Optical coherence tomography (OCT) is a non-invasive imaging modality which is widely used in clinical ophthalmology. OCT images are capable of visualizing deep retinal layers which is crucial for early diagnosis of retinal diseases. In this paper, we describe a comprehensive open-access database containing more than 500 highresolution images categorized into different pathological conditions. The image classes include Normal (NO), Macular Hole (MH), Age-related Macular Degeneration (AMD), Central Serous Retinopathy (CSR), and Diabetic Retinopathy (DR). The images were obtained from a raster scan protocol with a 2mm scan length and 512x1024 pixel resolution. We have also included 25 normal OCT images with their corresponding ground truth delineations which can be used for an accurate evaluation of OCT image segmentation. In addition, we have provided a user friendly GUI which can be used by clinicians for manual (and semi-automated) segmentation.
Purpose: Many interventional procedures require the precise placement of needles or therapy applicators (tools) to correctly achieve planned targets for optimal diagnosis or treatment of cancer, typically leveraging the temporal resolution of ultrasound (US) to provide real-time feedback. Identifying tools in two-dimensional (2D) images can often be time-consuming with the precise position difficult to distinguish. We have developed and implemented a deep learning method to segment tools in 2D US images in near real-time for multiple anatomical sites, despite the widely varying appearances across interventional applications. Methods: A U-Net architecture with a Dice similarity coefficient (DSC) loss function was used to perform segmentation on input images resized to 256 × 256 pixels. The U-Net was modified by adding 50% dropouts and the use of transpose convolutions in the decoder section of the network. The proposed approach was trained with 917 images and manual segmentations from prostate/gynecologic brachytherapy, liver ablation, and kidney biopsy/ablation procedures, as well as phantom experiments. Real-time data augmentation was applied to improve generalizability and doubled the dataset for each epoch. Postprocessing to identify the tool tip and trajectory was performed using two different approaches, comparing the largest island with a linear fit to random sample consensus (RAN-SAC) fitting. Results: Comparing predictions from 315 unseen test images to manual segmentations, the overall median [first quartile, third quartile] tip error, angular error, and DSC were 3.5 [1.3, 13.5] mm, 0.8 [0.3, 1.7]°, and 73.3 [56.2, 82.3]%, respectively, following RANSAC postprocessing. The predictions with the lowest median tip and angular errors were observed in the gynecologic images (median tip error: 0.3 mm; median angular error: 0.4°) with the highest errors in the kidney images (median tip error: 10.1 mm; median angular error: 2.9°). The performance on the kidney images was likely due to a reduction in acoustic signal associated with oblique insertions relative to the US probe and the increased number of anatomical interfaces with similar echogenicity. Unprocessed segmentations were performed with a mean time of approximately 50 ms per image. Conclusions: We have demonstrated that our proposed approach can accurately segment tools in 2D US images from multiple anatomical locations and a variety of clinical interventional procedures in near real-time, providing the potential to improve image guidance during a broad range of diagnostic and therapeutic cancer interventions.
Objective This study aimed to determine whether there are differences in the lateral ventricular volumes, measured by three-dimensional ultrasound (3D US) depending on the posture of the neonate (right and left lateral decubitus). Study Design This was a prospective analysis of the lateral ventricular volumes of preterm neonates recruited from Victoria Hospital, London, Ontario (June 2018–November 2019). A total of 24 premature neonates were recruited. The first cohort of 18 unstable premature neonates were imaged with 3D US in their current sides providing 15 right-sided and 16 left-sided 3D US images. The neonates in the second cohort of six relatively stable infants were imaged after positioning in each lateral decubitus position for 30 minutes, resulting in 40 3D US images obtained from 20 posture change sessions. The images were segmented and the ventricle volumes in each lateral posture were compared with determine whether the posture of the head influenced the volume of the upper and lower ventricle. Results For the first cohort who did not have their posture changed, the mean of the right and left ventricle volumes were 23.81 ± 15.51 and 21.61 ± 16.19 cm3, respectively, for the 15 images obtained in a right lateral posture and 13.96 ± 8.69 and 14.92 ± 8.77 cm3, respectively, for the 16 images obtained in the left lateral posture. Similarly, for the second cohort who had their posture changed, the mean of right and left ventricle volumes were 20.92 ± 17.3 and 32.74 ± 32.33 cm3, respectively, after 30 minutes in the right lateral posture, and 21.25 ± 18.4 and 32.65 ± 31.58 cm3, respectively, after 30 minutes in the left lateral posture. Our results failed to show a statistically significant difference in ventricular volumes dependence on posture. Conclusion Head positioned to any lateral side for 30 minutes does not have any effect on the lateral ventricular volumes of neonates. Key Points
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.