3D Optical Coherence Tomography Research Articles

Noninvasive virtual biopsy using micro-registered optical coherence tomography (OCT) in human subjects.

Histological hematoxylin and eosin-stained (H&E) tissue sections are used as the gold standard for pathologic detection of cancer, tumor margin detection, and disease diagnosis. Producing H&E sections, however, is invasive and time-consuming. While deep learning has shown promise in virtual staining of unstained tissue slides, true virtual biopsy requires staining of images taken from intact tissue. In this work, we developed a micron-accuracy coregistration method [micro-registered optical coherence tomography (OCT)] that can take a two-dimensional (2D) H&E slide and find the exact corresponding section in a 3D OCT image taken from the original fresh tissue. We trained a conditional generative adversarial network using the paired dataset and showed high-fidelity conversion of noninvasive OCT images to virtually stained H&E slices in both 2D and 3D. Applying these trained neural networks to in vivo OCT images should enable physicians to readily incorporate OCT imaging into their clinical practice, reducing the number of unnecessary biopsy procedures.

Enhancing point annotations with superpixel and confident learning guided for improving semi-supervised OCT fluid segmentation

Automatic segmentation of fluid in Optical Coherence Tomography (OCT) images is beneficial for ophthalmologists to make an accurate diagnosis. Although semi-supervised OCT fluid segmentation networks enhance their performance by introducing additional unlabeled data, the performance enhancement is limited. To address this, we propose Superpixel and Confident Learning Guide Point Annotations Network (SCLGPA-Net) based on the teacher-student architecture, which can learn OCT fluid segmentation from limited fully-annotated data and abundant point-annotated data. Specifically, we use points to annotate fluid regions in unlabeled OCT images and the Superpixel-Guided Pseudo-Label Generation (SGPLG) module generates pseudo-labels and pixel-level label trust maps from the point annotations. The label trust maps provide an indication of the reliability of the pseudo-labels. Furthermore, we propose the Confident Learning Guided Label Refinement (CLGLR) module identifies error information in the pseudo-labels and leads to further refinement. Experiments on the RETOUCH dataset show that we are able to reduce the need for fully-annotated data by 94.22%, closing the gap with the best fully supervised baselines to a mean IoU of only 2%. Furthermore, we constructed a private 2D OCT fluid segmentation dataset for evaluation. Compared with other methods, comprehensive experimental results demonstrate that the proposed method can achieve excellent performance in OCT fluid segmentation.

Deep-Learning-Based Group Pointwise Spatial Mapping of Structure to Function in Glaucoma

PurposeTo establish generalizable point-wise spatial relationship between structure and function through occlusion analysis of a deep-learning (DL) model for predicting the visual field (VF) sensitivities from three-dimensional (3D) optical coherence tomography (OCT) scan. DesignRetrospective cross-sectional study. Participants2151 eyes from 1129 patients. MethodsA DL model was trained to predict 52 VF sensitivities of 24-2 standard automated perimetry from 3D spectral-domain OCT images of the optic nerve head (ONH) with 12915 OCT-VF pairs. Using occlusion analysis, the contribution of each individual cube covering a 240 x 240 x 31.25 μm region of the ONH to the model's prediction was systematically evaluated for each OCT-VF pair in a separate test set that consisted of 996 OCT-VF pairs. After simple translation (shifting in x and y-axes to match the ONH center), group t-statistic maps were derived to visualize statistically significant ONH regions for each VF test point within a group. This analysis allowed for understanding the importance of each super voxel (240 x 240 x 31.25 μm covering the entire 4.32 x 4.32 x 1.125 mm ONH cube) in predicting VF test points for specific patient groups. Main Outcome MeasuresThe region at the ONH corresponding to each VF test point and the effect of the former on the latter. ResultsThe test set was divided to two groups, the healthy-to-early-glaucoma group (792 OCT-VF pairs, VF mean deviation (MD): -1.32 ± 1.90 dB) and the moderate-to-advanced-glaucoma group (204 OCT-VF pairs, VF MD: -17.93 ± 7.68 dB). Two-dimensional group t-statistic maps (x, y projection) were generated for both groups, assigning related ONH regions to visual field test points. The identified influential structural locations for VF sensitivity prediction at each test point aligned well with existing knowledge and understanding of structure-function spatial relationships. ConclusionsThis study successfully visualized the global trend of point-by-point spatial relationships between OCT-based structure and VF-based function without the need for prior knowledge or segmentation of OCTs. The revealed spatial correlations were consistent with previously published mappings. This presents possibilities of learning from trained machine learning models without applying any prior knowledge, potentially robust and free from bias.

Robust and accurate corneal interfaces segmentation in 2D and 3D OCT images.

Segmentation of corneal layer interfaces in optical coherence tomography (OCT) images is important for diagnostic and surgical purposes, while manual segmentation is a time-consuming and tedious process. This paper presents a novel technique for the automatic segmentation of corneal layer interfaces using customized initial layer estimation and a gradient-based segmentation method. The proposed method was also extended to three-dimensional OCT images. Validation was performed on two corneal datasets, one with 37 B-scan images of healthy human eyes and the other with a 3D volume scan of a porcine eye. The approach showed robustness in extracting different layer boundaries in the low-SNR region with lower computational cost but higher accuracy compared to existing techniques. It achieved segmentation errors below 2.1 pixels for both the anterior and posterior layer boundaries in terms of mean unsigned surface positioning error for the first dataset and 2.6 pixels (5.2 μm) for segmenting all three layers that can be resolved in the second dataset. On average, it takes 0.7 and 0.4 seconds to process a cross-sectional B-scan image for datasets one and two, respectively. Our comparative study also showed that it outperforms state-of-the-art methods for quantifying layer interfaces in terms of accuracy and time efficiency.

Rigid alignment method for secondary analyses of optical coherence tomography volumes.

Optical coherence tomography (OCT) provides micron level resolution of retinal tissue and is widely used in ophthalmology. Millions of pre-existing OCT images are available from research and clinical databases. Analysis of this data often requires or can benefit significantly from image registration and reduction of speckle noise. One method of reducing noise is to align and average multiple OCT scans together. We propose to use surface feature information and whole volume information to create a novel and simple pipeline that can rigidly align, and average multiple previously acquired 3D OCT volumes from a commercially available OCT device. This pipeline significantly improves both image quality and visualization of clinically relevant image features over single, unaligned volumes from the commercial scanner.

3D Optical Coherence Tomography image processing in BISCAP: characterization of biofilm structure and properties.

BISCAP is a state-of-the-art tool for automatically characterizing biofilm images obtained from Optical Coherence Tomography. Limited availability of other software tools is reported in the field. BISCAP's first version processes 2D images only. Processing 3D images is a problem of greater scientific relevance since it deals with the entire structure of biofilms instead of their 2D slices. Building on the image-processing principles and algorithms proposed earlier for 2D images, these were adapted to the 3D case, and a more general implementation of BISCAP was developed. The primary goal concerns the extension of the initial methodology to incorporate the depth axis in 3D images; multiple improvements were also made to boost computational performance. The calculation of structural properties and visual outputs was extended to offer new insights into the 3D structure of biofilms. BISCAP was tested using 3D images of biofilms with different morphologies, consistently delivering accurate characterizations of 3D structures in a few minutes using standard laptop machines. Low user dependency is required for image analysis. BISCAP is available from https://github.com/diogonarciso/BISCAP. All images used in the tutorials and the validation examples are available from https://web.fe.up.pt/∼fgm/biscap3d.

OCT angiography indices and the choroidal vascularity index in wild-type transthyretin (TTR) amyloidosis (ATTRwt).

Retinal angiopathy represents a well-known ocular manifestation of hereditary transthyretin amyloidosis (ATTRv). Until recently, there have been no reports on retinal changes in ATTRwt. In this retrospective observational clinical study, we aimed to determine whether vessel density (VD) indices and the choroidal vascularity index (CVI) could offer insights into retinal and choroidal vascular changes among patients affected by ATTRwt. Eighteen patients with a confirmed diagnosis of ATTRwt underwent structural optical coherence tomography (OCT) and OCT angiography (OCTA). We established a control group consisting of 16 healthy subjects for statistical comparisons. The 3D OCT and OCTA datasets were analyzed to assess retinal and choroidal thickness and VD. For measuring CVI, we obtained measurements for the total choroid area (TCA), luminal area (LA), and stromal area (SA). The mean VD exhibited a statistically significant reduction in the superficial capillary plexus (SCP), deep capillary plexus (DCP), and choriocapillaris (CC) among the ATTRwt group in comparison to the control group (p < 0.0001). Notably, ATTRwt patients displayed decreased choroidal thickness (p = 0.08). Additionally, the median CVI was lower in the ATTRwt group than in the control group (p = 0.04). The indices from OCTA and CVI have the potential to serve as non-invasive biomarkers for the quantitative evaluation of retinal and choroidal vascular involvement in patients with ATTRwt.

3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression from Longitudinal OCTs.

Self-supervised learning (SSL) has emerged as a powerful technique for improving the efficiency and effectiveness of deep learning models. Contrastive methods are a prominent family of SSL that extract similar representations of two augmented views of an image while pushing away others in the representation space as negatives. However, the state-of-the-art contrastive methods require large batch sizes and augmentations designed for natural images that are impractical for 3D medical images. To address these limitations, we propose a new longitudinal SSL method, 3DTINC, based on non-contrastive learning. It is designed to learn perturbation-invariant features for 3D optical coherence tomography (OCT) volumes, using augmentations specifically designed for OCT. We introduce a new non-contrastive similarity loss term that learns temporal information implicitly from intra-patient scans acquired at different times. Our experiments show that this temporal information is crucial for predicting progression of retinal diseases, such as age-related macular degeneration (AMD). After pretraining with 3DTINC, we evaluated the learned representations and the prognostic models on two large-scale longitudinal datasets of retinal OCTs where we predict the conversion to wet-AMD within a six-month interval. Our results demonstrate that each component of our contributions is crucial for learning meaningful representations useful in predicting disease progression from longitudinal volumetric scans.

GAMMA challenge: Glaucoma grAding from Multi-Modality imAges.

Glaucoma is a chronic neuro-degenerative condition that is one of the world's leading causes of irreversible but preventable blindness. The blindness is generally caused by the lack of timely detection and treatment. Early screening is thus essential for early treatment to preserve vision and maintain life quality. Colour fundus photography and Optical Coherence Tomography (OCT) are the two most cost-effective tools for glaucoma screening. Both imaging modalities have prominent biomarkers to indicate glaucoma suspects, such as the vertical cup-to-disc ratio (vCDR) on fundus images and retinal nerve fiber layer (RNFL) thickness on OCT volume. In clinical practice, it is often recommended to take both of the screenings for a more accurate and reliable diagnosis. However, although numerous algorithms are proposed based on fundus images or OCT volumes for the automated glaucoma detection, there are few methods that leverage both of the modalities to achieve the target. To fulfil the research gap, we set up the Glaucoma grAding from Multi-Modality imAges (GAMMA) Challenge to encourage the development of fundus & OCT-based glaucoma grading. The primary task of the challenge is to grade glaucoma from both the 2D fundus images and 3D OCT scanning volumes. As part of GAMMA, we have publicly released a glaucoma annotated dataset with both 2D fundus colour photography and 3D OCT volumes, which is the first multi-modality dataset for machine learning based glaucoma grading. In addition, an evaluation framework is also established to evaluate the performance of the submitted methods. During the challenge, 1272 results were submitted, and finally, ten best performing teams were selected for the final stage. We analyse their results and summarize their methods in the paper. Since all the teams submitted their source code in the challenge, we conducted a detailed ablation study to verify the effectiveness of the particular modules proposed. Finally, we identify the proposed techniques and strategies that could be of practical value for the clinical diagnosis of glaucoma. As the first in-depth study of fundus & OCT multi-modality glaucoma grading, we believe the GAMMA Challenge will serve as an essential guideline and benchmark for future research.

Choroidal Vessel and Stromal Volumetric Analysis After Photodynamic Therapy or Focal Laser for Central Serous Chorioretinopathy.

To utilize volumetric analysis to quantify volumetric changes in choroidal vessels and stroma after photodynamic therapy (PDT) and focal laser photocoagulation (PC) for central serous chorioretinopathy (CSCR). This retrospective, comparative study included 58 eyes (58 patients) with CSCR (PC, 33 eyes; PDT, 25 eyes) followed up with swept-source optical coherence tomography at 3 months after treatment. Three-dimensional (3D) choroidal vessel and stromal volumes in each area of the central 1.5-mm-diameter circle, the torus-shaped area with 6-mm-diameter circle excluding the area of the central 1.5-mm-diameter circle, and the treated area of the Early Treatment Diabetic Retinopathy Study (ETDRS) grid centered at the fovea were analyzed using a deep learning-based method. Changes in volume at baseline and 1 and 3 months after treatment were compared. The mean patient age was 49.3 ± 10.5 years. In the central 1.5-mm-diameter circle, the mean vessel and stromal volume rates significantly decreased after the treatment in both the PDT and PC groups (P = 0.00029 and P = 0.0014, respectively), and significant differences between the PDT and PC groups of continuous variables within times were observed in both volumes (P = 0.024 and P = 0.037, respectively). In the torus-shaped area and treated area, the PDT and PC groups both showed similar decreases in vessel and stromal volume over time. In the 3D optical coherence tomography volumetric analysis, both PDT and focal PC reduced choroid vessel volume in eyes with CSCR. This new finding is useful in elucidating the pathogenesis and healing mechanisms of CSCR.

RC-Net: A region-level context network for hyperreflective dots segmentation in retinal OCT images

Due to chronic exposure to hyperglycemia, the ocular biomechanical homeostasis of diabetics is disturbed, which may cause multiple ocular diseases, such as diabetic retinopathy (DR). In retinal optical coherence tomography (OCT) images of patients with DR, hyperreflective dots (HRDs) are spot-shaped areas with high reflectivity and high local contrast. Quantitative analyses of HRDs are the key to make appropriate decisions on diagnosis and treatment. The small scale, similarity to background and interference of other foci bring great challenges to accurate and automatic segmentation of HRDs. To address above challenges, we propose a novel region-level context network (RC-Net), which introduces region-level position attention module (RPAM) and region-level channel attention module (RCAM) for HRDs segmentation. Four RPAMs are embedded behind ordinary convolution blocks to extract rich contextual dependencies, which help to cluster pixels in same class and reveal differences between HRDs and background. To further improve feature representation, a RCAM is embedded into the top of the encoder structure to adaptively utilize the semantic dependencies between different channels. We evaluate the proposed RC-Net on a dataset, which consists of 450 2D OCT B-scans. The mean and standard deviation of dice similarity coefficient (DSC), intersection over union (IoU), recall (R) and precision (P) are 75.29±0.42%, 62.27±0.54%, 78.36±1.79% and 75.34±0.52%, respectively. The experiments show that the proposed RC-Net achieves superior segmentation performance of HRDs segmentation to state-of-the-art methods.

Integration of cellular-resolution optical coherence tomography and Raman spectroscopy for discrimination of skin cancer cells with machine learning.

An integrated cellular-resolution optical coherence tomography (OCT) module with near-infrared Raman spectroscopy was developed on the discrimination of various skin cancer cells and normal cells. Micron-level three-dimensional (3D) spatial resolution and the spectroscopic capability on chemical component determination can be obtained simultaneously. We experimentally verified the effectiveness of morphology, intensity, and spectroscopy features for discriminating skin cells. Both spatial and spectroscopic features were employed for the discrimination of five types of skin cells, including keratinocytes (HaCaT), the cell line of squamous cell carcinoma (A431), the cell line of basal cell carcinoma (BCC-1/KMC), primary melanocytes, and the cell line of melanoma (A375). The cell volume, compactness, surface roughness, average intensity, and internal intensity standard deviation were extracted from the 3D OCT images. After removing the fluorescence components from the acquired Raman spectra, the entire spectra (600 to ) were used. An accuracy of 85% in classifying five types of skin cells was achieved. The cellular-resolution OCT images effectively differentiate cancer and normal cells, whereas Raman spectroscopy can distinguish the cancer cells with nearly 100% accuracy. Among the OCT image features, cell surface roughness, internal average intensity, and standard deviation of internal intensity distribution effectively differentiate the cancerous and normal cells. The three features also worked well in sorting the keratinocyte and melanocyte. Using the full Raman spectra, the melanoma and keratinocyte-based cell carcinoma cancer cells can be discriminated effectively.

