相关实验视频

Updated: Jan 20, 2026

A Semantic Priming Event-related Potential ERP Task to Study Lexico-semantic and Visuo-semantic Processing in Autism Spectrum Disorder

A Semantic Priming Event-related Potential ERP Task to Study Lexico-semantic and Visuo-semantic Processing in Autism Spectrum Disorder

Published on: April 12, 2018

MegaSeg: 针对兆像素图像进行可扩展的语义细分

Solomon Kefas Kaura¹, Jialun Wu², Zeyu Gao³

¹School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, China; Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an, 710049, China.

Medical image analysis

|January 18, 2026

概括

MegaSeg使用新的流媒体U-Net架构高效地细分大型组织病理图像. 这个框架保留了关键的本地细节和全球上下文,克服了用于兆像素图像分析的GPU内存限制.

科学领域:

医疗图像分析医学图像分析
计算病理学计算病理学
对于组织病理学的深度学习.

背景情况:

兆像素图像细分对于高分辨率的组织病理学分析至关重要.
当前的GPU内存限制需要补丁和降低样本,从而损害了上下文信息.
对大格式图像的高效细分仍然是一个重大挑战.

研究的目的:

介绍MegaSeg,这是一个端到端的框架,用于兆像素基因病理图像的语义细分.
在不牺牲细节或上下文的情况下,能够有效处理大型图像 (例如,8192×8192像素).
在高分辨率图像分析中减少内存使用.

主要方法:

开发了MegaSeg,这是一个端到端的框架,利用流动卷积网络在U形架构中.
在处理大型图像时,实施了分裂与征服策略.
在解码路径内提出了注意密集精制模块 (ADRM),以增强本地细节和上下文信息.

主要成果:

MegaSeg能够高效地对67MP图像进行语义细分,同时保留全球结构和本地细节.
在公共基因病理学数据集上表现出卓越的性能.
在CAMELYON16数据集上,在将输入大小从4MP扩大到67MP时,自由响应操作特征 (FROC) 评分从0.78到0.89显著改善.

结论:

MegaSeg有效地克服了用于兆像素图像分割的GPU内存限制.
该框架以高分辨率的基因病理学图像保存了基本的全球和本地上下文信息.
MegaSeg为大规模医疗图像分析提供了一个有前途的解决方案,增强了诊断能力.

关键词:

一个兆像素的图像.语义细分语义细分是指语义细分.流媒体的流媒体.这就是U-Net.

更多相关视频

Studying Language Processing: the N400 in Semantic Incongruity

Studying Language Processing: the N400 in Semantic Incongruity

Published on: April 30, 2023

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

相关概念视频

A Semantic Priming Event-related Potential (ERP) Task to Study Lexico-semantic and Visuo-semantic Processing in Autism Spectrum Disorder

A Semantic Priming Event-related Potential (ERP) Task to Study Lexico-semantic and Visuo-semantic Processing in Autism Spectrum Disorder

This paper describes a semantic priming ERP task using within-modality pairs of pictures and words to investigate semantic processing in individuals with autism spectrum disorder...

Language: The N400 in Semantic Incongruity

Language: The N400 in Semantic Incongruity

Source: Laboratories of Sarah I. Gimbel and Jonas T. Kaplan— University of Southern California
Understanding language is one of the most complex cognitive tasks that humans are capable of. Given the incredible amount of possible choices when combining individual words to form meaning in sentences, it is crucial that the brain is able to identify when words form coherent combinations and when an anomaly appears that undermines meaning. Extensive research has shown that certain...

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

We present a protocol to explore the relative activation sequence of phonology and semantics in visual word recognition. The results show that consistent with interactive accounts, semantic and phonological representations may be processed interactively, and higher-level linguistic representations may affect early...

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

The goal of this manuscript is to study the hippocampus and hippocampal subfields using MRI. The manuscript describes a protocol for segmenting the hippocampus and five hippocampal substructures: cornu ammonis (CA) 1, CA2/CA3, CA4/dentate gyrus, strata radiatum/lacunosum/moleculare, and subiculum.

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

The intravital imaging method described here utilizes collagen second harmonic generation and endogenous fluorescence from the metabolic co-factor NAD(P)H to non-invasively segment an unlabeled tumor microenvironment into tumor, stromal, and vascular compartments for in-depth analysis of 4D intravital...

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

This protocol describes the process of applying seven different automated segmentation tools to structural T1-weighted MRI scans to delineate grey matter regions that can be used for the quantification of grey matter volume.