A Novel Meibomian Gland Morphology Analytic System Based on a Convolutional Neural Network
Meibomian glands dysfunction (MGD) is the main cause of dry eyes. Biological parameters of meibomian gland (MG) such as height, tortuosity and the degree of atrophy are closely related to its function. However, Thus, an effective quantitative diagnostic tool is needed for clinical diagnosis. Automat...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9343837/ |
| _version_ | 1818725420987580416 |
|---|---|
| author | Qi Dai Xinyi Liu Xiaolei Lin Yana Fu Chaoqiao Chen Xinxin Yu Zuhui Zhang Tiankun Li Mengting Liu Weihua Yang Juan Ye |
| author_facet | Qi Dai Xinyi Liu Xiaolei Lin Yana Fu Chaoqiao Chen Xinxin Yu Zuhui Zhang Tiankun Li Mengting Liu Weihua Yang Juan Ye |
| author_sort | Qi Dai |
| collection | DOAJ |
| description | Meibomian glands dysfunction (MGD) is the main cause of dry eyes. Biological parameters of meibomian gland (MG) such as height, tortuosity and the degree of atrophy are closely related to its function. However, Thus, an effective quantitative diagnostic tool is needed for clinical diagnosis. Automatic quantification of MGs' morphological features could be a challenging task and play an important role in MGD diagnosis and classification. Our main objective is to develop an artificial intelligence (AI) system for evaluating MGs' morphology and explore the relationship between the morphological parameters and functions. We proposed a novel MGs extraction method based on convolutional neural network (CNN) with enhanced mini U-Net. A prospective study was conducted, 120 subjects were included and taken meibography. The training and validation sets encompassed 60 subjects; and the test set consisted of other 60 subjects with comprehensive examinations for ocular surface disease index questionnaire (OSDI), tear meniscus height (TMH), tear break-up time (TBUT), corneal fluorescein staining (CFS), lid margin score, and meibum expressibility score. The algorithm effectively extracted MGs from meibography even with this small training sample. As a result, while the intersection over union (IoU) achieved 0.9077, the repeatability was 100%. The processing time for each image was 100ms. Using this method, the investigators identified a significant and linear correlation between MG morphology and clinical parameters. This study provided a new method for quantification of MGs' morphological features obtained by meibography, which has advantages in reducing analysis time, improving diagnostic efficiency, and assisting ophthalmologists with limited clinical expertise. |
| first_indexed | 2024-12-17T21:42:02Z |
| format | Article |
| id | doaj.art-326d70605a9144feb9988cfc7f845632 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T21:42:02Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-326d70605a9144feb9988cfc7f8456322022-12-21T21:31:34ZengIEEEIEEE Access2169-35362021-01-019230832309410.1109/ACCESS.2021.30562349343837A Novel Meibomian Gland Morphology Analytic System Based on a Convolutional Neural NetworkQi Dai0https://orcid.org/0000-0002-9950-6161Xinyi Liu1Xiaolei Lin2Yana Fu3Chaoqiao Chen4Xinxin Yu5Zuhui Zhang6Tiankun Li7Mengting Liu8Weihua Yang9Juan Ye10https://orcid.org/0000-0002-1948-2500Department of Ophthalmology, School of Medicine, Second Affiliated Hospital, Zhejiang University, Hangzhou, ChinaSchool of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, ChinaDepartment of Ophthalmology and Visual Science, Eye, Ear, Nose, and Throat Hospital, Shanghai Medical College, Fudan University, Shanghai, ChinaSchool of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, ChinaSchool of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, ChinaSchool of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, ChinaSchool of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, ChinaSchool of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, ChinaSchool of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, ChinaAffiliated Eye Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Ophthalmology, School of Medicine, Second Affiliated Hospital, Zhejiang University, Hangzhou, ChinaMeibomian glands dysfunction (MGD) is the main cause of dry eyes. Biological parameters of meibomian gland (MG) such as height, tortuosity and the degree of atrophy are closely related to its function. However, Thus, an effective quantitative diagnostic tool is needed for clinical diagnosis. Automatic quantification of MGs' morphological features could be a challenging task and play an important role in MGD diagnosis and classification. Our main objective is to develop an artificial intelligence (AI) system for evaluating MGs' morphology and explore the relationship between the morphological parameters and functions. We proposed a novel MGs extraction method based on convolutional neural network (CNN) with enhanced mini U-Net. A prospective study was conducted, 120 subjects were included and taken meibography. The training and validation sets encompassed 60 subjects; and the test set consisted of other 60 subjects with comprehensive examinations for ocular surface disease index questionnaire (OSDI), tear meniscus height (TMH), tear break-up time (TBUT), corneal fluorescein staining (CFS), lid margin score, and meibum expressibility score. The algorithm effectively extracted MGs from meibography even with this small training sample. As a result, while the intersection over union (IoU) achieved 0.9077, the repeatability was 100%. The processing time for each image was 100ms. Using this method, the investigators identified a significant and linear correlation between MG morphology and clinical parameters. This study provided a new method for quantification of MGs' morphological features obtained by meibography, which has advantages in reducing analysis time, improving diagnostic efficiency, and assisting ophthalmologists with limited clinical expertise.https://ieeexplore.ieee.org/document/9343837/Deep learningconvolutional neural network (CNN)meibomian gland dysfunction (MGD)meibography |
| spellingShingle | Qi Dai Xinyi Liu Xiaolei Lin Yana Fu Chaoqiao Chen Xinxin Yu Zuhui Zhang Tiankun Li Mengting Liu Weihua Yang Juan Ye A Novel Meibomian Gland Morphology Analytic System Based on a Convolutional Neural Network IEEE Access Deep learning convolutional neural network (CNN) meibomian gland dysfunction (MGD) meibography |
| title | A Novel Meibomian Gland Morphology Analytic System Based on a Convolutional Neural Network |
| title_full | A Novel Meibomian Gland Morphology Analytic System Based on a Convolutional Neural Network |
| title_fullStr | A Novel Meibomian Gland Morphology Analytic System Based on a Convolutional Neural Network |
| title_full_unstemmed | A Novel Meibomian Gland Morphology Analytic System Based on a Convolutional Neural Network |
| title_short | A Novel Meibomian Gland Morphology Analytic System Based on a Convolutional Neural Network |
| title_sort | novel meibomian gland morphology analytic system based on a convolutional neural network |
| topic | Deep learning convolutional neural network (CNN) meibomian gland dysfunction (MGD) meibography |
| url | https://ieeexplore.ieee.org/document/9343837/ |
| work_keys_str_mv | AT qidai anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT xinyiliu anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT xiaoleilin anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT yanafu anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT chaoqiaochen anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT xinxinyu anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT zuhuizhang anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT tiankunli anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT mengtingliu anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT weihuayang anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT juanye anovelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT qidai novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT xinyiliu novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT xiaoleilin novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT yanafu novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT chaoqiaochen novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT xinxinyu novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT zuhuizhang novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT tiankunli novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT mengtingliu novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT weihuayang novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork AT juanye novelmeibomianglandmorphologyanalyticsystembasedonaconvolutionalneuralnetwork |