1
|
Qian G, Wang H, Wang Y, Chen X, Yu D, Luo S, Sun Y, Xu P, Ye J. Cascade spatial and channel-wise multifusion network with criss cross augmentation for corneal segmentation and reconstruction. Comput Biol Med 2024; 177:108602. [PMID: 38805809 DOI: 10.1016/j.compbiomed.2024.108602] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2024] [Revised: 04/22/2024] [Accepted: 05/11/2024] [Indexed: 05/30/2024]
Abstract
High-quality 3D corneal reconstruction from AS-OCT images has demonstrated significant potential in computer-aided diagnosis, enabling comprehensive observation of corneal thickness, precise assessment of morphological characteristics, as well as location and quantification of keratitis-affected regions. However, it faces two main challenges: (1) prevalent medical image segmentation networks often struggle to accurately process low-contrast corneal regions, which is a vital pre-processing step for 3D corneal reconstruction, and (2) there are no reconstruction methods that can be directly applied to AS-OCT sequences with 180-degree scanning. To combat these, we propose CSCM-CCA-Net, a simple yet efficient network for accurate corneal segmentation. This network incorporates two key techniques: cascade spatial and channel-wise multifusion (CSCM), which captures intricate contextual interdependencies and effectively extracts low-contrast and obscure corneal features; and criss cross augmentation (CCA), which enhances shape-preserved feature representation to improve segmentation accuracy. Based on the obtained corneal segmentation results, we reconstruct the 3D volume data and generate a topographic map of corneal thickness through corneal image alignment. Additionally, we design a transfer function based on the analysis of intensity histogram and gradient histogram to explore more internal cues for better visualization results. Experimental results on CORNEA benchmark demonstrate the impressive performance of our proposed method in terms of both corneal segmentation and 3D reconstruction. Furthermore, we compare CSCM-CCA-Net with state-of-the-art medical image segmentation approaches using three challenging medical fundus segmentation datasets (DRIVE, CHASEDB1, FIVES), highlighting its superiority in terms of segmentation accuracy. The code and models will be made available at https://github.com/qianguiping/CSCM-CCA-Net.
Collapse
Affiliation(s)
- Guiping Qian
- College of Media Engineering, Communication University of Zhejiang, Hangzhou, 310018, China.
| | - Huaqiong Wang
- College of Media Engineering, Communication University of Zhejiang, Hangzhou, 310018, China
| | - Yaqi Wang
- College of Media Engineering, Communication University of Zhejiang, Hangzhou, 310018, China
| | - Xiaodiao Chen
- School of Computer, Hangzhou Dianzi University, Hangzhou, 310018, China
| | - Dingguo Yu
- College of Media Engineering, Communication University of Zhejiang, Hangzhou, 310018, China
| | - Shan Luo
- College of Media Engineering, Communication University of Zhejiang, Hangzhou, 310018, China
| | - Yiming Sun
- Department of Ophthalmology, The Second Affiliated Hospital of Zhejiang University, School of Medicine, Hangzhou, 310005, China
| | - Peifang Xu
- Department of Ophthalmology, The Second Affiliated Hospital of Zhejiang University, School of Medicine, Hangzhou, 310005, China
| | - Juan Ye
- Department of Ophthalmology, The Second Affiliated Hospital of Zhejiang University, School of Medicine, Hangzhou, 310005, China
| |
Collapse
|
2
|
Engelmann J, Burke J, Hamid C, Reid-Schachter M, Pugh D, Dhaun N, Moukaddem D, Gray L, Strang N, McGraw P, Storkey A, Steptoe PJ, King S, MacGillivray T, Bernabeu MO, MacCormick IJC. Choroidalyzer: An Open-Source, End-to-End Pipeline for Choroidal Analysis in Optical Coherence Tomography. Invest Ophthalmol Vis Sci 2024; 65:6. [PMID: 38833259 PMCID: PMC11156207 DOI: 10.1167/iovs.65.6.6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2023] [Accepted: 04/22/2024] [Indexed: 06/06/2024] Open
Abstract
Purpose To develop Choroidalyzer, an open-source, end-to-end pipeline for segmenting the choroid region, vessels, and fovea, and deriving choroidal thickness, area, and vascular index. Methods We used 5600 OCT B-scans (233 subjects, six systemic disease cohorts, three device types, two manufacturers). To generate region and vessel ground-truths, we used state-of-the-art automatic methods following manual correction of inaccurate segmentations, with foveal positions manually annotated. We trained a U-Net deep learning model to detect the region, vessels, and fovea to calculate choroid thickness, area, and vascular index in a fovea-centered region of interest. We analyzed segmentation agreement (AUC, Dice) and choroid metrics agreement (Pearson, Spearman, mean absolute error [MAE]) in internal and external test sets. We compared Choroidalyzer to two manual graders on a small subset of external test images and examined cases of high error. Results Choroidalyzer took 0.299 seconds per image on a standard laptop and achieved excellent region (Dice: internal 0.9789, external 0.9749), very good vessel segmentation performance (Dice: internal 0.8817, external 0.8703), and excellent fovea location prediction (MAE: internal 3.9 pixels, external 3.4 pixels). For thickness, area, and vascular index, Pearson correlations were 0.9754, 0.9815, and 0.8285 (internal)/0.9831, 0.9779, 0.7948 (external), respectively (all P < 0.0001). Choroidalyzer's agreement with graders was comparable to the intergrader agreement across all metrics. Conclusions Choroidalyzer is an open-source, end-to-end pipeline that accurately segments the choroid and reliably extracts thickness, area, and vascular index. Especially choroidal vessel segmentation is a difficult and subjective task, and fully automatic methods like Choroidalyzer could provide objectivity and standardization.
