Deep learning-based inpainting of saturation artifacts in optical coherence tomography images

Limited by the dynamic range of the detector,saturation artifacts usually occur in optical coherence tomography(OCT)imaging for high scattering media.The available methods are difficult to remove saturation artifacts and restore texture completely in OCT images.We proposed a deep learning-based inpainting method of saturation artifacts in this paper.The generation mechanism of saturation artifacts was analyzed,and experimental and simulated datasets were built based on the mechanism.Enhanced super-resolution generative adversarial networks were trained by the clear–saturated phantom image pairs.The perfect reconstructed results of experimental zebrafish and thyroid OCT images proved its feasibility,strong generalization,and robustness.

Intravascular photoacoustic and optical coherence tomography imaging dual-mode system for detecting spontaneous coronary artery dissection: A feasibility study

In this work,we present an intravascular dual-mode endoscopic system capable of both intravascular photoacoustic imaging(IVPAI)and intravascular optical coherence tomography(IVOCT)for recognizing spontaneous coronary artery dissection(SCAD)phantoms.IVPAI provides high-resolution and high-penetration images of intramural hematoma(IMH)at different depths,so it is especially useful for imaging deep blood clots associated with imaging phantoms.IVOCT can readily visualize the double-lumen morphology of blood vessel walls to identify intimal tears.We also demonstrate the capability of this dual-mode endoscopic system using mimicking phantoms and biological samples of blood clots in ex vivo porcine arteries.The results of the experiments indicate that the combined IVPAI and IVOCT technique has the potential to provide a more accurate SCAD assessment method for clinical applications.

Segmentation of retinal fluid based on deep learning:application of three-dimensional fully convolutional neural networks in optical coherence tomography images

AIM: To explore a segmentation algorithm based on deep learning to achieve accurate diagnosis and treatment of patients with retinal fluid.METHODS: A two-dimensional(2D) fully convolutional network for retinal segmentation was employed. In order to solve the category imbalance in retinal optical coherence tomography(OCT) images, the network parameters and loss function based on the 2D fully convolutional network were modified. For this network, the correlations of corresponding positions among adjacent images in space are ignored. Thus, we proposed a three-dimensional(3D) fully convolutional network for segmentation in the retinal OCT images.RESULTS: The algorithm was evaluated according to segmentation accuracy, Kappa coefficient, and F1 score. For the 3D fully convolutional network proposed in this paper, the overall segmentation accuracy rate is 99.56%, Kappa coefficient is 98.47%, and F1 score of retinal fluid is 95.50%. CONCLUSION: The OCT image segmentation algorithm based on deep learning is primarily founded on the 2D convolutional network. The 3D network architecture proposed in this paper reduces the influence of category imbalance, realizes end-to-end segmentation of volume images, and achieves optimal segmentation results. The segmentation maps are practically the same as the manual annotations of doctors, and can provide doctors with more accurate diagnostic data.

Automatic diagnosis of diabetic retinopathy using vision transformer based on wide-field optical coherence tomography angiography

Diabetic retinopathy(DR)is one of the major causes of visual impairment in adults with diabetes.Optical coherence tomography angiography(OCTA)is nowadays widely used as the golden criterion for diagnosing DR.Recently,wide-field OCTA(WF-OCTA)provided more abundant information including that of the peripheral retinal degenerative changes and it can contribute in accurately diagnosing DR.The need for an automatic DR diagnostic system based on WF-OCTA pictures attracts more and more attention due to the large diabetic population and the prevalence of retinopathy cases.In this study,automatic diagnosis of DR using vision transformer was performed using WF-OCTA images(12 mm×12 mm single-scan)centered on the fovea as the dataset.WF-OCTA images were automatically classified into four classes:No DR,mild nonproliferative diabetic retinopathy(NPDR),moderate to severe NPDR,and proliferative diabetic retinopathy(PDR).The proposed method for detecting DR on the test set achieves accuracy of 99.55%,sensitivity of 99.49%,and specificity of 99.57%.The accuracy of the method for DR staging reaches up to 99.20%,which has been proven to be higher than that attained by classical convolutional neural network models.Results show that the automatic diagnosis of DR based on vision transformer and WF-OCTA pictures is more effective for detecting and staging DR.

