國家衛生研究院 NHRI:Item 3990099045/13723

NHRI > National Institute of Environmental Health Sciences > Yue-Liang Guo > Periodical Articles > Item 3990099045/13723

Please use this identifier to cite or link to this item: http://ir.nhri.org.tw/handle/3990099045/13723

Title:	Lumbar disc herniation automatic detection in magnetic resonance imaging based on deep learning
Authors:	Tsai, JY;Hung, IYJ;Guo, YL;Jan, YK;Lin, CY;Shih, TTF;Chen, BB;Lung, CW
Contributors:	National Institute of Environmental Health Sciences
Abstract:	Background: Lumbar disc herniation (LDH) is among the most common causes of lower back pain and sciatica. The causes of LDH have not been fully elucidated but most likely involve a complex combination of mechanical and biological processes. Magnetic resonance imaging (MRI) is a tool most frequently used for LDH because it can show abnormal soft tissue areas around the spine. Deep learning models may be trained to recognize images with high speed and accuracy to diagnose LDH. Although the deep learning model requires huge numbers of image datasets to train and establish the best model, this study processed enhanced medical image features for training the small-scale deep learning dataset. Methods: We propose automatic detection to assist the initial LDH exam for lower back pain. The subjects were between 20 and 65 years old with at least 6 months of work experience. The deep learning method employed the YOLOv3 model to train and detect small object changes such as LDH on MRI. The dataset images were processed and combined with labeling and annotation from the radiologist’s diagnosis record. Results: Our method proves the possibility of using deep learning with a small-scale dataset with limited medical images. The highest mean average precision (mAP) was 92.4% at 550 images with data augmentation (550-aug), and the YOLOv3 LDH training was 100% with the best average precision at 550-aug among all datasets. This study used data augmentation to prevent under- or overfitting in an object detection model that was trained with the small-scale dataset. Conclusions: The data augmentation technique plays a crucial role in YOLOv3 training and detection results. This method displays a high possibility for rapid initial tests and auto-detection for a limited clinical dataset.
Date:	2021-08-19
Relation:	Frontiers in Bioengineering and Biotechnology. 2021 Aug 19;9:Article number 708137.
Link to:	http://dx.doi.org/10.3389/fbioe.2021.708137
JIF/Ranking 2023:	http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=NHRI&SrcApp=NHRI_IR&KeyISSN=2296-4185&DestApp=IC2JCR
Cited Times(WOS):	https://www.webofscience.com/wos/woscc/full-record/WOS:000693832800001
Cited Times(Scopus):	https://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85114311258
Appears in Collections:	[Yue-Liang Guo] Periodical Articles

Files in This Item:

File	Description	Size	Format
SCP85114311258.pdf		1295Kb	Adobe PDF	639	View/Open

Loading...