Diagnosis of dental caries based on attenuation coefficients analysis of optical coherence tomography images.

Quantitative analysis of optical attenuation based on optical coherence tomography images will offer an effective method to enhance diagnostic capabilities. In this paper, the optical attenuation in demineralized caries specimens was calculated to distinguish between normal teeth and carious teeth and further to differentiate the severity of caries, and thus come to the half-automated diagnosis of dental caries. Results show that the attenuation coefficient in carious regions is approximately 4.97 mm - 1 ± 0.206 $$ 4.97\ {\mathrm{mm}}^{-1}\left(\pm 0.206\right) $$ , while that of normal teeth is about 3.69 mm - 1 ± 0.231 $$ 3.69\ {\mathrm{mm}}^{-1}\ \left(\pm 0.231\right) $$ . Attenuation coefficient of carious regions is 35% higher than that of normal teeth. Moreover, five classes of caries were qualified and classified based on the optical attenuation coefficient. Compared with the healthy teeth, there is a noticeable disparity in the attenuation coefficients of carious teeth, both on the surface and at the dentinoenamel junction. This study provides a method for accurate caries diagnosis, particularly in detection of early lesions and subtle structural changes.

Multi-label classification of retinal diseases based on fundus images using Resnet and Transformer.

Retinal disorders are a major cause of irreversible vision loss, which can be mitigated through accurate and early diagnosis. Conventionally, fundus images are used as the gold diagnosis standard in detecting retinal diseases. In recent years, more and more researchers have employed deep learning methods for diagnosing ophthalmic diseases using fundus photography datasets. Among the studies, most of them focus on diagnosing a single disease in fundus images, making it still challenging for the diagnosis of multiple diseases. In this paper, we propose a framework that combines ResNet and Transformer for multi-label classification of retinal disease. This model employs ResNet to extract image features, utilizes Transformer to capture global information, and enhances the relationships between categories through learnable label embedding. On the publicly available Ocular Disease Intelligent Recognition (ODIR-5 k) dataset, the proposed method achieves a mean average precision of 92.86%, an area under the curve (AUC) of 97.27%, and a recall of 90.62%, which outperforms other state-of-the-art approaches for the multi-label classification. The proposed method represents a significant advancement in the field of retinal disease diagnosis, offering a more accurate, efficient, and comprehensive model for the detection of multiple retinal conditions.

ATN-Res2Unet: an advanced deep learning network for the elimination of saturation artifacts in endoscopy optical coherence tomography.

Endoscopic optical coherence tomography (OCT) possesses the capability to non-invasively image internal lumens; however, it is susceptible to saturation artifacts arising from robust reflective structures. In this study, we introduce an innovative deep learning network, ATN-Res2Unet, designed to mitigate saturation artifacts in endoscopic OCT images. This is achieved through the integration of multi-scale perception, multi-attention mechanisms, and frequency domain filters. To address the challenge of obtaining ground truth in endoscopic OCT, we propose a method for constructing training data pairs. Experimental in vivo data substantiates the effectiveness of ATN-Res2Unet in reducing diverse artifacts while preserving structural information. Comparative analysis with prior studies reveals a notable enhancement, with average quantitative indicators increasing by 45.4-83.8%. Significantly, this study marks the inaugural exploration of leveraging deep learning to eradicate artifacts from endoscopic OCT images, presenting considerable potential for clinical applications.

Self-attention CNN for retinal layer segmentation in OCT.

The structure of the retinal layers provides valuable diagnostic information for many ophthalmic diseases. Optical coherence tomography (OCT) obtains cross-sectional images of the retina, which reveals information about the retinal layers. The U-net based approaches are prominent in retinal layering methods, which are usually beneficial to local characteristics but not good at obtaining long-distance dependence for contextual information. Furthermore, the morphology of retinal layers with the disease is more complex, which brings more significant challenges to the task of retinal layer segmentation. We propose a U-shaped network combining an encoder-decoder architecture and self-attention mechanisms. In response to the characteristics of retinal OCT cross-sectional images, a self-attentive module in the vertical direction is added to the bottom of the U-shaped network, and an attention mechanism is also added in skip connection and up-sampling to enhance essential features. In this method, the transformer's self-attentive mechanism obtains the global field of perception, thus providing the missing context information for convolutions, and the convolutional neural network also efficiently extracts local features, compensating the local details the transformer ignores. The experiment results showed that our method is accurate and better than other methods for segmentation of the retinal layers, with the average Dice scores of 0.871 and 0.820, respectively, on two public retinal OCT image datasets. To perform the layer segmentation of retinal OCT image better, the proposed method incorporates the transformer's self-attention mechanism in a U-shaped network, which is helpful for ophthalmic disease diagnosis.

