Collaborative Multi-Metadata Fusion to Improve the Classification of Lumbar Disc Herniation

计算机科学 人工智能 特征(语言学) 模式识别(心理学) 卷积神经网络 特征选择 上下文图像分类 计算机辅助诊断 最小边界框 特征提取 Sørensen–骰子系数 分割 图像分割 计算机视觉 图像(数学) 哲学 语言学
作者
Shuyi Lu,Jinhua Liu,Xiaojie Wang,Yuanfeng Zhou
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:42 (12): 3590-3601 被引量:1
标识
DOI:10.1109/tmi.2023.3294248
摘要

Computed tomography (CT) images are the most commonly used radiographic imaging modality for detecting and diagnosing lumbar diseases. Despite many outstanding advances, computer-aided diagnosis (CAD) of lumbar disc disease remains challenging due to the complexity of pathological abnormalities and poor discrimination between different lesions. Therefore, we propose a Collaborative Multi-Metadata Fusion classification network (CMMF-Net) to address these challenges. The network consists of a feature selection model and a classification model. We propose a novel Multi-scale Feature Fusion (MFF) module that can improve the edge learning ability of the network region of interest (ROI) by fusing features of different scales and dimensions. We also propose a new loss function to improve the convergence of the network to the internal and external edges of the intervertebral disc. Subsequently, we use the ROI bounding box from the feature selection model to crop the original image and calculate the distance features matrix. We then concatenate the cropped CT images, multiscale fusion features, and distance feature matrices and input them into the classification network. Next, the model outputs the classification results and the class activation map (CAM). Finally, the CAM of the original image size is returned to the feature selection network during the upsampling process to achieve collaborative model training. Extensive experiments demonstrate the effectiveness of our method. The model achieved 91.32% accuracy in the lumbar spine disease classification task. In the labelled lumbar disc segmentation task, the Dice coefficient reaches 94.39%. The classification accuracy in the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) reaches 91.82%.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
无辜访彤发布了新的文献求助10
刚刚
刚刚
英俊的铭应助miemie阳采纳,获得10
刚刚
一叶知秋完成签到,获得积分10
2秒前
胡杨完成签到,获得积分10
2秒前
思源应助刘宇采纳,获得10
2秒前
bind发布了新的文献求助10
2秒前
2秒前
zyj完成签到,获得积分10
3秒前
贺兰鸵鸟完成签到,获得积分10
3秒前
zwenng完成签到,获得积分10
3秒前
4秒前
4秒前
XHH1994发布了新的文献求助10
4秒前
KB完成签到,获得积分10
5秒前
SYLH应助典雅的静采纳,获得10
6秒前
yatou5651完成签到,获得积分10
6秒前
6秒前
JOUJOU完成签到,获得积分10
6秒前
Hiker完成签到,获得积分10
6秒前
傲娇尔曼完成签到,获得积分10
7秒前
Zhuzhu完成签到 ,获得积分10
7秒前
咖飞完成签到,获得积分10
8秒前
8秒前
8秒前
8秒前
liushoujia完成签到,获得积分10
8秒前
抹茶肥肠完成签到,获得积分10
9秒前
cwqcqw完成签到,获得积分10
9秒前
9秒前
就好完成签到 ,获得积分10
9秒前
王陈龙发布了新的文献求助10
10秒前
南宫书瑶完成签到,获得积分10
10秒前
Orange应助狂野世立采纳,获得10
11秒前
joybee完成签到,获得积分0
11秒前
小二郎应助ZJU采纳,获得10
11秒前
Qyyy发布了新的文献求助10
11秒前
lyp7028完成签到,获得积分10
11秒前
铅笔刀完成签到,获得积分10
11秒前
AZE应助Hossiu采纳,获得10
11秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968719
求助须知:如何正确求助?哪些是违规求助? 3513608
关于积分的说明 11168681
捐赠科研通 3248960
什么是DOI,文献DOI怎么找? 1794573
邀请新用户注册赠送积分活动 875194
科研通“疑难数据库(出版商)”最低求助积分说明 804716