Clinically, optical coherence tomography (OCT) has been utilized to obtain the images of the kidney’s proximal convoluted tubules (PCTs), which can be used to quantify the morphometric parameters such as tubular density and diameter. Such parameters are useful for evaluating the status of the donor kidney for transplant. Quantifying PCTs from OCT images by human readers is a time-consuming and tedious process. Despite the fact that conventional deep learning models such as conventional neural networks (CNNs) have achieved great success in the automatic segmentation of kidney OCT images, gaps remain regarding the segmentation accuracy and reliability. Attention-based deep learning model has benefits over regular CNNs as it is intended to focus on the relevant part of the image and extract features for those regions. This paper aims at developing an Attention-based UNET model for automatic image analysis, pattern recognition, and segmentation of kidney OCT images. We evaluated five methods including the Residual-Attention-UNET, Attention-UNET, standard UNET, Residual UNET, and fully convolutional neural network using 14403 OCT images from 169 transplant kidneys for training and testing. Our results show that Residual-Attention-UNET outperformed the other four methods in segmentation by showing the highest values of all the six metrics including dice score (0.81 ± 0.01), intersection over union (IOU, 0.83 ± 0.02), specificity (0.84 ± 0.02), recall (0.82 ± 0.03), precision (0.81 ± 0.01), and accuracy (0.98 ± 0.08). Our results also show that the performance of the Residual-Attention-UNET is equivalent to the human manual segmentation (dice score = 0.84 ± 0.05). Residual-Attention-UNET and Attention-UNET also demonstrated good performance when trained on a small dataset (3456 images) whereas the performance of the other three methods dropped dramatically. In conclusion, our results suggested that the soft Attention-based models and specifically Residual-Attention-UNET are powerful and reliable methods for tubule lumen identification and segmentation and can help clinical evaluation of transplant kidney viability as fast and accurate as possible.
Three-dimensional precise models of teeth are critical for a variety of dental procedures, including orthodontics, prosthodontics, and implantology. While X-ray-based imaging devices are commonly used to obtain anatomical information about teeth, optical devices offer a promising alternative for acquiring 3D data of teeth without exposing patients to harmful radiation. Previous research has not examined the optical interactions with all dental tissue compartments nor provided a thorough analysis of detected signals at various boundary conditions for both transmittance and reflectance modes. To address this gap, a GPU-based Monte Carlo (MC) method has been utilized to assess the feasibility of diffuse optical spectroscopy (DOS) systems operating at 633 nm and 1310 nm wavelengths for simulating light-tissue interactions in a 3D tooth model. The results show that the system’s sensitivity to detect pulp signals at both 633 nm and 1310 nm wavelengths is higher in the transmittance compared with that in the reflectance mode. Analyzing the recorded absorbance, reflectance, and transmittance data verified that surface reflection at boundaries can improve the detected signal, especially from the pulp region in both reflectance and transmittance DOS systems. These findings could ultimately lead to more accurate and effective dental diagnosis and treatment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.