozukanto imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT machinohidenori imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT yasutomisuguru imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT arakakitatsuya imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT asadaken imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT kanekosyuzo imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT matsuokaryu imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT aokidaisuke imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT sekizawaakihiko imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation
AT hamamotoryuji imagesegmentationoftheventricularseptuminfetalcardiacultrasoundvideosbasedondeeplearningusingtimeseriesinformation