1
|
de Vente C, van Ginneken B, Hoyng CB, Klaver CCW, Sánchez CI. Uncertainty-aware multiple-instance learning for reliable classification: Application to optical coherence tomography. Med Image Anal 2024; 97:103259. [PMID: 38959721 DOI: 10.1016/j.media.2024.103259] [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: 01/21/2023] [Revised: 06/17/2024] [Accepted: 06/24/2024] [Indexed: 07/05/2024]
Abstract
Deep learning classification models for medical image analysis often perform well on data from scanners that were used to acquire the training data. However, when these models are applied to data from different vendors, their performance tends to drop substantially. Artifacts that only occur within scans from specific scanners are major causes of this poor generalizability. We aimed to enhance the reliability of deep learning classification models using a novel method called Uncertainty-Based Instance eXclusion (UBIX). UBIX is an inference-time module that can be employed in multiple-instance learning (MIL) settings. MIL is a paradigm in which instances (generally crops or slices) of a bag (generally an image) contribute towards a bag-level output. Instead of assuming equal contribution of all instances to the bag-level output, UBIX detects instances corrupted due to local artifacts on-the-fly using uncertainty estimation, reducing or fully ignoring their contributions before MIL pooling. In our experiments, instances are 2D slices and bags are volumetric images, but alternative definitions are also possible. Although UBIX is generally applicable to diverse classification tasks, we focused on the staging of age-related macular degeneration in optical coherence tomography. Our models were trained on data from a single scanner and tested on external datasets from different vendors, which included vendor-specific artifacts. UBIX showed reliable behavior, with a slight decrease in performance (a decrease of the quadratic weighted kappa (κw) from 0.861 to 0.708), when applied to images from different vendors containing artifacts; while a state-of-the-art 3D neural network without UBIX suffered from a significant detriment of performance (κw from 0.852 to 0.084) on the same test set. We showed that instances with unseen artifacts can be identified with OOD detection. UBIX can reduce their contribution to the bag-level predictions, improving reliability without retraining on new data. This potentially increases the applicability of artificial intelligence models to data from other scanners than the ones for which they were developed. The source code for UBIX, including trained model weights, is publicly available through https://github.com/qurAI-amsterdam/ubix-for-reliable-classification.
Collapse
Affiliation(s)
- Coen de Vente
- Quantitative Healthcare Analysis (QurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, Noord-Holland, Netherlands; Department of Biomedical Engineering and Physics, Amsterdam University Medical Center, Amsterdam, Noord-Holland, Netherlands; Diagnostic Image Analysis Group (DIAG), Department of Radiology and Nuclear Medicine, Radboudumc, Nijmegen, Gelderland, Netherlands.
| | - Bram van Ginneken
- Diagnostic Image Analysis Group (DIAG), Department of Radiology and Nuclear Medicine, Radboudumc, Nijmegen, Gelderland, Netherlands
| | - Carel B Hoyng
- Department of Ophthalmology, Radboudumc, Nijmegen, Gelderland, Netherlands
| | - Caroline C W Klaver
- Department of Ophthalmology, Radboudumc, Nijmegen, Gelderland, Netherlands; Ophthalmology & Epidemiology, Erasmus MC, Rotterdam, Zuid-Holland, Netherlands
| | - Clara I Sánchez
- Quantitative Healthcare Analysis (QurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, Noord-Holland, Netherlands; Department of Biomedical Engineering and Physics, Amsterdam University Medical Center, Amsterdam, Noord-Holland, Netherlands
| |
Collapse
|
2
|
de Vente C, Valmaggia P, Hoyng CB, Holz FG, Islam MM, Klaver CCW, Boon CJF, Schmitz-Valckenberg S, Tufail A, Saßmannshausen M, Sánchez CI. Generalizable Deep Learning for the Detection of Incomplete and Complete Retinal Pigment Epithelium and Outer Retinal Atrophy: A MACUSTAR Report. Transl Vis Sci Technol 2024; 13:11. [PMID: 39235402 PMCID: PMC11379096 DOI: 10.1167/tvst.13.9.11] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/06/2024] Open
Abstract
Purpose The purpose of this study was to develop a deep learning algorithm for detecting and quantifying incomplete retinal pigment epithelium and outer retinal atrophy (iRORA) and complete retinal pigment epithelium and outer retinal atrophy (cRORA) in optical coherence tomography (OCT) that generalizes well to data from different devices and to validate in an intermediate age-related macular degeneration (iAMD) cohort. Methods The algorithm comprised a domain adaptation (DA) model, promoting generalization across devices, and a segmentation model for detecting granular biomarkers defining iRORA/cRORA, which are combined into iRORA/cRORA segmentations. Manual annotations of iRORA/cRORA in OCTs from different devices in the MACUSTAR study (168 patients with iAMD) were compared to the algorithm's output. Eye level classification metrics included sensitivity, specificity, and quadratic weighted Cohen's κ score (κw). Segmentation performance was assessed quantitatively using Bland-Altman plots and qualitatively. Results For ZEISS OCTs, sensitivity and specificity for iRORA/cRORA classification were 38.5% and 93.1%, respectively, and 60.0% and 96.4% for cRORA. For Spectralis OCTs, these were 84.0% and 93.7% for iRORA/cRORA, and 62.5% and 97.4% for cRORA. The κw scores for 3-way classification (none, iRORA, and cRORA) were 0.37 and 0.73 for ZEISS and Spectralis, respectively. Removing DA reduced κw from 0.73 to 0.63 for Spectralis. Conclusions The DA-enabled iRORA/cRORA segmentation algorithm showed superior consistency compared to human annotations, and good generalization across OCT devices. Translational Relevance The application of this algorithm may help toward precise and automated tracking of iAMD-related lesion changes, which is crucial in clinical settings and multicenter longitudinal studies on iAMD.
Collapse
Affiliation(s)
- Coen de Vente
- Quantitative Healthcare Analysis (qurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
- Amsterdam UMC location University of Amsterdam, Biomedical Engineering and Physics, Amsterdam, The Netherlands
- Diagnostic Image Analysis Group (DIAG), Department of Radiology and Nuclear Medicine, Radboud UMC, Nijmegen, The Netherlands
| | - Philippe Valmaggia
- Department of Biomedical Engineering, Universität Basel, Basel, Basel-Stadt, Switzerland
- Institute of Molecular and Clinical Ophthalmology Basel, Basel, Basel-Stadt, Switzerland
| | - Carel B Hoyng
- Department of Ophthalmology, Radboudumc, Nijmegen, The Netherlands
| | - Frank G Holz
- Department of Ophthalmology and GRADE Reading Center, University Hospital Bonn, Germany
| | - Mohammad M Islam
- Quantitative Healthcare Analysis (qurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
- Amsterdam UMC location University of Amsterdam, Biomedical Engineering and Physics, Amsterdam, The Netherlands
| | - Caroline C W Klaver
- Department of Ophthalmology, Radboudumc, Nijmegen, The Netherlands
- Ophthalmology and Epidemiology, Erasmus MC, Rotterdam, The Netherlands
| | - Camiel J F Boon
- Department of Ophthalmology, Leiden University Medical Center, Leiden, The Netherlands
- Department of Ophthalmology, Amsterdam University Medical Centers, Amsterdam, The Netherlands
| | - Steffen Schmitz-Valckenberg
- Department of Ophthalmology and GRADE Reading Center, University Hospital Bonn, Germany
- John A. Moran Eye Center, University of Utah, Salt Lake City, UT, USA
| | - Adnan Tufail
- Moorfields Eye Hospital NHS Foundation Trust, London, UK
| | | | - Clara I Sánchez
- Quantitative Healthcare Analysis (qurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
- Amsterdam UMC location University of Amsterdam, Biomedical Engineering and Physics, Amsterdam, The Netherlands
| |
Collapse
|
3
|
Peng J, Xie X, Lu Z, Xu Y, Xie M, Luo L, Xiao H, Ye H, Chen L, Yang J, Zhang M, Zhao P, Zheng C. Generative adversarial networks synthetic optical coherence tomography images as an education tool for image diagnosis of macular diseases: a randomized trial. Front Med (Lausanne) 2024; 11:1424749. [PMID: 39050535 PMCID: PMC11266019 DOI: 10.3389/fmed.2024.1424749] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2024] [Accepted: 06/19/2024] [Indexed: 07/27/2024] Open
Abstract
Purpose This study aimed to evaluate the effectiveness of generative adversarial networks (GANs) in creating synthetic OCT images as an educational tool for teaching image diagnosis of macular diseases to medical students and ophthalmic residents. Methods In this randomized trial, 20 fifth-year medical students and 20 ophthalmic residents were enrolled and randomly assigned (1:1 allocation) into Group real OCT and Group GANs OCT. All participants had a pretest to assess their educational background, followed by a 30-min smartphone-based education program using GANs or real OCT images for macular disease recognition training. Two additional tests were scheduled: one 5 min after the training to assess short-term performance, and another 1 week later to assess long-term performance. Scores and time consumption were recorded and compared. After all the tests, participants completed an anonymous subjective questionnaire. Results Group GANs OCT scores increased from 80.0 (46.0 to 85.5) to 92.0 (81.0 to 95.5) 5 min after training (p < 0.001) and 92.30 ± 5.36 1 week after training (p < 0.001). Similarly, Group real OCT scores increased from 66.00 ± 19.52 to 92.90 ± 5.71 (p < 0.001), respectively. When compared between two groups, no statistically significant difference was found in test scores, score improvements, or time consumption. After training, medical students had a significantly higher score improvement than residents (p < 0.001). Conclusion The education tool using synthetic OCT images had a similar educational ability compared to that using real OCT images, which improved the interpretation ability of ophthalmic residents and medical students in both short-term and long-term performances. The smartphone-based educational tool could be widely promoted for educational applications.Clinical trial registration: https://www.chictr.org.cn, Chinese Clinical Trial Registry [No. ChiCTR 2100053195].
Collapse
Affiliation(s)
- Jie Peng
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xiaoling Xie
- Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, China
| | - Zupeng Lu
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Department of Ophthalmology, Shanghai Children’s Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Yu Xu
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Meng Xie
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Li Luo
- Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, China
| | - Haodong Xiao
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Hongfei Ye
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Li Chen
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Jianlong Yang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Mingzhi Zhang
- Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, China
| | - Peiquan Zhao
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Ce Zheng
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Institute of Hospital Development Strategy, China Hospital Development Institute Shanghai Jiao Tong University, Shanghai, China
| |
Collapse
|
4
|
Fu DJ, Bagga P, Naik G, Glinton S, Faes L, Liefers B, Lima R, Wignall G, Keane PA, Ioannidou E, Ribeiro Reis AP, McKeown A, Scheibler L, Patel PJ, Moghul I, Pontikos N, Balaskas K. Pegcetacoplan Treatment and Consensus Features of Geographic Atrophy Over 24 Months. JAMA Ophthalmol 2024; 142:548-558. [PMID: 38722644 PMCID: PMC11082756 DOI: 10.1001/jamaophthalmol.2024.1269] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2023] [Accepted: 02/24/2024] [Indexed: 05/12/2024]
Abstract
Importance Despite widespread availability and consensus on its advantages for detailed imaging of geographic atrophy (GA), spectral-domain optical coherence tomography (SD-OCT) might benefit from automated quantitative OCT analyses in GA diagnosis, monitoring, and reporting of its landmark clinical trials. Objective To analyze the association between pegcetacoplan and consensus GA SD-OCT end points. Design, Setting, and Participants This was a post hoc analysis of 11 614 SD-OCT volumes from 936 of the 1258 participants in 2 parallel phase 3 studies, the Study to Compare the Efficacy and Safety of Intravitreal APL-2 Therapy With Sham Injections in Patients With Geographic Atrophy (GA) Secondary to Age-Related Macular Degeneration (OAKS) and Study to Compare the Efficacy and Safety of Intravitreal APL-2 Therapy With Sham Injections in Patients With Geographic Atrophy (GA) Secondary to Age-Related Macular Degeneration (DERBY). OAKS and DERBY were 24-month, multicenter, randomized, double-masked, sham-controlled studies conducted from August 2018 to July 2020 among adults with GA with total area 2.5 to 17.5 mm2 on fundus autofluorescence imaging (if multifocal, at least 1 lesion ≥1.25 mm2). This analysis was conducted from September to December 2023. Interventions Study participants received pegcetacoplan, 15 mg per 0.1-mL intravitreal injection, monthly or every other month, or sham injection monthly or every other month. Main Outcomes and Measures The primary end point was the least squares mean change from baseline in area of retinal pigment epithelium and outer retinal atrophy in each of the 3 treatment arms (pegcetacoplan monthly, pegcetacoplan every other month, and pooled sham [sham monthly and sham every other month]) at 24 months. Feature-specific area analysis was conducted by Early Treatment Diabetic Retinopathy Study (ETDRS) regions of interest (ie, foveal, parafoveal, and perifoveal). Results Among 936 participants, the mean (SD) age was 78.5 (7.22) years, and 570 participants (60.9%) were female. Pegcetacoplan, but not sham treatment, was associated with reduced growth rates of SD-OCT biomarkers for GA for up to 24 months. Reductions vs sham in least squares mean (SE) change from baseline of retinal pigment epithelium and outer retinal atrophy area were detectable at every time point from 3 through 24 months (least squares mean difference vs pooled sham at month 24, pegcetacoplan monthly: -0.86 mm2; 95% CI, -1.15 to -0.57; P < .001; pegcetacoplan every other month: -0.69 mm2; 95% CI, -0.98 to -0.39; P < .001). This association was more pronounced with more frequent dosing (pegcetacoplan monthly vs pegcetacoplan every other month at month 24: -0.17 mm2; 95% CI, -0.43 to 0.08; P = .17). Stronger associations were observed in the parafoveal and perifoveal regions for both pegcetacoplan monthly and pegcetacoplan every other month. Conclusions and Relevance These findings offer additional insight into the potential effects of pegcetacoplan on the development of GA, including potential effects on the retinal pigment epithelium and photoreceptors. Trial Registration ClinicalTrials.gov Identifiers: NCT03525600 and NCT03525613.
