Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks
Computed tomography (CT) imaging of the orbit with measurement of extraocular muscle size can be useful for diagnosing and monitoring conditions that affect extraocular muscles. However, the manual measurement of extraocular muscle size can be time-consuming and tedious. The purpose of this study is...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/7/1553 |
| _version_ | 1797440070695780352 |
|---|---|
| author | Ramkumar Rajabathar Babu Jai Shanker Michael H. Zhang Daniel T. Ginat |
| author_facet | Ramkumar Rajabathar Babu Jai Shanker Michael H. Zhang Daniel T. Ginat |
| author_sort | Ramkumar Rajabathar Babu Jai Shanker |
| collection | DOAJ |
| description | Computed tomography (CT) imaging of the orbit with measurement of extraocular muscle size can be useful for diagnosing and monitoring conditions that affect extraocular muscles. However, the manual measurement of extraocular muscle size can be time-consuming and tedious. The purpose of this study is to evaluate the effectiveness of deep learning algorithms in segmenting extraocular muscles and measuring muscle sizes from CT images. Consecutive CT scans of orbits from 210 patients between 1 January 2010 and 31 December 2019 were used. Extraocular muscles were manually annotated in the studies, which were then used to train the deep learning algorithms. The proposed U-net algorithm can segment extraocular muscles on coronal slices of 32 test samples with an average dice score of 0.92. The thickness and area measurements from predicted segmentations had a mean absolute error (MAE) of 0.35 mm and 3.87 mm<sup>2</sup>, respectively, with a corresponding mean absolute percentage error (MAPE) of 7 and 9%, respectively. On qualitative analysis of 32 test samples, 30 predicted segmentations from the U-net algorithm were accepted while 2 were rejected. Based on the results from quantitative and qualitative evaluation, this study demonstrates that CNN-based deep learning algorithms are effective at segmenting extraocular muscles and measuring muscles sizes. |
| first_indexed | 2024-03-09T12:01:46Z |
| format | Article |
| id | doaj.art-8283ef60c6924185802aa1b24d447857 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T12:01:46Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-8283ef60c6924185802aa1b24d4478572023-11-30T23:02:41ZengMDPI AGDiagnostics2075-44182022-06-01127155310.3390/diagnostics12071553Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural NetworksRamkumar Rajabathar Babu Jai Shanker0Michael H. Zhang1Daniel T. Ginat2Department of Radiology, University of Chicago, Chicago, IL 60615, USADepartment of Radiology, University of Chicago, Chicago, IL 60615, USADepartment of Radiology, Section of Neuroradiology, University of Chicago, Chicago, IL 60615, USAComputed tomography (CT) imaging of the orbit with measurement of extraocular muscle size can be useful for diagnosing and monitoring conditions that affect extraocular muscles. However, the manual measurement of extraocular muscle size can be time-consuming and tedious. The purpose of this study is to evaluate the effectiveness of deep learning algorithms in segmenting extraocular muscles and measuring muscle sizes from CT images. Consecutive CT scans of orbits from 210 patients between 1 January 2010 and 31 December 2019 were used. Extraocular muscles were manually annotated in the studies, which were then used to train the deep learning algorithms. The proposed U-net algorithm can segment extraocular muscles on coronal slices of 32 test samples with an average dice score of 0.92. The thickness and area measurements from predicted segmentations had a mean absolute error (MAE) of 0.35 mm and 3.87 mm<sup>2</sup>, respectively, with a corresponding mean absolute percentage error (MAPE) of 7 and 9%, respectively. On qualitative analysis of 32 test samples, 30 predicted segmentations from the U-net algorithm were accepted while 2 were rejected. Based on the results from quantitative and qualitative evaluation, this study demonstrates that CNN-based deep learning algorithms are effective at segmenting extraocular muscles and measuring muscles sizes.https://www.mdpi.com/2075-4418/12/7/1553CTsemantic segmentationextraocular musclesdeep learningconvolutional neural networksdice coefficient |
| spellingShingle | Ramkumar Rajabathar Babu Jai Shanker Michael H. Zhang Daniel T. Ginat Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks Diagnostics CT semantic segmentation extraocular muscles deep learning convolutional neural networks dice coefficient |
| title | Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks |
| title_full | Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks |
| title_fullStr | Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks |
| title_full_unstemmed | Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks |
| title_short | Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks |
| title_sort | semantic segmentation of extraocular muscles on computed tomography images using convolutional neural networks |
| topic | CT semantic segmentation extraocular muscles deep learning convolutional neural networks dice coefficient |
| url | https://www.mdpi.com/2075-4418/12/7/1553 |
| work_keys_str_mv | AT ramkumarrajabatharbabujaishanker semanticsegmentationofextraocularmusclesoncomputedtomographyimagesusingconvolutionalneuralnetworks AT michaelhzhang semanticsegmentationofextraocularmusclesoncomputedtomographyimagesusingconvolutionalneuralnetworks AT danieltginat semanticsegmentationofextraocularmusclesoncomputedtomographyimagesusingconvolutionalneuralnetworks |