Computer-aided diagnosis system for breast ultrasound images using deep learning

卷积神经网络 人工智能 计算机科学 乳腺超声检查 计算机辅助诊断 深度学习 双雷达 计算机辅助设计 恶性肿瘤 超声波 试验装置 乳腺摄影术 模式识别(心理学) 放射科 人工神经网络 乳房成像 医学 乳腺癌 病理 内科学 癌症 工程类 工程制图
作者
H. Tanaka,Shih Wei Chiu,Takanori Watanabe,Setsuko Kaoku,Takuhiro Yamaguchi
出处
期刊:Physics in Medicine and Biology [IOP Publishing]
卷期号:64 (23): 235013-235013 被引量:78
标识
DOI:10.1088/1361-6560/ab5093
摘要

The purpose of this study was to develop a computer-aided diagnosis (CAD) system for the classification of malignant and benign masses in the breast using ultrasonography based on a convolutional neural network (CNN), a state-of-the-art deep learning technique. We explored the regions for the correct classification by generating a heat map that presented the important regions used by the CNN for human malignancy/benign classification. Clinical data was obtained from a large-scale clinical trial previously conducted by the Japan Association of Breast and Thyroid Sonology. Images of 1536 breast masses (897 malignant and 639 benign) confirmed by pathological examinations were collected, with each breast mass captured from various angles using an ultrasound (US) imaging probe. We constructed an ensemble network by combining two CNN models (VGG19 and ResNet152) fine-tuned on balanced training data with augmentation and used the mass-level classification method to enable the CNN to classify a given mass using all views. For an independent test set consisting of 154 masses (77 malignant and 77 benign), our network showed outstanding classification performance with a sensitivity of 90.9% (95% confidence interval 84.5–97.3), a specificity of 87.0% (79.5–94.5), and area under the curve (AUC) of 0.951 (0.916–0.987) compared to that of the two CNN models. In addition, our study indicated that the breast masses themselves were not detected by the CNN as important regions for correct mass classification. Collectively, this CNN-based CAD system is expected to assist doctors by improving the diagnosis of breast cancer in clinical practice.
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
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
科研通AI5应助冷酸灵采纳,获得30
刚刚
科研通AI5应助冷酸灵采纳,获得10
刚刚
科研通AI5应助冷酸灵采纳,获得10
刚刚
科研通AI5应助冷酸灵采纳,获得10
刚刚
科研通AI5应助冷酸灵采纳,获得10
刚刚
科研通AI2S应助冷酸灵采纳,获得10
刚刚
科研通AI5应助冷酸灵采纳,获得10
刚刚
科研通AI5应助冷酸灵采纳,获得10
1秒前
科研通AI5应助冷酸灵采纳,获得10
1秒前
FashionBoy应助冷酸灵采纳,获得10
1秒前
1秒前
1秒前
困于昭昭完成签到,获得积分10
2秒前
科研通AI5应助任大帅采纳,获得10
2秒前
呼取尽余杯完成签到,获得积分10
2秒前
2秒前
Kk发布了新的文献求助10
2秒前
善良身影发布了新的文献求助10
3秒前
3秒前
4秒前
nyota发布了新的文献求助10
4秒前
明理碧完成签到 ,获得积分10
4秒前
浮光完成签到,获得积分10
4秒前
5秒前
小犁牛完成签到 ,获得积分10
6秒前
Desmond完成签到,获得积分10
6秒前
建新发布了新的文献求助10
7秒前
情怀应助乐君采纳,获得10
8秒前
YP_024发布了新的文献求助30
9秒前
10秒前
酷波er应助偶像肄业生采纳,获得10
10秒前
隐形曼青应助guard采纳,获得50
10秒前
桐桐应助优雅的母鸡采纳,获得20
10秒前
10秒前
不想改格式了完成签到,获得积分10
11秒前
12秒前
搜集达人应助科研通管家采纳,获得10
12秒前
maox1aoxin应助科研通管家采纳,获得30
12秒前
科研通AI5应助科研通管家采纳,获得10
12秒前
英姑应助科研通管家采纳,获得20
12秒前
高分求助中
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Mechanistic Modeling of Gas-Liquid Two-Phase Flow in Pipes 2500
Structural Load Modelling and Combination for Performance and Safety Evaluation 800
Conference Record, IAS Annual Meeting 1977 610
Interest Rate Modeling. Volume 3: Products and Risk Management 600
Interest Rate Modeling. Volume 2: Term Structure Models 600
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3555076
求助须知:如何正确求助?哪些是违规求助? 3130818
关于积分的说明 9388790
捐赠科研通 2830291
什么是DOI,文献DOI怎么找? 1555914
邀请新用户注册赠送积分活动 726331
科研通“疑难数据库(出版商)”最低求助积分说明 715716