Collapse
Affiliation(s)
- Dun Jack Fu
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Pallavi Bagga
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Gunjan Naik
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Sophie Glinton
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Livia Faes
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Bart Liefers
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
- Department of Ophthalmology, Erasmus University Medical Center, Rotterdam, the Netherlands
| | - Rosana Lima
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Georgina Wignall
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Pearse A. Keane
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Estelle Ioannidou
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Ana Paula Ribeiro Reis
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | | | | | - Praveen J. Patel
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Ismail Moghul
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Nikolas Pontikos
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| | - Konstantinos Balaskas
- National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital and University College London Institute of Ophthalmology, London, United Kingdom
| |
Collapse
|
5
|
Mrokon A, Oehler J, Breunig I. Continuous adiabatic frequency conversion for FMCW-LiDAR. Sci Rep 2024; 14:4990. [PMID: 38424205 PMCID: PMC10904768 DOI: 10.1038/s41598-024-55687-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2023] [Accepted: 02/26/2024] [Indexed: 03/02/2024] Open
Abstract
Continuous tuning of the frequency of laser light serves as the fundamental basis for a myriad of applications spanning basic scientific research to industrial settings. These applications encompass endeavors such as the detection of gravitational waves, the development of precise optical clocks, environmental monitoring for health and ecological purposes, as well as distance measurement techniques. However, achieving a broad tuning range exceeding 100 GHz along with sub-microsecond tuning times, inherent linearity in tuning, and coherence lengths beyond 10 m presents significant challenges. Here, we demonstrate that electro-optically driven adiabatic frequency converters utilizing high-Q microresonators fabricated from lithium niobate possess the capability to convert arbitrary voltage signals into frequency chirps with temporal resolutions below 1 µs. The temporal evolution of the frequency correlates accurately with the applied voltage signal. We have achieved to generate 200-ns-long frequency chirps with deviations of less than 1 % from perfect linearity without requiring supplementary measures. The coefficient of determination isR 2 > 0.999 . Moreover, the coherence length of the emitted light exceeds 20 m. To validate these findings, we employ the linear frequency sweeps for Frequency-Modulated Continuous Wave (FMCW) LiDAR covering distances ranging from 0.5 to 10 m. Leveraging the demonstrated nanosecond-level tuning capabilities, coupled with the potential to tune the eigenfrequency of lithium-niobate-based resonators by several hundred GHz, our results show that electro-optically driven adiabatic frequency converters can be used in applications that require ultrafast and flexible continuous frequency tuning characterized by inherent linearity and substantial coherence length.
Collapse
Affiliation(s)
- Alexander Mrokon
- Laboratory for Optical Systems, Department of Microsystems Engineering - IMTEK, University of Freiburg, Georges-Köhler-Allee 102, Freiburg, 79110, Germany.
| | - Johanna Oehler
- Laboratory for Optical Systems, Department of Microsystems Engineering - IMTEK, University of Freiburg, Georges-Köhler-Allee 102, Freiburg, 79110, Germany
| | - Ingo Breunig
- Laboratory for Optical Systems, Department of Microsystems Engineering - IMTEK, University of Freiburg, Georges-Köhler-Allee 102, Freiburg, 79110, Germany
- Fraunhofer Institute for Physical Measurement Techniques IPM, Georges-Köhler-Allee 301, Freiburg, 79110, Germany
| |
Collapse
|
6
|
Singh AP, Göb M, Ahrens M, Eixmann T, Schulte B, Schulz-Hildebrandt H, Hüttmann G, Ellrichmann M, Huber R, Rahlves M. Virtual Hall sensor triggered multi-MHz endoscopic OCT imaging for stable real-time visualization. OPTICS EXPRESS 2024; 32:5809-5825. [PMID: 38439298 DOI: 10.1364/oe.514636] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Accepted: 01/18/2024] [Indexed: 03/06/2024]
Abstract
Circumferential scanning in endoscopic imaging is crucial across various disciplines, and optical coherence tomography (OCT) is often the preferred choice due to its high-speed, high-resolution, and micron-scale imaging capabilities. Moreover, real-time and high-speed 3D endoscopy is a pivotal technology for medical screening and precise surgical guidance, among other applications. However, challenges such as image jitter and non-uniform rotational distortion (NURD) are persistent obstacles that hinder real-time visualization during high-speed OCT procedures. To address this issue, we developed an innovative, low-cost endoscope that employs a brushless DC motor for scanning, and a sensorless technique for triggering and synchronizing OCT imaging with the scanning motor. This sensorless approach uses the motor's electrical feedback (back electromotive force, BEMF) as a virtual Hall sensor to initiate OCT image acquisition and synchronize it with a Fourier Domain Mode-Locked (FDML)-based Megahertz OCT system. Notably, the implementation of BEMF-triggered OCT has led to a substantial reduction in image jitter and NURD (<4 mrad), thereby opening up a new window for real-time visualization capabilities. This approach suggests potential benefits across various applications, aiming to provide a more accurate, deployable, and cost-effective solution. Subsequent studies can explore the adaptability of this system to specific clinical scenarios and its performance under practical endoscopic conditions.
Collapse
|
7
|
Lu J, Cheng Y, Hiya FE, Shen M, Herrera G, Zhang Q, Gregori G, Rosenfeld PJ, Wang RK. Deep-learning-based automated measurement of outer retinal layer thickness for use in the assessment of age-related macular degeneration, applicable to both swept-source and spectral-domain OCT imaging. BIOMEDICAL OPTICS EXPRESS 2024; 15:413-427. [PMID: 38223170 PMCID: PMC10783897 DOI: 10.1364/boe.512359] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Revised: 12/17/2023] [Accepted: 12/17/2023] [Indexed: 01/16/2024]
Abstract
Effective biomarkers are required for assessing the progression of age-related macular degeneration (AMD), a prevalent and progressive eye disease. This paper presents a deep learning-based automated algorithm, applicable to both swept-source OCT (SS-OCT) and spectral-domain OCT (SD-OCT) scans, for measuring outer retinal layer (ORL) thickness as a surrogate biomarker for outer retinal degeneration, e.g., photoreceptor disruption, to assess AMD progression. The algorithm was developed based on a modified TransUNet model with clinically annotated retinal features manifested in the progression of AMD. The algorithm demonstrates a high accuracy with an intersection of union (IoU) of 0.9698 in the testing dataset for segmenting ORL using both SS-OCT and SD-OCT datasets. The robustness and applicability of the algorithm are indicated by strong correlation (r = 0.9551, P < 0.0001 in the central-fovea 3 mm-circle, and r = 0.9442, P < 0.0001 in the 5 mm-circle) and agreement (the mean bias = 0.5440 um in the 3-mm circle, and 1.392 um in the 5-mm circle) of the ORL thickness measurements between SS-OCT and SD-OCT scans. Comparative analysis reveals significant differences (P < 0.0001) in ORL thickness among 80 normal eyes, 30 intermediate AMD eyes with reticular pseudodrusen, 49 intermediate AMD eyes with drusen, and 40 late AMD eyes with geographic atrophy, highlighting its potential as an independent biomarker for predicting AMD progression. The findings provide valuable insights into the ORL alterations associated with different stages of AMD and emphasize the potential of ORL thickness as a sensitive indicator of AMD severity and progression.
Collapse
Affiliation(s)
- Jie Lu
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
| | - Yuxuan Cheng
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
| | - Farhan E. Hiya
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Mengxi Shen
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Gissel Herrera
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Qinqin Zhang
- Research and Development, Carl Zeiss Meditec, Inc., Dublin, CA, USA
| | - Giovanni Gregori
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Philip J. Rosenfeld
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Ruikang K. Wang
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
- Department of Ophthalmology, University of Washington, Seattle, Washington, USA
| |
Collapse
|
8
|
Zhang H, Yang J, Zhang J, Zhao S, Zhang A. Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT. BIOMEDICAL OPTICS EXPRESS 2024; 15:319-335. [PMID: 38223193 PMCID: PMC10783899 DOI: 10.1364/boe.512337] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/20/2023] [Accepted: 12/13/2023] [Indexed: 01/16/2024]
Abstract
Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography (OCT) imaging and its functional extensions, such as angiography and elastography. Current NURD correction methods require time-consuming feature tracking/registration or cross-correlation calculations and thus sacrifice temporal resolution. Here we propose a cross-attention learning method for the NURD correction in OCT. Our method is inspired by the recent success of the self-attention mechanism in natural language processing and computer vision. By leveraging its ability to model long-range dependencies, we can directly obtain the spatial correlation between OCT A-lines at any distance, thus accelerating the NURD correction. We develop an end-to-end stacked cross-attention network and design three types of optimization constraints. We compare our method with two traditional feature-based methods and a CNN-based method on two publicly-available endoscopic OCT datasets. We further verify the NURD correction performance of our method on 3D stent reconstruction using a home-built endoscopic OCT system. Our method achieves a ∼3 × speedup to real time (26 ± 3 fps), and superior correction performance.
Collapse
Affiliation(s)
- Haoran Zhang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Jianlong Yang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Jingqian Zhang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Shiqing Zhao
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Aili Zhang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| |
Collapse
|
9
|
Suciu CI, Marginean A, Suciu VI, Muntean GA, Nicoară SD. Diabetic Macular Edema Optical Coherence Tomography Biomarkers Detected with EfficientNetV2B1 and ConvNeXt. Diagnostics (Basel) 2023; 14:76. [PMID: 38201384 PMCID: PMC10795694 DOI: 10.3390/diagnostics14010076] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2023] [Revised: 12/18/2023] [Accepted: 12/26/2023] [Indexed: 01/12/2024] Open
Abstract
(1) Background: Diabetes mellitus (DM) is a growing challenge, both for patients and physicians, in order to control the impact on health and prevent complications. Millions of patients with diabetes require medical attention, which generates problems regarding the limited time for screening but also addressability difficulties for consultation and management. As a result, screening programs for vision-threatening complications due to DM have to be more efficient in the future in order to cope with such a great healthcare burden. Diabetic macular edema (DME) is a severe complication of DM that can be prevented if it is timely screened with the help of optical coherence tomography (OCT) devices. Newly developing state-of-the-art artificial intelligence (AI) algorithms can assist physicians in analyzing large datasets and flag potential risks. By using AI algorithms in order to process OCT images of large populations, the screening capacity and speed can be increased so that patients can be timely treated. This quick response gives the physicians a chance to intervene and prevent disability. (2) Methods: This study evaluated ConvNeXt and EfficientNet architectures in correctly identifying DME patterns on real-life OCT images for screening purposes. (3) Results: Firstly, we obtained models that differentiate between diabetic retinopathy (DR) and healthy scans with an accuracy of 0.98. Secondly, we obtained a model that can indicate the presence of edema, detachment of the subfoveolar neurosensory retina, and hyperreflective foci (HF) without using pixel level annotation. Lastly, we analyzed the extent to which the pretrained weights on natural images "understand" OCT scans. (4) Conclusions: Pretrained networks such as ConvNeXt or EfficientNet correctly identify features relevant to the differentiation between healthy retinas and DR, even though they were pretrained on natural images. Another important aspect of our research is that the differentiation between biomarkers and their localization can be obtained even without pixel-level annotation. The "three biomarkers model" is able to identify obvious subfoveal neurosensory detachments, retinal edema, and hyperreflective foci, as well as very small subfoveal detachments. In conclusion, our study points out the possible usefulness of AI-assisted diagnosis of DME for lowering healthcare costs, increasing the quality of life of patients with diabetes, and reducing the waiting time until an appropriate ophthalmological consultation and treatment can be performed.
Collapse
Affiliation(s)
- Corina Iuliana Suciu
- Department of Ophthalmology, “Iuliu Haţieganu” University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania; (C.I.S.); (G.A.M.); (S.D.N.)
| | - Anca Marginean
- Department of Computer Science, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, Romania
| | - Vlad-Ioan Suciu
- Department of Neuroscience, “Iuliu Haţieganu” University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania;
| | - George Adrian Muntean
- Department of Ophthalmology, “Iuliu Haţieganu” University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania; (C.I.S.); (G.A.M.); (S.D.N.)
| | - Simona Delia Nicoară
- Department of Ophthalmology, “Iuliu Haţieganu” University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania; (C.I.S.); (G.A.M.); (S.D.N.)
- Department of Ophthalmology, Emergency County Hospital, 400006 Cluj-Napoca, Romania
| |
Collapse
|
10
|
Opoku M, Weyori BA, Adekoya AF, Adu K. CLAHE-CapsNet: Efficient retina optical coherence tomography classification using capsule networks with contrast limited adaptive histogram equalization. PLoS One 2023; 18:e0288663. [PMID: 38032915 PMCID: PMC10688733 DOI: 10.1371/journal.pone.0288663] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2023] [Accepted: 07/01/2023] [Indexed: 12/02/2023] Open
Abstract
Manual detection of eye diseases using retina Optical Coherence Tomography (OCT) images by Ophthalmologists is time consuming, prone to errors and tedious. Previous researchers have developed a computer aided system using deep learning-based convolutional neural networks (CNNs) to aid in faster detection of the retina diseases. However, these methods find it difficult to achieve better classification performance due to noise in the OCT image. Moreover, the pooling operations in CNN reduce resolution of the image that limits the performance of the model. The contributions of the paper are in two folds. Firstly, this paper makes a comprehensive literature review to establish current-state-of-act methods successfully implemented in retina OCT image classifications. Additionally, this paper proposes a capsule network coupled with contrast limited adaptive histogram equalization (CLAHE-CapsNet) for retina OCT image classification. The CLAHE was implemented as layers to minimize the noise in the retina image for better performance of the model. A three-layer convolutional capsule network was designed with carefully chosen hyperparameters. The dataset used for this study was presented by University of California San Diego (UCSD). The dataset consists of 84,495 X-Ray images (JPEG) and 4 categories (NORMAL, CNV, DME, and DRUSEN). The images went through a grading system consisting of multiple layers of trained graders of expertise for verification and correction of image labels. Evaluation experiments were conducted and comparison of results was done with state-of-the-art models to find out the best performing model. The evaluation metrics; accuracy, sensitivity, precision, specificity, and AUC are used to determine the performance of the models. The evaluation results show that the proposed model achieves the best performing model of accuracies of 97.7%, 99.5%, and 99.3% on overall accuracy (OA), overall sensitivity (OS), and overall precision (OP), respectively. The results obtained indicate that the proposed model can be adopted and implemented to help ophthalmologists in detecting retina OCT diseases.
Collapse
Affiliation(s)
- Michael Opoku
- Department of Computer Science and Informatics, University of Energy and Natural Resource, Sunyani, Ghana
| | - Benjamin Asubam Weyori
- Department of Computer Science and Informatics, University of Energy and Natural Resource, Sunyani, Ghana
| | - Adebayo Felix Adekoya
- Department of Computer Science and Informatics, University of Energy and Natural Resource, Sunyani, Ghana
| | - Kwabena Adu
- Department of Computer Science and Informatics, University of Energy and Natural Resource, Sunyani, Ghana
| |
Collapse
|
11
|
Fujimoto JG, Swanson EA, Huang D. Optical Coherence Tomography-History, Evolution, and Future Prospects: 2023 Lasker-DeBakey Clinical Medical Research Award. JAMA 2023; 330:1427-1428. [PMID: 37732826 DOI: 10.1001/jama.2023.16942] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 09/22/2023]
Abstract
In this Viewpoint, 2023 Lasker-DeBakey Clinical Medical Research Award winners James G. Fujimoto, David Huang, and Eric A. Swanson discuss their invention—optical coherence tomography, which allows rapid detection of diseases of the retina that impair vision.
