Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning
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...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/18/3849 |
| _version_ | 1811323854687043584 |
|---|---|
| author | Hiroyuki Sugimori Masashi Kawakami |
| author_facet | Hiroyuki Sugimori Masashi Kawakami |
| author_sort | Hiroyuki Sugimori |
| collection | DOAJ |
| description | 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 × 64 pixels and 32 × 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 × 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 × 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. |
| first_indexed | 2024-04-13T14:04:02Z |
| format | Article |
| id | doaj.art-179f0214eb154371a127e706645f0332 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-13T14:04:02Z |
| publishDate | 2019-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-179f0214eb154371a127e706645f03322022-12-22T02:43:58ZengMDPI AGApplied Sciences2076-34172019-09-01918384910.3390/app9183849app9183849Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep LearningHiroyuki Sugimori0Masashi Kawakami1Faculty of Health Sciences, Hokkaido University, Sapporo 060-0812, JapanGraduate School of Biomedical Science and Engineering, School of Medicine, Hokkaido University, Sapporo 060-0812, JapanRecently, 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 × 64 pixels and 32 × 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 × 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 × 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.https://www.mdpi.com/2076-3417/9/18/3849object detectionstandard line for brainfaster R-CNNmedical image analysismagnetic resonance imaging |
| spellingShingle | Hiroyuki Sugimori Masashi Kawakami Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning Applied Sciences object detection standard line for brain faster R-CNN medical image analysis magnetic resonance imaging |
| title | Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning |
| title_full | Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning |
| title_fullStr | Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning |
| title_full_unstemmed | Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning |
| title_short | Automatic Detection of a Standard Line for Brain Magnetic Resonance Imaging Using Deep Learning |
| title_sort | automatic detection of a standard line for brain magnetic resonance imaging using deep learning |
| topic | object detection standard line for brain faster R-CNN medical image analysis magnetic resonance imaging |
| url | https://www.mdpi.com/2076-3417/9/18/3849 |
| work_keys_str_mv | AT hiroyukisugimori automaticdetectionofastandardlineforbrainmagneticresonanceimagingusingdeeplearning AT masashikawakami automaticdetectionofastandardlineforbrainmagneticresonanceimagingusingdeeplearning |