没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
摘 要
I
摘 要
对于癌症、心脏病等有着极高致死率的疾病,早期诊断通常情况下可以提高患者
的存活率,简化检测流程是极为重要的。在传统情况中,病患医疗数据往往需要专业
医师人工检测分析,但我国医患比例严重失调,大量的数据对于专业医师的水平和耐
心要求极为苛刻。在检测分析过程中还有可能因为测人员的状态、数据的不规则、随
机性和数据的复杂度等一系列外在因素,导致检测分析的质量参差不齐,这无论对于
患者还是专业医师来说都是灾难性的。于是,寻求一种可以自动寻找生物标记的方法
已然成为许多医护人员的诉求。
近年来,随着计算机软硬件的飞速发展,新的机器学习和深度学习算法在自然语
言识别和图像处理领域得到长足发展,成果瞩目。深度学习分支卷积神经网络凭借强
大的非线性表征能力,在许多领域拔得头筹。本文受到卷积神经网络在其它领域广泛
应用的启发,深度结合各生物医学信号自身的特点,重点针对生物医学信号处理分析
技术,提出高性能、强鲁棒性和高识别率的医学信号自动识别算法。本研究主要以心
电信号和乳腺癌病理学组织图像这两种医学信号作为研究对象进行深入研究,主要研
究内容如下:
1. 在基于改进的残差网络对心电信号识别任务中,首先从 MIT-BIH 的心律不齐数
据库中选取五种昀常见的心脏病数据,通过心电信号波形中的 R 峰定位波形,以 1×600
作为一个单位分割波形。接着将分割后的数据汇入第一个卷积层,利用堆叠的残差块
进行特征提取,昀后使用 Softmax 分类器进行多病例识别。实验中使用 K 折交叉验证
对 MIT-BIH 心律失常数据集进行训练、验证和测试,提出的模型在没有任何额外的人
工特征和数据增强进行辅助的情况下,获得了 97.20%的准确率、92.85%的敏感度、
98.29%的特异性、93.16%的精确度和 93.00%的 F1 分数。
2. 在乳腺癌病理学组织图像分类任务中,针对乳腺癌病理学组织图像的复杂特
征,传统网络无法充分表达其特征的问题。本文设计了一种深层的网络模型通过加深
网络深度以获得更深层的特征信息,解决因模型层数增加带来的网络退化问题。将传
统卷积替换为空洞卷积,不带来额外参数的同时提升感受视野。使用 Adam 优化器,
学习率随着训练的进行呈指数自衰减。实验以 BreaKHis 中数据作为数据集,研究设计
一套预处理框架,提升模型的兼容性。使用 K 折交叉验证进行评估,并且使用提前停
止算法避免过/欠拟合的发生。实验进行了数据集放大类别的独立实验,并且还将提出
的模型与现有的模型和文献进行横向对比。实验结果表明提出的模型对于乳腺癌病理
学组织图像的良恶性识别与乳腺癌病理学组织图像精细化多病例识别来说,高效、准
江苏科技大学工程硕士学位论文
II
确、可靠。
关键词 深度学习;神经网络;残差网络;医学信号;心电信号;乳腺癌图像
Abstract
III
Abstract
For diseases such as cancer and heart disease, which have very high mortality rates. Early diagnosis can often
improve the survival rate of patients and simplifying the detection process is extremely important. In the traditional
situation, the medical data of patients often requires manual detection and analysis by professional physicians.
However, the proportion of doctors and patients in China is seriously unbalanced and the large amount of data is
extremely demanding for the level and patience of professional physicians. In the process of detection and analysis,
there may be a series of external factors, such as the status of testers, irregular data, randomness, and complexity of
data, leading to uneven quality of detection and analysis which is disastrous for both patients and professional
physicians. Therefore, seeking a method that can automatically search for biomarkers has become the appeal of
many medical workers.
With the rapid development of computer hardware and software, new machine learning and deep learning
algorithms have made great progress in the fields of natural language recognition and image processing with
remarkable achievements. Deep learning branched convolutional neural network has taken the lead in many fields
by virtue of its powerful nonlinear representation capability. Inspired by the extensive application of convolutional
neural network in other fields, this thesis proposed an automatic recognition algorithm of medical signals with high
performance, strong robustness and high recognition rate based on the characteristics of each biomedical signal
and focusing on the processing and analysis technology of biomedical signals. In this study, two kinds of medical
signals, namely ECG signal and breast cancer pathological tissue image, were taken as the research objects for
in-depth research. The main research contents are as follows:
1. In the ECG signal recognition task based on the improved residual network, five kinds of most common
heart disease data were selected from the MIT-BIH arrhythmia database. The waveform was positioned through
the R-peak in the ECG signal waveform and the waveform was segmfied by 1×600 as a unit. Then, the segmented
data was imported into the first convolution layer and the stacked residual blocks were used for feature extraction.