Detecting early changes in choroidal vascularity and thickness using optical coherence tomography in patients with corneal crosslinking for keratoconus

AIM:To investigate changes in choroidal thickness and vascularity in keratoconus patients treated with corneal crosslinking.METHODS:This study evaluated 28 eyes of 22 patients with keratoconus who underwent corneal crosslinking.The choroidal thicknesses were evaluated on enhanced depth imaging optical coherence tomography at the preoperative and postoperative 3d,1,and 3mo.Choroidal thickness in the four cardinal quadrants and the fovea were evaluated.The choroidal vascularity index was also calculated.RESULTS:There was no significant difference in central choroidal thickness between the preoperative and postoperative 3d,1mo(P>0.05).There was a significant increase in the 3mo(P=0.034)and a significant decrease in the horizontal choroidal vascularity index on the postoperative 3d(P=0.014),there was no statistically significant change in vertical axes and other visits in horizontal sections(P>0.05).CONCLUSION:This study sheds light on choroidal changes in postoperative corneal crosslinking for keratoconus.While it suggests the procedure’s relative safety for submacular choroid,more extensive research is necessary to confirm these findings and their clinical significance.

Vascular Stress Analysis Based on in vivo Intravascular Optical Coherence Tomography Image Segmentation

Identification of carotid artery atherosclerosis is crucial for the diagnosis of the cerebral apoplexy and other vascular diseases.Intravascular optical tomography(IVOCT)has been employed to clinical coronary imaging for several years.Vessel morphological information on IVOCT images together with blood flow information on Doppler OCT(DOCT)images could provide a more accurate internal environment of arteries.Images integrated with fluid-structure interaction(FSI)could obtain the accurate mechanical responses and the quantitative material characters.A porcine carotid artery was imaged with an intravascular system(C7-XR,St.Jude Medical Inc.St.Paul,Minnesota,USA)in vivo,during which 120 images of one section and 600 images of a 5 mm/s pull back were captured within 6 s.Those images were then overlapped with Doppler phase changes to imply the changes in flow profiles.Segmentation and quantification of vessel structure was done in the software(MATLAB 2014b),including specifically the segmentation of lumen,imaging catheter,vessel wall and the guide wire.Appropriate interpolation functions are selected in the coordinate transformation algorithm to have smooth boundaries from images.A set of flow algorithms include image segmentation,three-dimensional/two-dimensional model reconstruction,inversion of material parameters,fitting of experimental velocity data and theoretical derivation based on simulation results is proposed.All steps are programmed to provide a theoretical basis for the future simplified process control.3D-reconstruction FSI model was built in SOLIDWORKS by lofting operation based on the segmentation results.Commercial finite element software(COMSOL 5.3,Sweden)numerically analyzed the entity model to obtain vessel stress/strain and flow shear stress data.Boundary conditions are from the OCT detection.Material of the artery was set to be the modified Mooney-Rivlin constitutive model and the parameters used were adjusted in an algorithm to match an ex vivo experiment.Wall shear stresses(WSS)and vessel deformations were chosen to measure the conditions of the artery and would serve as a target variables for future prediction.Thus,the geometric information together with the data of materials and other mechanical properties are possible to obtain during the imaging process.Segmentation process provided anatomically correct models of a two-layered artery.Numerical simulation permits reliable stress distribution in which the position of catheter and the artery curvature have a neglectable disturbance.Shear stress of the fluid is quite small compared with that of the wall at the same interface,which shows good agreement with the former studies.Moreover,a high flushing speed of 0.1 mps have little impact on the stress distributions and magnitudes,which denotes that the OCT imaging process brings little harm to the vessel.It is the first attempt to combine the OCT imaging and Doppler OCT within a full algorithm and a structural analysis.This study is helpful for the biomechanical property studies of carotid arteries and the development of medical imaging technology.

Image Distortion of Optical Coherence Tomography

A kind of image distortion in Optical Coherence Tomography (OCT) resulted from average refractive index changes between structures of bio tissue is discussed for the first time.Analysis is given on following situations:1) Exact refraction index changes between microstructures;2)The gradient of average refractive index change between different tissue layers is parallel to the probe beam;3) The gradient of average refractive index change is vertical to the probe beam.The results show that the image distortion of situation 1) is usually negligible;in situation 2) there is a spread or shrink effect without relative location error; however,in situation 3) there is a significant image error inducing relative location displacement between different structures.Preliminary design to eliminate the distortion is presented,the method of which mainly based on the image classification and pixel array re arrangement.

