在使用Grad-CAM的骨扫描中诊断骨转移时,CNN和变压器模型的比较
Sehyun Pak1, Hye Joo Son2, Dongwoo Kim3
1Department of Medicine, Hallym University College of Medicine, Chuncheon, Gangwon, Republic of Korea.
Clinical nuclear medicine
|April 16, 2025
概括
与其他深度学习模型相比,ConvNeXt模型在骨扫描上检测骨转移的性能优越. 这种先进的卷积神经网络 (CNN) 显示了在瘤学中改善医学图像分析的前景.
科学领域:
- 医疗成像医学成像
- 在瘤学中使用人工智能
- 深度学习用于检测骨转移.
背景情况:
- 卷积神经网络 (CNN) 用于在骨扫描上检测骨转移.
- 在这个应用程序中,像ConvNeXt和变压器架构这样的新型号的性能还没有很好地确立.
研究的目的:
- 评估各种深度学习模型的诊断性能,包括ConvNeXt和变压器模型,用于检测骨转移.
- 将这些模型的有效性与已建立的CNN进行比较.
主要方法:
- 对2个机构骨扫描数据集的回顾性分析 (n=4626培训/验证,n=1428测试).
- 评估ResNet18,数据效率图像转换器 (DeiT),视觉转换器 (ViT大16),Swin转换器 (Swin基础) 和ConvNeXt大型模型.
- 用于模型可视化的梯度加权类激活映射 (Grad-CAM).
主要成果:
- ConvNeXt Large实现了最高的性能 (验证:0.969,测试:0.885),超过了ResNet的表现 (验证:0.892,测试:0.725).
- 斯文基还表现出强的表现 (验证:0.965,测试:0.840),明显优于ResNet.
- 所有模型在检测多元转移方面都表现更好,而不是寡头转移. ConvNeXt专注于局部病变,Swin Base专注于全球地区.
结论:
- 与传统的CNN和变压器模型相比,ConvNeXt在骨头扫描上检测骨转移的诊断性能优越.
- ConvNeXt模型显示了在癌症诊断中增强医学图像分析的巨大潜力,特别是在多转移病例中.
更多相关视频
12:23Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound
Published on: August 14, 2012
14.2K
04:23A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
1.7K
相关概念视频
01:14Imaging Studies I: CT and MRI
103
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
103
01:10Computed Tomography
4.1K
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...
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...
4.1K