Collapse
Affiliation(s)
- James G Fujimoto
- Department of Electrical Engineering and Research Laboratory of Electronics, Massachusetts Institute of Technology
| | - Eric A Swanson
- Affiliate of the Research Laboratory of Electronics, Massachusetts Institute of Technology
| | - David Huang
- Casey Eye Institute, Ophthalmology & Biomedical Engineering, Oregon Health and Science University, Portland
| |
Collapse
|
12
|
Davis TH. QnAs with James G. Fujimoto, David Huang, and Eric A. Swanson: Winners of the 2023 Lasker~DeBakey Clinical Medical Research Award. Proc Natl Acad Sci U S A 2023; 120:e2313883120. [PMID: 37732757 PMCID: PMC10523481 DOI: 10.1073/pnas.2313883120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/22/2023] Open
|
13
|
Tzaridis S, Friedlander M. Optical coherence tomography: when a picture is worth a million words. J Clin Invest 2023:e174951. [PMID: 37731358 DOI: 10.1172/jci174951] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/22/2023] Open
Affiliation(s)
- Simone Tzaridis
- Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, USA
- The Lowy Medical Research Institute, La Jolla, California, USA
- Department of Ophthalmology, University Hospital of Bonn, Bonn, Germany
| | - Martin Friedlander
- Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, USA
- The Lowy Medical Research Institute, La Jolla, California, USA
- Division of Ophthalmology, Scripps Clinic, La Jolla, California, USA
| |
Collapse
|
14
|
Rosenfeld PJ, Cheng Y, Shen M, Gregori G, Wang RK. Unleashing the power of optical attenuation coefficients to facilitate segmentation strategies in OCT imaging of age-related macular degeneration: perspective. BIOMEDICAL OPTICS EXPRESS 2023; 14:4947-4963. [PMID: 37791280 PMCID: PMC10545179 DOI: 10.1364/boe.496080] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/22/2023] [Revised: 07/22/2023] [Accepted: 07/27/2023] [Indexed: 10/05/2023]
Abstract
The use of optical attenuation coefficients (OAC) in optical coherence tomography (OCT) imaging of the retina has improved the segmentation of anatomic layers compared with traditional intensity-based algorithms. Optical attenuation correction has improved our ability to measure the choroidal thickness and choroidal vascularity index using dense volume scans. Algorithms that combine conventional intensity-based segmentation with depth-resolved OAC OCT imaging have been used to detect elevations of the retinal pigment epithelium (RPE) due to drusen and basal laminar deposits, the location of hyperpigmentation within the retina and along the RPE, the identification of macular atrophy, the thickness of the outer retinal (photoreceptor) layer, and the presence of calcified drusen. OAC OCT algorithms can identify the risk-factors that predict disease progression in age-related macular degeneration.
Collapse
Affiliation(s)
- Philip J. Rosenfeld
- Department of Ophthalmology, Bascom Palmer
Eye Institute, University of Miami Miller School of
Medicine, Miami, Florida, USA
| | - Yuxuan Cheng
- Department of Bioengineering,
University of Washington, Seattle,
Washington, USA
| | - Mengxi Shen
- Department of Ophthalmology, Bascom Palmer
Eye Institute, University of Miami Miller School of
Medicine, Miami, Florida, USA
| | - Giovanni Gregori
- Department of Ophthalmology, Bascom Palmer
Eye Institute, University of Miami Miller School of
Medicine, Miami, Florida, USA
| | - Ruikang K. Wang
- Department of Bioengineering,
University of Washington, Seattle,
Washington, USA
- Department of Ophthalmology,
University of Washington, Seattle,
Washington, USA
| |
Collapse
|
15
|
Wang J, Zong Y, He Y, Shi G, Jiang C. Domain Adaptation-Based Automated Detection of Retinal Diseases from Optical Coherence Tomography Images. Curr Eye Res 2023; 48:836-842. [PMID: 37203787 DOI: 10.1080/02713683.2023.2212878] [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: 11/09/2022] [Revised: 05/03/2023] [Accepted: 05/05/2023] [Indexed: 05/20/2023]
Abstract
PURPOSE To verify the effectiveness of domain adaptation in generalizing a deep learning-based anomaly detection model to unseen optical coherence tomography (OCT) images. METHODS Two datasets (source and target, where labelled training data was only available for the source) captured by two different OCT facilities were collected to train the model. We defined the model containing a feature extractor and a classifier as Model One and trained it with only labeled source data. The proposed domain adaptation model was defined as Model Two, which has the same feature extractor and classifier as Model One but has an additional domain critic in the training phase. We trained the Model Two with both the source and target datasets; the feature extractor was trained to extract domain-invariant features while the domain critic learned to capture the domain discrepancy. Finally, a well-trained feature extractor was used to extract domain-invariant features and a classifier was used to detect images with retinal pathologies in the two domains. RESULTS The target data consisted of 3,058 OCT B-scans captured from 163 participants. Model One achieved an area under the curve (AUC) of 0.912 [95% confidence interval (CI), 0.895-0.962], while Model Two achieved an overall AUC of 0.989 [95% CI, 0.982-0.993] for detecting pathological retinas from healthy samples. Moreover, Model Two achieved an average retinopathies detection accuracy of 94.52%. Heat maps showed that the algorithm focused on the area with pathological changes during processing, similar to manual grading in daily clinical work. CONCLUSIONS The proposed domain adaptation model showed a strong ability in reducing the domain distance between different OCT datasets.
Collapse
Affiliation(s)
- Jing Wang
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, People's Republic of China
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Suzhou, People's Republic of China
| | - Yuan Zong
- Department of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan University, Shanghai, People's Republic of China
- Key Laboratory of Myopia of State Health Ministry and Key Laboratory of Visual Impairment and Restoration, Shanghai, People's Republic of China
| | - Yi He
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, People's Republic of China
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Suzhou, People's Republic of China
| | - Guohua Shi
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, People's Republic of China
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Suzhou, People's Republic of China
| | - Chunhui Jiang
- Department of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan University, Shanghai, People's Republic of China
- Key Laboratory of Myopia of State Health Ministry and Key Laboratory of Visual Impairment and Restoration, Shanghai, People's Republic of China
| |
Collapse
|
16
|
Zhang Z, Yang X, Zhao Z, Zeng F, Ye S, Baldock SJ, Lin H, Hardy JG, Zheng Y, Shen Y. Rapid imaging and product screening with low-cost line-field Fourier domain optical coherence tomography. Sci Rep 2023; 13:10809. [PMID: 37402736 PMCID: PMC10319780 DOI: 10.1038/s41598-023-37646-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 06/25/2023] [Indexed: 07/06/2023] Open
Abstract
Fourier domain optical coherence tomography (FD-OCT) is a well-established imaging technique that provides high-resolution internal structure images of an object at a fast speed. Modern FD-OCT systems typically operate at speeds of 40,000-100,000 A-scans/s, but are priced at least tens of thousands of pounds. In this study, we demonstrate a line-field FD-OCT (LF-FD-OCT) system that achieves an OCT imaging speed of 100,000 A-scan/s at a hardware cost of thousands of pounds. We demonstrate the potential of LF-FD-OCT for biomedical and industrial imaging applications such as corneas, 3D printed electronics, and printed circuit boards.
Collapse
Affiliation(s)
- Zijian Zhang
- Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UK
- Department of Eye and Vision Sciences, University of Liverpool, Liverpool, L7 8TX, UK
| | - Xingyu Yang
- Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UK
| | - Zhiyi Zhao
- Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UK
| | - Feng Zeng
- Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UK
| | - Sicong Ye
- Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UK
| | - Sara J Baldock
- Department of Chemistry, Lancaster University, Lancaster, LA1 4YB, UK
| | - Hungyen Lin
- School of Engineering, Lancaster University, Lancaster, LA1 4YW, UK
- Materials Science Institute, Lancaster University, Lancaster, LA1 4YB, UK
| | - John G Hardy
- Department of Chemistry, Lancaster University, Lancaster, LA1 4YB, UK
- Materials Science Institute, Lancaster University, Lancaster, LA1 4YB, UK
| | - Yalin Zheng
- Department of Eye and Vision Sciences, University of Liverpool, Liverpool, L7 8TX, UK.
| | - Yaochun Shen
- Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UK.
| |
Collapse
|
17
|
Zhang H, Yang J, Zheng C, Zhao S, Zhang A. Annotation-efficient learning for OCT segmentation. BIOMEDICAL OPTICS EXPRESS 2023; 14:3294-3307. [PMID: 37497504 PMCID: PMC10368022 DOI: 10.1364/boe.486276] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/23/2023] [Revised: 04/29/2023] [Accepted: 05/26/2023] [Indexed: 07/28/2023]
Abstract
Deep learning has been successfully applied to OCT segmentation. However, for data from different manufacturers and imaging protocols, and for different regions of interest (ROIs), it requires laborious and time-consuming data annotation and training, which is undesirable in many scenarios, such as surgical navigation and multi-center clinical trials. Here we propose an annotation-efficient learning method for OCT segmentation that could significantly reduce annotation costs. Leveraging self-supervised generative learning, we train a Transformer-based model to learn the OCT imagery. Then we connect the trained Transformer-based encoder to a CNN-based decoder, to learn the dense pixel-wise prediction in OCT segmentation. These training phases use open-access data and thus incur no annotation costs, and the pre-trained model can be adapted to different data and ROIs without re-training. Based on the greedy approximation for the k-center problem, we also introduce an algorithm for the selective annotation of the target data. We verified our method on publicly-available and private OCT datasets. Compared to the widely-used U-Net model with 100% training data, our method only requires ∼10% of the data for achieving the same segmentation accuracy, and it speeds the training up to ∼3.5 times. Furthermore, our proposed method outperforms other potential strategies that could improve annotation efficiency. We think this emphasis on learning efficiency may help improve the intelligence and application penetration of OCT-based technologies.
Collapse
Affiliation(s)
- Haoran Zhang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Jianlong Yang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Ce Zheng
- Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Shiqing Zhao
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Aili Zhang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| |
Collapse
|
18
|
Rodríguez-Robles F, Verdú-Monedero R, Berenguer-Vidal R, Morales-Sánchez J, Sellés-Navarro I. Analysis of the Asymmetry between Both Eyes in Early Diagnosis of Glaucoma Combining Features Extracted from Retinal Images and OCTs into Classification Models. SENSORS (BASEL, SWITZERLAND) 2023; 23:4737. [PMID: 37430650 DOI: 10.3390/s23104737] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/08/2023] [Revised: 05/05/2023] [Accepted: 05/11/2023] [Indexed: 07/12/2023]
Abstract
This study aims to analyze the asymmetry between both eyes of the same patient for the early diagnosis of glaucoma. Two imaging modalities, retinal fundus images and optical coherence tomographies (OCTs), have been considered in order to compare their different capabilities for glaucoma detection. From retinal fundus images, the difference between cup/disc ratio and the width of the optic rim has been extracted. Analogously, the thickness of the retinal nerve fiber layer has been measured in spectral-domain optical coherence tomographies. These measurements have been considered as asymmetry characteristics between eyes in the modeling of decision trees and support vector machines for the classification of healthy and glaucoma patients. The main contribution of this work is indeed the use of different classification models with both imaging modalities to jointly exploit the strengths of each of these modalities for the same diagnostic purpose based on the asymmetry characteristics between the eyes of the patient. The results show that the optimized classification models provide better performance with OCT asymmetry features between both eyes (sensitivity 80.9%, specificity 88.2%, precision 66.7%, accuracy 86.5%) than with those extracted from retinographies, although a linear relationship has been found between certain asymmetry features extracted from both imaging modalities. Therefore, the resulting performance of the models based on asymmetry features proves their ability to differentiate healthy from glaucoma patients using those metrics. Models trained from fundus characteristics are a useful option as a glaucoma screening method in the healthy population, although with lower performance than those trained from the thickness of the peripapillary retinal nerve fiber layer. In both imaging modalities, the asymmetry of morphological characteristics can be used as a glaucoma indicator, as detailed in this work.
Collapse
Affiliation(s)
- Francisco Rodríguez-Robles
- Departamento de Tecnologías de la Información y las Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
| | - Rafael Verdú-Monedero
- Departamento de Tecnologías de la Información y las Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
| | - Rafael Berenguer-Vidal
- Departamento de Ciencias Politécnicas, Universidad Católica de Murcia (UCAM), 30107 Guadalupe, Spain
| | - Juan Morales-Sánchez
- Departamento de Tecnologías de la Información y las Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
| | | |
Collapse
|
19
|
Draelos M, Ortiz P, Narawane A, McNabb RP, Kuo AN, Izatt JA. Robotic Optical Coherence Tomography of Human Subjects with Posture-Invariant Head and Eye Alignment in Six Degrees of Freedom. ... INTERNATIONAL SYMPOSIUM ON MEDICAL ROBOTICS. INTERNATIONAL SYMPOSIUM ON MEDICAL ROBOTICS 2023; 2023:10.1109/ismr57123.2023.10130250. [PMID: 39092148 PMCID: PMC11293772 DOI: 10.1109/ismr57123.2023.10130250] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/04/2024]
Abstract
Ophthalmic optical coherence tomography (OCT) has achieved remarkable clinical success but remains sequestered in ophthalmology specialty offices. Recently introduced robotic OCT systems seek to expand patient access but fall short of their full potential due to significant imaging workspace and motion planning restrictions. Here, we present a next-generation robotic OCT system capable of imaging in any head orientation or posture that is mechanically reachable. This system overcomes prior restrictions by eliminating fixed-base tracking components, extending robot reach, and planning alignment in six degrees of freedom. With this robotic system, we show repeatable subject imaging independent of posture (standing, seated, reclined, and supine) under widely varying head orientations for multiple human subjects. For each subject, we obtained a consistent view of the retina, including the fovea, retinal vasculature, and edge of the optic nerve head. We believe this robotic approach can extend OCT as an eye disease screening, diagnosis, and monitoring tool to previously unreached patient populations.
Collapse
Affiliation(s)
- Mark Draelos
- Departments of Robotics and Ophthalmology, University of Michigan, 2505 Hayward St, Ann Arbor, MI USA
| | - Pablo Ortiz
- Department of Biomedical Engineering, Duke University, 101 Science Dr, Durham, NC USA
| | - Amit Narawane
- Department of Biomedical Engineering, Duke University, 101 Science Dr, Durham, NC USA
| | - Ryan P McNabb
- Department of Ophthalmology, Duke University Medical Center, 2351 Erwin Rd, Durham, NC USA
| | - Anthony N Kuo
- Department of Ophthalmology, Duke University Medical Center, 2351 Erwin Rd, Durham, NC USA
- Department of Biomedical Engineering, Duke University, 101 Science Dr, Durham, NC USA
| | - Joseph A Izatt
- Department of Biomedical Engineering, Duke University, 101 Science Dr, Durham, NC USA
- Department of Ophthalmology, Duke University Medical Center, 2351 Erwin Rd, Durham, NC USA
| |
Collapse
|
20
|
de Souza E Silva KY, Falcão CMC, Fernandes LO, Gomes ASL. Exploiting optical coherence tomography to evaluate wear in spiral dental polishing systems. APPLIED OPTICS 2023; 62:C8-C13. [PMID: 37133052 DOI: 10.1364/ao.476769] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
This study aimed to evaluate the behavior of spiral polishing systems in restorative materials through optical coherence tomography (OCT). Performance of spiral polishers specific to resin and ceramics were evaluated. The surface roughness of restorative materials was measured, and images of the polishers were acquired by OCT and stereomicroscope. Surface roughness was reduced in ceramic and glass-ceramic composite polished with a system specific to resin (p<0.01). Surface area variation was observed on all polishers, except for the medium-grit polisher tested in ceramic (p<0.05). Similarity between images obtained through OCT and stereomicroscopy presented a Kappa inter- and intra-observer of 0.94 and 0.96, respectively. Then, OCT was able to evaluate wear areas in spiral polishers.