Intraoperative imaging of oral-maxillofacial lesions using optical coherence tomography

Histopathological examination is still the gold standard for diagnoses of oral-maxillofacial lesions,but it is invasive and time-consuming.Optical coherence tomography(OCT)provides a kind of noninvasive,label-free,real-time and high-resolution imaging technology.In this study,in order to assess the feasibility of OCT in oral clinical application,fresh excised tissue specimens from 59 patients undergoing oral-maxillofacial surgery were imaged in detail by using a benchtop sweptsource OCT system.It is shown that different lesions or tissues can be obviously distinguished based on their different microstructural features in OCT images,and the features are similar to those of their corresponding histopathological images.It is proven that OCT has great feasibility and potential as a diagnostic aid for surgeons in oral medicine.

Parallel Spectral-Domain Optical Coherence Tomography for Non-Scattering Object Imaging

The parallel spectral-domain optical coherence tomography（PSDOCT） is described for highspeed optical coherence tomography（OCT） without lateral scanning. In this setup, the self-elimination of auto-correlation（AC） interference algorithm was used for eradicating the AC interference and ghost images. However, when performed in free space OCT, this algorithm still generated a weak DC component. The algorithm was improved by adding the background intensity part to compensate for the mutual interference between object and reference arms. The results demonstrate that the DC component can be eradicated. Compared with conventional QCT and complex Fourier-domain optical coherence to- mography, the advantages of PSDOCT with the improved algorithm in free space are that it has no moving parts to generate consecutive phase shift, the structure of the object can be reconstructed immediately and automatically, and the speed is approximately 16 times faster than those of the other two in the same case.

Optical coherence tomography with or without enhanced depth imaging for peripapillary retinal nerve fiber layer and choroidal thickness

AIM：To assess peripapillary retinal nerve fiber layer（RNFL）and choroidal thickness obtained with enhanced depth imaging（EDI）mode compared with those obtained without EDI mode using Heidelberg Spectralis optical coherence tomography（OCT）.METHODS：Fifty eyes of 25 normal healthy subjects and32 eyes of 20 patients with different eye diseases were included in the study.All subjects underwent 3.4 mm diameter peripapillary circular OCT scan centered on the optic disc using both the conventional and the EDI OCT protocols.The visualization of RNFL and choroidoscleral junction was assessed using an ordinal scoring scale.The paired t-test,intraclass correlation coefficient（ICC）,95%limits of agreement（LoA）,and Bland and Altman plots were used to test the agreement of measurements.RESULTS：The visibility score of RNFL obtained with and without EDI was of no significant difference（P=0.532）,the visualization of choroidoscleral junction was better using EDI protocol than conventional protocol（P〈0.001）.Peripapillary RNFL thickness obtained with EDI was slightly thicker than that obtained without EDI（103.25±9.42μm vs 101.87±8.78μm,P=0.010）.The ICC of the two protocols was excellent with the value of 0.867 to 0.924,the 95%LoA of global RNFL thickness was between-10.0 to 7.4μm.Peripapillary choroidal thickness obtained with EDI was slightly thinner than that obtained without EDI（147.23±51.04μm vs 150.90±51.84μm,P〈0.001）.The ICC was also excellent with the value of 0.960 to 0.987,the 95%LoA of global choroidal thickness was between-12.5 to 19.8μm.CONCLUSION：Peripapillary circular OCT scan with or without EDI mode shows comparable results in the measurement of peripapillary RNFL and choroidal thickness.