Collapse
Affiliation(s)
- Justin Engelmann
- School of Informatics, University of Edinburgh, Edinburgh, United Kingdom
- Centre for Medical Informatics, University of Edinburgh, Edinburgh, United Kingdom
| | - Jamie Burke
- School of Mathematics, University of Edinburgh, Edinburgh, United Kingdom
| | - Charlene Hamid
- Clinical Research Facility and Imaging, University of Edinburgh, Edinburgh, United Kingdom
| | - Megan Reid-Schachter
- Clinical Research Facility and Imaging, University of Edinburgh, Edinburgh, United Kingdom
| | - Dan Pugh
- British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, United Kingdom
| | - Neeraj Dhaun
- British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, United Kingdom
| | - Diana Moukaddem
- Department of Vision Sciences, Glasgow Caledonian University, Glasgow, United Kingdom
| | - Lyle Gray
- Department of Vision Sciences, Glasgow Caledonian University, Glasgow, United Kingdom
| | - Niall Strang
- Department of Vision Sciences, Glasgow Caledonian University, Glasgow, United Kingdom
| | - Paul McGraw
- School of Psychology, University of Nottingham, Nottingham, United Kingdom
| | - Amos Storkey
- Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh, Edinburgh, United Kingdom
| | - Paul J. Steptoe
- Princess Alexandra Eye Pavilion, NHS Lothian, Edinburgh, United Kingdom
| | - Stuart King
- School of Mathematics, University of Edinburgh, Edinburgh, United Kingdom
| | - Tom MacGillivray
- Clinical Research Facility and Imaging, University of Edinburgh, Edinburgh, United Kingdom
- Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom
| | - Miguel O. Bernabeu
- Centre for Medical Informatics, University of Edinburgh, Edinburgh, United Kingdom
- The Bayes Centre, University of Edinburgh, Edinburgh, United Kingdom
| | - Ian J. C. MacCormick
- Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh, Edinburgh, United Kingdom
- Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom
| |
Collapse
|
3
|
Burke J, Engelmann J, Hamid C, Reid-Schachter M, Pearson T, Pugh D, Dhaun N, Storkey A, King S, MacGillivray TJ, Bernabeu MO, MacCormick IJC. An Open-Source Deep Learning Algorithm for Efficient and Fully Automatic Analysis of the Choroid in Optical Coherence Tomography. Transl Vis Sci Technol 2023; 12:27. [PMID: 37988073 PMCID: PMC10668622 DOI: 10.1167/tvst.12.11.27] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2023] [Accepted: 10/24/2023] [Indexed: 11/22/2023] Open
Abstract
Purpose To develop an open-source, fully automatic deep learning algorithm, DeepGPET, for choroid region segmentation in optical coherence tomography (OCT) data. Methods We used a dataset of 715 OCT B-scans (82 subjects, 115 eyes) from three clinical studies related to systemic disease. Ground-truth segmentations were generated using a clinically validated, semiautomatic choroid segmentation method, Gaussian Process Edge Tracing (GPET). We finetuned a U-Net with the MobileNetV3 backbone pretrained on ImageNet. Standard segmentation agreement metrics, as well as derived measures of choroidal thickness and area, were used to evaluate DeepGPET, alongside qualitative evaluation from a clinical ophthalmologist. Results DeepGPET achieved excellent agreement with GPET on data from three clinical studies (AUC = 0.9994, Dice = 0.9664; Pearson correlation = 0.8908 for choroidal thickness and 0.9082 for choroidal area), while reducing the mean processing time per image on a standard laptop CPU from 34.49 ± 15.09 seconds using GPET to 1.25 ± 0.10 seconds using DeepGPET. Both methods performed similarly according to a clinical ophthalmologist who qualitatively judged a subset of segmentations by GPET and DeepGPET, based on smoothness and accuracy of segmentations. Conclusions DeepGPET, a fully automatic, open-source algorithm for choroidal segmentation, will enable researchers to efficiently extract choroidal measurements, even for large datasets. As no manual interventions are required, DeepGPET is less subjective than semiautomatic methods and could be deployed in clinical practice without requiring a trained operator. Translational Relevance DeepGPET addresses the lack of open-source, fully automatic, and clinically relevant choroid segmentation algorithms, and its subsequent public release will facilitate future choroidal research in both ophthalmology and wider systemic health.
