Background And Objective: Swept-source optical coherence tomography angiography (SS-OCTA) and different boundary-specific segmentation strategies were used to distinguish type 1 macular neovascularization (MNV) from type 2 MNV in eyes with exudative age-related macular degeneration (AMD).

Patients And Methods: Eyes with exudative AMD were enrolled in a prospective study. Segmentation strategies included a slab from the outer retina (OR) to the choriocapillaris (CC) for the entire MNV, a slab from the retinal pigment epithelium (RPE) to the CC for the type 1 MNV, and a slab from the OR to the RPE for the type 2 MNV.

Results: In 13 eyes, SS-OCTA B-scans and en face images using different segmentation strategies were able to identify type 1 and type 2 components of the MNV.

Conclusion: In eyes with exudative AMD, SS-OCTA imaging and commercially available boundary-specific segmentation strategies were used to distinguish between type 1 and type 2 MNV. [Ophthalmic Surg Lasers Imaging Retina. 2018;49:878-886.].

Download full-text PDF

Source
http://dx.doi.org/10.3928/23258160-20181101-09DOI Listing

Publication Analysis

Top Keywords

segmentation strategies
16
type type
12
type mnv
12
eyes exudative
12
type
10
type macular
8
macular neovascularization
8
boundary-specific segmentation
8
strategies distinguish
8
distinguish type
8

Similar Publications

Background: The presence of significant tortuosity in access routes to aneurysms can interfere with catheter guidance and manipulation and significantly impact treatment strategies.

Observations: In this report, the authors combined intentional staged aneurysm embolization with the construction of a new direct access route, which they call a "highway bypass," for a symptomatic posterior circulation cerebral aneurysm that was difficult to access with a catheter. Notably, the highway bypass is used for catheter passage, and technical tips should be considered.

View Article and Find Full Text PDF

Background: External ventricular drains (EVDs) provide an invaluable diagnostic method for accessing cerebrospinal fluid and therapeutically treating elevated intracranial pressure. Although complications including hemorrhage and infection have been well documented, the formation of iatrogenic pseudoaneurysms following EVD placement has rarely been reported. The authors present a case of this exceedingly rare complication of iatrogenic pseudoaneurysm formation following EVD placement.

View Article and Find Full Text PDF

Source-free domain adaptation (SFDA) has become crucial in medical image analysis, enabling the adaptation of source models across diverse datasets without labeled target domain images. Self-training, a popular SFDA approach, iteratively refines self-generated pseudo-labels using unlabeled target domain data to adapt a pre-trained model from the source domain. However, it often faces model instability due to incorrect pseudo-label accumulation and foreground-background class imbalance.

View Article and Find Full Text PDF

Resource Segmentation: A New Dimension of the Segmentation Hypothesis in Drought Adaptive Strategies and Its Links to Tree Growth Performance.

Plant Cell Environ

January 2025

Qianyanzhou Ecological Research Station, Key Laboratory of Ecosystem Network Observation and Modeling, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China.

The segmentation hypothesis, a framework for understanding plant drought adaptive strategy, has long been based on hydraulic resistance and vulnerability. Storage of water and carbohydrate resources is another critical function and shapes plant drought adaption and fitness together with hydraulic efficiency and vulnerability. However, patterns and implications of the interdependency of stored water and carbohydrate resources in the context of the segmentation hypothesis are poorly understood.

View Article and Find Full Text PDF

This study aimed to develop and evaluate an efficient method to automatically segment T1- and T2-weighted brain magnetic resonance imaging (MRI) images. We specifically compared the segmentation performance of individual convolutional neural network (CNN) models against an ensemble approach to advance the accuracy of MRI-guided radiotherapy (RT) planning..

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!