相关实验视频

Updated: Jul 6, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

斯特恩:以注意力驱动的空间转换器网络用于检测胸部X射线图像中的异常

Joana Rocha¹, Sofia Cardoso Pereira¹, João Pedrosa¹

¹INESC TEC and Faculty of Engineering, University of Porto, R. Dr. Roberto Frias s/n, 4200-465, Porto, Portugal.

Artificial intelligence in medicine

|January 6, 2024

概括

这项研究引入了一个新的深度学习模型用于胸部X射线分析,通过专注于胸部区域和减少文物来提高准确性. 空间变压器网络 (STERN) 增强了异常检测,而不需要定位标签.

科学领域:

医学成像分析医学成像分析
医疗保健中的人工智能
深度学习用于放射学.

背景情况:

胸部X射线对于检测异常至关重要,但容易出现导致自动化分析偏差的工件.
目前用于胸部X射线解释的深度学习模型可能会受到图像工件的负面影响,导致错误的阳性.
需要精确识别感兴趣的胸部区域的自动化系统来提高诊断准确度.

研究的目的:

开发一个以注意力驱动的,在空间上不受监督的空间变压器网络 (STERN),用于在胸部X射线中自动选择胸部区域.
通过减轻人工物诱导的偏差来提高胸部X射线中二元分类 (正常与异常) 的准确性.
为STERN架构中更好地框架感兴趣的区域提出一个新的域特定损失函数.

主要方法:

一个端到端的架构,利用空间变压器网络 (STERN) 进行基于注意力的区域选择,采用翻译和非同位素缩放.
一个新的域特定损失函数,旨在指导STERN准确地框架感兴趣的胸部区域.
使用CheXpert数据集对胸部X射线图像 (正常/异常) 的二元分类,与基于YOLO的方法进行性能比较.

主要成果:

斯特恩模型在区分异常的额头胸部X射线中获得了85.67%的平均AUC,比基线分类器提高了2.55%.
斯特恩显示了与YOLO剪切图像相似的性能,但计算成本降低,不需要本地化标签.
与基线相比,STERN方法使用的培训参数不到2/3的培训参数,并增加了最小的推理时间 (每批<2 ms).

结论:

拟议的STERN有效地识别并专注于胸部X射线中感兴趣的胸部区域,减少文物偏差并提高分类准确性.
在深度学习管道中,STERN提供了一个计算效率高,标签效率高的替代传统物体检测方法,用于预处理胸部X射线图像.
这种以注意力驱动的空间变压器网络为自动胸部X射线解释提供了有希望的进步,提高了临床环境中的诊断可靠性.

关键词:

注意模块的注意力模块.二元分类二元分类二元分类.深度学习是一种深度学习.对象检测检测对象检测对象检测病理学病理学病理学胸部胸部胸部胸部

更多相关视频

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

相关概念视频

Radiological Investigation I: X-ray and CT

Radiological Investigation I: X-ray and CT

Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...