Rethinking Information Loss in Medical Image Segmentation with Various-sized Targets

Zapisane w:
Opis bibliograficzny
Wydane w:arXiv.org (Mar 28, 2024), p. n/a
1. autor: Liu, Tianyi
Kolejni autorzy: Tan, Zhaorui, Huang, Kaizhu, Jiang, Haochuan
Wydane:
Cornell University Library, arXiv.org
Hasła przedmiotowe:
Dostęp online:Citation/Abstract
Full text outside of ProQuest
Etykiety: Dodaj etykietę
Nie ma etykietki, Dołącz pierwszą etykiete!

MARC

LEADER 00000nab a2200000uu 4500
001 3015048159
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3015048159 
045 0 |b d20240328 
100 1 |a Liu, Tianyi 
245 1 |a Rethinking Information Loss in Medical Image Segmentation with Various-sized Targets 
260 |b Cornell University Library, arXiv.org  |c Mar 28, 2024 
513 |a Working Paper 
520 3 |a Medical image segmentation presents the challenge of segmenting various-size targets, demanding the model to effectively capture both local and global information. Despite recent efforts using CNNs and ViTs to predict annotations of different scales, these approaches often struggle to effectively balance the detection of targets across varying sizes. Simply utilizing local information from CNNs and global relationships from ViTs without considering potential significant divergence in latent feature distributions may result in substantial information loss. To address this issue, in this paper, we will introduce a novel Stagger Network (SNet) and argues that a well-designed fusion structure can mitigate the divergence in latent feature distributions between CNNs and ViTs, thereby reducing information loss. Specifically, to emphasize both global dependencies and local focus, we design a Parallel Module to bridge the semantic gap. Meanwhile, we propose the Stagger Module, trying to fuse the selected features that are more semantically similar. An Information Recovery Module is further adopted to recover complementary information back to the network. As a key contribution, we theoretically analyze that the proposed parallel and stagger strategies would lead to less information loss, thus certifying the SNet's rationale. Experimental results clearly proved that the proposed SNet excels comparisons with recent SOTAs in segmenting on the Synapse dataset where targets are in various sizes. Besides, it also demonstrates superiority on the ACDC and the MoNuSeg datasets where targets are with more consistent dimensions. 
653 |a Datasets 
653 |a Modules 
653 |a Image segmentation 
653 |a Medical imaging 
653 |a Target detection 
700 1 |a Tan, Zhaorui 
700 1 |a Huang, Kaizhu 
700 1 |a Jiang, Haochuan 
773 0 |t arXiv.org  |g (Mar 28, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3015048159/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2403.19177