Diagnostic value of 3D Optical Coherence Tomography Multimode Images in the Diagnosis of Acute Central Serous Chorioretinopathy.

Spectral-Domain Optical Coherence Tomography (SD-OCT) provides non-invasive, high-speed, high-resolution, three-dimensional cross-section imaging of the macula. This study aimed to investigate the diagnostic value of the multimodal imaging technique of three-dimension (3D) optical coherence tomography (OCT) (3D-OCT) for the diagnosis and characterization of acute central serous chorioretinopathy (CSC). In this prospective clinical study 3D-OCT examinations of 82 cases with acute CSC were performed on the macular area, and the image characteristics were analyzed. Our study included a total of 87 eyes from 82 cases of CSC patients, 67 males and 15 females (mean age ± standard deviation (SD): 42.89 ±7.80 years old; age range: 27 to 56 years old. The 3D-OCT images were evaluated for the presence of subretinal fluid, subretinal space, fluctuation of the internal limiting membrane (ILM), folds of retinal pigment epithelial (RPE), retinal pigment epithelium detachment (PED), and flat irregular PED. The foveal thickness was measured using the manual caliper of OCT software. The OCT B-scan images showed 87 (100%) eyes had exudative retinal detachment (ERD), 38 (44%) had flat irregular PED, 36 (41%) had PED, 8 (9%) had subretinal turbidity structure, 2 (2%) had subretinal dot-like precipitates, 1 (1%) had focal choroidal excavation (FCE), and 1 (1%) eye had fluctuation of internal limiting membrane (FI). In the ILM-RPE thickness map, all eyes had a round or round like regular uniform domes. Fifty-seven (66%) domes were limited in the examination area and 30 (44%) domes were beyond the scope of this examination and only a partial section of the dome could be observed. In the en-face image, all eyes had a round or round-like black figure that corresponded with domes in the ILM-RPE thickness map. In RPE surface, 76 (87%) eyes had a shallow plate depression, 71(82%) had small focal uplift, and 1 (1%) eye had a focal concave feature. In the OCT ILM-RPE thickness, en-face image, and RPE surface maps, acute CSC exhibited specific imaging characteristics that can be helpful for reliable diagnosis and differential diagnosis of CSC.

Automated Age-Related Macular Degeneration Detector on Optical Coherence Tomography Images Using Slice-Sum Local Binary Patterns and Support Vector Machine.

Artificial intelligence has revolutionised smart medicine, resulting in enhanced medical care. This study presents an automated detector chip for age-related macular degeneration (AMD) using a support vector machine (SVM) and three-dimensional (3D) optical coherence tomography (OCT) volume. The aim is to assist ophthalmologists by reducing the time-consuming AMD medical examination. Using the property of 3D OCT volume, a modified feature vector connected method called slice-sum is proposed, reducing computational complexity while maintaining high detection accuracy. Compared to previous methods, this method significantly reduces computational complexity by at least a hundredfold. Image adjustment and noise removal steps are excluded for classification accuracy, and the feature extraction algorithm of local binary patterns is determined based on hardware consumption considerations. Through optimisation of the feature vector connection method after feature extraction, the computational complexity of SVM detection is significantly reduced, making it applicable to similar 3D datasets. Additionally, the design supports model replacement, allowing users to train and update classification models as needed. Using TSMC 40 nm CMOS technology, the proposed detector achieves a core area of 0.12 mm2 while demonstrating a classification throughput of 8.87 decisions/s at a maximum operating frequency of 454.54 MHz. The detector achieves a final testing classification accuracy of 92.31%.

Rapid Quantification of Microvessels of Three-Dimensional Blood-Brain Barrier Model Using Optical Coherence Tomography and Deep Learning Algorithm.

The blood-brain barrier (BBB) is a selective barrier that controls the transport between the blood and neural tissue features and maintains brain homeostasis to protect the central nervous system (CNS). In vitro models can be useful to understand the role of the BBB in disease and assess the effects of drug delivery. Recently, we reported a 3D BBB model with perfusable microvasculature in a Transwell insert. It replicates several key features of the native BBB, as it showed size-selective permeability of different molecular weights of dextran, activity of the P-glycoprotein efflux pump, and functionality of receptor-mediated transcytosis (RMT), which is the most investigated pathway for the transportation of macromolecules through endothelial cells of the BBB. For quality control and permeability evaluation in commercial use, visualization and quantification of the 3D vascular lumen structures is absolutely crucial. Here, for the first time, we report a rapid, non-invasive optical coherence tomography (OCT)-based approach to quantify the microvessel network in the 3D in vitro BBB model. Briefly, we successfully obtained the 3D OCT images of the BBB model and further processed the images using three strategies: morphological imaging processing (MIP), random forest machine learning using the Trainable Weka Segmentation plugin (RF-TWS), and deep learning using pix2pix cGAN. The performance of these methods was evaluated by comparing their output images with manually selected ground truth images. It suggested that deep learning performed well on object identification of OCT images and its computation results of vessel counts and surface areas were close to the ground truth results. This study not only facilitates the permeability evaluation of the BBB model but also offers a rapid, non-invasive observational and quantitative approach for the increasing number of other 3D in vitro models.

Thermal modulation of skin friction at the finger pad

Preliminary human studies show that reduced skin temperature minimises the risk of mechanically induced skin damage. However, the mechanisms by which cooling enhances skin tolerance to pressure and shear remain poorly understood. We hypothesized that skin cooling below thermo-neutral conditions will decrease kinetic friction at the skin-material interface. To test our hypothesis, we measured the friction coefficient of a thermally pre-conditioned index finger pad sliding at a normal load (5N) across a plate maintained at three different temperatures (38, 24, and 16 °C) in 8 healthy young adults (29±5y). To quantify the temperature distribution of the skin tissue, we used 3D surface scanning and Optical Coherence Tomography to develop an anatomically representative thermal model of the finger. Our group-level data indicated that the sliding finger with thermally affected tissues (up to 8 mm depth) experienced significantly lower frictional forces (p<0.01) at plate temperatures of 16 °C (i.e. 32% decrease) and 24 °C (i.e. 13% decrease) than at 38 °C, respectively. This phenomenon occurred consistently across participants (i.e. N = 6/8, 75%) and without large changes in skin hydration during sliding. Our complementary experimental and theoretical results provide new insights into thermal modulation of skin friction that can be employed for developing thermal technologies to maintain skin integrity under mechanical loading and shearing.

Automated robot-assisted wide-field optical coherence tomography using structured light camera.

Optical coherence tomography (OCT) is a promising real-time and non-invasive imaging technology widely utilized in biomedical and material inspection domains. However, limited field of view (FOV) in conventional OCT systems hampers their broader applicability. Here, we propose an automated system integrating a structured light camera and robotic arm for large-area OCT scanning. The system precisely detects tissue contours, automates scan path generation, and enables accurate scanning of expansive sample areas. The proposed system consists of a robotic arm, a three-dimensional (3D) structured light camera, and a customized portable OCT probe. The 3D structured light camera is employed to generate a precise 3D point cloud of the sample surface, enabling automatic planning of the scanning path for the robotic arm. Meanwhile, the OCT probe is mounted on the robotic arm, facilitating scanning of the sample along the predetermined path. Continuous OCT B-scans are acquired during the scanning process, facilitating the generation of high-resolution and large-area 3D OCT reconstructions of the sample. We conducted position error tests and presented examples of 3D macroscopic imaging of different samples, such as ex vivo kidney, skin and leaf blade. The robotic arm can accurately reach the planned positions with an average absolute error of approximately 0.16 mm. The findings demonstrate that the proposed system enables the acquisition of 3D OCT images covering an area exceeding 20 cm2, indicating wide-ranging potential for utilization in diverse domains such as biomedical, industrial, and agricultural fields.

Polarization-isolated stretched-pulse mode-locked swept laser for 10.3-MHz A-line rate optical coherence tomography.