Collapse
|
21
|
Lu J, Cheng Y, Li J, Liu Z, Shen M, Zhang Q, Liu J, Herrera G, Hiya FE, Morin R, Joseph J, Gregori G, Rosenfeld PJ, Wang RK. Automated segmentation and quantification of calcified drusen in 3D swept source OCT imaging. BIOMEDICAL OPTICS EXPRESS 2023; 14:1292-1306. [PMID: 36950236 PMCID: PMC10026581 DOI: 10.1364/boe.485999] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Revised: 02/18/2023] [Accepted: 02/19/2023] [Indexed: 06/18/2023]
Abstract
Qualitative and quantitative assessments of calcified drusen are clinically important for determining the risk of disease progression in age-related macular degeneration (AMD). This paper reports the development of an automated algorithm to segment and quantify calcified drusen on swept-source optical coherence tomography (SS-OCT) images. The algorithm leverages the higher scattering property of calcified drusen compared with soft drusen. Calcified drusen have a higher optical attenuation coefficient (OAC), which results in a choroidal hypotransmission defect (hypoTD) below the calcified drusen. We show that it is possible to automatically segment calcified drusen from 3D SS-OCT scans by combining the OAC within drusen and the hypoTDs under drusen. We also propose a correction method for the segmentation of the retina pigment epithelium (RPE) overlying calcified drusen by automatically correcting the RPE by an amount of the OAC peak width along each A-line, leading to more accurate segmentation and quantification of drusen in general, and the calcified drusen in particular. A total of 29 eyes with nonexudative AMD and calcified drusen imaged with SS-OCT using the 6 × 6 mm2 scanning pattern were used in this study to test the performance of the proposed automated method. We demonstrated that the method achieved good agreement with the human expert graders in identifying the area of calcified drusen (Dice similarity coefficient: 68.27 ± 11.09%, correlation coefficient of the area measurements: r = 0.9422, the mean bias of the area measurements = 0.04781 mm2).
Collapse
Affiliation(s)
- Jie Lu
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
| | - Yuxuan Cheng
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
| | - Jianqing Li
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Ziyu Liu
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
| | - Mengxi Shen
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Qinqin Zhang
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
- Research and Development, Carl Zeiss Meditec, Inc., Dublin, CA, USA
| | - Jeremy Liu
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Gissel Herrera
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Farhan E. Hiya
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Rosalyn Morin
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Joan Joseph
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Giovanni Gregori
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Philip J. Rosenfeld
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Ruikang K. Wang
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
- Department of Ophthalmology, University of Washington, Seattle, Washington, USA
| |
Collapse
|
22
|
Fitzgerald S, Akhtar J, Schartner E, Ebendorff-Heidepriem H, Mahadevan-Jansen A, Li J. Multimodal Raman spectroscopy and optical coherence tomography for biomedical analysis. JOURNAL OF BIOPHOTONICS 2023; 16:e202200231. [PMID: 36308009 PMCID: PMC10082563 DOI: 10.1002/jbio.202200231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/20/2022] [Revised: 10/19/2022] [Accepted: 10/26/2022] [Indexed: 06/16/2023]
Abstract
Optical techniques hold great potential to detect and monitor disease states as they are a fast, non-invasive toolkit. Raman spectroscopy (RS) in particular is a powerful label-free method capable of quantifying the biomolecular content of tissues. Still, spontaneous Raman scattering lacks information about tissue morphology due to its inability to rapidly assess a large field of view. Optical Coherence Tomography (OCT) is an interferometric optical method capable of fast, depth-resolved imaging of tissue morphology, but lacks detailed molecular contrast. In many cases, pairing label-free techniques into multimodal systems allows for a more diverse field of applications. Integrating RS and OCT into a single instrument allows for both structural imaging and biochemical interrogation of tissues and therefore offers a more comprehensive means for clinical diagnosis. This review summarizes the efforts made to date toward combining spontaneous RS-OCT instrumentation for biomedical analysis, including insights into primary design considerations and data interpretation.
Collapse
Affiliation(s)
- Sean Fitzgerald
- Vanderbilt Biophotonics Center, Nashville, Tennessee, USA
- Department of Biomedical Engineering, Vanderbilt University, Nashville, Tennessee, USA
| | - Jobaida Akhtar
- School of Physical Sciences, The University of Adelaide, Adelaide, South Australia, Australia
- Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, South Australia, Australia
| | - Erik Schartner
- School of Physical Sciences, The University of Adelaide, Adelaide, South Australia, Australia
- Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, South Australia, Australia
| | - Heike Ebendorff-Heidepriem
- School of Physical Sciences, The University of Adelaide, Adelaide, South Australia, Australia
- Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, South Australia, Australia
| | - Anita Mahadevan-Jansen
- Vanderbilt Biophotonics Center, Nashville, Tennessee, USA
- Department of Biomedical Engineering, Vanderbilt University, Nashville, Tennessee, USA
| | - Jiawen Li
- Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, South Australia, Australia
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, South Australia, Australia
- School of Electrical and Electronic Engineering, The University of Adelaide, Adelaide, South Australia, Australia
| |
Collapse
|
23
|
Gende M, de Moura J, Novo J, Penedo MG, Ortega M. A new generative approach for optical coherence tomography data scarcity: unpaired mutual conversion between scanning presets. Med Biol Eng Comput 2023; 61:1093-1112. [PMID: 36680707 PMCID: PMC10083164 DOI: 10.1007/s11517-022-02742-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Accepted: 12/09/2022] [Indexed: 01/22/2023]
Abstract
In optical coherence tomography (OCT), there is a trade-off between the scanning time and image quality, leading to a scarcity of high quality data. OCT platforms provide different scanning presets, producing visually distinct images, limiting their compatibility. In this work, a fully automatic methodology for the unpaired visual conversion of the two most prevalent scanning presets is proposed. Using contrastive unpaired translation generative adversarial architectures, low quality images acquired with the faster Macular Cube preset can be converted to the visual style of high visibility Seven Lines scans and vice-versa. This modifies the visual appearance of the OCT images generated by each preset while preserving natural tissue structure. The quality of original and synthetic generated images was compared using BRISQUE. The synthetic generated images achieved very similar scores to original images of their target preset. The generative models were validated in automatic and expert separability tests. These models demonstrated they were able to replicate the genuine look of the original images. This methodology has the potential to create multi-preset datasets with which to train robust computer-aided diagnosis systems by exposing them to the visual features of different presets they may encounter in real clinical scenarios without having to obtain additional data. Graphical Abstract Unpaired mutual conversion between scanning presets. Two generative adversarial models are trained for the conversion of OCT images into images of another scanning preset, replicating the visual features that characterise said preset.
Collapse
Affiliation(s)
- Mateo Gende
- Grupo, VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, A Coruña, 15006, A Coruña, Spain.,Centro de investigación, CITIC, Universidade da Coruña, Campus de Elviña s/n, A Coruña, 15071, A Coruña, Spain
| | - Joaquim de Moura
- Grupo, VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, A Coruña, 15006, A Coruña, Spain. .,Centro de investigación, CITIC, Universidade da Coruña, Campus de Elviña s/n, A Coruña, 15071, A Coruña, Spain.
| | - Jorge Novo
- Grupo, VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, A Coruña, 15006, A Coruña, Spain.,Centro de investigación, CITIC, Universidade da Coruña, Campus de Elviña s/n, A Coruña, 15071, A Coruña, Spain
| | - Manuel G Penedo
- Grupo, VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, A Coruña, 15006, A Coruña, Spain.,Centro de investigación, CITIC, Universidade da Coruña, Campus de Elviña s/n, A Coruña, 15071, A Coruña, Spain
| | - Marcos Ortega
- Grupo, VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, A Coruña, 15006, A Coruña, Spain.,Centro de investigación, CITIC, Universidade da Coruña, Campus de Elviña s/n, A Coruña, 15071, A Coruña, Spain
| |
Collapse
|
24
|
Nelson MS, Liu Y, Wilson HM, Li B, Rosado-Mendez IM, Rogers JD, Block WF, Eliceiri KW. Multiscale Label-Free Imaging of Fibrillar Collagen in the Tumor Microenvironment. Methods Mol Biol 2023; 2614:187-235. [PMID: 36587127 DOI: 10.1007/978-1-0716-2914-7_13] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/02/2023]
Abstract
With recent advances in cancer therapeutics, there is a great need for improved imaging methods for characterizing cancer onset and progression in a quantitative and actionable way. Collagen, the most abundant extracellular matrix protein in the tumor microenvironment (and the body in general), plays a multifaceted role, both hindering and promoting cancer invasion and progression. Collagen deposition can defend the tumor with immunosuppressive effects, while aligned collagen fiber structures can enable tumor cell migration, aiding invasion and metastasis. Given the complex role of collagen fiber organization and topology, imaging has been a tool of choice to characterize these changes on multiple spatial scales, from the organ and tumor scale to cellular and subcellular level. Macroscale density already aids in the detection and diagnosis of solid cancers, but progress is being made to integrate finer microscale features into the process. Here we review imaging modalities ranging from optical methods of second harmonic generation (SHG), polarized light microscopy (PLM), and optical coherence tomography (OCT) to the medical imaging approaches of ultrasound and magnetic resonance imaging (MRI). These methods have enabled scientists and clinicians to better understand the impact collagen structure has on the tumor environment, at both the bulk scale (density) and microscale (fibrillar structure) levels. We focus on imaging methods with the potential to both examine the collagen structure in as natural a state as possible and still be clinically amenable, with an emphasis on label-free strategies, exploiting intrinsic optical properties of collagen fibers.
Collapse
Affiliation(s)
- Michael S Nelson
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, USA.,Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI, USA
| | - Yuming Liu
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, USA
| | - Helen M Wilson
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, USA.,Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI, USA
| | - Bin Li
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, USA.,Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI, USA.,Morgridge Institute for Research, Madison, WI, USA
| | - Ivan M Rosado-Mendez
- Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, USA
| | - Jeremy D Rogers
- Morgridge Institute for Research, Madison, WI, USA.,McPherson Eye Research Institute, University of Wisconsin-Madison, Madison, WI, USA
| | - Walter F Block
- Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, USA
| | - Kevin W Eliceiri
- Center for Quantitative Cell Imaging, University of Wisconsin-Madison, Madison, WI, USA. .,Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI, USA. .,Morgridge Institute for Research, Madison, WI, USA. .,Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, USA. .,McPherson Eye Research Institute, University of Wisconsin-Madison, Madison, WI, USA.
| |
Collapse
|
25
|
Faubert AC, Larina IV, Wang S. Open-source, highly efficient, post-acquisition synchronization for 4D dual-contrast imaging of the mouse embryonic heart over development with optical coherence tomography. BIOMEDICAL OPTICS EXPRESS 2023; 14:163-181. [PMID: 36698661 PMCID: PMC9842004 DOI: 10.1364/boe.475027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/06/2022] [Revised: 11/18/2022] [Accepted: 11/19/2022] [Indexed: 05/28/2023]
Abstract
Dynamic imaging of the beating embryonic heart in 3D is critical for understanding cardiac development and defects. Optical coherence tomography (OCT) plays an important role in embryonic heart imaging with its unique imaging scale and label-free contrasts. In particular, 4D (3D + time) OCT imaging enabled biomechanical analysis of the developing heart in various animal models. While ultrafast OCT systems allow for direct volumetric imaging of the beating heart, the imaging speed remains limited, leading to an image quality inferior to that produced by post-acquisition synchronization. As OCT systems become increasingly available to a wide range of biomedical researchers, a more accessible 4D reconstruction method is required to enable the broader application of OCT in the dynamic, volumetric assessment of embryonic heartbeat. Here, we report an open-source, highly efficient, post-acquisition synchronization method for 4D cardiodynamic and hemodynamic imaging of the mouse embryonic heart. Relying on the difference between images to characterize heart wall movements, the method provides good sensitivity to the cardiac activity when aligning heartbeat phases, even at early stages when the heart wall occupies only a small number of pixels. The method works with a densely sampled single 3D data acquisition, which, unlike the B-M scans required by other methods, is readily available in most commercial OCT systems. Compared with an existing approach for the mouse embryonic heart, this method shows superior reconstruction quality. We present the robustness of the method through results from different embryos with distinct heart rates, ranging from 1.24 Hz to 2.13 Hz. Since the alignment process operates on a 1D signal, the method has a high efficiency, featuring sub-second alignment time while utilizing ∼100% of the original image files. This allows us to achieve repeated, dual-contrast imaging of mouse embryonic heart development. This new, open-source method could facilitate research using OCT to study early cardiogenesis.
Collapse
Affiliation(s)
- Andre C. Faubert
- Department of Biomedical Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA
| | - Irina V. Larina
- Department of Integrative Physiology, Baylor College of Medicine, Houston, TX 77030, USA
| | - Shang Wang
- Department of Biomedical Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA
| |
Collapse
|
26
|
Mozaffari S, Feroldi F, LaRocca F, Tiruveedhula P, Gregory PD, Park BH, Roorda A. Retinal imaging using adaptive optics optical coherence tomography with fast and accurate real-time tracking. BIOMEDICAL OPTICS EXPRESS 2022; 13:5909-5925. [PMID: 36733754 PMCID: PMC9872892 DOI: 10.1364/boe.467634] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Revised: 08/11/2022] [Accepted: 10/04/2022] [Indexed: 05/02/2023]
Abstract
One of the main obstacles in high-resolution 3-D retinal imaging is eye motion, which causes blur and distortion artifacts that require extensive post-processing to be corrected. Here, an adaptive optics optical coherence tomography (AOOCT) system with real-time active eye motion correction is presented. Correction of ocular aberrations and of retinal motion is provided by an adaptive optics scanning laser ophthalmoscope (AOSLO) that is optically and electronically combined with the AOOCT system. We describe the system design and quantify its performance. The AOOCT system features an independent focus adjustment that allows focusing on different retinal layers while maintaining the AOSLO focus on the photoreceptor mosaic for high fidelity active motion correction. The use of a high-quality reference frame for eye tracking increases revisitation accuracy between successive imaging sessions, allowing to collect several volumes from the same area. This system enables spatially targeted retinal imaging as well as volume averaging over multiple imaging sessions with minimal correction of motion in post processing.