Collapse
Affiliation(s)
- Jamie Burke
- School of Mathematics, University of Edinburgh, Edinburgh, UK
| | - Justin Engelmann
- School of Informatics, University of Edinburgh, Edinburgh, UK
- Centre for Medical Informatics, University of Edinburgh, Edinburgh, UK
| | - Charlene Hamid
- Clinical Research Facility and Imaging, University of Edinburgh, Edinburgh, UK
| | | | - Tom Pearson
- University Hospital Wales, NHS Wales, Cardiff, Wales, UK
| | - Dan Pugh
- British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
| | - Neeraj Dhaun
- British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
| | - Amos Storkey
- Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh, Edinburgh, UK
| | - Stuart King
- School of Mathematics, University of Edinburgh, Edinburgh, UK
| | - Tom J. MacGillivray
- Clinical Research Facility and Imaging, University of Edinburgh, Edinburgh, UK
- Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, UK
| | - Miguel O. Bernabeu
- Centre for Medical Informatics, University of Edinburgh, Edinburgh, UK
- The Bayes Centre, University of Edinburgh, Edinburgh, UK
| | - Ian J. C. MacCormick
- Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh, Edinburgh, UK
- Centre for Inflammation Research, The Queen's Medical Research Institute, University of Edinburgh, Edinburgh, UK
| |
Collapse
|
4
|
Ibrahim MN, Bashar SB, Rasheed MA, Selvam A, Sant V, Sahel JA, Chhablani J, Vupparaboina KK, Jana S. Volumetric quantification of choroid and Haller's sublayer using OCT scans: An accurate and unified approach based on stratified smoothing. Comput Med Imaging Graph 2022; 99:102086. [PMID: 35717830 DOI: 10.1016/j.compmedimag.2022.102086] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2021] [Revised: 05/10/2022] [Accepted: 05/31/2022] [Indexed: 11/23/2022]
Abstract
BACKGROUND AND OBJECTIVE The choroid, a dense vascular structure in the posterior segment of the eye, maintains the health of the retina by supplying oxygen and nutrients, and assumes clinical significance in screening ocular diseases including age-related macular degeneration (AMD) and central serous chorioretinopathy (CSCR). As a technological assist, algorithmic estimation of choroidal biomarkers has been suggested based on sectional (B-scan) optical coherence tomography (OCT) images. However, most such 2D estimation techniques are compute-intensive, yet enjoy limited accuracy and have only been validated on OCT image datasets of healthy eyes. Not surprisingly, fine-scale analyses, including those involving Haller's sublayer, remain relatively rare and unsophisticated. Against this backdrop, we propose an efficient algorithm to quantify desired biomarkers with improved accuracy based on volume OCT scans. Specifically, we attempted an accurate, computationally light volumetric segmentation method involving stratified smoothing to detect choroid and Haller's sublayer. METHODS For detecting the various boundaries of the choroid and the Haller's sublayer, we propose a common volumetric method that performs suitable exponential enhancement and maintains smooth spatial continuity across 2D B-scans. Further, we achieve suitable volumetric smoothing by primarily deploying light-duty linear regression, and sparingly using compute-intensive tensor voting, and hence significantly reduce overall complexity. The proposed methodology is tested on five health and five diseased OCT volumes considering various metrics including volumetric Dice coefficient and corresponding quotient measures to facilitate comparison vis-à-vis intra-observer repeatability. RESULTS On five healthy and five diseased OCT volumes, respectively, the proposed method for choroid segmentation recorded volumetric Dice coefficients of 93.53 % and 93.30 %, which closely approximate the respective reference observer repeatability values of 95.60 % and 95.49 %. In terms of related quotient measures, our method achieved more than 50 % improvement over a recently reported method. In detecting Haller's sublayer as well, our algorithm records statistical performance closely matching that of reference manual method. CONCLUSION Advancing the state-of-the-art, the proposed volumetric segmentation, tested on both healthy and diseased datasets, demonstrated close match with the manual reference. Our method assumes significance in accurate screening of chorioretinal diseases including AMD, CSCR and pachychoroid. Further, it enables generating accurate training data for developing deep learning models for improved detection of choroid and Haller's sublayer.