Assessment of chronic radiation proctopathy and radiofrequency ablation treatment follow-up with optical coherence tomography angiography: A pilot study

BACKGROUND Chronic radiation proctopathy(CRP) occurs as a result of pelvic radiation therapy and is associated with formation of abnormal vasculature that may lead to persistent rectal bleeding. While incidence is declining due to refinement of radiation delivery techniques, CRP remains one of the major complications of pelvic radiation therapy and significantly affects patient quality of life.Radiofrequency ablation(RFA) is an emerging treatment modality for eradicating abnormal vasculature associated with CRP. However, questions remain regarding CRP pathophysiology and optimal disease management.AIM To study feasibility of optical coherence tomography angiography(OCTA) for investigating subsurface vascular alterations in CRP and response to RFA treatment.METHODS Two patients with normal rectum and 8 patients referred for, or undergoing endoscopic RFA treatment for CRP were imaged with a prototype ultrahighspeed optical coherence tomography(OCT) system over 15 OCT/colonoscopy visits(2 normal patients, 5 RFA-na?ve patients, 8 RFA-follow-up visits). OCT and OCTA was performed by placing the OCT catheter onto the dentate line and rectum without endoscopic guidance. OCTA enabled depth-resolved microvasculature imaging using motion contrast from flowing blood, withoutrequiring injected dyes. OCTA features of normal and abnormal microvasculature were assessed in the mucosa and submucosa. Blinded reading of OCTA images was performed to assess the association of abnormal rectal microvasculature with CRP and RFA treatment, and rectal telangiectasia density endoscopic scoring.RESULTS OCTA/OCT images are intrinsically co-registered and enabled depth-resolved visualization of microvasculature in the mucosa and submucosa. OCTA visualized normal vascular patterns with regular honeycomb patterns vs abnormal vasculature with distorted honeycomb patterns and ectatic/tortuous microvasculature in the rectal mucosa. Normal arterioles and venules < 200 μm in diameter versus abnormal heterogenous enlarged arterioles and venules > 200μm in diameter were visualized in the rectal submucosa. Abnormal mucosal vasculature occurred in 0 of 2 normal patients and 3 of 5 RFA-na?ve patients,while abnormal submucosal vasculature occurred more often, in 1 of 2 normal patients and 5 of 5 RFA-na?ve patients. After RFA treatment, vascular abnormalities decreased, with abnormal mucosal vasculature observed in 0 of 8 RFA-follow-up visits and abnormal submucosal vasculature observed in only and 2 of 8 RFA-follow-up visits.CONCLUSION OCTA visualizes depth-resolved microvascular abnormalities in CRP, allowing assessment of superficial features which are endoscopically visible as well as deeper vasculature which cannot be seen endoscopically. OCTA/OCT of the rectum can be performed in conjunction with, or independently from endoscopy.Further studies are warranted to investigate if OCTA/OCT can elucidate pathophysiology of CRP or improve management.

Standardization of choroidal thickness measurements using enhanced depth imaging optical coherence tomography

AIM: To describe and evaluate a standardized protocol for measuring the choroidal thickness(Ch T) using enhanced depth imaging optical coherence tomography(EDI OCT).METHODS: Single 9 mm EDI OCT line scans across the fovea were used for this study. The protocol used in this study classified the EDI OCT images into four groups based on the appearance of the choroidal-scleral interface and suprachoroidal space. Two evaluation iterations of experiments were performed: first, the protocol was validated in a pilot study of 12 healthy eyes. Afterwards, the applicability of the protocol was tested in 82 eyes of patients with diabetes. Inter-observer and intra-observer agreements on image classifications were performed using Cohen’s kappa coefficient(κ). Intraclass correlation coefficient(ICC) and Bland-Altman’s methodology were used for the measurement of the Ch T.RESULTS: There was a moderate(κ=0.42) and perfect(κ =1) inter- and intra-observer agreements on image classifications from healthy eyes images and substantial(κ =0.66) and almost perfect(κ =0.86) agreements from diabetic eyes images. The proposed protocol showed excellent inter- and intra-observer agreements for the Ch T measurements on both, healthy eyes and diabetic eyes(ICC 】0.90 in all image categories). The Bland-Altman plot showed a relatively large Ch T measurement agreement in the scans that contained less visible choroidal outer boundary. CONCLUSION: A protocol to standardize Ch T measurements in EDI OCT images has been developed;the results obtained using this protocol show that the technique is accurate and reliable for routine clinical practice and research.