Collapse
Affiliation(s)
- Sanam Mozaffari
- Herbert Wertheim School of Optometry and Vision Science, University of California, Berkeley, Berkeley, CA 94720, USA
| | - Fabio Feroldi
- Herbert Wertheim School of Optometry and Vision Science, University of California, Berkeley, Berkeley, CA 94720, USA
| | - Francesco LaRocca
- Herbert Wertheim School of Optometry and Vision Science, University of California, Berkeley, Berkeley, CA 94720, USA
| | - Pavan Tiruveedhula
- Herbert Wertheim School of Optometry and Vision Science, University of California, Berkeley, Berkeley, CA 94720, USA
| | - Patrick D. Gregory
- Department of Bioengineering, University of California, Riverside, CA 92521, USA
| | - B. Hyle Park
- Department of Bioengineering, University of California, Riverside, CA 92521, USA
| | - Austin Roorda
- Herbert Wertheim School of Optometry and Vision Science, University of California, Berkeley, Berkeley, CA 94720, USA
| |
Collapse
|
27
|
Xu L, Zhang L, Wang K, Liu C, Zhang C, Zhang X. Dual-comb based time-stretch optical coherence tomography for large and segmental imaging depth. OPTICS EXPRESS 2022; 30:39014-39024. [PMID: 36258452 DOI: 10.1364/oe.469795] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Accepted: 09/29/2022] [Indexed: 06/16/2023]
Abstract
Optical coherence tomography based on time-stretch enables high frame rate and high-resolution imaging for the inertia-free wavelength-swept mechanism. The fundamental obstacle is still the acquisition bandwidth's restriction on imaging depth. By introducing dual-comb with slightly different repetition rates, the induced Vernier effect is found to be capable of relieving the problem. In our work, a dual-comb based time-stretch optical coherence tomography is proposed and experimentally demonstrated, achieving a 1.5-m imaging depth and 200-kHz A-scan rate. Moreover, about a 33.4-µm resolution and 25-µm accuracy are achieved. In addition, by adjusting the frequency detuning of the dual-comb, the A-scan rate can be further boosted to video-rate imaging. With enlarged imaging depth, this scheme is promising for a wide range of applications, including light detection and ranging.
Collapse
|
28
|
Deep Learning Technology Applied to Medical Image Tissue Classification. Diagnostics (Basel) 2022; 12:diagnostics12102430. [PMID: 36292119 PMCID: PMC9600639 DOI: 10.3390/diagnostics12102430] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Revised: 09/28/2022] [Accepted: 09/28/2022] [Indexed: 11/17/2022] Open
Abstract
Medical image classification is a novel technology that presents a new challenge. It is essential that pathological images are automatically and correctly classified to enable doctors to provide precise treatment. Convolutional neural networks have demonstrated their effectiveness in classifying images in deep learning, which may have dozens or hundreds of layers, to illustrate the relationship between them in terms of their different neural network features. Convolutional layers consisting of small kernels take weights as input and guide them through an activation function as output. The main advantage of using convolutional neural networks (CNNs) instead of traditional neural networks is that they reduce the model parameters for greater accuracy. However, many studies have simply been focused on finding the best CNN model and classification results from a single medical image classification. Therefore, we applied a common deep learning network model in an attempt to identify the best model framework by training and validating different model parameters to classify medical images. After conducting experiments on six publicly available databases of pathological images, including colorectal cancer tissue, chest X-rays, common skin lesions, diabetic retinopathy, pediatric chest X-ray, and breast ultrasound image datasets, we were able to confirm that the recognition accuracy of the Inception V3 method was significantly better than that of other existing deep learning models.
Collapse
|
29
|
Wang T, Pfeiffer T, Akyildiz A, van Beusekom HMM, Huber R, van der Steen AFW, van Soest G. Intravascular optical coherence elastography. BIOMEDICAL OPTICS EXPRESS 2022; 13:5418-5433. [PMID: 36425628 PMCID: PMC9664873 DOI: 10.1364/boe.470039] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/11/2022] [Revised: 08/30/2022] [Accepted: 08/31/2022] [Indexed: 05/07/2023]
Abstract
Optical coherence elastography (OCE), a functional extension of optical coherence tomography (OCT), visualizes tissue strain to deduce the tissue's biomechanical properties. In this study, we demonstrate intravascular OCE using a 1.1 mm motorized catheter and a 1.6 MHz Fourier domain mode-locked OCT system. We induced an intraluminal pressure change by varying the infusion rate from the proximal end of the catheter. We analysed the pixel-matched phase change between two different frames to yield the radial strain. Imaging experiments were carried out in a phantom and in human coronary arteries in vitro. At an imaging speed of 3019 frames/s, we were able to capture the dynamic strain. Stiff inclusions in the phantom and calcification in atherosclerotic plaques are associated with low strain values and can be distinguished from the surrounding soft material, which exhibits elevated strain. For the first time, circumferential intravascular OCE images are provided side by side with conventional OCT images, simultaneously mapping both the tissue structure and stiffness.
Collapse
Affiliation(s)
- Tianshi Wang
- Thoraxcentre, Erasmus University Medical Centre, Rotterdam 3015 AA, The Netherlands
| | - Tom Pfeiffer
- Institut für Biomedizinische Optik, Universität zu Lübeck, Lübeck 23562, Germany
| | - Ali Akyildiz
- Thoraxcentre, Erasmus University Medical Centre, Rotterdam 3015 AA, The Netherlands
- Department of Biomechanical Engineering, Delft University of Technology, Delft 2600 AA, The Netherlands
| | | | - Robert Huber
- Institut für Biomedizinische Optik, Universität zu Lübeck, Lübeck 23562, Germany
| | - Antonius F. W. van der Steen
- Thoraxcentre, Erasmus University Medical Centre, Rotterdam 3015 AA, The Netherlands
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518005, China
- Department of Imaging Science and Technology, Delft University of Technology, Delft 2600 AA, The Netherlands
| | - Gijs van Soest
- Thoraxcentre, Erasmus University Medical Centre, Rotterdam 3015 AA, The Netherlands
| |
Collapse
|
30
|
Berenguer-Vidal R, Verdú-Monedero R, Morales-Sánchez J, Sellés-Navarro I, Kovalyk O, Sancho-Gómez JL. Decision Trees for Glaucoma Screening Based on the Asymmetry of the Retinal Nerve Fiber Layer in Optical Coherence Tomography. SENSORS 2022; 22:s22134842. [PMID: 35808338 PMCID: PMC9269200 DOI: 10.3390/s22134842] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/06/2022] [Revised: 06/23/2022] [Accepted: 06/24/2022] [Indexed: 12/10/2022]
Abstract
Purpose: The aim of this study was to analyze the relevance of asymmetry features between both eyes of the same patient for glaucoma screening using optical coherence tomography. Methods: Spectral-domain optical coherence tomography was used to estimate the thickness of the peripapillary retinal nerve fiber layer in both eyes of the patients in the study. These measurements were collected in a dataset from healthy and glaucoma patients. Several metrics for asymmetry in the retinal nerve fiber layer thickness between the two eyes were then proposed. These metrics were evaluated using the dataset by performing a statistical analysis to assess their significance as relevant features in the diagnosis of glaucoma. Finally, the usefulness of these asymmetry features was demonstrated by designing supervised machine learning models that can be used for the early diagnosis of glaucoma. Results: Machine learning models were designed and optimized, specifically decision trees, based on the values of proposed asymmetry metrics. The use of these models on the dataset provided good classification of the patients (accuracy 88%, sensitivity 70%, specificity 93% and precision 75%). Conclusions: The obtained machine learning models based on retinal nerve fiber layer asymmetry are simple but effective methods which offer a good trade-off in classification of patients and simplicity. The fast binary classification relies on a few asymmetry values of the retinal nerve fiber layer thickness, allowing their use in the daily clinical practice for glaucoma screening.
Collapse
Affiliation(s)
- Rafael Berenguer-Vidal
- Departamento de Ciencias Politécnicas, Universidad Católica de Murcia UCAM, 30107 Guadalupe, Spain;
| | - Rafael Verdú-Monedero
- Departamento de Tecnologías de la Información y Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain; (J.M.-S.); (O.K.); (J.-L.S.-G.)
- Correspondence:
| | - Juan Morales-Sánchez
- Departamento de Tecnologías de la Información y Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain; (J.M.-S.); (O.K.); (J.-L.S.-G.)
| | | | - Oleksandr Kovalyk
- Departamento de Tecnologías de la Información y Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain; (J.M.-S.); (O.K.); (J.-L.S.-G.)
| | - José-Luis Sancho-Gómez
- Departamento de Tecnologías de la Información y Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain; (J.M.-S.); (O.K.); (J.-L.S.-G.)
| |
Collapse
|
31
|
Interleaved Optical Coherence Tomography: Clinical and Laboratory Biomarkers in Patients with Diabetic Macular Edema. J Pers Med 2022; 12:jpm12050765. [PMID: 35629188 PMCID: PMC9147367 DOI: 10.3390/jpm12050765] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2022] [Revised: 05/03/2022] [Accepted: 05/06/2022] [Indexed: 02/05/2023] Open
Abstract
(1) Background: The global burden of diabetes mellitus (DM) has been estimated to reach 600 million patients worldwide by 2040. Approximately 200 million people will develop diabetic retinopathy within this time frame. Diabetic macular edema (DME) is a severe, vision-threatening complication that can develop at any stage of diabetic retinopathy, and it represents the main cause of vision loss in patients with DM. Its harmful consequences on visual function could be prevented with timely recognition and treatment. (2) Methods: This study assessed the clinical (demographic characteristics, diabetic evolution, and systemic vascular complications); laboratory (glycated hemoglobin, metabolic parameters, capillary oxygen saturation, and renal function); ophthalmologic exam; and spectral-domain optical coherence tomography (SD–OCT) (macular volume, central macular thickness, maximal central thickness, minimal central thickness, foveal thickness, superior inner, inferior inner, nasal inner, temporal inner, inferior outer, superior outer, nasal outer, and temporal outer thicknesses, disruption of the ellipsoid zone, and disruption of the inner retinal layers (DRIL) parameters in three groups of individuals: healthy controls (HC), patients with DME and type 1 DM (T1DM—group A), and patients with DME and type 2 DM (T2DM—group B) to identify novel correlations between them that would open a path to new pathogenetic hypotheses and, implicitly, to the identification of new therapeutic methods, as part of a tailored treatment within the concept of precision medicine. (3) Results: The duration of DM was significantly longer in group A as compared with group B, as were the prevalence of smoking and systemic vascular complications. Capillary oxygen saturation and estimated glomerular filtration rates were significantly lower, and serum creatinine levels were significantly higher in group A as compared to group B. Regarding the OCT findings, DME had a predominantly eccentric pattern, and the right eye was more severely affected in both groups of patients. Significantly higher values were obtained in group B as compared to group A for the following OCT biomarkers: macular volume, central macular thickness, maximal central thickness, minimal central thickness, foveal thickness, superior inner, inferior inner, nasal inner, inferior outer and nasal outer thickness. The disruption of the ellipsoid zone was significantly more prevalent within group A, whereas the overall disruption of the retinal inner layers (DRIL) was identified significantly more frequently in group B. (4) Conclusions: Whereas systemic and laboratory biomarkers were more severely affected in patients with DME and T1DM, the OCT quantitative biomarkers revealed significantly higher values in patients with DME and T2DM.
Collapse
|
32
|
Yuksel Elgin C, Chen D, Al‐Aswad LA. Ophthalmic imaging for the diagnosis and monitoring of glaucoma: A review. Clin Exp Ophthalmol 2022; 50:183-197. [DOI: 10.1111/ceo.14044] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2021] [Revised: 12/16/2021] [Accepted: 01/03/2022] [Indexed: 12/21/2022]
Affiliation(s)
- Cansu Yuksel Elgin
- Department of Ophthalmology, NYU Langone Health NYU Grossman School of Medicine New York New York USA
| | - Dinah Chen
- Department of Ophthalmology, NYU Langone Health NYU Grossman School of Medicine New York New York USA
| | - Lama A. Al‐Aswad
- Department of Ophthalmology, NYU Langone Health NYU Grossman School of Medicine New York New York USA
- Department of Population Health, NYU Langone Health NYU Grossman School of Medicine New York New York USA
| |
Collapse
|
33
|
Das A, Raposo GCC, Lopes DS, da Silva EJ, Carneiro VSM, Mota CCBDO, Amaral MM, Zezell DM, Barbosa-Silva R, Gomes ASL. Exploiting Nanomaterials for Optical Coherence Tomography and Photoacoustic Imaging in Nanodentistry. NANOMATERIALS (BASEL, SWITZERLAND) 2022; 12:506. [PMID: 35159853 PMCID: PMC8838952 DOI: 10.3390/nano12030506] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/29/2021] [Revised: 01/09/2022] [Accepted: 01/21/2022] [Indexed: 02/06/2023]
Abstract
There is already a societal awareness of the growing impact of nanoscience and nanotechnology, with nanomaterials (with at least one dimension less than 100 nm) now incorporated in items as diverse as mobile phones, clothes or dentifrices. In the healthcare area, nanoparticles of biocompatible materials have already been used for cancer treatment or bioimaging enhancement. Nanotechnology in dentistry, or nanodentistry, has already found some developments in dental nanomaterials for caries management, restorative dentistry and orthodontic adhesives. In this review, we present state-of-the-art scientific development in nanodentistry with an emphasis on two imaging techniques exploiting nanomaterials: optical coherence tomography (OCT) and photoacoustic imaging (PAI). Examples will be given using OCT with nanomaterials to enhance the acquired imaging, acting as optical clearing agents for OCT. A novel application of gold nanoparticles and nanorods for imaging enhancement of incipient occlusal caries using OCT will be described. Additionally, we will highlight how the OCT technique can be properly managed to provide imaging with spatial resolution down to 10's-100's nm resolution. For PAI, we will describe how new nanoparticles, namely TiN, prepared by femtosecond laser ablation, can be used in nanodentistry and will show photoacoustic microscopy and tomography images for such exogenous agents.
Collapse
Affiliation(s)
- Avishek Das
- Physics Department, Universidade Federal de Pernambuco, Recife 50670-901, PE, Brazil; (R.B.-S.); (A.S.L.G.)
| | - Gisele Cruz Camboim Raposo
- Graduate Program in Dentistry, Universidade Federal de Pernambuco, Recife 50670-901, PE, Brazil; (G.C.C.R.); (E.J.d.S.)
| | - Daniela Siqueira Lopes
- Faculty of Dentistry, Campus Arcoverde, Universidade de Pernambuco, Arcoverde 56503-146, PE, Brazil;
| | - Evair Josino da Silva
- Graduate Program in Dentistry, Universidade Federal de Pernambuco, Recife 50670-901, PE, Brazil; (G.C.C.R.); (E.J.d.S.)
| | | | | | - Marcello Magri Amaral
- Scientific and Technological Institute, Universidade Brasil, Fernandópolis 15600-000, SP, Brazil;
| | - Denise Maria Zezell
- Center for Lasers and Applications, Instituto de Pesquisas Energéticas e Nucleares IPEN—CNEN, São Paulo 05411-000, SP, Brazil;
| | - Renato Barbosa-Silva
- Physics Department, Universidade Federal de Pernambuco, Recife 50670-901, PE, Brazil; (R.B.-S.); (A.S.L.G.)
| | - Anderson Stevens Leonidas Gomes
- Physics Department, Universidade Federal de Pernambuco, Recife 50670-901, PE, Brazil; (R.B.-S.); (A.S.L.G.)
