文献类型：期刊文献

英文题名：GyroLCE-Seg: Accuracy-Efficiency-Balanced Visual State-Space Segmentation of Gyrodactylus Hard Structures

作者：Peng, Xiaohong[1];Xiao, Zhuohan[1];Yu, Yinghuai[1];Chen, Jing[1];Lu, Ronghan[1];Jin, Xiao[2];Chen, Huapu[2]

机构：[1]Guangdong Ocean Univ, Coll Math & Comp Sci, Zhanjiang 524088, Peoples R China;[2]Guangdong Ocean Univ, Coll Fisheries, Zhanjiang 524088, Peoples R China

年份：2026

卷号：16

期号：16

外文期刊名：APPLIED SCIENCES-BASEL

收录：SCI-EXPANDED(收录号：WOS:001858647700001)、、WOS

基金：This research study was funded by Research and Application Demonstration of Key Technologies for the Digitalization of Marine Ranching, grant number 2024R1003; Guangdong Intelligence Platform of Prawn Modern Seed Industry, grant number 2022GCZX001; Research and Application Demonstration of Key Technologies for Intelligent Prawn Breeding, grant number 2023ZDZX4012; National Key R&D Program of China, grant number 2024YFC33080041; Natural Science Foundation of Guangdong Province, grant number 2026A1515011448; and Youth Science and Technology Innovation Talent of Guangdong TeZhi plan talent, grant number 2023TQ07A888.

语种：英文

外文关键词：Gyrodactylus; microscopic images; semantic segmentation; state-space model; deformable convolution

外文摘要：Fine-grained segmentation of Gyrodactylus opisthaptoral hard structures is challenging because of small targets, weak boundaries, local deformation, and debris interference. Using 175 microscopy images at a resolution of 2048 & times;2048 , we constructed a four-class pixel-level dataset and designed task-specific augmentation strategies. We propose GyroLCE-Seg, a framework designed to balance segmentation accuracy and computational efficiency by combining visual state-space modeling with LocalConv-based local-detail refinement, content-aware upsampling, deformable convolution, and efficient multi-scale fusion. Under image-level five-fold cross-validation and the four-class foreground macro protocol, GyroLCE-Seg achieved a MeanClassPrecision of 0.7336, a MeanClassRecall of 0.8746, a MeanIoU of 0.6582, and a MeanDice of 0.7886. At an input size of 1024 & times;1024 , it used 13.02 million parameters and 107.79 GFLOPs and achieved 34.0036 +/- 0.4242 FPS on the reported GPU platform. Among the evaluated models, GyroLCE-Seg achieved the highest foreground macro recall and outperformed the lighter YOLO-series baselines on all four foreground macro metrics while offering lower resource consumption and higher throughput than the U-Net series. These results position GyroLCE-Seg as a practical intermediate option for biological laboratories equipped with routine workstation or mid-range GPU resources.