Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Health Sciences / Faculty of Health Sciences >
Peer-reviewed Journal Articles, etc >
Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning
This item is licensed under:Creative Commons Attribution 4.0 International
Title: | Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning |
Authors: | Sugimori, Hiroyuki Browse this author →KAKEN DB | Kawakami, Masashi Browse this author |
Keywords: | object detection | standard line for brain | faster R-CNN | medical image analysis | magnetic resonance imaging |
Issue Date: | 13-Sep-2019 |
Publisher: | MDPI |
Journal Title: | Applied sciences |
Volume: | 9 |
Issue: | 18 |
Start Page: | 3849 |
Publisher DOI: | 10.3390/app9183849 |
Abstract: | Recently, deep learning technology has been applied to medical images. This study aimed to create a detector able to automatically detect an anatomical structure presented in a brain magnetic resonance imaging (MRI) scan to draw a standard line. A total of 1200 brain sagittal MRI scans were used for training and validation. Two sizes of regions of interest (ROIs) were drawn on each anatomical structure measuring 64 x 64 pixels and 32 x 32 pixels, respectively. Data augmentation was applied to these ROIs. The faster region-based convolutional neural network was used as the network model for training. The detectors created were validated to evaluate the precision of detection. Anatomical structures detected by the model created were processed to draw the standard line. The average precision of anatomical detection, detection rate of the standard line, and accuracy rate of achieving a correct drawing were evaluated. For the 64 x 64-pixel ROI, the mean average precision achieved a result of 0.76 +/- 0.04, which was higher than the outcome achieved with the 32 x 32-pixel ROI. Moreover, the detection and accuracy rates of the angle of difference at 10 degrees for the orbitomeatal line were 93.3 +/- 5.2 and 76.7 +/- 11.0, respectively. The automatic detection of a reference line for brain MRI can help technologists improve this examination. |
Rights: | © 2019 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 License (http://creativecommons.org/licenses/by/4.0/). | https://creativecommons.org/licenses/by/4.0/ |
Type: | article |
URI: | http://hdl.handle.net/2115/76199 |
Appears in Collections: | 保健科学院・保健科学研究院 (Graduate School of Health Sciences / Faculty of Health Sciences) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
Submitter: 杉森 博行
|