- Graduate Program in Dentistry, Universidade Federal de Pernambuco, Recife 50670-901, PE, Brazil; (G.C.C.R.); (E.J.d.S.)
| |
Collapse
|
34
|
Rank EA, Agneter A, Schmoll T, Leitgeb RA, Drexler W. Miniaturizing optical coherence tomography. TRANSLATIONAL BIOPHOTONICS 2022. [DOI: 10.1002/tbio.202100007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Affiliation(s)
- Elisabet A. Rank
- Center for Medical Physics and Biomedical Engineering Medical University of Vienna Vienna Austria
| | - Anja Agneter
- Center for Medical Physics and Biomedical Engineering Medical University of Vienna Vienna Austria
| | - Tilman Schmoll
- Center for Medical Physics and Biomedical Engineering Medical University of Vienna Vienna Austria
- Carl Zeiss Meditec, Inc. Dublin California USA
| | - Rainer A. Leitgeb
- Center for Medical Physics and Biomedical Engineering Medical University of Vienna Vienna Austria
| | - Wolfgang Drexler
- Center for Medical Physics and Biomedical Engineering Medical University of Vienna Vienna Austria
| |
Collapse
|
35
|
Automatic Segmentation of the Retinal Nerve Fiber Layer by Means of Mathematical Morphology and Deformable Models in 2D Optical Coherence Tomography Imaging. SENSORS 2021; 21:s21238027. [PMID: 34884031 PMCID: PMC8659929 DOI: 10.3390/s21238027] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/29/2021] [Revised: 11/17/2021] [Accepted: 11/25/2021] [Indexed: 11/17/2022]
Abstract
Glaucoma is a neurodegenerative disease process that leads to progressive damage of the optic nerve to produce visual impairment and blindness. Spectral-domain OCT technology enables peripapillary circular scans of the retina and the measurement of the thickness of the retinal nerve fiber layer (RNFL) for the assessment of the disease status or progression in glaucoma patients. This paper describes a new approach to segment and measure the retinal nerve fiber layer in peripapillary OCT images. The proposed method consists of two stages. In the first one, morphological operators robustly detect the coarse location of the layer boundaries, despite the speckle noise and diverse artifacts in the OCT image. In the second stage, deformable models are initialized with the results of the previous stage to perform a fine segmentation of the boundaries, providing an accurate measurement of the entire RNFL. The results of the RNFL segmentation were qualitatively assessed by ophthalmologists, and the measurements of the thickness of the RNFL were quantitatively compared with those provided by the OCT inbuilt software as well as the state-of-the-art methods.
Collapse
|
36
|
In vivo human retinal swept source optical coherence tomography and angiography at 830 nm with a CMOS compatible photonic integrated circuit. Sci Rep 2021; 11:21052. [PMID: 34702941 PMCID: PMC8548589 DOI: 10.1038/s41598-021-00637-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2021] [Accepted: 10/15/2021] [Indexed: 11/29/2022] Open
Abstract
Photonic integrated circuits (PIC) provide promising functionalities to significantly reduce the size and costs of optical coherence tomography (OCT) systems. This paper presents an imaging platform operating at a center wavelength of 830 nm for ophthalmic application using PIC-based swept source OCT. An on-chip Mach–Zehnder interferometer (MZI) configuration, which comprises an input power splitter, polarization beam splitters in the sample and the reference arm, and a 50/50 coupler for signal interference represents the core element of the system with a footprint of only \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$(12 \times 5)\;{\text {mm}}^2$$\end{document}(12×5)mm2. The system achieves 94 dB imaging sensitivity with 750 \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\upmu $$\end{document}μW on the sample, 50 kHz imaging speed and 5.5 \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\upmu $$\end{document}μm axial resolution (in soft tissue). With this setup, in vivo human retinal imaging of healthy subjects was performed producing B-scans, three-dimensional renderings as well as OCT angiography. These promising results are significant prerequisites for further integration of optical and electronic building blocks on a single swept source-OCT PIC.
Collapse
|
37
|
Abstract
Early detection and monitoring are critical to the diagnosis and management of glaucoma, a progressive optic neuropathy that causes irreversible blindness. Optical coherence tomography (OCT) has become a commonly utilized imaging modality that aids in the detection and monitoring of structural glaucomatous damage. Since its inception in 1991, OCT has progressed through multiple iterations, from time-domain OCT, to spectral-domain OCT, to swept-source OCT, all of which have progressively improved the resolution and speed of scans. Even newer technological advancements and OCT applications, such as adaptive optics, visible-light OCT, and OCT-angiography, have enriched the use of OCT in the evaluation of glaucoma. This article reviews current commercial and state-of-the-art OCT technologies and analytic techniques in the context of their utility for glaucoma diagnosis and management, as well as promising future directions.
Collapse
Affiliation(s)
- Alexi Geevarghese
- Department of Ophthalmology, NYU Langone Health, NYU Grossman School of Medicine, New York, NY 10016, USA;
| | - Gadi Wollstein
- Department of Ophthalmology, NYU Langone Health, NYU Grossman School of Medicine, New York, NY 10016, USA;
- Department of Biomedical Engineering, NYU Tandon School of Engineering, Brooklyn, New York 11201, USA
- Center for Neural Science, NYU College of Arts and Sciences, New York, NY 10003, USA
| | - Hiroshi Ishikawa
- Department of Ophthalmology, NYU Langone Health, NYU Grossman School of Medicine, New York, NY 10016, USA;
- Department of Biomedical Engineering, NYU Tandon School of Engineering, Brooklyn, New York 11201, USA
| | - Joel S Schuman
- Department of Ophthalmology, NYU Langone Health, NYU Grossman School of Medicine, New York, NY 10016, USA;
- Department of Biomedical Engineering, NYU Tandon School of Engineering, Brooklyn, New York 11201, USA
- Center for Neural Science, NYU College of Arts and Sciences, New York, NY 10003, USA
- Department of Physiology and Neuroscience, NYU Langone Health, NYU Grossman School of Medicine, New York, NY 10016, USA
| |
Collapse
|
38
|
Wang J, Li W, Chen Y, Fang W, Kong W, He Y, Shi G. Weakly supervised anomaly segmentation in retinal OCT images using an adversarial learning approach. BIOMEDICAL OPTICS EXPRESS 2021; 12:4713-4729. [PMID: 34513220 PMCID: PMC8407839 DOI: 10.1364/boe.426803] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/02/2021] [Revised: 06/17/2021] [Accepted: 06/26/2021] [Indexed: 05/09/2023]
Abstract
Lesion detection is a critical component of disease diagnosis, but the manual segmentation of lesions in medical images is time-consuming and experience-demanding. These issues have recently been addressed through deep learning models. However, most of the existing algorithms were developed using supervised training, which requires time-intensive manual labeling and prevents the model from detecting unaware lesions. As such, this study proposes a weakly supervised learning network based on CycleGAN for lesions segmentation in full-width optical coherence tomography (OCT) images. The model was trained to reconstruct underlying normal anatomic structures from abnormal input images, then the lesions can be detected by calculating the difference between the input and output images. A customized network architecture and a multi-scale similarity perceptual reconstruction loss were used to extend the CycleGAN model to transfer between objects exhibiting shape deformations. The proposed technique was validated using an open-source retinal OCT image dataset. Image-level anomaly detection and pixel-level lesion detection results were assessed using area-under-curve (AUC) and the Dice similarity coefficient, producing results of 96.94% and 0.8239, respectively, higher than all comparative methods. The average test time required to generate a single full-width image was 0.039 s, which is shorter than that reported in recent studies. These results indicate that our model can accurately detect and segment retinopathy lesions in real-time, without the need for supervised labeling. And we hope this method will be helpful to accelerate the clinical diagnosis process and reduce the misdiagnosis rate.
Collapse
Affiliation(s)
- Jing Wang
- Jiangsu Key Laboratory of Medical Optics, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou 215163, China
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230026, China
| | - Wanyue Li
- Jiangsu Key Laboratory of Medical Optics, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou 215163, China
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230026, China
| | - Yiwei Chen
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230026, China
| | - Wangyi Fang
- Department of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan University, Shanghai 201112, China
- Key Laboratory of Myopia of State Health Ministry, and Key Laboratory of Visual Impairment and Restoration of Shanghai, Shanghai 200003, China
| | - Wen Kong
- Jiangsu Key Laboratory of Medical Optics, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou 215163, China
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230026, China
| | - Yi He
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230026, China
| | - Guohua Shi
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230026, China
- Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Science, Shanghai 200031, China
| |
Collapse
|
39
|
Rao D S S, Jensen M, Grüner-Nielsen L, Olsen JT, Heiduschka P, Kemper B, Schnekenburger J, Glud M, Mogensen M, Israelsen NM, Bang O. Shot-noise limited, supercontinuum-based optical coherence tomography. LIGHT, SCIENCE & APPLICATIONS 2021; 10:133. [PMID: 34183643 PMCID: PMC8239030 DOI: 10.1038/s41377-021-00574-x] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/22/2020] [Revised: 05/26/2021] [Accepted: 06/07/2021] [Indexed: 05/19/2023]
Abstract
We present the first demonstration of shot-noise limited supercontinuum-based spectral domain optical coherence tomography (SD-OCT) with an axial resolution of 5.9 μm at a center wavelength of 1370 nm. Current supercontinuum-based SD-OCT systems cannot be operated in the shot-noise limited detection regime because of severe pulse-to-pulse relative intensity noise of the supercontinuum source. To overcome this disadvantage, we have developed a low-noise supercontinuum source based on an all-normal dispersion (ANDi) fiber, pumped by a femtosecond laser. The noise performance of our 90 MHz ANDi fiber-based supercontinuum source is compared to that of two commercial sources operating at 80 and 320 MHz repetition rate. We show that the low-noise of the ANDi fiber-based supercontinuum source improves the OCT images significantly in terms of both higher contrast, better sensitivity, and improved penetration. From SD-OCT imaging of skin, retina, and multilayer stacks we conclude that supercontinuum-based SD-OCT can enter the domain of shot-noise limited detection.
Collapse
Affiliation(s)
- Shreesha Rao D S
- DTU Fotonik, Dept. of Photonics Engineering, Technical University of Denmark, Ørsteds Plads, 2800, Kongens Lyngby, Denmark
| | - Mikkel Jensen
- DTU Fotonik, Dept. of Photonics Engineering, Technical University of Denmark, Ørsteds Plads, 2800, Kongens Lyngby, Denmark
| | - Lars Grüner-Nielsen
- DTU Fotonik, Dept. of Photonics Engineering, Technical University of Denmark, Ørsteds Plads, 2800, Kongens Lyngby, Denmark
| | | | - Peter Heiduschka
- Department of Ophthalmology, University of Münster Medical Centre, Domagkstr. 15, D-48149, Münster, Germany
| | - Björn Kemper
- Biomedical Technology Center of the Medical Faculty, University of Münster, Mendelstr. 17, D-48149, Münster, Germany
| | - Jürgen Schnekenburger
- Biomedical Technology Center of the Medical Faculty, University of Münster, Mendelstr. 17, D-48149, Münster, Germany
| | - Martin Glud
- Department of Dermatology, Bisbebjerg Hospital, University of Copenhagen, Bispebjerg Bakke 23, 2400, Copenhagen NV, Denmark
| | - Mette Mogensen
- Department of Dermatology, Bisbebjerg Hospital, University of Copenhagen, Bispebjerg Bakke 23, 2400, Copenhagen NV, Denmark
| | - Niels Møller Israelsen
- DTU Fotonik, Dept. of Photonics Engineering, Technical University of Denmark, Ørsteds Plads, 2800, Kongens Lyngby, Denmark
| | - Ole Bang
- DTU Fotonik, Dept. of Photonics Engineering, Technical University of Denmark, Ørsteds Plads, 2800, Kongens Lyngby, Denmark.
- NKT Photonics A/S, Blokken 84, 3460, Birkerød, Denmark.
| |
Collapse
|
40
|
Li J, Montarello NJ, Hoogendoorn A, Verjans JW, Bursill CA, Peter K, Nicholls SJ, McLaughlin RA, Psaltis PJ. Multimodality Intravascular Imaging of High-Risk Coronary Plaque. JACC Cardiovasc Imaging 2021; 15:145-159. [PMID: 34023267 DOI: 10.1016/j.jcmg.2021.03.028] [Citation(s) in RCA: 29] [Impact Index Per Article: 9.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/18/2020] [Revised: 03/01/2021] [Accepted: 03/22/2021] [Indexed: 01/13/2023]
Abstract
The majority of coronary atherothrombotic events presenting as myocardial infarction (MI) occur as a result of plaque rupture or erosion. Understanding the evolution from a stable plaque into a life-threatening, high-risk plaque is required for advancing clinical approaches to predict atherothrombotic events, and better treat coronary atherosclerosis. Unfortunately, none of the coronary imaging approaches used in clinical practice can reliably predict which plaques will cause an MI. Currently used imaging techniques mostly identify morphological features of plaques, but are not capable of detecting essential molecular characteristics known to be important drivers of future risk. To address this challenge, engineers, scientists, and clinicians have been working hand-in-hand to advance a variety of multimodality intravascular imaging techniques, whereby 2 or more complementary modalities are integrated into the same imaging catheter. Some of these have already been tested in early clinical studies, with other next-generation techniques also in development. This review examines these emerging hybrid intracoronary imaging techniques and discusses their strengths, limitations, and potential for clinical translation from both an engineering and clinical perspective.
