Pathological myopia (PM) is a serious public health issue which potentially leads to severe visual impairment. Traditionally, fundus color photography (FCP) is employed to detect PM for its precision and image quality. However, manual analysis of FCP is time-consuming and susceptible to errors. Current automated detection methods lack the necessary granularity in classifying different stages of PM lesions. To address this problem, we developed an intelligent method for automatic PM detection, utilizing Vision Transformer (ViT) to perform detailed classification of PM. This system achieved an accuracy of 98.66% and an area under the curve (AUC) of 99.98% in detecting PM. Compared to traditional ophthalmological diagnostic methods, this model demonstrates higher efficiency and accuracy
In recent years, endoscopic optical coherence tomography (OCT) has garnered widespread attention for non-invasive advantages in achieving three-dimensional visualization of internal organ cavities. In early-stage lesions, microvascular alterations occur before morphological tissue changes. Therefore, utilizing endoscopic OCTA for the detection of superficial capillaries serves as an adjunctive method for early disease screening. About ten years ago, the advantages of high-speed and stable operation of distal motorized catheters enabled the realization of endoscopic OCTA. However, the internal micro-motors lead to a larger outer diameter of distal imaging catheters, which restricts their clinical applicability for monitoring diseases in narrow luminal structures. Consequently, proximal imaging catheters, with their smaller size, have found its wide application in the commercial arena. However, due to limitations in external motor speed and susceptibility to external vibrations, there were no reports of proximal imaging catheters achieving endoscopic OCTA for a long time. Recently, we proposed the MB-scan scheme to mitigate the impact of external motion artifacts and achieve endoscopic OCTA based on a proximal catheter. The Singular Value Decomposition (SVD) algorithm was employed to eliminate static tissue information and obtain en face OCTA images of the murine rectum. In this study, we proposed a fast endoscopic OCTA using proximal scanning catheter based on B-scan scheme and a customed image registration algorithm. Image registration based on the similarity between adjacent B-scan frames was utilized to reduce the impact of external motor vibrations and improve image quality. Based on the registered images at the same scanning position, the speckle variance (SVAR) algorithm was employed to calculate variation of OCT intensity signals. Finally, en face OCTA images were generated. Collecting data from the mouse rectum, endoscopic OCTA images were obtained from the registered data using the SVAR algorithm.
In this study, we proposed a fast endoscopic OCTA using proximal scanning catheter based on B-scan scheme and a customed image registration algorithm. Image registration based on the similarity between adjacent B-scan frames was utilized to reduce the impact of external motor vibrations and improve image quality. Based on the registered images at the same scanning position, the speckle variance (SVAR) algorithm was employed to calculate variation of OCT intensity signals. Finally, en face OCTA images were generated. Preliminary results of endoscopic OCTA performance using microfluidic phantom proved the feasibility of the proposed technique.
Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical diagnosis. In recent years, convolutional neural network (CNN) has been used to diagnose retinal disease and has proven its superiority in detection and classification tasks. Vision transformer is a new image classification model that has been proposed in 2020. It does not rely on any CNN and completely performs based on the transformer structure which has a different feature extraction method from CNN. In this study, diagnosis of retinal disease using vision transformer was presented using optical coherence tomography (OCT) images. A multi-class classification layer in the vision transformer model was used to group the OCT images into the normal and three abnormal type, Choroidal Neovascularization (CNV), Drusen, and Diabetic Macular Edema (DME). The proposed method achieved a accuracy of 95.76%, sensitivity of 95.77% and specificity of 98.59% in detecting CNV, DME and DRUSEN. Results showed that the classification accuracy of vision transformer is higher than that of other traditional CNN models. The performance of vision transformer was evaluated with different performance metrics like accuracy, sensitivity, and specificity, which proved that vision transformer is a statistically significant method than other standard CNN architectures in classifying retinal diseases using OCT images. This technology enables early diagnosis of retinal diseases, which may be useful for optimal treatment to reduce vision loss.
In recent years, transcorneal electrical stimulation(TES)has been regarded as a potential treatment method for degenerative retinal disease. However, the mechanism of TES therapy is still not understood till now. As one of the manifestations of retinal degenerative diseases, the fundus non-vascular perfusion area has been shown to be related to the degeneration of retinal photoreceptor cells and the attenuation of the retinal vasculature and there is a great probability to be cured by TES treatment. The purpose of this study was to analyze the variation of the intrinsic optical signal (IOS) characteristic and the retinal blood vasculature induced by TES in mice and to investigate the therapeutic mechanism of TES for retinal degenerative diseases. In this study, swept-source optical coherence tomography (SS-OCT) system was custom-built to record the IOS and fundus vascular response under TES in pre-, during, and post-stimulation periods, respectively. Results showed that the vessel density (VD) of retinal vessels slightly increased under TES, positive and negative IOS changes significantly increased in all retinal layers, and recovery of the microvascular access in the lesion area was obviously observed. This study might be useful to understanding the treatment mechanism of TES on degenerative retinal diseases and it proved that OCT and OCTA could be used as monitoring techniques for TES therapy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.