Data Augmentation for a Deep Learning Framework for Ventricular Septal Defect Ultrasound Image Classification

doi:10.1007/978-3-030-68799-1_22

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 會議論文 > Item 987654321/121525

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/121525

Title:	Data Augmentation for a Deep Learning Framework for Ventricular Septal Defect Ultrasound Image Classification
Authors:	Chen, Shih-Hsin;Tai, I-Hsin;Chen, Yi-Hui;Weng, Ken-Pen;Hsieh, Kai-Sheng
Keywords:	Ventricular septal defect (VSD);Echo;Deep learning;Classification;Data augmentation
Date:	2021-01-10
Issue Date:	2021-10-20 12:10:21 (UTC+8)
Abstract:	Congenital heart diseases (CHD) can be detected through ultrasound imaging. Although ultrasound can be used for immediate diagnosis, doctors require considerable time to read dynamic clips; typically, physicians must continuously examine disease data from beating heart images. Most importantly, this type of diagnosis relies heavily on the expertise and experience of the diagnosing physician. This study established an ultrasound image classification with deep learning algorithms to overcome the challenges involved in CHD diagnosis. We detected the most common CHD, namely the first, second, and fourth types of ventricular septal defect (VSD). We improved the performance levels of well-known deep learning algorithms (InceptionV3, ResNet, and DenseNet). Because algorithm optimization and overfitting problems can influence the performance of deep learning algorithms, we studied some optimizer algorithms and early-stopping strategies. To enhance the solution quality, we used data augmentation methods for solving this classification problem. The selected approach was further compared with Google AutoML, which applies structure search for quality prediction. Our results revealed that the proposed deep learning algorithm was able to recognize most types of VSD. However, one type of VSD remains unconquered and warrants more advanced techniques.
Relation:	Pattern Recognition. ICPR International Workshops and Challenges, p.310-322
DOI:	10.1007/978-3-030-68799-1_22
Appears in Collections:	[資訊工程學系暨研究所] 會議論文

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	44	View/Open

Loading...