Dataset Information

Deep Learning-based Quantification of Anterior Segment OCT Parameters.

ABSTRACT:

Objective

To develop and validate a deep learning algorithm that could automate the annotation of scleral spur (SS) and segmentation of anterior chamber (AC) structures for measurements of AC, iris, and angle width parameters in anterior segment OCT (ASOCT) scans.

Design

Cross-sectional study.

Subjects

Data from 2 population-based studies (i.e., the Singapore Chinese Eye Study and Singapore Malay Eye Study) and 1 clinical study on angle-closure disease were included in algorithm development. A separate clinical study on angle-closure disease was used for external validation.

Method

Image contrast of ASOCT scans were first enhanced with CycleGAN. We utilized a heat map regression approach with coarse-to-fine framework for SS annotation. Then, an ensemble network of U-Net, full resolution residual network, and full resolution U-Net was used for structure segmentation. Measurements obtained from predicted SSs and structure segmentation were measured and compared with measurements obtained from manual SS annotation and structure segmentation (i.e., ground truth).

Main outcome measures

We measured Euclidean distance and intraclass correlation coefficients (ICC) to evaluate SS annotation and Dice similarity coefficient for structure segmentation. The ICC, Bland-Altman plot, and repeatability coefficient were used to evaluate agreement and precision of measurements.

Results

For SS annotation, our algorithm achieved a Euclidean distance of 124.7 μm, ICC ≥ 0.95, and a 3.3% error rate. For structure segmentation, we obtained Dice similarity coefficient ≥ 0.91 for cornea, iris, and AC segmentation. For angle width measurements, ≥ 95% of data points were within the 95% limits-of-agreement in Bland-Altman plot with insignificant systematic bias (all P > 0.12). The ICC ranged from 0.71-0.87 for angle width measurements, 0.54 for IT750, 0.83-0.85 for other iris measurements, and 0.89-0.99 for AC measurements. Using the same SS coordinates from a human expert, measurements obtained from our algorithm were generally less variable than measurements obtained from a semiautomated angle assessment program.

Conclusion

We developed a deep learning algorithm that could automate SS annotation and structure segmentation in ASOCT scans like human experts, in both open-angle and angle-closure eyes. This algorithm reduces the time needed and subjectivity in obtaining ASOCT measurements.

Financial disclosures

The author(s) have no proprietary or commercial interest in any materials discussed in this article.

SUBMITTER: Soh ZD

PROVIDER: S-EPMC10587633 | biostudies-literature | 2024 Jan-Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning-based Quantification of Anterior Segment OCT Parameters.

Soh Zhi Da ZD Tan Mingrui M Nongpiur Monisha Esther ME Yu Marco M Qian Chaoxu C Tham Yih Chung YC Koh Victor V Aung Tin T Xu Xinxing X Liu Yong Y Cheng Ching-Yu CY

Ophthalmology science 20230703 1

<h4>Objective</h4>To develop and validate a deep learning algorithm that could automate the annotation of scleral spur (SS) and segmentation of anterior chamber (AC) structures for measurements of AC, iris, and angle width parameters in anterior segment OCT (ASOCT) scans.<h4>Design</h4>Cross-sectional study.<h4>Subjects</h4>Data from 2 population-based studies (i.e., the Singapore Chinese Eye Study and Singapore Malay Eye Study) and 1 clinical study on angle-closure disease were included in algo ...[more]

PMID: 37869016

Similar Datasets

Project description:PURPOSE:To develop and test deep learning classifiers that detect gonioscopic angle closure and primary angle closure disease (PACD) based on fully automated analysis of anterior segment OCT (AS-OCT) images. METHODS:Subjects were recruited as part of the Chinese-American Eye Study (CHES), a population-based study of Chinese Americans in Los Angeles, California, USA. Each subject underwent a complete ocular examination including gonioscopy and AS-OCT imaging in each quadrant of the anterior chamber angle (ACA). Deep learning methods were used to develop 3 competing multi-class convolutional neural network (CNN) classifiers for modified Shaffer grades 0, 1, 2, 3, and 4. Binary probabilities for closed (grades 0 and 1) and open (grades 2, 3, and 4) angles were calculated by summing over the corresponding grades. Classifier performance was evaluated by 5-fold cross-validation and on an independent test dataset. Outcome measures included area under the receiver operating characteristic curve (AUC) for detecting gonioscopic angle closure and PACD, defined as either 2 or 3 quadrants of gonioscopic angle closure per eye. RESULTS:A total of 4036 AS-OCT images with corresponding gonioscopy grades (1943 open, 2093 closed) were obtained from 791 CHES subjects. Three competing CNN classifiers were developed with a cross-validation dataset of 3396 images (1632 open, 1764 closed) from 664 subjects. The remaining 640 images (311 open, 329 closed) from 127 subjects were segregated into a test dataset. The best-performing classifier was developed by applying transfer learning to the ResNet-18 architecture. For detecting gonioscopic angle closure, this classifier achieved an AUC of 0.933 (95% confidence interval, 0.925-0.941) on the cross-validation dataset and 0.928 on the test dataset. For detecting PACD based on 2- and 3-quadrant definitions, the ResNet-18 classifier achieved AUCs of 0.964 and 0.952, respectively, on the test dataset. CONCLUSION:Deep learning classifiers effectively detect gonioscopic angle closure and PACD based on automated analysis of AS-OCT images. These methods could be used to automate clinical evaluations of the ACA and improve access to eye care in high-risk populations.

