Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information
Autor: | Akira Sakai, Reina Komatsu, Ryu Matsuoka, Suguru Yasutomi, Daisuke Aoki, Syuzo Kaneko, Kanto Shozu, Ken Asada, Ai Dozen, Ryuji Hamamoto, Hidenori Machino, Akihiko Sekizawa, Tatsuya Arakaki, Masaaki Komatsu |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
Time Factors
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION lcsh:QR1-502 030204 cardiovascular system & hematology Biochemistry Article lcsh:Microbiology 030218 nuclear medicine & medical imaging 03 medical and health sciences Fetus 0302 clinical medicine Intersection Pregnancy Image Processing Computer-Assisted Humans Segmentation Molecular Biology ComputingMethodologies_COMPUTERGRAPHICS Ultrasonography Contextual image classification business.industry Deep learning Ultrasound segmentation deep learning Pattern recognition Image segmentation equipment and supplies congenital heart disease eye diseases Object detection body regions fetal cardiac ultrasound video ventricular septum cardiovascular system Female sense organs Artificial intelligence business Test data |
Zdroj: | Biomolecules, Vol 10, Iss 1526, p 1526 (2020) Biomolecules Volume 10 Issue 11 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |