- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Integrating Handcrafted and Deep Features for Optical Coherence Tomography Based Retinal Disease Classification
摘要： Deep Neural Networks (DNNs) have been widely applied to automatic analysis of medical images for disease diagnosis, and to help human experts by efficiently processing immense amounts of images. While handcrafted feature has been used for eye disease detection or classification since the 1990s, DNN was recently adopted in this area and showed very promising performance. Since handcrafted and deep feature can extract complementary information, we propose in this paper three different integration frameworks to combine handcrafted and deep feature for optical coherence tomography (OCT) image based eye disease classification. In addition, to integrate the handcrafted feature at Input and Fully Connection (FC) layers using existing networks like VGG, DenseNet and Xception, a novel ribcage network (RC Net) is also proposed for feature integration at middle layers. For RC Net, two “rib” channels are designed to independently process deep and handcrafted features, and another so called “spine” channel is designed for the integration. While dense blocks are the main components of the three channels, sum operation is proposed for the feature map integration. Our experimental results showed that the deep networks achieved better classification accuracy after integration of the handcrafted features e.g. SIFT and Gabor. The RC Net showed the best performance among all proposed feature integration methods.
关键词： feature integration,deep learning,Artificial intelligence,optical coherence tomography
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Ultrasonics Symposium (IUS) - Kobe, Japan (2018.10.22-2018.10.25)] 2018 IEEE International Ultrasonics Symposium (IUS) - High Intensity Focused Ultrasound (HIFU) Combines Optical Coherence Tomography(OCT) for Biological Tissue Treatment and Evaluation
摘要： Light intensity focused ultrasound (LIFU) is an early stage medical technology that is in various stages of development to treat a range of disorders including super?cial diseases. Optical coherence tomography (OCT) is a rapid development imaging technique in recent ten years, which is a good way to monitor the tissue structure of super?cial diseases. In this study, OCT system is used to monitor the tissue structure of super?cial diseases during LIFU treatment. During the treatment, LIFU was performed on the lesion area of the sample with different energy levels for different times: 5s, 10s, 15s, 20s, 25s, 30s, respectively. During the treatment, the OCT system was working to monitor the tissue structure. The results showed that the light intensity of the lesion area increased with the treatment time, and the structure of the tissue changed. This study provides a new method for monitoring the treatment of super?cial diseases with LIFU.
关键词： Monitoring,Optical coherence tomography,Tissue structure,Super?cial diseases,Light intensity focused ultrasound
更新于2025-09-23 15:22:29
-
A Comprehensive Model for Correcting RNFL Readings of Varying Signal Strengths in Cirrus Optical Coherence Tomography
摘要： PURPOSE. To develop a model for the Cirrus HD-OCT that allows for the comparison of retinal nerve fiber layer (RNFL) thickness measurements with dissimilar signal strengths (SS) and accounts for test–retest variability. METHODS. Retinal nerve fiber layers were obtained in normals using the Cirrus optic disc cube 200 3 200 protocol during a single encounter. Five RNFL scans were obtained with a SS of 9 or 10. Diffusion lens filters were used to degrade SS to obtain five scans at each SS group of 7 or 8, 5 or 6, and 3 or 4. The relationship between average RNFL thickness and SS was established, and an equation was developed to allow for adjustment of an RNFL measurement had it been a SS of 7. Intravisit interclass correlation coefficient (ICC) and coefficient of variation (CV) parameter estimates for each SS group were calculated. Repeatability and upper tolerance limit were calculated as 1.96 3 =2 3 within-subject standard deviation (Sw) and 1.645 3 =2 3 Sw, respectively. RESULTS. There was a linear relationship between average RNFL and SS. RNFLadj ? RNFL (cid:2) 1.03*SS t 7.21 allows for the adjustment of RNFL readings to the same SS. Interclass correlation coefficients and CVs were good for all measurements down to SS of 3 or 4. Repeatability and upper tolerance limit were 5.24 and 4.40 lm, respectively. CONCLUSIONS. Our model adjusts RNFL readings based on SS and includes an upper tolerance limit of 5 lm. If validated, this model could improve the detection of real RNFL changes. Further study to validate this model should be performed before widespread use is adopted.
