Cross-Shaped Heat Tensor Network for Morphometric Analysis Using Zebrafish Larvae Feature Keypoints
文献类型: 外文期刊
作者: Xin Chai;Tan Sun;Zhaoxin Li;Yanqi Zhang;Qixin Sun;Ning Zhang;Jing Qiu;Xiujuan Chai
作者机构:
关键词: deep feature learning;digital phenotype;keypoints localization;non-destructive examination;zebrafish
期刊名称: Sensors
ISSN: 1424-8220
年卷期: 2025 年 25 卷 1 期
页码:
收录情况: SCIE(2025版) ; ; EI(2025版)
摘要: Deep learning-based morphometric analysis of zebrafish is widely utilized for non-destructively identifying abnormalities and diagnosing diseases. However, obtaining discriminative and continuous organ category decision boundaries poses a significant challenge by directly observing zebrafish larvae from the outside. To address this issue, this study simplifies the organ areas to polygons and focuses solely on the endpoint positioning. Specifically, we introduce a deep learning-based feature endpoint detection method for quantitatively determining zebrafish larvae’s essential phenotype and organ features. We propose the cross-shaped heat tensor network (CSHT-Net), a feature point detection framework consisting of a novel keypoint training method named cross-shaped heat tensor and a feature extractor called combinatorial convolutional block. Our model alleviates the problem of the heatmap-based method that restricts attention to local regions around key points while enhancing the model’s ability to learn continuous, strip-like features. Moreover, we compiled a dataset of 4389 bright-field micrographs of zebrafish larvae at 120 h post-fertilization for the model training and algorithm evaluation of zebrafish phenotypic traits. The proposed framework achieves an average precision (AP) of 83.2% and an average recall (AR) of 85.8%, outperforming multiple widely adopted keypoint detection techniques. This approach enables robust phenotype extraction and reliable morphometric analysis for zebrafish larvae, fostering efficient hazard identification for chemicals and medical products.
分类号:
- 相关文献
作者其他论文 更多>>
-
Novel Applications of Optical Sensors and Machine Learning in Agricultural Monitoring—2nd Edition
作者:Haikuan Feng;Yanjun Yang;Ning Zhang;Chengquan Zhou;Jibo Yue
关键词:
-
Enhancing gougerotin production by screening endogenous promoters for the transporter gene gouM in Streptomyces albulus CK-15
作者:Binghua Liu;Qianying Zhou;Ruixin Qiao;Kunping Zhou;Ning Zhang;Beibei Ge
关键词:endogenous promoter;gougerotin;high-yield strain;Streptomyces albulus;transporter gene
-
AECA-FBMamba: A Framework with Adaptive Environment Channel Alignment and Mamba Bridging Semantics and Details
作者:Xin Chai;Wenrong Zhang;Zhaoxin Li;Ning Zhang;Xiujuan Chai
关键词:deep learning;Mamba;remote sensing;Transformer;weakly supervised learning
-
DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo
作者:Zhenlong Yuan;Jinguo Luo;Fei Shen;Zhaoxin Li;Cong Liu;Tianlu Mao;Zhaoqi Wang
关键词:
-
A Vegetable-Price Forecasting Method Based on Mixture of Experts
作者:Chenyun Zhao;Xiaodong Wang;Anping Zhao;Yunpeng Cui;Ting Wang;Juan Liu;Ying Hou;Mo Wang;Li Chen;Huan Li;Jinming Wu;Tan Sun
关键词:deep learning;large language models;mixture-of-experts;time-series forecasting;vegetable-price forecasting
-
Digital twin-driven system for efficient tomato harvesting in greenhouses
作者:Yining Lang;Yanqi Zhang;Tan Sun;Xiujuan Chai;Ning Zhang
关键词:Decision;Digital-twin;Greenhouse;Harvest;Reinforcement-learning;Tomato
-
Synergistic effects of combined lead and iprodione exposure on P53 signaling-mediated hepatotoxicity, enterotoxicity and transgenerational toxicity in zebrafish
作者:Ruike Wang;Ligang Deng;Yanhua Wang;Na Liu;Menglian Yang;Jing Qiu;Chen Chen
关键词:Combined exposure;Iprodione;Lead;Liver-gut axis;P53 signaling pathway;Transgenerational toxicity