CSANet: a lightweight channel and spatial attention neural network for grading diabetic retinopathy with optical coherence tomography angiography.

Background: Diabetic retinopathy (DR) is one of the most common eye diseases. Convolutional neural networks (CNNs) have proven to be a powerful tool for learning DR features; however, accurate DR grading remains challenging due to the small lesions in optical coherence tomography angiography (OCTA) images and the small number of samples. Methods: In this article, we developed a novel deep-learning framework to achieve the fine-grained classification of DR; that is, the lightweight channel and spatial attention network (CSANet). Our CSANet comprises two modules: the baseline model, and the hybrid attention module (HAM) based on spatial attention and channel attention. The spatial attention module is used to mine small lesions and obtain a set of spatial position weights to address the problem of small lesions being ignored during the convolution process. The channel attention module uses a set of channel weights to focus on useful features and suppress irrelevant features. Results: The extensive experimental results for the OCTA-DR and diabetic retinopathy analysis challenge (DRAC) 2022 data sets showed that the CSANet achieved state-of-the-art DR grading results, showing the effectiveness of the proposed model. The CSANet had an accuracy rate of 97.41% for the OCTA-DR data set and 85.71% for the DRAC 2022 data set. Conclusions: Extensive experiments using the OCTA-DR and DRAC 2022 data sets showed that the proposed model effectively mitigated the problems of mutual confusion between DRs of different severity and small lesions being neglected in the convolution process, and thus improved the accuracy of DR classification.

High-precision retinal blood vessel segmentation based on a multi-stage and dual-channel deep learning network.

Objective.The high-precision segmentation of retinal vessels in fundus images is important for the early diagnosis of ophthalmic diseases. However, the extraction for microvessels is challenging due to their characteristics of low contrast and high structural complexity. Although some works have been developed to improve the segmentation ability in thin vessels, they have only been successful in recognizing small vessels with relatively high contrast.Approach.Therefore, we develop a deep learning (DL) framework with a multi-stage and dual-channel network model (MSDC_NET) to further improve the thin-vessel segmentation with low contrast. Specifically, an adaptive image enhancement strategy combining multiple preprocessing and the DL method is firstly proposed to elevate the contrast of thin vessels; then, a two-channel model with multi-scale perception is developed to implement whole- and thin-vessel segmentation; and finally, a series of post-processing operations are designed to extract more small vessels in the predicted maps from thin-vessel channels.Main results.Experiments on DRIVE, STARE and CHASE_DB1 demonstrate the superiorities of the proposed MSDC_NET in extracting more thin vessels in fundus images, and quantitative evaluations on several parameters based on the advanced ground truth further verify the advantages of our proposed DL model. Compared with the previous multi-branch method, the specificity and F1score are improved by about 2.18%, 0.68%, 1.73% and 2.91%, 0.24%, 8.38% on the three datasets, respectively.Significance.This work may provide richer information to ophthalmologists for the diagnosis and treatment of vascular-related ophthalmic diseases.

Image segmentation of mouse eye in vivo with optical coherence tomography based on Bayesian classification.

OBJECTIVES: Optical coherence tomography (OCT) is a new imaging technology that uses an optical analog of ultrasound imaging for biological tissues. Image segmentation plays an important role in dealing with quantitative analysis of medical images. METHODS: We have proposed a novel framework to deal with the low intensity problem, based on the labeled patches and Bayesian classification (LPBC) model. The proposed method includes training and testing phases. During the training phase, firstly, we manually select the sub-images of background and Region of Interest (ROI) from the training image, and then extract features by patches. Finally, we train the Bayesian model with the features. The segmentation threshold of each patch is computed by the learned Bayesian model. RESULTS: In addition, we have collected a new dataset of mouse eyes in vivo with OCT, named MEVOCT, which can be found at URL https://17861318579.github.io/LPBC. MEVOCT consists of 20 high-resolution images. The resolution of every image is 2048 × 2048 pixels. CONCLUSIONS: The experimental results demonstrate the effectiveness of the LPBC method on the new MEVOCT dataset. The ROI segmentation is of great importance for the distortion correction.

Deep-learning segmentation method for optical coherence tomography angiography in ophthalmology.

PURPOSE: The optic disc and the macular are two major anatomical structures in the human eye. Optic discs are associated with the optic nerve. Macular mainly involves degeneration and impaired function of the macular region. Reliable optic disc and macular segmentation are necessary for the automated screening of retinal diseases. METHODS: A swept-source OCTA system was designed to capture OCTA images of human eyes. To address these segmentation tasks, first, we constructed a new Optic Disc and Macula in fundus Image with optical coherence tomography angiography (OCTA) dataset (ODMI). Second, we proposed a Coarse and Fine Attention-Based Network (CFANet). RESULTS: The five metrics of our methods on ODMI are 98.91 % , 98.47 % , 89.77 % , 98.49 % , and 89.77 % , respectively. CONCLUSIONS: Experimental results show that our CFANet has achieved good performance on segmentation for the optic disc and macula in OCTA.

A new retinal OCT-angiography diabetic retinopathy dataset for segmentation and DR grading.

PURPOSE: Diabetic retinopathy (DR) is one of the most common diseases caused by diabetes and can lead to vision loss or even blindness. The wide-field optical coherence tomography (OCT) angiography is non-invasive imaging technology and convenient to diagnose DR. METHODS: A newly constructed Retinal OCT-Angiography Diabetic retinopathy (ROAD) dataset is utilized for segmentation and grading tasks. It contains 1200 normal images, 1440 DR images, and 1440 ground truths for DR image segmentation. To handle the problem of grading DR, we propose a novel and effective framework, named projective map attention-based convolutional neural network (PACNet). RESULTS: The experimental results demonstrate the effectiveness of our PACNet. The accuracy of the proposed framework for grading DR is 87.5% on the ROAD dataset. CONCLUSIONS: The information on ROAD can be viewed at URL https://mip2019.github.io/ROAD. The ROAD dataset will be helpful for the development of the early detection of DR field and future research. TRANSLATIONAL RELEVANCE: The novel framework for grading DR is a valuable research and clinical diagnosis method.

Endoscopic optical coherence tomography angiography using an externally driving catheter.

Endoscopic optical coherence tomography (OCT) is an imaging modality that enables cross-sectional subsurface imaging of tubular organs and cavities. Recently, endoscopic OCT angiography (OCTA) was successfully achieved in distal scanning systems using an internal-motor-driving catheter. In conventional OCT systems using externally driving catheters, the mechanical instability in the proximal actuation causes difficulties for differentiating capillaries in tissues. In this study, OCTA in an endoscopic OCT system using an external-motor-driving catheter was proposed. Blood vessels were visualized by using a high-stability inter-A-scan scheme and the spatiotemporal singular value decomposition algorithm. It is not limited by nonuniform rotation distortion caused by the catheter and physiological motion artifacts. Results show that microvasculature in a custom-made microfluidic phantom and the submucosal capillaries in the mouse rectum are successfully visualized. Furthermore, OCTA using a catheter with a small size (outer diameter less than 1 mm) makes it possible for early diagnosis of narrow lumens, such as pancreatic and bile duct cancers.

Improved FAST algorithm for non-uniform rotational distortion correction in OCT endoscopic imaging.

Optical Coherence Tomography (OCT) is widely used for endoscopic imaging in endoluminal organs because of its high imaging accuracy and resolution. However, OCT endoscopic imaging suffers from Non-Uniform Rotational Distortion (NURD), which can be caused by many factors, such as irregular motor rotation and changes in friction between the probe and the sheath. Correcting this distortion is essential to obtaining high-quality Optical Coherence Tomography Angiography (OCTA) images. There are two main approaches for correcting NURD: hardware-based methods and algorithm-based methods. Hardware-based methods can be costly, challenging to implement, and may not eliminate NURD. Algorithm-based methods, such as image registration, can be effective for correcting NURD but can also be prone to the problem of NURD propagation. To address this issue, we process frames by coarse and fine registration, respectively. The new reference frame is generated by filtering out the A-scan that may have the NURD problem by coarse registration. And the fine registration uses this frame to achieve the final NURD correction. In addition, we have improved the Features from Accelerated Segment Test (FAST) algorithm and put it into coarse and fine registration process. Four evaluation functions were used for the experimental results, including signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), mean squared error (MSE), and structural similarity index measure (SSIM). By comparing with Scale-invariant feature transform (SIFT), Speeded up robust features (SURF), Oriented FAST and Rotated BRIEF (ORB), intensity-based (Cross-correlation), and Optical Flow algorithms, our algorithm has a higher similarity between the corrected frames. Moreover, the noise in the OCTA data is better suppressed, and the vascular information is well preserved. Our image registration-based algorithm reduces the problem of NURD propagation between B-scan frames and improves the imaging quality of OCT endoscopic images.

Time-Serial Evaluation of the Development and Treatment of Myopia in Mice Eyes Using OCT and ZEMAX.

Myopia is a significant cause of visual impairment which may lead to many complications. However, the understanding of the mechanisms of myopia is still limited. In this paper, in order to investigate the development and the treatment of myopia, we analyzed the biological structure parameters of mice eyes, obtained from optical coherence tomography (OCT), and the optical performance of mice eyes calculated using ZEMAX software (ZEMAX Development Corporation, Kirkland, WA, USA) in which the optical model was built on the segment-by-segment optically corrected OCT 3D-images. Time-serial evaluation of three groups of mice eyes (form-deprivation myopia mice eyes, normal mice eyes, and atropine-treated myopia mice eyes) was performed. In addition to the biological structure parameters, imaging performance with the development of root-mean-square wavefront aberration at six filed angles was compared and analyzed. Results show that the biological structure parameters of the eye are closely related to the development of myopia. The peripheral defocus of the retina has a significant impact on inducing myopia, which verifies the new theory of myopia development. The delaying effect of atropine solution on myopia development is shown to verify the therapeutic effect of the medicine. This study provides technical support for the investigation of the myopia mechanism.

Development of a multi-scene universal multiple wavelet-FFT algorithm (MW-FFTA) for denoising motion artifacts in OCT-angiography in vivo imaging.

Optical coherence tomography angiography (OCTA) images suffer from inevitable micromotion (breathing, heartbeat, and blinking) noise. These image artifacts can severely disturb the visibility of results and reduce accuracy of vessel morphological and functional metrics quantization. Herein, we propose a multiple wavelet-FFT algorithm (MW-FFTA) comprising multiple integrated processes combined with wavelet-FFT and minimum reconstruction that can be used to effectively attenuate motion artifacts and significantly improve the precision of quantitative information. We verified the fidelity of image information and reliability of MW-FFTA by the image quality evaluation. The efficiency and robustness of MW-FFTA was validated by the vessel parameters on multi-scene in vivo OCTA imaging. Compared with previous algorithms, our method provides better visual and quantitative results. Therefore, the MW-FFTA possesses the potential capacity to improve the diagnosis of clinical diseases with OCTA.

Correction of refractive distortion in whole-eye optical coherence tomography imaging of the mouse eye.

Optical coherence tomography (OCT) is an imaging modality that acquires high-resolution cross-sectional images of living tissues and it has become the standard in ophthalmological diagnoses. However, most quantitative morphological measurements are based on the raw OCT images which are distorted by several mechanisms such as the refraction of probe light in the sample and the scan geometries and thus the analysis of the raw OCT images inevitably induced calculation errors. In this paper, based on Fermat's principle and the concept of inverse light tracing, image distortions due to refraction occurred at tissue boundaries in the whole-eye OCT imaging of mouse by telecentric scanning were corrected. Specially, the mathematical correction models were deducted for each interface, and the high-precision whole-eye image was recovered segment by segment. We conducted phantom and in vivo experiments on mouse and human eyes to verify the distortion correction algorithm, and several parameters of the radius of curvature, thickness of tissues and error, were calculated to quantitatively evaluate the images. Experimental results demonstrated that the method can provide accurate and reliable measurements of whole-eye parameters and thus be a valuable tool for the research and clinical diagnosis.

A single-step regression method based on transformer for retinal layer segmentation.

The shape and structure of retinal layers are basic characteristics for the diagnosis of many ophthalmological diseases. Based on B-Scans of optical coherence tomography, most of retinal layer segmentation methods are composed of two-steps: classifying pixels and extracting retinal layers, in which the optimization of two independent steps decreases the accuracy. Although the methods based on deep learning are highly accurate, they require a large amount of labeled data. This paper proposes a single-step method based on transformer for retinal layer segmentation, which is trained by axial data (A-Scans), to obtain the boundary of each layer. The proposed method was evaluated on two public data sets. The first one contains eight retinal layer boundaries for diabetic macular edema, and the second one contains nine retinal layer boundaries for healthy controls and subjects with multiple sclerosis. Its absolute average distance errors are 0.99 pixels and 3.67 pixels, respectively, for the two sets, and its root mean square error is 1.29 pixels for the latter set. In addition, its accuracy is acceptable even if the training data is reduced to 0.3. The proposed method achieves state-of-the-art performance while maintaining the correct topology and requires less labeled data.

Integrated US-OCT-NIRF Tri-Modality Endoscopic Imaging System for Pancreaticobiliary Duct Imaging.

Pancreaticobiliary carcinomas is a highly malignant gastrointestinal tumor. Most pancreaticobiliary cancers arise from epithelial proliferation within the pancreaticobiliary ducts, referred to as pancreatic intraepithelial neoplasias (PanINs). Some PanINs are benign metaplasia, while others progress to invasive duct adenocarcinoma (IDAC). However, there is no standard program to diagnose the progression from PanINs to IDAC. In this study, we present a tri-modality imaging system, which integrates ultrasound (US), optical coherence tomography (OCT), and near-infrared fluorescence (NIRF) for pancreaticobiliary duct imaging. This system can obtain OCT, US, and NIRF images in real-time with a frame rate of 30 frames per second. For the endoscopy probe with an outer diameter of 0.9 mm, the US transducer and fiber ball lens were placed back to back. In vivo experiments were performed on the rectums of Sprague-Dawley rats to demonstrate the imaging performance of US, OCT, and fluorescence angiography. An ex vivo experiment on a human pancreatic duct was performed for a more accurate assessment of the pancreaticobiliary duct. The tomography images of rat rectums and human pancreatic ducts were correlated with hematoxylin and eosin (H&E) histology to check the measurement accuracy. The integrated tri-modality system has great clinical potential in mechanism studies, early diagnosis, and prognosis evaluation of malignant pancreaticobiliary carcinomas.

Classification-based framework for binarization on mice eye image in vivo with optical coherence tomography.

Optical coherence tomography (OCT) angiography has drawn much attention in the medical imaging field. Binarization plays an important role in quantitative analysis of eye with optical coherence tomography. To address the problem of few training samples and contrast-limited scene, we proposed a new binarization framework with specific-patch SVM (SPSVM) for low-intensity OCT image, which is open and classification-based framework. This new framework contains two phases: training model and binarization threshold. In the training phase, firstly, the patches of target and background from few training samples are extracted as the ROI and the background, respectively. Then, PCA is conducted on all patches to reduce the dimension and learn the eigenvector subspace. Finally, the classification model is trained from the features of patches to get the target value of different patches. In the testing phase, the learned eigenvector subspace is conducted on the pixels of each patch. The binarization threshold of patch is obtained with the learned SVM model. We acquire a new OCT mice eye (OCT-ME) database, which is publicly available at https://mip2019.github.io/spsvm. Extensive experiments were performed to demonstrate the effectiveness of the proposed SPSVM framework.

Intravital Whole-Process Monitoring Thermo-Chemotherapy Via 2D Silicon Nanoplatform: A Macro Guidance and Long-Term Microscopic Precise Imaging Strategy.

Tumor angiogenesis is a complex process that is unamenable to intravital whole-process monitoring, especially on microscopic assessment of tumor microvessel and quantifying microvascular hemodynamics before and after the nanotherapeutics, which hinder the understanding of nanotheranostics outcomes in tumor treatment. Herein, a new photoacoustic (PA) imaging-optical coherence tomography angiography (OCTA)-laser speckle (LS) multimodal imaging strategy is first proposed, which is not only able to precisely macro guide the thermo-chemotherapy of tumor by monitoring blood oxygen saturation (SaO2 ) and hemoglobin content (HbT), but also capable of long-term microscopic investigating the microvessel morphology (microvascular density) and hemodynamics changes (relative blood flow) before and after the nanotherapeutics in vivo. Moreover, to realize the tumor thermo-chemotherapy treatment based on this novel multimodal imaging strategy, a 2D 5-fluorouracil silicon nanosheets (5-Fu-Si NSs) therapeutic agent is designed. Furthermore, 2D high-resolution tumor microvascular images in different stage display that tendency of the thermo-chemotherapy effect is closely associated with tumor angiogenesis. Taken together, the investigations establish the fundamental base in theory and technology for further tailoring the novel specific diagnosis and treatment strategy in tumor. More importantly, this technique will be beneficial to evaluate the tumor microvascular response to nanotherapeutics at microscale.

Imaging depth extension of optical coherence tomography in rabbit eyes using optical clearing agents.

Optical coherence tomography has become an indispensable diagnostic tool in ophthalmology for imaging the retina and the anterior segment of the eye. However, the imaging depth of optical coherence tomography is limited by light attenuation in tissues due to optical scattering and absorption. In this study of rabbit eye both ex vivo and in vivo, optical coherence tomography imaging depth of the anterior and posterior segments of the eye was extended by using optical clearing agents to reduce multiple scattering. The sclera, the iris, and the ciliary body were clearly visualized by direct application of glycerol at an incision on the conjunctiva, and the posterior boundary of sclera and even the deeper tissues were detected by submerging the posterior segment of eye in glycerol solution ex vivo or by retro-bulbar injection of glycerol in vivo. The ex vivo rabbit eyes recovered to their original state in 60 s after saline-wash treatment, and normal optical coherence tomography images of the posterior segment of the sample eyes proved the self-recovery of in vivo performance. Signal intensities of optical coherence tomography images obtained before and after glycerol treatment were compared to analysis of the effect of optical clearing. To the best of our knowledge, this is the first study for imaging depth extension of optical coherence tomography in both the anterior and posterior segments of eye by using optical clearing agents.

Evaluation of Retinal Pigment Epithelium and Choroidal Neovascularization in Rats Using Laser-Scanning Optical-Resolution Photoacoustic Microscopy.

PURPOSE: To demonstrate the value of the laser-scanning optical-resolution (LSOR)-photoacoustic (PA) microscopy (PAM) system and the conventional multimodal imaging techniques in the evaluation of laser-induced retinal injury and choroidal neovascularization (CNV) in rats. METHODS: Different degrees of retinal injury were induced using laser photocoagulation. We compared the LSOR-PAM system with conventional imaging techniques in evaluating retinal injury with or without CNV. Six additional rats, treated with an anti-VEGF antibody or immunoglobulin G immediately after photocoagulation, were imaged 7 and 14 days after injection, and CNV lesion areas were compared. RESULTS: In the retinal injury model, fundus autofluorescence showed well-defined hyperreflection, while the lesion displayed abundant PA signals demonstrating nonuniform melanin distribution in retinal pigment epithelium (RPE). RPE was detected with higher contrast in the PAM B-scan image than optical coherence tomography (OCT). Additionally, the CNV lesion was present with multiple PA signal intensities which distinctly characterized the location and area of CNV as found in fundus fluorescein angiography. Furthermore, the decreased PA signals extending from the CNV lesion were similar to those of the vascular bud in ex vivo imaging, which was invisible in other in vivo images. When treated with anti-VEGF agents, statistically significant differences can be demonstrated by PAM similar to other modalities. CONCLUSIONS: LSOR-PAM can detect the melanin distribution of RPE in laser-induced retinal injury and CNV in rats. PAM imaging provides a potential new tool to evaluate the vitality and functionality of RPE in vivo as well as to monitor the development and treatment of CNV.