关键词： glaucoma anterior segment,Cirrus OCT,signal strength,optical coherence tomography
更新于2025-09-23 15:22:29
-
Cell Motility as Contrast Agent in Retinal Explant Imaging With Full-Field Optical Coherence Tomography
摘要： PURPOSE. To use cell motility as a contrast agent in retinal explants. METHODS. Macaque and mouse retinal explants were imaged with high resolution full field optical coherence tomography (FFOCT) and dynamic FFOCT, coupled with fluorescence imaging. RESULTS. Static and dynamic FFOCT create complementary contrast from different structures within a cell. When imaging in vitro samples, static FFOCT detects steep refractive index gradients to reveal stationary structures including fibers, vessels, collagen, and cell contours, while dynamic FFOCT emphasizes metabolic activity of moving structures that are mainly intracellular, thus creating or enhancing contrast in cells that were previously hidden in noise. Dynamic FFOCT enables detection of most of the retinal cell types in the ganglion cell, inner and outer nuclear layers, where static FFOCT contrast is too low in relation to the noise background. CONCLUSIONS. Composite static and dynamic FFOCT provides a new kind of FFOCT image containing valuable information for imaging of retinal explants. It provides label-free en face images of living retinas, with a subcellular resolution. Dynamic FFOCT adds information about cell activity, which is of interest in longitudinal explant studies.
关键词： explant,motility,optical coherence tomography
更新于2025-09-23 15:22:29
-
Relationship between Peripapillary Retinal Nerve Fiber Layer Thickness Measured by Optical Coherence Tomography and Visual Field Severity Indices
摘要： Purpose: Though there are many reports regarding the structure-function relationship in glaucoma, they are too complicated to apply to the routine clinical setting. The aim of this study was to investigate the direct relationship between peripapillary retinal nerve fiber layer (RNFL) thickness measured by optical coherence tomography (OCT) and visual field (VF) severity indices computed by standard automated perimetry. Methods: This cross-sectional comparative study included 104 glaucomatous patients and 59 healthy subjects. Peripapillary RNFL thickness was measured by spectral domain (SD) and time domain (TD) OCTs. Four glaucoma VF severity indices, including mean deviation (MD), pattern standard deviation (PSD), Collaborative Initial Glaucoma Treatment Study (CIGTS) VF score, and Advanced Glaucoma Intervention Study (AGIS) VF score, were calculated using standard automated perimetry. The Pearson’s correlation coefficients (r) between the average and quadrants of peripapillary RNFL thicknesses and the four VF severity indices were calculated. Results: In glaucomatous eyes, the r value between the average RNFL thickness measured by SD OCT and each VF severity index were 0.562, -0.514, -0.577, and -0.567 for the MD, PSD, CIGTS VF score, and AGIS VF score, respectively (all p < 0.001). Among each quadrant, the inferior RNFL thickness showed the largest r value; 0.587, -0.552, -0.613, and -0.598 for the MD, PSD, CIGTS VF score, and AGIS VF score, respectively (all p < 0.001). Measurements by TD OCT showed similar strengths of association with SD OCT. Conclusions: Moderate correlation was identified between peripapillary RNFL thicknesses measured by SD/TD OCT and glaucoma VF severity indices. Among each quadrant, the inferior RNFL thickness showed the greatest association with glaucoma VF severity indices. There was no significant difference according to the type of VF severity index or the type of OCTs.