Stretched-pulse mode-locked (SPML) lasing based on a chirped fiber Bragg grating (CFBG) has proven to be a powerful method to generate wavelength-swept lasers at speeds of tens of megahertz. However, light transmitted through the CFBG may lead to undesirable laser oscillation that disrupts the mechanism of the laser active mode locking in the theta ring cavity. In this Letter, we demonstrate a simple and low-cost approach to suppress the transmitted light and achieve an effective duty cycle of ∼100% with only one CFBG and no need for intra-cavity semiconductor optical amplifier (SOA) modulation, extra-cavity optical buffering, and post amplification. By utilizing polarization isolation of the bi-directional CFBG, a swept laser centered at 1305 nm, with repetition rate of 10.3 MHz, optical power of 84 mW, and 3 dB bandwidth of 109 nm, is demonstrated. Ultrahigh speed 3D optical coherence tomography (OCT) structural imaging of a human palm in vivo using this swept laser is also demonstrated. We believe that this ultrahigh speed swept laser will greatly promote the OCT technique for industrial and biomedical applications.

Cross-Attention Based Multi-Resolution Feature Fusion Model for Self-Supervised Cervical OCT Image Classification.

Cervical cancer seriously endangers the health of the female reproductive system and even risks women's life in severe cases. Optical coherence tomography (OCT) is a non-invasive, real-time, high-resolution imaging technology for cervical tissues. However, since the interpretation of cervical OCT images is a knowledge-intensive, time-consuming task, it is tough to acquire a large number of high-quality labeled images quickly, which is a big challenge for supervised learning. In this study, we introduce the vision Transformer (ViT) architecture, which has recently achieved impressive results in natural image analysis, into the classification task of cervical OCT images. Our work aims to develop a computer-aided diagnosis (CADx) approach based on a self-supervised ViT-based model to classify cervical OCT images effectively. We leverage masked autoencoders (MAE) to perform self-supervised pre-training on cervical OCT images, so the proposed classification model has a better transfer learning ability. In the fine-tuning process, the ViT-based classification model extracts multi-scale features from OCT images of different resolutions and fuses them with the cross-attention module. The ten-fold cross-validation results on an OCT image dataset from a multi-center clinical study of 733 patients in China indicate that our model achieved an AUC value of 0.9963 ± 0.0069 with a 95.89 ± 3.30% sensitivity and 98.23 ± 1.36 % specificity, outperforming some state-of-the-art classification models based on Transformers and convolutional neural networks (CNNs) in the binary classification task of detecting high-risk cervical diseases, including high-grade squamous intraepithelial lesion (HSIL) and cervical cancer. Furthermore, our model with the cross-shaped voting strategy achieved a sensitivity of 92.06% and specificity of 95.56% on an external validation dataset containing 288 three-dimensional (3D) OCT volumes from 118 Chinese patients in a different new hospital. This result met or exceeded the average of four medical experts who have used OCT for over one year. In addition to promising classification performance, our model has a remarkable ability to detect and visualize local lesions using the attention map of the standard ViT model, providing good interpretability for gynecologists to locate and diagnose possible cervical diseases.

Segmentation-Free OCT-Volume-Based Deep Learning Model Improves Pointwise Visual Field Sensitivity Estimation.

The structural changes measured by optical coherence tomography (OCT) are related to functional changes in visual fields (VFs). This study aims to accurately assess the structure-function relationship and overcome the challenges brought by the minimal measurable level (floor effect) of segmentation-dependent OCT measurements commonly used in prior studies. We developed a deep learning model to estimate the functional performance directly from three-dimensional (3D) OCT volumes and compared it to the model trained with segmentation-dependent two-dimensional (2D) OCT thickness maps. Moreover, we proposed a gradient loss to utilize the spatial information of VFs. Our 3D model was significantly better than the 2D model both globally and pointwise regarding both mean absolute error (MAE = 3.11 + 3.54 vs. 3.47 ± 3.75 dB, P < 0.001) and Pearson's correlation coefficient (0.80 vs. 0.75, P < 0.001). On a subset of test data with floor effects, the 3D model showed less influence from floor effects than the 2D model (MAE = 5.24 ± 3.99 vs. 6.34 ± 4.58 dB, P < 0.001, and correlation 0.83 vs. 0.74, P < 0.001). The gradient loss improved the estimation error for low-sensitivity values. Furthermore, our 3D model outperformed all prior studies. By providing a better quantitative model to encapsulate the structure-function relationship more accurately, our method may help deriving VF test surrogates. DL-based VF surrogates not only benefit patients by reducing the testing time of VFs but also allow clinicians to make clinical judgments without the inherent limitations of VFs.