Virtual-OCT:A simulated optical coherence tomography instrument

We report the virtual instrumentation of both time-domain(TD)and spectral-domain(SD)opticai coherence tomography(OCT)systems.With a virtual partial coherence source fromeither a simulated or measured spectrum,the OCT signals of both A-scan and B-scan weredemonstrated.The spectrometric detector's pixel number,dynamic range,noise,as well asspectral resolution can be simulated in the virtual spectral domain(SD-OCT).The virtual-OCT system provides an environment for parameter evaluation and algorithm optimization for ex-perimental OCT instrumentation,and promotes the understanding of OCT imaging and signal post-processing processes.The authors thank Dr.Thomas FitzGibbon forcomments on earlier drafts of the manuscript.

Peripapillary choroidal thickness in Chinese children using enhanced depth imaging optical coherence tomography

AIM：To evaluate the peripapillary choroidal thickness（PPCT） in Chinese children,and to analyze the influencing factors.METHODS： PPCT was measured with enhanced depth imaging optical coherence tomography（EDI-OCT） in 70children（53 myopes and 17 non-myopes） aged 7 to 18 y,with spherical equivalent refractive errors between 0.50and-5.87 diopters（D）.Peripapillary choroidal imaging was performed using circular scans of a diameter of 3.4 mm around the optic disc.PPCT was measured by EDI-OCT in six sectors： nasal（N）,superonasal（SN）,superotemporal（ST）,temporal（T）,inferotemporal（IT）and inferonasal（IN）,as well as global RNFL thickness（G）.RESULTS： The mean global PPCT was 165.49±33.76 μm.The temporal,inferonasal,inferotemporal PPCT were significantly thinner than the nasal,superonasal,superotemporal segments PPCT were significantly thinner in the myopic group at temporal,superotemporal and inferotemporal segments.The axial length was significantly associated with the average global（β=-0.419,P =0.014）,superonasal（β=-2.009,P=0.049） and inferonasal（β=-2.000,P=0.049） PPCT.The other factors（gender,age,SE） were not significantly associated with PPCT.CONCLUSION： PPCT was thinner in the myopic group at temporal,superotemporal and inferotemporal segments.The axial length was found to be negatively correlated to PPCT.We need more further studies about the relationship between PPCT and myopia.

IMAGE IMPROVEMENT IN THE WAVELET DOMAIN FOR OPTICAL COHERENCE TOMOGRAMS

In this paper,an image processing method for improving the quality of optical coherence tomography(OCT)images is proposed.Wavelet denoising based on context modeling and contrast enhancement by means of the contrast measure in the wavelet domain is carried out on the OCT images in succession.Three parameters are selected to assess the effectiveness of the method.It is shown from the results that the proposed method can not only enhance the contrast of images,but also improve signal-to-noise ratio.Compared with two other typical algorithms,it has the best visual effect.

Dynamic imaging of a small artery underneath skin surface of a human finger by optical coherence tomography

OCT is a powerful tool for detection of physiological functions of micro organs underneath the human skin surface, besides the clinical application to ophthalmology, as recently demonstrated by the authors’ group. In particular, dynamics of peripheral vessels can be observed clearly in the time-sequential OCT images. Among the vascular system, only the small artery has two physiological functions both for the elastic artery and for muscle-controlled one. It, therefore, is important for dynamic analysis of blood flow and circulation. In the time-sequential OCT images obtained with 25 frames/sec, it is found that the small artery makes a sharp response to sound stress for contraction and expansion while it continues pulsation in synchronization with the heartbeats. This result indicates that the small artery exhibits clearly the two physiological functions for blood flow and circulation. In response to sound stress, blood flow is controlled effectively by thickness change of the tunica media which consists of five to six layers of smooth muscles. It is thus found that the thickness of the tunica media changes remarkably in response to external stress, which shows the activity of the sympathetic nerve. The dynamic analysis of the small artery presented here will allow us not only to understand the mechanism of blood flow control and also to detect abnormal physiological functions in the whole vascular system.