Collapse
Affiliation(s)
- Jiawen Li
- Adelaide Medical School, University of Adelaide, Adelaide, Australia; Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, Australia; Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, Australia
| | - Nicholas J Montarello
- Department of Cardiology, Central Adelaide Local Health Network, Adelaide, Australia
| | - Ayla Hoogendoorn
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, Australia; Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, Australia; Vascular Research Centre, Heart and Vascular Program, Lifelong Health Theme, South Australian Health and Medical Research Institute, Adelaide, Australia
| | - Johan W Verjans
- Adelaide Medical School, University of Adelaide, Adelaide, Australia; Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, Australia; Department of Cardiology, Central Adelaide Local Health Network, Adelaide, Australia; Vascular Research Centre, Heart and Vascular Program, Lifelong Health Theme, South Australian Health and Medical Research Institute, Adelaide, Australia
| | - Christina A Bursill
- Adelaide Medical School, University of Adelaide, Adelaide, Australia; Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, Australia; Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, Australia; Vascular Research Centre, Heart and Vascular Program, Lifelong Health Theme, South Australian Health and Medical Research Institute, Adelaide, Australia
| | | | - Stephen J Nicholls
- Monash Cardiovascular Research Centre, Victorian Heart Institute, Monash University, Melbourne, Australia
| | - Robert A McLaughlin
- Adelaide Medical School, University of Adelaide, Adelaide, Australia; Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, Australia; Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, Australia
| | - Peter J Psaltis
- Adelaide Medical School, University of Adelaide, Adelaide, Australia; Department of Cardiology, Central Adelaide Local Health Network, Adelaide, Australia; Vascular Research Centre, Heart and Vascular Program, Lifelong Health Theme, South Australian Health and Medical Research Institute, Adelaide, Australia.
| |
Collapse
|
41
|
Luo Y, Xu Q, Jin R, Wu M, Liu L. Automatic detection of retinopathy with optical coherence tomography images via a semi-supervised deep learning method. BIOMEDICAL OPTICS EXPRESS 2021; 12:2684-2702. [PMID: 34123497 PMCID: PMC8176801 DOI: 10.1364/boe.418364] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/22/2020] [Revised: 03/27/2021] [Accepted: 04/02/2021] [Indexed: 05/03/2023]
Abstract
Automatic detection of retinopathy via computer vision techniques is of great importance for clinical applications. However, traditional deep learning based methods in computer vision require a large amount of labeled data, which are expensive and may not be available in clinical applications. To mitigate this issue, in this paper, we propose a semi-supervised deep learning method built upon pre-trained VGG-16 and virtual adversarial training (VAT) for the detection of retinopathy with optical coherence tomography (OCT) images. It only requires very few labeled and a number of unlabeled OCT images for model training. In experiments, we have evaluated the proposed method on two popular datasets. With only 80 labeled OCT images, the proposed method can achieve classification accuracies of 0.942 and 0.936, sensitivities of 0.942 and 0.936, specificities of 0.971 and 0.979, and AUCs (Area under the ROC Curves) of 0.997 and 0.993 on the two datasets, respectively. When comparing with human experts, it achieves expert level with 80 labeled OCT images and outperforms four out of six experts with 200 labeled OCT images. Furthermore, we also adopt the Gradient Class Activation Map (Grad-CAM) method to visualize the key regions that the proposed method focuses on when making predictions. It shows that the proposed method can accurately recognize the key patterns of the input OCT images when predicting retinopathy.
Collapse
Affiliation(s)
- Yuemei Luo
- School of Electrical and Electronic
Engineering, Nanyang Technological
University, Singapore, 639798, Singapore
| | - Qing Xu
- Institute for Infocomm
Research, Agency for Science, Technology and Research
(A*STAR), Singapore, 138632, Singapore
| | - Ruibing Jin
- Institute for Infocomm
Research, Agency for Science, Technology and Research
(A*STAR), Singapore, 138632, Singapore
| | - Min Wu
- Institute for Infocomm
Research, Agency for Science, Technology and Research
(A*STAR), Singapore, 138632, Singapore
| | - Linbo Liu
- School of Electrical and Electronic
Engineering, Nanyang Technological
University, Singapore, 639798, Singapore
- School of Chemical and Biomedical
Engineering, Nanyang Technological
University, Singapore, 637459, Singapore
| |
Collapse
|
42
|
Dremin V, Marcinkevics Z, Zherebtsov E, Popov A, Grabovskis A, Kronberga H, Geldnere K, Doronin A, Meglinski I, Bykov A. Skin Complications of Diabetes Mellitus Revealed by Polarized Hyperspectral Imaging and Machine Learning. IEEE TRANSACTIONS ON MEDICAL IMAGING 2021; 40:1207-1216. [PMID: 33406038 DOI: 10.1109/tmi.2021.3049591] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/08/2023]
Abstract
Aging and diabetes lead to protein glycation and cause dysfunction of collagen-containing tissues. The accompanying structural and functional changes of collagen significantly contribute to the development of various pathological malformations affecting the skin, blood vessels, and nerves, causing a number of complications, increasing disability risks and threat to life. In fact, no methods of non-invasive assessment of glycation and associated metabolic processes in biotissues or prediction of possible skin complications, e.g., ulcers, currently exist for endocrinologists and clinical diagnosis. In this publication, utilizing emerging photonics-based technology, innovative solutions in machine learning, and definitive physiological characteristics, we introduce a diagnostic approach capable of evaluating the skin complications of diabetes mellitus at the very earlier stage. The results of the feasibility studies, as well as the actual tests on patients with diabetes and healthy volunteers, clearly show the ability of the approach to differentiate diabetic and control groups. Furthermore, the developed in-house polarization-based hyperspectral imaging technique accomplished with the implementation of the artificial neural network provides new horizons in the study and diagnosis of age-related diseases.
Collapse
|
43
|
Maloca PM, Müller PL, Lee AY, Tufail A, Balaskas K, Niklaus S, Kaiser P, Suter S, Zarranz-Ventura J, Egan C, Scholl HPN, Schnitzer TK, Singer T, Hasler PW, Denk N. Unraveling the deep learning gearbox in optical coherence tomography image segmentation towards explainable artificial intelligence. Commun Biol 2021; 4:170. [PMID: 33547415 PMCID: PMC7864998 DOI: 10.1038/s42003-021-01697-y] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2020] [Accepted: 01/13/2021] [Indexed: 01/30/2023] Open
Abstract
Machine learning has greatly facilitated the analysis of medical data, while the internal operations usually remain intransparent. To better comprehend these opaque procedures, a convolutional neural network for optical coherence tomography image segmentation was enhanced with a Traceable Relevance Explainability (T-REX) technique. The proposed application was based on three components: ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization ('neural recording'). An overall average variability of 1.75% between the human graders and the algorithm was found, slightly minor to 2.02% among human graders. The ambiguity in ground truth had noteworthy impact on machine learning results, which could be visualized. The convolutional neural network balanced between graders and allowed for modifiable predictions dependent on the compartment. Using the proposed T-REX setup, machine learning processes could be rendered more transparent and understandable, possibly leading to optimized applications.
Collapse
Affiliation(s)
- Peter M. Maloca
- grid.508836.0Institute of Molecular and Clinical Ophthalmology Basel (IOB), Basel, Switzerland ,grid.410567.1OCTlab, Department of Ophthalmology, University Hospital Basel, Basel, Switzerland ,grid.6612.30000 0004 1937 0642Department of Ophthalmology, University of Basel, Basel, Switzerland ,grid.436474.60000 0000 9168 0080Moorfields Eye Hospital NHS Foundation Trust, London, UK
| | - Philipp L. Müller
- grid.436474.60000 0000 9168 0080Moorfields Eye Hospital NHS Foundation Trust, London, UK ,grid.10388.320000 0001 2240 3300Department of Ophthalmology, University of Bonn, Bonn, Germany
| | - Aaron Y. Lee
- grid.267047.00000 0001 2105 7936Department of Ophthalmology, Puget Sound Veteran Affairs, Seattle, WA USA ,grid.34477.330000000122986657eScience Institute, University of Washington, Seattle, WA USA ,grid.34477.330000000122986657Department of Ophthalmology, University of Washington, Seattle, WA USA
| | - Adnan Tufail
- grid.436474.60000 0000 9168 0080Moorfields Eye Hospital NHS Foundation Trust, London, UK
| | - Konstantinos Balaskas
- grid.436474.60000 0000 9168 0080Moorfields Eye Hospital NHS Foundation Trust, London, UK ,Moorfields Ophthalmic Reading Centre, London, UK
| | - Stephanie Niklaus
- grid.417570.00000 0004 0374 1269Pharma Research and Early Development (pRED), Pharmaceutical Sciences (PS), Roche, Innovation Center Basel, Basel, Switzerland
| | - Pascal Kaiser
- grid.483647.aSupercomputing Systems, Zurich, Switzerland
| | - Susanne Suter
- grid.483647.aSupercomputing Systems, Zurich, Switzerland ,grid.19739.350000000122291644Zurich University of Applied Sciences, Waedenswil, Switzerland
| | - Javier Zarranz-Ventura
- grid.410458.c0000 0000 9635 9413Institut Clínic d’Oftalmologia, Hospital Clínic de Barcelona, Barcelona, Spain
| | - Catherine Egan
- grid.436474.60000 0000 9168 0080Moorfields Eye Hospital NHS Foundation Trust, London, UK
| | - Hendrik P. N. Scholl
- grid.508836.0Institute of Molecular and Clinical Ophthalmology Basel (IOB), Basel, Switzerland ,grid.6612.30000 0004 1937 0642Department of Ophthalmology, University of Basel, Basel, Switzerland
| | - Tobias K. Schnitzer
- grid.417570.00000 0004 0374 1269Pharma Research and Early Development (pRED), Pharmaceutical Sciences (PS), Roche, Innovation Center Basel, Basel, Switzerland
| | - Thomas Singer
- grid.417570.00000 0004 0374 1269Pharma Research and Early Development (pRED), Pharmaceutical Sciences (PS), Roche, Innovation Center Basel, Basel, Switzerland
| | - Pascal W. Hasler
- grid.410567.1OCTlab, Department of Ophthalmology, University Hospital Basel, Basel, Switzerland ,grid.6612.30000 0004 1937 0642Department of Ophthalmology, University of Basel, Basel, Switzerland
| | - Nora Denk
- grid.6612.30000 0004 1937 0642Department of Ophthalmology, University of Basel, Basel, Switzerland ,grid.417570.00000 0004 0374 1269Pharma Research and Early Development (pRED), Pharmaceutical Sciences (PS), Roche, Innovation Center Basel, Basel, Switzerland
| |
Collapse
|
44
|
Chen TH, Wu YC, Tsai TY, Chueh CB, Huang BH, Huang YP, Tsai MT, Yasuno Y, Lee HC. Effect of A-scan rate and interscan interval on optical coherence angiography. BIOMEDICAL OPTICS EXPRESS 2021; 12:722-736. [PMID: 33680538 PMCID: PMC7901325 DOI: 10.1364/boe.409636] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/07/2020] [Revised: 12/04/2020] [Accepted: 12/22/2020] [Indexed: 05/25/2023]
Abstract
Optical coherence tomography angiography (OCTA) can provide rapid, volumetric, and noninvasive imaging of tissue microvasculature without the requirement of exogenous contrast agents. To investigate how A-scan rate and interscan time affected the contrast and dynamic range of OCTA, we developed a 1.06-µm swept-source OCT system enabling 100-kHz or 200-kHz OCT using two light sources. After system settings were carefully adjusted, almost the same detection sensitivity was achieved between the 100-kHz and 200-kHz modalities. OCTA of ear skin was performed on five mice. We used the variable interscan time analysis algorithm (VISTA) and the designated scanning protocol with OCTA images reconstructed through the correlation mapping method. With a relatively long interscan time (e.g., 12.5 ms vs. 6.25 ms for 200-kHz OCT), OCTA can identify more intricate microvascular networks. OCTA image sets with the same interscan time (e.g., 12.5 ms) were compared. OCTA images acquired with a 100-kHz A-scan rate showed finer microvasculature than did other imaging modalities. We performed quantitative analysis on the contrast from OCTA images reconstructed with different A-scan rates and interscan time intervals in terms of vessel area, total vessel length, and junction density.
Collapse
Affiliation(s)
- Ting-Hao Chen
- Graduate Institute of Photonics and Optoelectronics, National Taiwan University, Taipei 10617, Taiwan
| | - Yi-Chun Wu
- Graduate Institute of Photonics and Optoelectronics, National Taiwan University, Taipei 10617, Taiwan
| | - Ting-Yen Tsai
- Graduate Institute of Photonics and Optoelectronics, National Taiwan University, Taipei 10617, Taiwan
| | - Chuan-Bor Chueh
- Graduate Institute of Photonics and Optoelectronics, National Taiwan University, Taipei 10617, Taiwan
| | - Bo-Huei Huang
- Department of Electrical Engineering, Chang Gung University, Taoyuan 33302, Taiwan
| | - Yin-Peng Huang
- Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei 10617, Taiwan
| | - Meng-Tsan Tsai
- Department of Electrical Engineering, Chang Gung University, Taoyuan 33302, Taiwan
- Department of Neurosurgery, Chang Gung Memorial Hospital, Linkou, Taoyuan 33306, Taiwan
| | - Yoshiaki Yasuno
- Computational Optics Group, University of Tsukuba, Tennodai 1-1-1, Tsukuba, Ibaraki 305-8573, Japan
| | - Hsiang-Chieh Lee
- Graduate Institute of Photonics and Optoelectronics, National Taiwan University, Taipei 10617, Taiwan
- Department of Electrical Engineering, National Taiwan University, Taipei 10617, Taiwan
- Molecular Imaging Center, National Taiwan University, Taipei 10617, Taiwan
| |
Collapse
|
45
|
Rank EA, Sentosa R, Harper DJ, Salas M, Gaugutz A, Seyringer D, Nevlacsil S, Maese-Novo A, Eggeling M, Muellner P, Hainberger R, Sagmeister M, Kraft J, Leitgeb RA, Drexler W. Toward optical coherence tomography on a chip: in vivo three-dimensional human retinal imaging using photonic integrated circuit-based arrayed waveguide gratings. LIGHT, SCIENCE & APPLICATIONS 2021; 10:6. [PMID: 33402664 PMCID: PMC7785745 DOI: 10.1038/s41377-020-00450-0] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/27/2020] [Revised: 11/14/2020] [Accepted: 12/03/2020] [Indexed: 05/19/2023]
Abstract
In this work, we present a significant step toward in vivo ophthalmic optical coherence tomography and angiography on a photonic integrated chip. The diffraction gratings used in spectral-domain optical coherence tomography can be replaced by photonic integrated circuits comprising an arrayed waveguide grating. Two arrayed waveguide grating designs with 256 channels were tested, which enabled the first chip-based optical coherence tomography and angiography in vivo three-dimensional human retinal measurements. Design 1 supports a bandwidth of 22 nm, with which a sensitivity of up to 91 dB (830 µW) and an axial resolution of 10.7 µm was measured. Design 2 supports a bandwidth of 48 nm, with which a sensitivity of 90 dB (480 µW) and an axial resolution of 6.5 µm was measured. The silicon nitride-based integrated optical waveguides were fabricated with a fully CMOS-compatible process, which allows their monolithic co-integration on top of an optoelectronic silicon chip. As a benchmark for chip-based optical coherence tomography, tomograms generated by a commercially available clinical spectral-domain optical coherence tomography system were compared to those acquired with on-chip gratings. The similarities in the tomograms demonstrate the significant clinical potential for further integration of optical coherence tomography on a chip system.
