Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nam, Siwoo | - |
dc.contributor.author | Jeong, Jaehoon | - |
dc.contributor.author | Luna, Acevedo Miguel Andres | - |
dc.contributor.author | Chikontwe, Philip | - |
dc.contributor.author | Park, Sang Hyun | - |
dc.date.accessioned | 2024-02-05T01:40:14Z | - |
dc.date.available | 2024-02-05T01:40:14Z | - |
dc.date.created | 2023-11-08 | - |
dc.date.issued | 2023-10-09 | - |
dc.identifier.isbn | 9783031439070 | - |
dc.identifier.issn | 1611-3349 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/47784 | - |
dc.description.abstract | Recently, weakly supervised nuclei segmentation methods using only points are gaining attention, as they can ease the tedious labeling process. However, most methods often fail to separate adjacent nuclei and are particularly sensitive to point annotations that deviate from the center of nuclei, resulting in lower accuracy. In this study, we propose a novel weakly supervised method to effectively distinguish adjacent nuclei and maintain robustness regardless of point label deviation. We detect and segment nuclei by combining a binary segmentation module, an offset regression module, and a center detection module to determine foreground pixels, delineate boundaries and identify instances. In training, we first generate pseudo binary masks using geodesic distance-based Voronoi diagrams and k-means clustering. Next, segmentation predictions are used to repeatedly generate pseudo offset maps that indicate the most likely nuclei center. Finally, an Expectation Maximization (EM) based process iteratively refines initial point labels based on the offset map predictions to fine-tune our framework. Experimental results show that our model consistently outperforms state-of-the-art methods on public datasets regardless of the point annotation accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. | - |
dc.language | English | - |
dc.publisher | The Medical Image Computing and Computer Assisted Intervention Society | - |
dc.title | PROnet: Point Refinement Using Shape-Guided Offset Map for Nuclei Instance Segmentation | - |
dc.type | Conference Paper | - |
dc.identifier.doi | 10.1007/978-3-031-43907-0_51 | - |
dc.identifier.scopusid | 2-s2.0-85174589789 | - |
dc.identifier.bibliographicCitation | International Conference on Medical Image Computing and Computer Assisted Intervention, pp.528 - 538 | - |
dc.identifier.url | https://conferences.miccai.org/2023/files/downloads/MICCAI2023-Main-Conference-Oral-and-Poster-Program.pdf | - |
dc.citation.conferencePlace | CN | - |
dc.citation.conferencePlace | Vancouver | - |
dc.citation.endPage | 538 | - |
dc.citation.startPage | 528 | - |
dc.citation.title | International Conference on Medical Image Computing and Computer Assisted Intervention | - |
There are no files associated with this item.