Key points are not available for this paper at this time.
In many scenarios, especially biomedical applications, the correct delineation of complex fine-scaled structures such as neurons, tissues, and vessels is critical for downstream analysis. Despite the strong predictive power of deep learning methods, they do not provide a satisfactory representation of these structures, thus creating significant barriers in scalable annotation and downstream analysis. In this dissertation, we tackle such challenges by proposing novel representations of these topological structures in a deep learning framework. We leverage the mathematical tools from topological data analysis, i.e., persistent homology and discrete Morse theory, to develop principled methods for better segmentation and uncertainty estimation, which will become powerful tools for scalable annotation.
Building similarity graph...
Analyzing shared references across papers
Loading...
Xiaoling Hu (Fri,) studied this question.
synapsesocial.com/papers/68e72ce0b6db6435876a69e4 — DOI: https://doi.org/10.48550/arxiv.2403.15361
Xiaoling Hu
Hong Kong Polytechnic University
Building similarity graph...
Analyzing shared references across papers
Loading...