Intravital imaging of adriamycin-induced renal pathology using two-photon microscopy and optical coherence tomography

Adriamycin(doxorubicin),a common cancer chemotherapeutic drug,can be used to induce a model of chronic progressive glomerular disease in rodents.In our studies,we evahuated renal changes in a rat model after Adriamydin injection using two photon microscopy(TPM),optical coherence tomography(OCT)and Doppler OCT(DOCT).Taking advantage of deep penetra-tion and fast scanning speed for three dimensional(3D)label-free imaging,OCT/DOCT system was able to reveal glomerular and tubular pathology noninvasively and in real time.By imaging renal pathology following the infusion of fAuorophore-labeled dextrans of different molecular weights,TPM can provide direct views of glomerular and tubular flow dynamics with the onset and progression of renal disease.Specifically,glomerular permeability and filtration,proximal and distal tubular flow dynamics can be revealed.6-8 weeks after injection of Adriamycin,TPM and OCT/DOCT imaging revealed glomerular sclerosis,compromised flow across the glomerular wall,tubular atrophy,tubular dilation,and variable intra-tubular flow dynamics.Our results indicate that TPM and OCT/DOCT provide real-time imaging of renal pathology in vivo that has not been previously available using conventional microscopic procedures.

Imaging of arterial plaque by quadrature swept-source optical coherence tomography with signal to noise ratio enhancements

Arterial plaque from a myocardial infarction-prone Watanabe heritable hyperlipidemic (WHHLMI) rabbit is visualized and characterized using a signal to noise ratio enhanced swept-source optical coherence tomography system with a quadrature interferometer (QSS-OCT). A semiconductor optical amplifier is used in the sample arm to amplify the weak signal scattered from arterial plague. Signal to noise ratio improvement are demonstrated in our QSS-OCT system. This finding results into an increase of the penetration depth possible in OCT images, from 1 mm to 2 mm. Preliminary results show that vulnerable plaque with fibrous cap, macrophage accumulations and calcification in the arterial tissue are measurable with our QSS-OCT system.

Optical coherence tomography enhanced depth imaging of chorioretinal folds in patients with orbital tumors

AIM:To characterize spectral-domain optical coherence tomography(SD-OCT)features of chorioretinal folds in orbital mass imaged using enhanced depth imaging(EDI).METHODS:Prospective observational case-control study was conducted in 20 eyes of 20 patients,the uninvolved eye served as a control.All the patients underwent clinical fundus photography,computed tomography,EDI SDOCT imaging before and after surgery.Two patients with cavernous hemangiomas underwent intratumoral injection of bleomycin A5;the remaining patients underwent tumor excision.Patients were followed 1 to 14mo following surgery(average follow up,5.8mo).RESULTS:Visual acuity prior to surgery ranged from 20/20 to 20/200.Following surgery,5 patients’visual acuity remained unchanged while the remaining 15 patients had a mean letter improvement of 10(range 4 to 26 letters).Photoreceptor inner/outer segment defects were found in 10 of 15 patients prior to surgery.Following surgical excision,photoreceptor inner/outer segment defects fully resolved in 8 of these 10 patients.CONCLUSION:Persistence of photoreceptor inner/outer segment defects caused by compression of the globe by an orbital mass can be associated with reduced visual prognosis.Our findings suggest that photoreceptor inner/outer segment defects on EDI SD-OCT could be an indicator for immediate surgical excision of an orbital mass causing choroidal compression.

Evaluating visual outcomes using optical coherence tomography(OCT)in pediatric multiple sclerosis and other neuroinflammatory conditions

Optical coherence tomography(OCT)is a technology that is widely used to assess structural abnormalities in the retina for a variety of pediatric conditions.The introduction of this instrument has allowed for widespread access to minimally invasive standardized,reproducible quantified structural assessments of the optic nerve and retina.This has had important implications in pediatric optic neuropathies,populations in whom monitoring of disease activity is essential to make treatment decisions.OCT has had particular relevance for inflammatory optic neuropathies,as onset of an inflammatory optic neuropathy may herald the onset of a chronic inflammatory disorder of the central nervous system(CNS)such as multiple sclerosis,neuromyelitis optica spectrum disorder(aquaporin 4 antibody positive),and myelin oligodendrocyte glycoprotein(MOG)associated disorders.This paper will focus on the application of OCT technology to this group of disorders in pediatrics.After reviewing pediatric-specific anatomic and practical issues pertinent to OCT,we will review knowledge related to the use of OCT in inflammatory pediatric optic neuropathies,with a focus on structural outcomes and their correlation with functional outcome metrics.