An official website of the United States government
Segmentation of curvilinear structures such as vasculature and road networks is challenging due to relatively weak signals and complex geometry/topology. To facilitate and accelerate large scale annotation, one has to adopt semi-automatic approaches such as proofreading by experts. In this work, we focus on uncertainty estimation for such tasks, so that highly uncertain, and thus error-prone structures can be identified for human annotators to verify. Unlike most existing works, which provide pixel-wise uncertainty maps, we stipulate it is crucial to estimate uncertainty in the units of topological structures, eg, small pieces of connections and branches. To achieve this, we leverage tools from topological data analysis, specifically discrete Morse theory (DMT), to first capture the structures, and then reason about their uncertainties. To model the uncertainty, we (1) propose a joint prediction model that estimates the uncertainty of a structure while taking the neighboring structures into consideration (inter-structural uncertainty); (2) propose a novel Probabilistic DMT to model the inherent uncertainty within each structure (intra-structural uncertainty) by sampling its representations via a perturb-and-walk scheme. On various 2D and 3D datasets, our method produces better structure-wise uncertainty maps compared to existing works.
more »
« less
This content will become publicly available on May 27, 2025
Topological Analysis of Mouse Brain Vasculature via 3D Light-sheet Microscopy Images
Vascular networks play a crucial role in understanding brain functionalities. Brain integrity and function, neuronal activity and plasticity, which are crucial for learning, are actively modulated by their local environments, specifically vascular networks. With recent developments in high-resolution 3D light-sheet microscopy imaging together with tissue processing techniques, it becomes feasible to obtain and examine large-scale brain vasculature in mice. To establish a structural foundation for functional study, however, we need advanced image analysis and structural modeling methods. Existing works use geometric features such as thickness, tortuosity, etc. However, geometric features cannot fully capture structural characteristics such as the richness of branches, connectivity, etc. In this paper, we study the morphology of brain vasculature through a topological lens. We extract topological features based on the theory of topological data analysis. Comparing of these robust and multi-scale topological structural features across different brain anatomical structures and between normal and obese populations sheds light on their promising future in studying neurological diseases.
more »
« less
- Award ID(s):
- 2144901
- PAR ID:
- 10537177
- Publisher / Repository:
- IEEE International Symposium on Biomedical Imaging (ISBI)
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Fliesler, S (Ed.)Abnormal vasculature in the retina, specifically tortuous vessels and capillary degeneration, is common in many of the most prevalent retinal degenerative diseases, currently affecting millions of people across the world. However, the formation and development of abnormal vasculature in the context of retinal degenerative diseases are still poorly understood. The FVB/N (rd1) and rd10 mice are well-studied animal models of retinal degenerative diseases, but how photoreceptor degeneration leads to vascular abnormality in the diseases remains to be elucidated. Here, we used advancements in confocal microscopy, immunohistochemistry, and image analysis software to systematically characterize the pathological vasculature in the FVB/N (rd1) and rd10 mice, known as a chronic, rapid and slower retinal degenerative model, respectively. We demonstrated that there was plexusspecific vascular degeneration in the retinal trilaminar vascular network paralleled to photoreceptor degeneration in the diseased retinas. We also quantitatively analyzed the vascular structural architecture in the wild-type and diseased retinas to provide valuable information on vascular remodeling in retinal degenerative diseasemore » « less
-
Abstract From microscaled capillaries to millimeter‐sized vessels, human vasculature spans multiple scales and cell types. The convergence of bioengineering, materials science, and stem cell biology has enabled tissue engineers to recreate the structure and function of different hierarchical levels of the vascular tree. Engineering large‐scale vessels aims to replace damaged arteries, arterioles, and venules and their routine application in the clinic may become a reality in the near future. Strategies to engineer meso‐ and microvasculature are extensively explored to generate models for studying vascular biology, drug transport, and disease progression as well as for vascularizing engineered tissues for regenerative medicine. However, bioengineering tissues for transplantation has failed to result in clinical translation due to the lack of proper integrated vasculature for effective oxygen and nutrient delivery. The development of strategies to generate multiscale vascular networks and their direct anastomosis to host vasculature would greatly benefit this formidable goal. In this review, design considerations and technologies for engineering millimeter‐, meso‐, and microscale vessels are discussed. Examples of recent state‐of‐the‐art strategies to engineer multiscale vasculature are also provided. Finally, key challenges limiting the translation of vascularized tissues are identified and perspectives on future directions for exploration are presented.more » « less
-
Wang, Yalin (Ed.)We introduce an innovative, data-driven topological data analysis (TDA) technique for estimating the state spaces of dynamically changing functional human brain networks at rest. Our method utilizes the Wasserstein distance to measure topological differences, enabling the clustering of brain networks into distinct topological states. This technique outperforms the commonly used k-means clustering in identifying brain network state spaces by effectively incorporating the temporal dynamics of the data without the need for explicit model specification. We further investigate the genetic underpinnings of these topological features using a twin study design, examining the heritability of such state changes. Our findings suggest that the topology of brain networks, particularly in their dynamic state changes, may hold significant hidden genetic information.more » « less
-
Abstract Childhood maltreatment may adversely affect brain development and consequently influence behavioral, emotional, and psychological patterns during adulthood. In this study, we propose an analytical pipeline for modeling the altered topological structure of brain white matter in maltreated and typically developing children. We perform topological data analysis (TDA) to assess the alteration in the global topology of the brain white matter structural covariance network among children. We use persistent homology, an algebraic technique in TDA, to analyze topological features in the brain covariance networks constructed from structural magnetic resonance imaging and diffusion tensor imaging. We develop a novel framework for statistical inference based on the Wasserstein distance to assess the significance of the observed topological differences. Using these methods in comparing maltreated children with a typically developing control group, we find that maltreatment may increase homogeneity in white matter structures and thus induce higher correlations in the structural covariance; this is reflected in the topological profile. Our findings strongly suggest that TDA can be a valuable framework to model altered topological structures of the brain. The MATLAB codes and processed data used in this study can be found at https://github.com/laplcebeltrami/maltreated.more » « less
