计算机科学 ›› 2018, Vol. 45 ›› Issue (1): 162-166.doi: 10.11896/j.issn.1002-137X.2018.01.028
赵鹏飞,赵涓涓,强彦,王峰智,赵文婷
ZHAO Peng-fei, ZHAO Juan-juan, QIANG Yan, WANG Feng-zhi and ZHAO Wen-ting
摘要: 针对传统计算机辅助诊断系统中肺部结节检出过程复杂,检出结果依赖于分类前期每个步骤的性能,以及存在假阳性率高的问题,提出了一种基于卷积神经网络的端到端的肺结节检测方法。该方法首先使用大量带标签的肺结节数据对构建的多输入卷积神经网络进行训练,实现从原始数据到语义标签的有监督学习。然后采用快速边缘检测方法和二维高斯概率密度函数构建候选区域模板,从待检测CT序列中获取候选区域并将其作为多输入卷积神经网络的输入数据。最后采用判定阈值实现疑似肺结节区域标注,同时在相邻的CT影像中进行重点检测。在LIDC-IDRI数据集上的大量实验结果表明,所提方法在肺部CT影像中对微、小结节的检出率较高;同时,重点检测模板能够小幅降低微、小结节检测的假阳率。
[1] SIEGEL R L,et al.Cancer Statistics[J].CA Ccancer Journal for Clinicians,2017,67(1):7-30. [2] PRUITT S L,LACCETTI A L,XUAN L,et al.Revisiting alongstanding clinical trial exclusion criterion:impact of prior cancer in early-stage lung cancer [J].British Journal of Cancer,2017,116(6):717-725. [3] LIU J K,JIANG H Y,GAO M D,et al.An Assisted Diagnosis System for Detection of Early Pulmonary Nodule in Computed Tomography Images[J].Journal of Medical Systems,2017,41(2):30. [4] JAVAID M,REHMAN M Z,et al.A novel approach to CAD system for the detection of lung nodules in CT images[J].Computer Methods & Programs in Biomedicine,2016,135:125-139. [5] MANIKANDAN T,BHARATHI N.Lung Cancer Detection Using Fuzzy Auto-Seed Cluster Means Morphological Segmentation and SVM Classifier[J].Journal of Medical Systems,2016,40(7):1-9. [6] KUMAR D,WONG A,CLAUSI D A.Lung Nodule Classification Using Deep Features in CT Images[C]∥Computer and Robot Vision.IEEE,2015:133-138. [7] SIRINUKUNWATTANA K,SHAN E A R,TSANG Y W,et al.Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images[J].IEEE Transactions on Medical Imaging,2016,35(99):1. [8] NIE D,ZHANG H,ADELI E,et al.3D Deep Learning forMulti-modal Imaging-Guided Survival Time Prediction of Brain Tumor Patients[C]∥Miccai.2016:212. [9] SETIO A A,CIOMPI F,LITJENS G,et al.Pulmonary nodule detection in CT images:false positive reduction using multi-view convolutional networks[J].IEEE Transactions on Medical Ima-ging,2016,35(5):1160-1169. [10] LIANG M,TANG W,XU D M,et al.Low-Dose CT Screening for Lung Cancer:Computer-aided Detection of Missed Lung Cancers[J].Radiology,2016,281(1):279. [11] WEI W Y,ZHANG G C,ZHANG G Z.An image retrievalmethod using image information entropy and fractal vector[J].Journal of Northwest Normal University(Natural Science),2006,42(1):32-35.(in Chinese) 魏伟一,张贵仓,张国治.一种基于图像熵及分形维矢量的图像检索技术[J].西北师范大学学报(自然科学版),2006,2(1):32-35. [12] HE K,ZHANG X,REN S,et al.Delving Deep into Rectifiers:Surpassing Human-Level Performance on ImageNet Classification[C]∥ICCV 2015.2015:1026-1034. [13] VAN KLAVEREN R J,OUDKERK M,PROKOP M,et al.Management of lung nodules detected by volume CT scanning[J].New England Journal of Medicine,2009,361(23):2221-2229. [14] MCNITT-GRAY M F,MEYER C R,et al(1)The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation[J].Academic Radiology,2007,14(12):1464-1474. [15] ARMATO S,MCLENNAN G,MCNITT-GRAY M,et al.WE-B-201B-02:The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI):A Completed Public Database of CT Scans for Lung Nodule Analysis[J].Medical Physics,2010,37(6):3416-3417. [16] MESSAY T,HARDIE R C,TUINSTRA T R.Segmentation of pulmonary nodules in computed tomography using a regression neural network approach and its application to the Lung Image Database Consortium and Image Database Resource Initiative dataset[J].Medical Image Analysis,2015,22(1):48. [17] ANIRUDH R.Lung nodule detection using 3D convolutionalneural networks trained on weakly labeled data[C]∥Pro.SPIE 9785,Medical Imaging:Computer-Aided Diagnosis.2016:978532. |
No related articles found! |
|