Finally, softmax classifier was used for multi-case recognition. In the experiment, K-fold cross validation was used
to train, verify, and test the MIT-BIH arrhythmia dataset. The proposed model was designed without any
additional artificial features and data enhancement assistance. The accuracy of 97.20%, sensitivity of 92.85%,
specificity of 98.29%, accuracy of 93.16% and F1 score of 93.00% were obtained.
2. In the classification task of breast cancer pathological tissue images, traditional networks are unable to
fully express the complex features of breast cancer pathological tissue images. In this thesis, a deep network model
was designed by deepening the depth of the network to obtain deeper characteristic information to solve the
problem of network degradation caused by the increase of model layers. The traditional convolution was replaced
by dilated convolution which improved the perception field without bringing additional parameters. With the
江苏科技大学工程硕士学位论文
IV
Adam optimizer, the learning rate decays exponentially with the training. In the experiment, dataset was from the
BreakHis and a set of preprocessing frameworks was designed to improve the compatibility of the model. K-fold
cross validation was used for the evaluation and an early stopping algorithm was used to avoid over/under fitting.
An independent experiment on the dataset amplification factory was conducted and the proposed model was
compared horizontally with existing models and literature. The experimental results show that the proposed model
was efficient, accurate and reliable for the recognition of benign and malignant breast cancer pathological tissue
images and for the fine identification of multiple cases in breast cancer pathological tissue images.
Keywords Deep learning; Neural network; Residual network; Medical signals; ECG signal; Breast cancer images
目 录
V
目 录
摘 要 ...................................................................................................................................... I
Abstract ................................................................................................................................. III
第 1 章 绪论 ........................................................................................................................... 1
1.1 课题研究的背景与意义 .............................................................................................. 1
1.2 生物医学信号处理 ...................................................................................................... 2
1.2.1 心电信号及其研究现状 ....................................................................................... 2
1.2.2 乳腺癌病理学图像及其研究现状 ....................................................................... 4
1.3 深度学习与神经网络 .................................................................................................. 5
1.3.1 浅层神经网络 ....................................................................................................... 6
1.3.2 深层神经网络 ....................................................................................................... 6
1.4 主要研究内容和章节安排 .......................................................................................... 7
第 2 章 医学信号与神经网络 ............................................................................................... 9
2.1 心电信号基础 .............................................................................................................. 9
2.1.1 心电信号产生原理 ............................................................................................... 9
2.1.2 心电信号诊断基础 ............................................................................................... 9
2.1.3 标准心电信号数据库 ......................................................................................... 10
2.2 乳腺癌诊断基础 ........................................................................................................ 11
2.2.1 乳腺癌病因 ......................................................................................................... 11
2.2.2 乳腺癌病理学组织图像数据库 ......................................................................... 12
2.3 卷积神经网络 ............................................................................................................ 13
2.4 空洞卷积 .................................................................................................................... 17
2.5 模型评估和评价指标 ................................................................................................ 18
2.5.1 K 折交叉验证 ...................................................................................................... 18
2.5.2 评价指标 ............................................................................................................. 19
2.6 本章小结 .................................................................................................................... 20
第 3 章 数据处理与网络模型 ............................................................................................. 21
3.1 引言 ............................................................................................................................ 21
3.2 实验框架 .................................................................................................................... 21
3.2.1 深度学习框架 ..................................................................................................... 21
3.2.2 实验平台及配置 ................................................................................................. 22
3.3 数据处理 .................................................................................................................... 22
3.3.1 心电信号数据处理 ............................................................................................. 22
3.3.2 乳腺癌病理学组织图像数据处理 ..................................................................... 25
3.4 深度学习模型 ............................................................................................................ 26
3.4.1 AlexNet ................................................................................................................. 27
3.4.2 VGGNet ................................................................................................................ 27
3.4.3 ResNet .................................................................................................................. 28
3.5 本章小结 .................................................................................................................... 29
第 4 章 基于改进残差网络对心电信号的识别方法 ......................................................... 31
4.1 引言 ............................................................................................................................ 31
4.2 网络结构设计 ............................................................................................................ 31
剩余70页未读,继续阅读
资源评论
2201_75761617
- 粉丝: 21
- 资源: 7339
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功