关键词： Glaucoma,Retinal nerve fiber layer thickness,Optical coherence tomography,Visual fields
更新于2025-09-23 15:22:29
-
Comparison of Kang's and Littmann's Methods of Correction for Ocular Magnification in Circumpapillary Retinal Nerve Fiber Layer Measurement
摘要： PURPOSE. To assess and compare the accuracy of Kang’s method for ocular magnification correction in circumpapillary retinal nerve fiber layer (cpRNFL) thickness measurement with that of the currently used Littmann’s method. METHODS. A total of 148 eyes of 148 healthy participants underwent cpRNFL measurement without correction and with correction by Littmann’s method using spectral-domain optical coherence tomography. Correction of ocular magnification by Kang’s method is based on the observed uncorrected cpRNFL thickness. The accuracy of Kang’s method was compared with that of Littmann’s method for magnification correction by using the Pearson product-moment correlation coefficient (r) and Bland–Altman analysis. RESULTS. A total of 132 eyes were assessed. The two methods used to correct the global cpRNFL thickness were strongly correlated (r = 0.940, P < 0.01), and the mean difference between the two methods was -0.4 μm, with 95% limits of agreement (LoA) of –6 μm without systemic bias (P > 0.05). Although the cpRNFL thicknesses corrected with the two methods at quadrant and 12-o’clock sectors showed a strong correlation (r > 0.731, P < 0.01), high LoAs ranging from –13.3 to –27.9 and systemic biases were observed at nasal and inferior sectors. CONCLUSION. No difference was found between Kang’s and Littmann’s methods for correction of ocular magnification in global cpRNFL thickness measurement. However, with regard to magnification correction for sectoral cpRNFL thickness, further scrutiny of Kang’s method is warranted, even in healthy participants, because of the high variability between Littmann’s and Kang’s methods.
关键词： Littmann’s method,optical coherence tomography,magnification correction,circumpapillary retinal nerve fiber layer,Kang’s method
更新于2025-09-23 15:22:29
-
Design Considerations for Murine Retinal Imaging Using Scattering Angle Resolved Optical Coherence Tomography
摘要： Optical coherence tomography (OCT), an optical imaging approach enabling cross-sectional analysis of turbid samples, is routinely used for retinal imaging in human and animal models of diseases affecting the retina. Scattering angle resolved (SAR-)OCT has previously been demonstrated as offering additional contrast in human studies, but no SAR-OCT system has been reported in detail for imaging the retinas of mice. An optical model of a mouse eye was designed and extended for validity at wavelengths of light around 1310 nm; this model was then utilized to develop a SAR-OCT design for murine retinal imaging. A Monte Carlo technique simulates light scattering from the retina, and the simulation results are confirmed with SAR-OCT images. Various images from the SAR-OCT system are presented and utility of the system is described. SAR-OCT is demonstrated as a viable and robust imaging platform to extend utility of retinal OCT imaging by incorporating scattering data into investigative ophthalmologic analysis.
关键词： angle resolved imaging,retinal imaging,optical coherence tomography,rodent imaging,scattering
更新于2025-09-23 15:22:29
-
Practical Challenges of Current Video Rate OCT Elastography: Accounting for Dynamic and Static Tissue Properties
摘要： Optical coherence tomography (OCT) elastography (OCTE) has the potential to be an important diagnostic tool for pathologies including coronary artery disease, osteoarthritis, malignancies, and even dental caries. Many groups have performed OCTE, including our own, using a wide range of approaches. However, we will demonstrate current OCTE approaches are not scalable to real-time, in vivo imaging. As will be discussed, among the most important reasons is current designs focus on the system and not the target. Specifically, tissue dynamic responses are not accounted, with examples being the tissue strain response time, preload variability, and conditioning variability. Tissue dynamic responses, and to a lesser degree static tissue properties, prevent accurate video rate modulus assessments for current embodiments. Accounting for them is the focus of this paper. A top-down approach will be presented to overcome these challenges to real time in vivo tissue characterization. Discussed first is an example clinical scenario where OCTE would be of substantial relevance, the prevention of acute myocardial infarction or heart attacks. Then the principles behind OCTE are examined. Next, constrains on in vivo application of current OCTE are evaluated, focusing on dynamic tissue responses. An example is the tissue strain response, where it takes about 20 msec after a stress is applied to reach plateau. This response delay is not an issue at slow acquisition rates, as most current OCTE approaches are preformed, but it is for video rate OCTE. Since at video rate each frame is only 30 msec, for essentially all current approaches this means the strain for a given stress is changing constantly during the B-scan. Therefore the modulus can’t be accurately assessed. This serious issue is an even greater problem for pulsed techniques as it means the strain/modulus for a given stress (at a location) is unpredictably changing over a B-scan. The paper concludes by introducing a novel video rate approach to overcome these challenges.