Project description:PurposeTo assess the effects of age and refractive status on anterior segment anatomical structures, including the ciliary body, using a new swept-source anterior segment optical coherence tomography (AS-OCT) device.MethodsThis prospective observational study included 63 healthy volunteers (mean age: 44.2 years). Images of the anterior segment were obtained using a new swept-source AS-OCT (ANTERION, Heidelberg Engineering GmbH, Heidelberg, Germany) with tracking and image averaging from the right eye of all participants. Repeatability as well as inter- and intra-observer reliability of biometric measurements were evaluated. The impact of image tracking and averaging on ciliary muscle measurements was tested. Univariate and multivariable statistical models were developed to evaluate the relationship of age and refractive status on anterior segment biometric measurements.ResultsFor all test-retest repeatability and inter- and intra-observer reproducibility of swept-source AS-OCT measurements, high intraclass correlation (ICC) was noted (0.88-1.00). The nasal maximum ciliary muscle thickness (CMTMAX) and distance between scleral spur to the thickest point of the ciliary muscle (SSMAX) were larger than those on the temporal side (p<0.001 and p = 0.006, respectively). Nasal and temporal CMTMAX (p = 0.004 and p<0.001, respectively) and lens thickness (p<0.01) increased with age. Nasal and temporal SSMAX decreased with older age and increasing hyperopia (p = 0.01 and p<0.001, respectively). Image averaging resulted in improved ciliary muscle measurements (p = 0.008 to 0.02). Lens vault increased with older age and increased hyperopia (p<0.01). OCT measurements of the angle decreased with older age and increased hyperopia (p<0.001 to 0.03). Aqueous depth decreased with older age and increased hyperopia (p<0.01). Pupil diameter decreased with older age (p<0.01).ConclusionsRepeatability and reproducibility of biometric measurements using the ANTERION AS-OCT were excellent. Image averaging improved the accuracy of ciliary muscle measurements. The device produced measurements of biometric parameters that described superficial and deep structures including the ciliary body and full lens thickness from a single image.

Project description:PurposeTo develop a deep learning (DL) algorithm for predicting anterior chamber depth (ACD) from smartphone-acquired anterior segment photographs.MethodsFor algorithm development, we included 4,157 eyes from 2,084 Chinese primary school students (aged 11-15 years) from Mojiang Myopia Progression Study (MMPS). All participants had with ACD measurement measured with Lenstar (LS 900) and anterior segment photographs acquired from a smartphone (iPhone Xs), which was mounted on slit lamp and under diffuses lighting. The anterior segment photographs were randomly selected by person into training (80%, no. of eyes = 3,326) and testing (20%, no. of eyes = 831) dataset. We excluded participants with intraocular surgery history or pronounced corneal haze. A convolutional neural network was developed to predict ACD based on these anterior segment photographs. To determine the accuracy of our algorithm, we measured the mean absolute error (MAE) and coefficient of determination (R 2) were evaluated. Bland Altman plot was used to illustrate the agreement between DL-predicted and measured ACD values.ResultsIn the test set of 831 eyes, the mean measured ACD was 3.06 ± 0.25 mm, and the mean DL-predicted ACD was 3.10 ± 0.20 mm. The MAE was 0.16 ± 0.13 mm, and R 2 was 0.40 between the predicted and measured ACD. The overall mean difference was -0.04 ± 0.20 mm, with 95% limits of agreement ranging between -0.43 and 0.34 mm. The generated saliency maps showed that the algorithm mainly utilized central corneal region (i.e., the site where ACD is clinically measured typically) in making its prediction, providing further plausibility to the algorithm's prediction.ConclusionsWe developed a DL algorithm to estimate ACD based on smartphone-acquired anterior segment photographs. Upon further validation, our algorithm may be further refined for use as a ACD screening tool in rural localities where means of assessing ocular biometry is not readily available. This is particularly important in China where the risk of primary angle closure disease is high and often undetected.

Dataset Information

Deep Learning-based Quantification of Anterior Segment OCT Parameters.

Objective

Design

Subjects

Method

Main outcome measures

Results

Conclusion

Financial disclosures

Publications

Deep Learning-based Quantification of Anterior Segment OCT Parameters.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets