Miao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Miao Zhang has a total of 91 co-authors. Here are the top co-authors by number of shared publications:
- Yali Jia
Oregon Health and Science University
21 shared publications David Huang
Casey Eye Institute, Oregon Health & Science University, Portland, OR 97239, USA
15 shared publications- Thomas S. Hwang
Casey Eye Institute, Oregon Health & Science University, Portland, OR, USA
15 shared publications David J. Wilson
Casey Eye Institute, Oregon Health & Science University, Portland, OR, 97239, USA
12 shared publicationsJie Wang
Casey Eye Institute, Oregon Health & Science University, Portland, OR 97239, USA
9 shared publicationsAcner Camino
Casey Eye Institute, Oregon Health & Science University, Portland, OR 97239, USA
6 shared publications
Latest Publications
- 24 April 2026
- Published by Springer Nature in Nature Biomedical Engineering
A three-dimensional multi-modal foundation model for optical coherence tomography
Vision loss caused by retinal diseases remains a leading global cause of disability. Optical coherence tomography (OCT) is an imaging technique that is used for diagnosing retinal diseases. Computational models can use OCT images for various diagnostic and prognostic tasks, but most existing approaches fail to fully leverage the rich three-dimensional (3D) structure of OCT data and lack the capability to integrate other retinal imaging modalities into the analysis. Here, to address these limitations, we present OCTCube-M, a 3D OCT-based multi-modal framework designed for the integrated analysis of 3D OCT and 2D en face (EF) images. OCTCube-M exploits COEP, an effective multi-modal contrastive learning method, to integrate OCT with other retinal imaging modalities, such as fundus autofluorescence imaging and infrared retinal imaging (IR). Using the OCTCube-M framework, we developed three models: OCTCube (uni-modal), OCTCube-IR (bi-modal) and OCTCube-EF (tri-modal). OCTCube, a 3D foundation model pre-trained on 26,605 3D OCT volumes comprising 1.62 million 2D OCT slices, achieved state-of-the-art performance in predicting 8 retinal diseases while demonstrating robust generalizability across cohorts, devices and modalities. OCTCube-IR extends OCTCube by incorporating 26,685 pairs of OCT and IR images, enabling accurate cross-modality retrieval and joint analysis of these two modalities. OCTCube-EF, trained on over 4 million 2D OCT slices and 400 thousand EF retinal images, excels in predicting the growth rate of geographic atrophy across datasets collected from 6 multi-centre clinical trials across 23 countries. Collectively, OCTCube-M is a 3D multi-modal foundation model framework for integrating OCT and other retinal imaging modalities. It demonstrated substantial advancements in cross-site, cross-device, cross-modality and systemic disease prediction, while offering substantial utility in geographic atrophy clinical trials.
- 24 April 2026
- Published by Springer Nature in Nature Biomedical Engineering
A three-dimensional multi-modal foundation model for optical coherence tomography
Vision loss caused by retinal diseases remains a leading global cause of disability. Optical coherence tomography (OCT) is an imaging technique that is used for diagnosing retinal diseases. Computational models can use OCT images for various diagnostic and prognostic tasks, but most existing approaches fail to fully leverage the rich three-dimensional (3D) structure of OCT data and lack the capability to integrate other retinal imaging modalities into the analysis. Here, to address these limitations, we present OCTCube-M, a 3D OCT-based multi-modal framework designed for the integrated analysis of 3D OCT and 2D en face (EF) images. OCTCube-M exploits COEP, an effective multi-modal contrastive learning method, to integrate OCT with other retinal imaging modalities, such as fundus autofluorescence imaging and infrared retinal imaging (IR). Using the OCTCube-M framework, we developed three models: OCTCube (uni-modal), OCTCube-IR (bi-modal) and OCTCube-EF (tri-modal). OCTCube, a 3D foundation model pre-trained on 26,605 3D OCT volumes comprising 1.62 million 2D OCT slices, achieved state-of-the-art performance in predicting 8 retinal diseases while demonstrating robust generalizability across cohorts, devices and modalities. OCTCube-IR extends OCTCube by incorporating 26,685 pairs of OCT and IR images, enabling accurate cross-modality retrieval and joint analysis of these two modalities. OCTCube-EF, trained on over 4 million 2D OCT slices and 400 thousand EF retinal images, excels in predicting the growth rate of geographic atrophy across datasets collected from 6 multi-centre clinical trials across 23 countries. Collectively, OCTCube-M is a 3D multi-modal foundation model framework for integrating OCT and other retinal imaging modalities. It demonstrated substantial advancements in cross-site, cross-device, cross-modality and systemic disease prediction, while offering substantial utility in geographic atrophy clinical trials.
- Open Access
- 16 November 2023
- Published by Elsevier in Ophthalmology Science
- Vol. 4 (3) , 100428
Deep Learning Approaches for Detecting of Nascent Geographic Atrophy in Age-Related Macular Degeneration
- 16 November 2023
- Published by Elsevier in Ophthalmology Science
- Vol. 4 (3) , 100428
Open AccessDeep Learning Approaches for Detecting of Nascent Geographic Atrophy in Age-Related Macular Degeneration
- 1 October 2023
- Published by Springer Nature
- p. 477-485
Weakly Supervised Lesion Localization of Nascent Geographic Atrophy in Age-Related Macular Degeneration
- 1 October 2023
- Published by Springer Nature
- p. 477-485
Weakly Supervised Lesion Localization of Nascent Geographic Atrophy in Age-Related Macular Degeneration
- Open Access
- 19 December 2020
- Published by Wiley in Biopharmaceutics & Drug Disposition
- Vol. 42 (1) , 24-34
Physiologically based pharmacokinetic model of renally cleared antibacterial drugs in Chinese renal impairment patients
To preliminarily develop physiologically based population models for Chinese renal impairment patients and to evaluate the prediction performance of new population models by renally cleared antibacterial drugs. First, demographic data and physiological parameters of Chinese renal impairment patients were collected, and then the coefficients of the relative demographic and physiological equation were recalibrated to construct the new population models. Second, drug‐independent parameters of ceftazidime, cefodizime, vancomycin, and cefuroxime were collected and verified by Chinese healthy volunteers, Caucasian healthy volunteers, and Caucasian renal impairment population models built in Simcyp. Finally, the newly developed population models were applied to predict the plasma concentration of four antibacterial drugs in Chinese renal impairment patients. The new physiologically based pharmacokinetic (PBPK) population models can predict the main pharmacokinetic parameters, including area under the plasma concentration–time curve extrapolated to infinity (AUCinf), renal clearance (CLr), and peak concentration (Cmax), of ceftazidime, cefodizime, vancomycin, and cefuroxime following intravenous administrations with less than twofold error in mild, moderate, and severe Chinese renal impairment patients. The accuracy and precision of the predictions were improved compared with the Chinese healthy volunteers and Caucasian renal impairment population models. The PBPK population models were preliminarily developed and the first‐step validation results of four antibacterial drugs following intravenous administration showed acceptable accuracy and precision. The population models still need more systematic validation by using more drugs and scenarios in future studies to support their applications on dosage recommendation for Chinese renal impairment patients.
- 19 December 2020
- Published by Wiley in Biopharmaceutics & Drug Disposition
- Vol. 42 (1) , 24-34
Open AccessPhysiologically based pharmacokinetic model of renally cleared antibacterial drugs in Chinese renal impairment patients
To preliminarily develop physiologically based population models for Chinese renal impairment patients and to evaluate the prediction performance of new population models by renally cleared antibacterial drugs. First, demographic data and physiological parameters of Chinese renal impairment patients were collected, and then the coefficients of the relative demographic and physiological equation were recalibrated to construct the new population models. Second, drug‐independent parameters of ceftazidime, cefodizime, vancomycin, and cefuroxime were collected and verified by Chinese healthy volunteers, Caucasian healthy volunteers, and Caucasian renal impairment population models built in Simcyp. Finally, the newly developed population models were applied to predict the plasma concentration of four antibacterial drugs in Chinese renal impairment patients. The new physiologically based pharmacokinetic (PBPK) population models can predict the main pharmacokinetic parameters, including area under the plasma concentration–time curve extrapolated to infinity (AUCinf), renal clearance (CLr), and peak concentration (Cmax), of ceftazidime, cefodizime, vancomycin, and cefuroxime following intravenous administrations with less than twofold error in mild, moderate, and severe Chinese renal impairment patients. The accuracy and precision of the predictions were improved compared with the Chinese healthy volunteers and Caucasian renal impairment population models. The PBPK population models were preliminarily developed and the first‐step validation results of four antibacterial drugs following intravenous administration showed acceptable accuracy and precision. The population models still need more systematic validation by using more drugs and scenarios in future studies to support their applications on dosage recommendation for Chinese renal impairment patients.
- 13 June 2019
- Published by Optica Publishing Group in Optics Letters
- Vol. 44 (12) , 3158-3161
Improve depth of field of optical coherence tomography using finite energy Airy beam
We report a technique to break the depth of field (DOF) limit in optical coherence tomography (OCT) using a finite energy Airy beam. The Airy beam is generated using a phase mask in a Fourier transform schematic and provides the DOF improvement due to its low diffraction. We compare Airy beam OCT with conventional Gaussian beam OCT using lateral resolution and sensitivity. Experimental data from the polystyrene beads in water as well as lemon tissue confirm the extension of DOF up to 10 mm in Airy beam OCT, while the DOF of Gaussian beam OCT is less than 3.0 mm. We also demonstrate that a modified Airy beam can be effectively used in OCT by adjusting the truncating factor of the Airy beam via changing the pattern scale of the phase mask. This result provides a selection method for the use of a finite energy Airy beam in OCT.
- 13 June 2019
- Published by Optica Publishing Group in Optics Letters
- Vol. 44 (12) , 3158-3161
Improve depth of field of optical coherence tomography using finite energy Airy beam
We report a technique to break the depth of field (DOF) limit in optical coherence tomography (OCT) using a finite energy Airy beam. The Airy beam is generated using a phase mask in a Fourier transform schematic and provides the DOF improvement due to its low diffraction. We compare Airy beam OCT with conventional Gaussian beam OCT using lateral resolution and sensitivity. Experimental data from the polystyrene beads in water as well as lemon tissue confirm the extension of DOF up to 10 mm in Airy beam OCT, while the DOF of Gaussian beam OCT is less than 3.0 mm. We also demonstrate that a modified Airy beam can be effectively used in OCT by adjusting the truncating factor of the Airy beam via changing the pattern scale of the phase mask. This result provides a selection method for the use of a finite energy Airy beam in OCT.
- 26 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Quantum Electronics
- Vol. 25 (1) , 1-6
Three-Dimensional Full-Range Dual-Band Fourier Domain Optical Coherence Tomography Accelerated by Graphic Processing Unit
The authors present a graphic processing unit (GPU) accelerated three-dimensional (3-D) full-range dual-band Fourier domain optical coherence tomography (FD-OCT) using a LabVIEW GPU program with GPU-adaptable algorithms. GPU can dramatically reduce the image processing time, but programming on GPU is more complex than that on central processing unit (CPU). This study implements GPU computing interfaced with LabVIEW, using a LabVIEW GPU analysis toolkit, which significantly reduces the programming complexity. The selected algorithms are suitable for GPU computing in multiband FD-OCT. The developed system overcomes the problem of long image processing time relative to data acquisition time in CPU. A 65-Hz frame rate is achieved for acquiring, processing, and displaying 2 × 450 × 800 full-range dual-band FD-OCT images. The high-speed processing made it possible to interactively display 3-D dual-band FD-OCT images in a real time, showing the potential application for improving multifunctional OCT systems currently using complex algorithms.
- 26 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Quantum Electronics
- Vol. 25 (1) , 1-6
Three-Dimensional Full-Range Dual-Band Fourier Domain Optical Coherence Tomography Accelerated by Graphic Processing Unit
The authors present a graphic processing unit (GPU) accelerated three-dimensional (3-D) full-range dual-band Fourier domain optical coherence tomography (FD-OCT) using a LabVIEW GPU program with GPU-adaptable algorithms. GPU can dramatically reduce the image processing time, but programming on GPU is more complex than that on central processing unit (CPU). This study implements GPU computing interfaced with LabVIEW, using a LabVIEW GPU analysis toolkit, which significantly reduces the programming complexity. The selected algorithms are suitable for GPU computing in multiband FD-OCT. The developed system overcomes the problem of long image processing time relative to data acquisition time in CPU. A 65-Hz frame rate is achieved for acquiring, processing, and displaying 2 × 450 × 800 full-range dual-band FD-OCT images. The high-speed processing made it possible to interactively display 3-D dual-band FD-OCT images in a real time, showing the potential application for improving multifunctional OCT systems currently using complex algorithms.
- 24 August 2018
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 9 (9) , 4429-4442
Automated segmentation of retinal layer boundaries and capillary plexuses in wide-field optical coherence tomographic angiography
Advances in the retinal layer segmentation of structural optical coherence tomography (OCT) images have allowed the separation of capillary plexuses in OCT angiography (OCTA). With the increased scanning speeds of OCT devices and wider field images (≥10 mm on fast-axis), greater retinal curvature and anatomic variations have introduced new challenges. In this study, we developed a novel automated method to segment seven retinal layer boundaries and two retinal plexuses in wide-field OCTA images. The algorithm was initialized by a series of points forming a guidance point array that estimates the location of retinal layer boundaries. A guided bidirectional graph search method consisting of an improvement of our previous segmentation algorithm was used to search for the precise boundaries. We validated the method on normal and diseased eyes, demonstrating subpixel accuracy for all groups. By allowing independent visualization of the superficial and deep plexuses, this method shows potential for the detection of plexus-specific peripheral vascular abnormalities.
- 24 August 2018
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 9 (9) , 4429-4442
Automated segmentation of retinal layer boundaries and capillary plexuses in wide-field optical coherence tomographic angiography
Advances in the retinal layer segmentation of structural optical coherence tomography (OCT) images have allowed the separation of capillary plexuses in OCT angiography (OCTA). With the increased scanning speeds of OCT devices and wider field images (≥10 mm on fast-axis), greater retinal curvature and anatomic variations have introduced new challenges. In this study, we developed a novel automated method to segment seven retinal layer boundaries and two retinal plexuses in wide-field OCTA images. The algorithm was initialized by a series of points forming a guidance point array that estimates the location of retinal layer boundaries. A guided bidirectional graph search method consisting of an improvement of our previous segmentation algorithm was used to search for the precise boundaries. We validated the method on normal and diseased eyes, demonstrating subpixel accuracy for all groups. By allowing independent visualization of the superficial and deep plexuses, this method shows potential for the detection of plexus-specific peripheral vascular abnormalities.
- 4 April 2018
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 9 (5) , 2056-2067
Automated spectroscopic retinal oximetry with visible-light optical coherence tomography
Accurate, quantitative assessment of retinal blood oxygen saturation (sO2) may provide a useful early indicator of pathophysiology in several ocular diseases. Here, with visible-light optical coherence tomography (OCT), we demonstrate an automated spectroscopic retinal oximetry algorithm to measure the sO2 within the retinal arteries (A-sO2) and veins (V-sO2) in rats by automatically detecting the vascular posterior boundary on cross-sectional structural OCT. The algorithm was validated in vitro with flow phantoms and in vivo in rats by comparing the sO2 results, respectively, to those obtained using a blood gas analyzer and pulse oximetry. We also investigated the response of oxygen extraction (A-V sO2), including inter-session reproducibility, at different inhaled oxygen concentrations.
- 4 April 2018
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 9 (5) , 2056-2067
Automated spectroscopic retinal oximetry with visible-light optical coherence tomography
Accurate, quantitative assessment of retinal blood oxygen saturation (sO2) may provide a useful early indicator of pathophysiology in several ocular diseases. Here, with visible-light optical coherence tomography (OCT), we demonstrate an automated spectroscopic retinal oximetry algorithm to measure the sO2 within the retinal arteries (A-sO2) and veins (V-sO2) in rats by automatically detecting the vascular posterior boundary on cross-sectional structural OCT. The algorithm was validated in vitro with flow phantoms and in vivo in rats by comparing the sO2 results, respectively, to those obtained using a blood gas analyzer and pulse oximetry. We also investigated the response of oxygen extraction (A-V sO2), including inter-session reproducibility, at different inhaled oxygen concentrations.
- 7 November 2017
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 8 (12) , 5384-5398
Automated detection of photoreceptor disruption in mild diabetic retinopathy on volumetric optical coherence tomography
Diabetic retinopathy is a pathology where microvascular circulation abnormalities ultimately result in photoreceptor disruption and, consequently, permanent loss of vision. Here, we developed a method that automatically detects photoreceptor disruption in mild diabetic retinopathy by mapping ellipsoid zone reflectance abnormalities from en face optical coherence tomography images. The algorithm uses a fuzzy c-means scheme with a redefined membership function to assign a defect severity level on each pixel and generate a probability map of defect category affiliation. A novel scheme of unsupervised clustering optimization allows accurate detection of the affected area. The achieved accuracy, sensitivity and specificity were about 90% on a population of thirteen diseased subjects. This method shows potential for accurate and fast detection of early biomarkers in diabetic retinopathy evolution.
- 7 November 2017
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 8 (12) , 5384-5398
Automated detection of photoreceptor disruption in mild diabetic retinopathy on volumetric optical coherence tomography
Diabetic retinopathy is a pathology where microvascular circulation abnormalities ultimately result in photoreceptor disruption and, consequently, permanent loss of vision. Here, we developed a method that automatically detects photoreceptor disruption in mild diabetic retinopathy by mapping ellipsoid zone reflectance abnormalities from en face optical coherence tomography images. The algorithm uses a fuzzy c-means scheme with a redefined membership function to assign a defect severity level on each pixel and generate a probability map of defect category affiliation. A novel scheme of unsupervised clustering optimization allows accurate detection of the affected area. The achieved accuracy, sensitivity and specificity were about 90% on a population of thirteen diseased subjects. This method shows potential for accurate and fast detection of early biomarkers in diabetic retinopathy evolution.
- 20 September 2017
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 8 (10) , 4595-4608
Angiographic and structural imaging using high axial resolution fiber-based visible-light OCT
Optical coherence tomography using visible-light sources can increase the axial resolution without the need for broader spectral bandwidth. Here, a high-resolution, fiber-based, visible-light optical coherence tomography system is built and used to image normal retina in rats and blood vessels in chicken embryo. In the rat retina, accurate segmentation of retinal layer boundaries and quantification of layer thicknesses are accomplished. Furthermore, three distinct capillary plexuses in the retina and the choriocapillaris are identified and the characteristic pattern of the nerve fiber layer thickness in rats is revealed. In the chicken embryo model, the microvascular network and a venous bifurcation are examined and the ability to identify and segment large vessel walls is demonstrated.
- 20 September 2017
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 8 (10) , 4595-4608
Angiographic and structural imaging using high axial resolution fiber-based visible-light OCT
Optical coherence tomography using visible-light sources can increase the axial resolution without the need for broader spectral bandwidth. Here, a high-resolution, fiber-based, visible-light optical coherence tomography system is built and used to image normal retina in rats and blood vessels in chicken embryo. In the rat retina, accurate segmentation of retinal layer boundaries and quantification of layer thicknesses are accomplished. Furthermore, three distinct capillary plexuses in the retina and the choriocapillaris are identified and the characteristic pattern of the nerve fiber layer thickness in rats is revealed. In the chicken embryo model, the microvascular network and a venous bifurcation are examined and the ability to identify and segment large vessel walls is demonstrated.