关键词： Optical Coherence Tomography,Elastography,Thin-capped fibroatheromas
更新于2025-09-23 15:22:29
-
Reproducibility of Disc and Macula Optical Coherence Tomography using the Canon OCT-HS100 as Compared with the Zeiss Cirrus HD-OCT
摘要： Purpose: In a clinical setting, the usefulness of optical coherence tomography (OCT) is strongly dependent on reproducibility of the measurement. The aim of the present study was to evaluate macula and optic disc measurement reproducibility with the new spectral-domain OCT (SD-OCT) from Canon (Canon OCT-HS100) and to compare reproducibility and obtained measurements with the Zeiss Cirrus HD-OCT. Methods: Macula and optic disc parameters from the right eyes of 31 subjects were obtained twice with both instruments. Interoperator reproducibility was evaluated by use of the coefficient of repeatability (CR), and the obtained measurements were compared between the instruments. Results: No difference in interoperator reproducibility could be found when comparing the 2 instruments and reproducibility ranged from 3.94% to 12.77% for optic disc parameters and from 1.19% to 3.54% for macula parameters. The lowest reproducibility was found for cup volume and vertical cup/disc ratio with both instruments. For all macula and retinal nerve fiber layer (RNFL) thickness measurements, there was a statistical difference when comparing the 2 instruments, except for RFNL measurements of the superior quadrant, with the Canon OCT-HS100 always evaluating the thickness to be thicker; however, the 2 instruments correlated well. Conclusions: The Canon OCT-HS100 is a reproducible instrument that matches the Zeiss Cirrus HD-OCT well. It remains to be evaluated how sensitive the Canon OCT-HS100 is to detect small subtle changes in optic disc parameters and macular nerve fiber layer thickness. Furthermore, due to the differences in thickness estimation, it is important to emphasize that SD-OCTs are not interchangeable.
关键词： Canon OCT-HS100,Reproducibility,Spectral domain,Optical coherence tomography
更新于2025-09-23 15:22:29
-
Evaluation of choroidal and retinal thickness measurements in adult hemodialysis patients using spectral-domain optical coherence tomography
摘要： Purpose: To assess the effect of hemodialysis on retinal and choroidal thicknesses using spectral-domain optical coherence tomography (SD-OCT). Methods: In this prospective interventional study, 25 hemodialysis patients (17 male, 8 female) were enrolled. All participants underwent high-speed, high-resolution SD-OCT (λ=840 mm; 26.000 A-scans/s; 5 μm resolution) before and after hemodialysis. Choroidal thickness was measured perpendicularly from the outer edge of the retinal pigment epithelium to the choroid-sclera boundary at the fovea and at five additional points: 500 μm and 1000 μm nasal to the fovea and 500 μm, 1000 μm, and 1500 μm temporal to the fovea. Two masked physicians performed the measurements. Choroidal and retinal thicknesses before and after hemodialysis were compared. results: The median choroidal thicknesses before and after hemodialysis were 182 μm (range, 103-374 μm) and 161 μm (range, 90-353 μm), respectively (P<0.001). The median retinal thicknesses were 246 μm (range, 179-296 μm) before and 248 μm (range, 141-299 μm) after hemodialysis (P>0.05). Systolic arterial pressure, diastolic arterial pressure, mean arterial pressure, heart rate, and ocular perfusion pressure significantly decreased after hemodialysis (P<0.001). Intraocular pressure did not vary significantly (P=0.540). conclusion: Hemodialysis seems to cause a significant decrease in choroidal thickness, whereas it has no effect on retinal thickness. This significant decrease in choroidal thickness might be due to the extensive fluid absorption in hemodialysis, which could result in decreased ocular blood flow.
关键词： Choroidal thickness,Hemodialysis,Optical coherence tomography
更新于2025-09-23 15:22:29