Automated segmentation of choroidal layers from 3-dimensional macular optical coherence tomography scans

Lee, Kyungmoo; Warren, Alexis K.; Abràmoff, Michael D.; Wahle, Andreas; Whitmore, S. Scott; Han, Ian C.; Fingert, John H.; Scheetz, Todd E.; Mullins, Robert F.; Sonka, Milan; Sohn, Elliott H.

doi:10.1016/j.jneumeth.2021.109267

Cited by 5 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average ChT in the test dataset composed of images with HM was 75.9±34.4 μm. As expected, the ChT was thinner than that reported in previous studies, as they had tended to focus on non-HM participants (38,39). By analyzing the difference of ICCs in the 9 regions, the ChT calculated in the outer nasal region was less consistent with the manual.…”

Section: Discussionsupporting

confidence: 40%

“…There are some studies that included the quantification of retinal features and ChT in AMD eyes (32)(33)(34), investigations on optic disc changes and their association with ChT in young myopic patients (35), and the use of algorithms to determine changes in ChT and volume of choroidal vessels (34,36,37). However, previous studies of automated ChT calculations were designed based on mostly non-HM eyes (38)(39)(40). Automated identification and calculation of ChT in HM eyes still warrant further study, and our team has research experience in this field (30,41).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Choroid automatic segmentation and thickness quantification on swept-source optical coherence tomography images of highly myopic patients

Li¹,

Zhou²,

Zou³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

Background: Thinning of the choroid has been linked with various ocular diseases, including high myopia (HM), which can lead to visual impairment. Although various artificial intelligence (AI) algorithms have been developed to quantify choroidal thickness (ChT), few patients with HM were included in their development.The choroid in patients with HM tends to be thinner than that of normal patients, making it harder to segment. Therefore, in this study, we aimed to develop and implement a novel deep learning algorithm based on a group-wise context selection network (GCS-Net) to automatically segment the choroid and quantify its thickness on swept-source optical coherence tomography (SS-OCT) images of HM patients.Methods: A total of 720 SS-OCT images were obtained from 40 HM eyes and 20 non-HM eyes and were used to develop a GCS-Net to segment the choroid. The intersection-over-union (IoU), Dice similarity coefficient (DSC), sensitivity, and specificity were used to assess the performance in relation to manually segmented ground truth. The independent test dataset included 3,192 images from 266 HM eyes. The ChT in the test dataset was measured manually and automatically at 9 different regions within the choroid. The average difference in the ChT between the 2 methods was calculated. The intraclass correlation coefficient (ICC) was calculated to evaluate the agreement between the 2 measurements.Results: Our method reached an IoU, DSC, sensitivity, and specificity of 87.89%, 93.40%, 92.42%, and 99.82% in HM, respectively. The average difference in the ChT between the 2 measurements was 5.54±4.57 μm. The ICC was above 0.90 (P<0.001) for all regions of the choroid, indicating a very high level of agreement. Conclusions:The GCS-Net proposed in our study provides a reliable and fast tool to quantify ChT in HM patients and could potentially be used as a tool for monitoring ChT in ocular diseases related to the choroid.

show abstract

Section: Discussionsupporting

confidence: 40%

Section: Discussionmentioning

confidence: 99%

Choroid automatic segmentation and thickness quantification on swept-source optical coherence tomography images of highly myopic patients

Li¹,

Zhou²,

Zou³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

show abstract

“…Deep learning approaches have achieved great success in OCT image segmentation tasks [19], [25], [32], [36], [41], [43], [48]. [47] developed a fully convolutional network with Gaussian process based post processing for retinal OCT segmentation.…”

Section: Related Workmentioning

confidence: 99%

Cardiac Adipose Tissue Segmentation via Image-Level Annotations

Huang

Gan

Lye

et al. 2023

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Automatically identifying the structural substrates underlying cardiac abnormalities can potentially provide real-time guidance for interventional procedures. With the knowledge of cardiac tissue substrates, the treatment of complex arrhythmias such as atrial fibrillation and ventricular tachycardia can be further optimized by detecting arrhythmia substrates to target for treatment (i.e., adipose) and identifying critical structures to avoid. Optical coherence tomography (OCT) is a real-time imaging modality that aids in addressing this need. Existing approaches for cardiac image analysis mainly rely on fully supervised learning techniques, which suffer from the drawback of workload on labor-intensive annotation process of pixelwise labeling. To lessen the need for pixel-wise labeling, we develop a two-stage deep learning framework for cardiac adipose tissue segmentation using image-level annotations on OCT images of human cardiac substrates. In particular, we integrate class activation mapping with superpixel segmentation to solve the sparse tissue seed challenge raised in cardiac tissue segmentation. Our study bridges the gap between the demand on automatic tissue analysis and the lack of high-quality pixel-wise annotations. To the best of our knowledge, this is the first study that attempts to address cardiac tissue segmentation on OCT images via weakly supervised learning techniques. Within an invitro human cardiac OCT dataset, we demonstrate that our weakly supervised approach on image-level annotations achieves comparable performance as fully supervised methods trained on pixel-wise annotations.

show abstract

“…[8][9][10][11] Several studies have analyzed the choroid layer using the B-scan image of OCT and arti cial intelligence. [22][23][24][25][26][27][28][29] However, OCT B-scan image shows a cross-sectional view of blood vessels at the one scan position. On the other hand, the en face OCT image, also known as C-scan image, provides a two-dimensional and plane view of the choroidal blood vessels in the scanned area.…”

Section: Introductionmentioning

confidence: 99%

Automated choroidal layer segmentation from en face swept-source optical coherence tomography images of normal eyes using machine learning

Lim

Yoon

Lee

et al. 2023

Preprint

View full text Add to dashboard Cite

The study aims to use machine learning in healthy eyes to develop an automated method to segment the choroidal layers of en-face swept-source optical coherence tomography (SS-OCT) images. We included 117 eyes of 117 healthy subjects who underwent an SS-OCT volume scan with a 12 x 9 mm range. SS-OCT en face images of the choroid were obtained every 2.6 µm from Bruch’s membrane (BM) to the chorioscleral border. The images at the start of the choriocapillaris, the onset of Sattler’s layer, and the beginning of Haller’s layer were identified, and the image numbers from the BM line were taken as the teacher data. Through the Boundary-Enhancing undersampling and sub-class ensemble learning, we obtained a balanced accuracy of 85.54% with an error range of 0 and 92.82% with an error range of 2. Automated stratification of the choroid in en- face SS-OCT images, including choroidal vessels outside the macula, can be done accurately through machine learning.

show abstract

Automated segmentation of choroidal layers from 3-dimensional macular optical coherence tomography scans

Cited by 5 publications

References 32 publications

Choroid automatic segmentation and thickness quantification on swept-source optical coherence tomography images of highly myopic patients

Choroid automatic segmentation and thickness quantification on swept-source optical coherence tomography images of highly myopic patients

Cardiac Adipose Tissue Segmentation via Image-Level Annotations

Automated choroidal layer segmentation from en face swept-source optical coherence tomography images of normal eyes using machine learning

Contact Info

Product

Resources

About