Multi-scale Convolutional Neural Networks for Lung Nodule Classification
文献类型：会议论文
| 作者 | Shen W(沈伟)1 ; Mu Zhou3; Feng Yang2; Caiyun Yang1; Jie Tian1; Tian J(田捷)
|
| 出版日期 | 2015 |
| 会议日期 | 2015-6 |
| 会议地点 | Sabhal Mor Ostaig College on the Isle of Skye, Scotland |
| 关键词 | Lung Nodule Classification Computed Tomography Imaging Convolutional Neural Networks Computer-aided Diagnoses |
| 英文摘要 | We investigate the problem of diagnostic lung nodule classifi cation using thoracic Computed Tomography (CT) screening. Unlike traditional studies primarily relying on nodule segmentation for regional analysis, we tackle a more challenging problem on directly modelling raw nodule patches without any prior de nition of nodule morphology. We propose a hierarchical learning framework--Multi-scale Convolutional Neural Networks (MCNN)--to capture nodule heterogeneity by extracting discriminative features from alternatingly stacked layers. In particular, to suff ciently quantify nodule characteristics, our framework utilizes multi-scale nodule patches to learn a set of class-speci c features simultaneously by concatenating response neuron activations obtained at the last layer from each input scale. We evaluate the proposed method on CT images from Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), where both lung nodule screening and nodule annotations are provided. Experimental results demonstrate the eff ectiveness of our method on classifying malignant and benign nodules without nodule segmentation. |
| 会议录 | IPMI
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/11699]  |
| 专题 | 自动化研究所_中国科学院分子影像重点实验室 |
| 通讯作者 | Tian J(田捷) |
| 作者单位 | 1.Key Laboratory of Molecular Imaging of Chinese Academy of Sciences, Institute of Automation, Chinese Academy of Sciences 2.School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China 3.Department of Computer Science and Engineering, University of South Florida, Tampa, United States |
| 推荐引用方式 GB/T 7714 | Shen W,Mu Zhou,Feng Yang,et al. Multi-scale Convolutional Neural Networks for Lung Nodule Classification[C]. 见:. Sabhal Mor Ostaig College on the Isle of Skye, Scotland. 2015-6. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。