Collapse
Affiliation(s)
- Elisabet A Rank
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20/4 L, 1090, Vienna, Austria.
| | - Ryan Sentosa
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20/4 L, 1090, Vienna, Austria
| | - Danielle J Harper
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20/4 L, 1090, Vienna, Austria
| | - Matthias Salas
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20/4 L, 1090, Vienna, Austria
| | - Anna Gaugutz
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20/4 L, 1090, Vienna, Austria
| | - Dana Seyringer
- Research Centre for Microtechnology, Vorarlberg University of Applied Sciences, Hochschulstrasse 1, 6850, Dornbirn, Austria
| | - Stefan Nevlacsil
- AIT Austrian Institute of Technology GmbH, Gieffinggasse 4, 1210, Vienna, Austria
| | - Alejandro Maese-Novo
- AIT Austrian Institute of Technology GmbH, Gieffinggasse 4, 1210, Vienna, Austria
| | - Moritz Eggeling
- AIT Austrian Institute of Technology GmbH, Gieffinggasse 4, 1210, Vienna, Austria
| | - Paul Muellner
- AIT Austrian Institute of Technology GmbH, Gieffinggasse 4, 1210, Vienna, Austria
| | - Rainer Hainberger
- AIT Austrian Institute of Technology GmbH, Gieffinggasse 4, 1210, Vienna, Austria
| | | | - Jochen Kraft
- ams AG, Tobelbader Strasse 30, 8141, Premstaetten, Austria
| | - Rainer A Leitgeb
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20/4 L, 1090, Vienna, Austria
| | - Wolfgang Drexler
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Waehringer Guertel 18-20/4 L, 1090, Vienna, Austria
| |
Collapse
|
46
|
Hao Q, Zhou K, Yang J, Hu Y, Chai Z, Ma Y, Liu G, Zhao Y, Gao S, Liu J. High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning. JOURNAL OF BIOMEDICAL OPTICS 2020; 25:JBO-200220SSR. [PMID: 33191687 PMCID: PMC7666869 DOI: 10.1117/1.jbo.25.12.123702] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/14/2020] [Accepted: 10/26/2020] [Indexed: 05/10/2023]
Abstract
SIGNIFICANCE Reducing the bit depth is an effective approach to lower the cost of an optical coherence tomography (OCT) imaging device and increase the transmission efficiency in data acquisition and telemedicine. However, a low bit depth will lead to the degradation of the detection sensitivity, thus reducing the signal-to-noise ratio (SNR) of OCT images. AIM We propose using deep learning to reconstruct high SNR OCT images from low bit-depth acquisition. APPROACH The feasibility of our approach is evaluated by applying this approach to the quantized 3- to 8-bit data from native 12-bit interference fringes. We employ a pixel-to-pixel generative adversarial network (pix2pixGAN) architecture in the low-to-high bit-depth OCT image transition. RESULTS Extensively, qualitative and quantitative results show our method could significantly improve the SNR of the low bit-depth OCT images. The adopted pix2pixGAN is superior to other possible deep learning and compressed sensing solutions. CONCLUSIONS Our work demonstrates that the proper integration of OCT and deep learning could benefit the development of healthcare in low-resource settings.
Collapse
Affiliation(s)
- Qiangjiang Hao
- Chinese Academy of Sciences, Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Ningbo, China
- University of Science and Technology of China, Nano Science and Technology Institute, Suzhou, China
| | - Kang Zhou
- Chinese Academy of Sciences, Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Ningbo, China
- ShanghaiTech University, School of Information Science and Technology, Shanghai, China
| | - Jianlong Yang
- Chinese Academy of Sciences, Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Ningbo, China
- Address all correspondence to Jianlong Yang,
| | - Yan Hu
- Southern University of Science and Technology, Department of Computer Science and Engineering, Shenzhen, China
| | - Zhengjie Chai
- Chinese Academy of Sciences, Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Ningbo, China
- ShanghaiTech University, School of Information Science and Technology, Shanghai, China
| | - Yuhui Ma
- Chinese Academy of Sciences, Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Ningbo, China
| | | | - Yitian Zhao
- Chinese Academy of Sciences, Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Ningbo, China
| | - Shenghua Gao
- ShanghaiTech University, School of Information Science and Technology, Shanghai, China
| | - Jiang Liu
- Chinese Academy of Sciences, Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Ningbo, China
- Southern University of Science and Technology, Department of Computer Science and Engineering, Shenzhen, China
| |
Collapse
|
47
|
Li J, Thiele S, Quirk BC, Kirk RW, Verjans JW, Akers E, Bursill CA, Nicholls SJ, Herkommer AM, Giessen H, McLaughlin RA. Ultrathin monolithic 3D printed optical coherence tomography endoscopy for preclinical and clinical use. LIGHT, SCIENCE & APPLICATIONS 2020; 9:124. [PMID: 32704357 PMCID: PMC7371638 DOI: 10.1038/s41377-020-00365-w] [Citation(s) in RCA: 38] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/16/2020] [Revised: 06/23/2020] [Accepted: 07/04/2020] [Indexed: 05/03/2023]
Abstract
Preclinical and clinical diagnostics increasingly rely on techniques to visualize internal organs at high resolution via endoscopes. Miniaturized endoscopic probes are necessary for imaging small luminal or delicate organs without causing trauma to tissue. However, current fabrication methods limit the imaging performance of highly miniaturized probes, restricting their widespread application. To overcome this limitation, we developed a novel ultrathin probe fabrication technique that utilizes 3D microprinting to reliably create side-facing freeform micro-optics (<130 µm diameter) on single-mode fibers. Using this technique, we built a fully functional ultrathin aberration-corrected optical coherence tomography probe. This is the smallest freeform 3D imaging probe yet reported, with a diameter of 0.457 mm, including the catheter sheath. We demonstrated image quality and mechanical flexibility by imaging atherosclerotic human and mouse arteries. The ability to provide microstructural information with the smallest optical coherence tomography catheter opens a gateway for novel minimally invasive applications in disease.
Collapse
Affiliation(s)
- Jiawen Li
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide Medical School, University of Adelaide, Adelaide, SA 5005 Australia
- Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, SA 5005 Australia
| | - Simon Thiele
- Institute of Applied Optics (ITO) and Research Center SCoPE, University of Stuttgart, 70569 Stuttgart, Germany
| | - Bryden C. Quirk
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide Medical School, University of Adelaide, Adelaide, SA 5005 Australia
- Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, SA 5005 Australia
| | - Rodney W. Kirk
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide Medical School, University of Adelaide, Adelaide, SA 5005 Australia
- Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, SA 5005 Australia
| | - Johan W. Verjans
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide Medical School, University of Adelaide, Adelaide, SA 5005 Australia
- South Australian Health and Medical Research Institute (SAHMRI), Adelaide, SA 5000 Australia
- Royal Adelaide Hospital, Adelaide, SA 5000 Australia
| | - Emma Akers
- South Australian Health and Medical Research Institute (SAHMRI), Adelaide, SA 5000 Australia
| | - Christina A. Bursill
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide Medical School, University of Adelaide, Adelaide, SA 5005 Australia
- South Australian Health and Medical Research Institute (SAHMRI), Adelaide, SA 5000 Australia
| | - Stephen J. Nicholls
- Monash Cardiovascular Research Centre, Monash University, Melbourne, VIC 3168 Australia
| | - Alois M. Herkommer
- Institute of Applied Optics (ITO) and Research Center SCoPE, University of Stuttgart, 70569 Stuttgart, Germany
| | - Harald Giessen
- 4th Physics Institute and Research Center SCoPE, University of Stuttgart, 70569 Stuttgart, Germany
| | - Robert A. McLaughlin
- Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide Medical School, University of Adelaide, Adelaide, SA 5005 Australia
- Institute for Photonics and Advanced Sensing, The University of Adelaide, Adelaide, SA 5005 Australia
| |
Collapse
|
48
|
Zheng C, Xie X, Zhou K, Chen B, Chen J, Ye H, Li W, Qiao T, Gao S, Yang J, Liu J. Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders. Transl Vis Sci Technol 2020; 9:29. [PMID: 32832202 PMCID: PMC7410116 DOI: 10.1167/tvst.9.2.29] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2019] [Accepted: 03/24/2020] [Indexed: 02/05/2023] Open
Abstract
PURPOSE To assess whether a generative adversarial network (GAN) could synthesize realistic optical coherence tomography (OCT) images that satisfactorily serve as the educational images for retinal specialists, and the training datasets for the classification of various retinal disorders using deep learning (DL). METHODS The GANs architecture was adopted to synthesize high-resolution OCT images trained on a publicly available OCT dataset, including urgent referrals (37,206 OCT images from eyes with choroidal neovascularization, and 11,349 OCT images from eyes with diabetic macular edema) and nonurgent referrals (8617 OCT images from eyes with drusen, and 51,140 OCT images from normal eyes). Four hundred real and synthetic OCT images were evaluated by two retinal specialists (with over 10 years of clinical retinal experience) to assess image quality. We further trained two DL models on either real or synthetic datasets and compared the performance of urgent versus nonurgent referrals diagnosis tested on a local (1000 images from the public dataset) and clinical validation dataset (278 images from Shanghai Shibei Hospital). RESULTS The image quality of real versus synthetic OCT images was similar as assessed by two retinal specialists. The accuracy of discrimination of real versus synthetic OCT images was 59.50% for retinal specialist 1 and 53.67% for retinal specialist 2. For the local dataset, the DL model trained on real (DL_Model_R) and synthetic OCT images (DL_Model_S) had an area under the curve (AUC) of 0.99, and 0.98, respectively. For the clinical dataset, the AUC was 0.94 for DL_Model_R and 0.90 for DL_Model_S. CONCLUSIONS The GAN synthetic OCT images can be used by clinicians for educational purposes and for developing DL algorithms. TRANSLATIONAL RELEVANCE The medical image synthesis based on GANs is promising in humans and machines to fulfill clinical tasks.
Collapse
Affiliation(s)
- Ce Zheng
- Department of Ophthalmology, Shanghai Children's Hospital, Shanghai Jiao Tong University, Shanghai, China
| | - Xiaolin Xie
- Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, Guangdong, China
| | - Kang Zhou
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, Zhejiang, China
- School of Information Science and Technology, ShanghaiTech University, Shanghai, China
| | - Bang Chen
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, Zhejiang, China
| | - Jili Chen
- Department of Ophthalmology, Shibei Hospital, Shanghai, China
| | - Haiyun Ye
- Department of Ophthalmology, Shanghai Children's Hospital, Shanghai Jiao Tong University, Shanghai, China
| | - Wen Li
- Department of Ophthalmology, Shanghai Children's Hospital, Shanghai Jiao Tong University, Shanghai, China
| | - Tong Qiao
- Department of Ophthalmology, Shanghai Children's Hospital, Shanghai Jiao Tong University, Shanghai, China
| | - Shenghua Gao
- School of Information Science and Technology, ShanghaiTech University, Shanghai, China
| | - Jianlong Yang
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, Zhejiang, China
| | - Jiang Liu
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, Zhejiang, China
- Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China
| |
Collapse
|
49
|
Liu Y, Zhu D, Xu J, Wang Y, Feng W, Chen D, Li Y, Liu H, Guo X, Qiu H, Gu Y. Penetration-enhanced optical coherence tomography angiography with optical clearing agent for clinical evaluation of human skin. Photodiagnosis Photodyn Ther 2020; 30:101734. [PMID: 32171879 DOI: 10.1016/j.pdpdt.2020.101734] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2020] [Revised: 03/05/2020] [Accepted: 03/09/2020] [Indexed: 12/14/2022]
Abstract
BACKGROUND Optical coherence tomography angiography (OCTA) is an emerging imaging technique which shows its advantages over visualizing microcirculation with free label. However, its shortcomings in imaging depth limit its development in dermatological field. Nowadays, the newly optical clearing agent (OCA) designed for skin optical imaging demonstrates its potential. In our study, whether this OCA can improve the imaging ability of OCTA in healthy human skin and whether the combination of them is beneficial to compare the lesions and the contralateral normal skins in the patients with port wine stains (PWS) have been investigated. METHODS Five healthy volunteers and 3 PWS patients were recruited in this study. In terms of healthy people, the opisthenar area which has same structure information as facial skin was taken for investigating the OCA's ability of enhancing OCTA imaging depth on healthy human skin, besides, in order to verifying whether the exists of skin corneum interfere OCA's function, we compared the effect of only using OCA with that of comprehensive using pre-processing skin and OCA. There are one physical removing corneum method by using medical tape to strip opisthenar skin for over 20-time and one chemical way through applying exfoliating cream. For PWS patient, the combining using OCA and OCTA was applied at the lesion area and the contralateral normal area for the purpose of verifying their ability to provide the information of vessels. RESULTS This novel OCA had excellent efficacy to increase the penetration depth of human opisthenar skin for the OCTA imaging by approximately 0.16 ± 0.03 mm. Pre-processing of stratum corneum with an exfoliating cream or medical tape stripping did not further benefit the penetrating efficacy of the OCA. Moreover, according to a comprehensive analysis of the OCTA images enhanced by the OCA, the PWS lesions usually have larger density and diameter of the vessels which located in deep layers (beyond 0.21 mm) than the contralateral normal skin. CONCLUSIONS The OCTA imaging depth and contrast were significantly improved by the OCA. The OCA application is a simple and efficient clinical procedure for OCTA enhancement. Moreover, it demonstrated great clinical value to compare the normal skin and the PWS lesions in the patients by the enhanced OCTA imaging.
Collapse
Affiliation(s)
- Yidi Liu
- Department of Laser Medicine, First Medical Center of PLA General Hospital, Beijing, 100853, China
| | - Dan Zhu
- Huazhong University of Science and Technology, Key Laboratory of Biomedical Photonics of Ministry of Education, Department of Biomedical Engineering, Wuhan, 430033, China
| | - Jingjiang Xu
- School of Physics and Optoelectronic Engineering, Foshan University, Foshan, 528000, China
| | - Ying Wang
- Department of Laser Medicine, First Medical Center of PLA General Hospital, Beijing, 100853, China
| | - Wei Feng
- Central People's Hospital of Zhanjiang, Zhanjiang, 524000, China
| | - Defu Chen
- Department of Laser Medicine, First Medical Center of PLA General Hospital, Beijing, 100853, China
| | - Yunqi Li
- Department of Laser Medicine, First Medical Center of PLA General Hospital, Beijing, 100853, China
| | - Haolin Liu
- Department of Laser Medicine, First Medical Center of PLA General Hospital, Beijing, 100853, China
| | - Xianghuan Guo
- Department of Laser Medicine, First Medical Center of PLA General Hospital, Beijing, 100853, China
| | - Haixia Qiu
- Department of Laser Medicine, First Medical Center of PLA General Hospital, Beijing, 100853, China.
| | - Ying Gu
- Department of Laser Medicine, First Medical Center of PLA General Hospital, Beijing, 100853, China; Institute of Engineering Medicine, Beijing Institute of Technology, Beijing 100081, China.
| |
Collapse
|
50
|
Zavareh AT, Hoyos S. Kalman-Based Real-Time Functional Decomposition for the Spectral Calibration in Swept Source Optical Coherence Tomography. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2020; 14:257-273. [PMID: 31751249 DOI: 10.1109/tbcas.2019.2953212] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
This paper presents a real-time functional decomposition adaptive algorithm for the optimal sampling of the interferometric signal in Swept-Source Optical Coherence Tomography imaging systems, which completely eliminates the input signal dependent nonlinearities that are problematic in current state-of-the-art OCT realizations that use interpolation and resampling. The proposed adaptive calibration algorithm uses the Kalman approach to estimate the wavenumber index parameter k from the Mach-Zender Interferometer signal which is then applied to an adaptive level crossing sampler to generate a sampling clock that k-linearizes the data on real-time during the sampling process. Such a system implements an artifact-free realization of the technology removing the need for classical interpolation and resampling. The new real-time linearization scheme has the additional capability of increasing the imaging acquisition speed by 10X while providing robustness to noise, properties that are demonstrated through mathematical analysis and simulation results throughout the paper.
Collapse
|