Collapse
Affiliation(s)
- M N Ibrahim
- Dept. of Electrical Engg, Indian Institute of Technology Hyderabad, Telangana, India; Dept. of Ophthalmology, University of Pittsburgh, Pittsburgh, PA, USA
| | - S Bin Bashar
- L. V. Prasad Eye Institute, Hyderabad, Telangana, India
| | - M A Rasheed
- School of Optometry and Vision Science, University of Waterloo, Ontario, Canada
| | - A Selvam
- School of Medicine, University of Pittsburgh, Pittsburgh, PA, USA
| | - V Sant
- Fox Chapel Area High School, Pittsburgh, PA, USA
| | - J A Sahel
- Dept. of Ophthalmology, University of Pittsburgh, Pittsburgh, PA, USA
| | - J Chhablani
- Dept. of Ophthalmology, University of Pittsburgh, Pittsburgh, PA, USA
| | - K K Vupparaboina
- Dept. of Ophthalmology, University of Pittsburgh, Pittsburgh, PA, USA.
| | - S Jana
- Dept. of Electrical Engg, Indian Institute of Technology Hyderabad, Telangana, India
| |
Collapse
|
5
|
Wang L, Shen M, Shi C, Zhou Y, Chen Y, Pu J, Chen H. EE-Net: An edge-enhanced deep learning network for jointly identifying corneal micro-layers from optical coherence tomography. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2021.103213] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
|
6
|
Wang L, Shen M, Chang Q, Shi C, Chen Y, Zhou Y, Zhang Y, Pu J, Chen H. Automated delineation of corneal layers on OCT images using a boundary-guided CNN. PATTERN RECOGNITION 2021; 120:108158. [PMID: 34421131 PMCID: PMC8372529 DOI: 10.1016/j.patcog.2021.108158] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/13/2023]
Abstract
Accurate segmentation of corneal layers depicted on optical coherence tomography (OCT) images is very helpful for quantitatively assessing and diagnosing corneal diseases (e.g., keratoconus and dry eye). In this study, we presented a novel boundary-guided convolutional neural network (CNN) architecture (BG-CNN) to simultaneously extract different corneal layers and delineate their boundaries. The developed BG-CNN architecture used three convolutional blocks to construct two network modules on the basis of the classical U-Net network. We trained and validated the network on a dataset consisting of 1,712 OCT images acquired on 121 subjects using a 10-fold cross-validation method. Our experiments showed an average dice similarity coefficient (DSC) of 0.9691, an intersection over union (IOU) of 0.9411, and a Hausdorff distance (HD) of 7.4423 pixels. Compared with several other classical networks, namely U-Net, Attention U-Net, Asymmetric U-Net, BiO-Net, CE-Net, CPFnte, M-Net, and Deeplabv3, on the same dataset, the developed network demonstrated a promising performance, suggesting its unique strength in segmenting corneal layers depicted on OCT images.
Collapse
Affiliation(s)
- Lei Wang
- School of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, China
- Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing, China
- Corresponding author. (L. Wang)
| | - Meixiao Shen
- School of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, China
| | - Qian Chang
- School of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, China
| | - Ce Shi
- School of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, China
| | - Yang Chen
- Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing, China
| | - Yuheng Zhou
- School of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, China
| | - Yanchun Zhang
- Department of Ophthalmology, Xi’an People’s Hospital (Xi’an Fourth Hospital), Xi’an, China
| | - Jiantao Pu
- Departments of Radiology and Bioengineering, University of Pittsburgh, Pittsburgh, PA 15213, United States
| | - Hao Chen
- School of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, China
| |
Collapse
|