| 本文已被：浏览 1808次 下载 1220次 |
码上扫一扫！ |
| 基于神经网络的显微高光谱乳腺癌组织图像研究 |
| 郑欣1,2,周梅1,孙力1,邱崧1,2,于观贞3,李庆利1* |
|
|
(1. 华东师范大学多维度信息处理上海市重点实验室, 上海 200241;
2. 华东师范大学空间信息与定位导航上海市高校工程技术研究中心, 上海 200241;
3. 上海中医药大学附属龙华医院肿瘤七科, 上海 200032
*通信作者) |
|
| 摘要: |
| 目的 探索神经网络结合显微高光谱成像识别乳腺癌组织的可行性和应用价值。方法 采用显微高光谱成像技术采集乳腺癌组织的图像数据，使用基于神经网络的显微高光谱乳腺癌组织图像分析方法，实现乳腺癌组织的自动分类和区域划分。提出数据预处理方法以提高图像的信噪比，利用神经网络训练图谱信息识别乳腺组织病变区域并突显以利于可视化。结果 基于神经网络的显微高光谱的乳腺组织识别分析方法同时利用了图谱两个方面的特征，获得了比传统彩色病理图像更好的识别结果。结论 基于神经网络的显微高光谱乳腺组织图像分析方法可以提供特征性的样本信息，是传统彩色病理图像的有效补充。在神经网络分析方法的支持下，将显微高光谱成像技术应用于乳腺癌组织的分析具有一定的应用前景。 |
| 关键词: 乳腺肿瘤 神经网络 显微高光谱图像 组织病理学 |
| DOI：10.16781/j.0258-879x.2018.08.0886 |
| 投稿时间：2018-06-21修订日期：2018-07-26 |
| 基金项目:国家自然科学基金（61377107）. |
|
| Micro-hyperspectral breast cancer tissue image analysis based on neural network |
| ZHENG Xin1,2,ZHOU Mei1,SUN Li1,QIU Song1,2,YU Guan-zhen3,LI Qing-li1* |
(1. Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, China;
2. Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai 200241, China;
3. Department of Oncology(Ⅶ), Longhua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai 200032, China
*Corresponding author) |
| Abstract: |
| Objective To explore the feasibility and value of neural network combined with micro-hyperspectral imaging in identifying breast cancer tissue.Methods The micro-hyperspectral imaging technology was used to collect image data of breast cancer tissue, and the micro-hyperspectral breast tissue image analysis method based on neural network was used to realize the automatic classification and regional division of breast cancer tissue. Meanwhile, data preprocessing method was proposed to improve the signal to noise ratio of the image, and map information was trained by neural network to identify breast tissue lesions and highlight them for visualization.Results The micro-hyperspectral breast tissue image analysis method based on neural network utilized two characteristics of the images at the same time, and it was better than traditional color pathological images in identifying breast tissue.Conclusion The micro-hyperspectral breast tissue image analysis method based on neural network can provide more characteristic sample information compared with traditional color pathology images, and may serve as an effective complement to traditional color pathological images. With the support of neural network, the micro-hyperspectral imaging technology has prospects in analyzing breast cancer tissue. |
| Key words: breast neoplasms neural networks micro-hyperspectral image histopathology |
