FDMNet: A Multi-Task Network for Joint Detection and Segmentation of Three Fish Diseases [0.03%]
基于多任务学习的联合检测与分割鱼类三种疾病的网络模型
Zhuofu Liu,Zigan Yan,Gaohan Li
Zhuofu Liu
Fish diseases are one of the primary causes of economic losses in aquaculture. Existing deep learning models have progressed in fish disease detection and lesion segmentation. However, many models still have limitations, such as detecting o...
A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis [0.03%]
纹理分析中基于视觉Transformer的特征提取方法综述
Leonardo Scabini,Andre Sacilotti,Kallil M Zielinski et al.
Leonardo Scabini et al.
Texture, a significant visual attribute in images, plays an important role in many pattern recognition tasks. While Convolutional Neural Networks (CNNs) have been among the most effective methods for texture analysis, alternative architectu...
AI-Generated Patient-Friendly MRI Fistula Summaries: A Pilot Randomised Study [0.03%]
基于人工智能的患者友好型MRI异常总结法：一项随机对照试点研究
Easan Anand,Itai Ghersin,Gita Lingam et al.
Easan Anand et al.
Perianal fistulising Crohn's disease (pfCD) affects 1 in 5 Crohn's patients and requires frequent MRI monitoring. Standard radiology reports are written for clinicians using technical language often inaccessible to patients, which can cause...
AnomNet: A Dual-Stage Centroid Optimization Framework for Unsupervised Anomaly Detection [0.03%]
无监督异常检测的双阶段中心优化框架
Yuan Gao,Yu Wang,Xiaoguang Tu et al.
Yuan Gao et al.
Anomaly detection plays a vital role in ensuring product quality and operational safety across various industrial applications, from manufacturing to infrastructure monitoring. However, current methods often struggle with challenges such as...
Compton Camera X-Ray Fluorescence Imaging Design and Image Reconstruction Algorithm Optimization [0.03%]
康普顿相机X射线荧光成像设计及图像重建算法优化
Shunmei Lu,Kexin Peng,Peng Feng et al.
Shunmei Lu et al.
Traditional X-ray fluorescence computed tomography (XFCT) suffers from issues such as low photon collection efficiency, slow data acquisition, severe noise interference, and poor imaging quality due to the limitations of mechanical collimat...
Hybrid-Recursive-Refinement Network for Camouflaged Object Detection [0.03%]
用于伪装目标检测的混合递归 refinement 网络
Hailong Chen,Xinyi Wang,Haipeng Jin
Hailong Chen
Camouflaged object detection (COD) seeks to precisely detect and delineate objects that are concealed within complex and ambiguous backgrounds. However, due to subtle texture variations and semantic ambiguity, it remains a highly challengin...
From Brain Lobes to Neurons: Navigating the Brain Using Advanced 3D Modeling and Visualization Tools [0.03%]
从大脑叶到神经元：利用先进的三维建模和可视化工具探索大脑
Mohamed Rowaizak,Ahmad Farhat,Reem Khalil
Mohamed Rowaizak
Neuroscience education must convey 3D structure with clarity and accuracy. Traditional 2D renderings are limited as they lose depth information and hinder spatial understanding. High-resolution resources now exist, yet many are difficult to...
Longitudinal Ultrasound Monitoring of Peripheral Muscle Loss in Neurocritical Patients [0.03%]
神经重症患者外周肌肉消耗的纵向超声监测
Talita Santos de Arruda,Rayssa Bruna Holanda Lima,Karla Luciana Magnani Seki et al.
Talita Santos de Arruda et al.
Ultrasound has become an important tool that offers clinical and practical benefits in the intensive care unit (ICU). Its real-time imaging provides immediate information to support prognostic evaluation and clinical decision-making. This s...
Shoji Tominaga,Motonori Doi,Hideaki Sakai
Shoji Tominaga
We study the relationship between the physical surface roughness of the glossy surfaces of dielectric objects and the roughness parameter in image rendering. The former refers to a measure of the microscopic surface structure of a real obje...
Test-Time Augmentation for Cross-Domain Leukocyte Classification via OOD Filtering and Self-Ensembling [0.03%]
基于=out-of-distribution过滤和自我集成的测试时间增强跨域白细胞分类方法
Lorenzo Putzu,Andrea Loddo,Cecilia Di Ruberto
Lorenzo Putzu
Domain shift poses a major challenge in many Machine Learning applications due to variations in data acquisition protocols, particularly in the medical field. Test-time augmentation (TTA) can solve the domain shift issue and improve robustn...