Classification of rotator cuff tears in ultrasound images using deep learning models

人工智能 卷积神经网络 深度学习 超声波 超参数 计算机科学 模式识别(心理学) 学习迁移 肩袖 可视化 磁共振成像 机器学习 医学 放射科
作者
Thao Thi Ho,Geun-Tae Kim,Taewoo Kim,Sanghun Choi,Eun‐Kee Park
出处
期刊:Medical & Biological Engineering & Computing [Springer Science+Business Media]
卷期号:60 (5): 1269-1278 被引量:34
标识
DOI:10.1007/s11517-022-02502-6
摘要

Rotator cuff tears (RCTs) are one of the most common shoulder injuries, which are typically diagnosed using relatively expensive and time-consuming diagnostic imaging tests such as magnetic resonance imaging or computed tomography. Deep learning algorithms are increasingly used to analyze medical images, but they have not been used to identify RCTs with ultrasound images. The aim of this study is to develop an approach to automatically classify RCTs and provide visualization of tear location using ultrasound images and convolutional neural networks (CNNs). The proposed method was developed using transfer learning and fine-tuning with five pre-trained deep models (VGG19, InceptionV3, Xception, ResNet50, and DenseNet121). The Bayesian optimization method was also used to optimize hyperparameters of the CNN models. A total of 194 ultrasound images from Kosin University Gospel Hospital were used to train and test the CNN models by five-fold cross-validation. Among the five models, DenseNet121 demonstrated the best classification performance with 88.2% accuracy, 93.8% sensitivity, 83.6% specificity, and AUC score of 0.832. A gradient-weighted class activation mapping (Grad-CAM) highlighted the sensitive features in the learning process on ultrasound images. The proposed approach demonstrates the feasibility of using deep learning and ultrasound images to assist RCTs' diagnosis.
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
ding应助熠熠生辉采纳,获得10
1秒前
1秒前
怡然的怀莲完成签到 ,获得积分20
2秒前
鸣笛应助和谐的阁采纳,获得70
2秒前
小马甲应助隐形的念芹采纳,获得10
3秒前
3秒前
5秒前
善学以致用应助努力采纳,获得10
6秒前
情怀应助111采纳,获得10
6秒前
NexusExplorer应助大力的迎松采纳,获得10
6秒前
瓜瓜完成签到,获得积分10
6秒前
yuchen发布了新的文献求助10
7秒前
传奇3应助tt采纳,获得10
8秒前
华仔应助欧气青年采纳,获得10
9秒前
10秒前
10秒前
英俊的铭应助萄哥布鸽采纳,获得10
10秒前
斯文败类应助freyr采纳,获得10
11秒前
汤泽琪发布了新的文献求助10
12秒前
12秒前
小二郎应助yuchen采纳,获得10
13秒前
zhao发布了新的文献求助10
15秒前
16秒前
伟川周完成签到 ,获得积分10
17秒前
大力的迎松完成签到,获得积分20
17秒前
yujian完成签到,获得积分10
17秒前
18秒前
爆米花应助Mark采纳,获得10
19秒前
情怀应助maozhehai29999采纳,获得10
20秒前
21秒前
yujian发布了新的文献求助10
21秒前
21秒前
寒霜扬名完成签到,获得积分10
23秒前
其亚关注了科研通微信公众号
24秒前
24秒前
25秒前
小马甲应助wang采纳,获得10
25秒前
27秒前
28秒前
乐乐应助lucky采纳,获得10
28秒前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Social Research Methods (4th Edition) by Maggie Walter (2019) 1030
A new approach to the extrapolation of accelerated life test data 1000
Indomethacinのヒトにおける経皮吸収 400
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 370
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3993793
求助须知:如何正确求助?哪些是违规求助? 3534447
关于积分的说明 11265507
捐赠科研通 3274273
什么是DOI,文献DOI怎么找? 1806326
邀请新用户注册赠送积分活动 883118
科研通“疑难数据库(出版商)”最低求助积分说明 809712