基于小波变换的多神经网络胸片骨骼分离

›› 2015, Vol. 28 ›› Issue (5): 124-.

基于小波变换的多神经网络胸片骨骼分离

陈胜,璩心波

(上海理工大学光电信息与计算机工程学院,上海 200093)

出版日期:2015-05-15 发布日期:2015-05-19
作者简介:陈胜(1976—),男,博士,副教授,硕士生导师。研究方向:胸片图像处理。Email:615728611@qq.com。璩心波(1989—),男,硕士研究生。研究方向:数字图像处理。

Chest Bone Segmentation Based on Wavelet Transform and Massive Training Artificial Neural Network

CHEN Sheng,QU Xinbo

(School of OpticalElectrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200090,China)

Online:2015-05-15 Published:2015-05-19

摘要/Abstract

摘要：

胸片中,因大量肺结点被锁骨或肋骨遮挡而被放射科医生忽略。为了从胸片图像中分割出骨骼结构,提出了一种基于小波变换的多分辨率人工神经网络,以获取去除骨骼结构的虚拟软组织胸片。该方法可有效保证肺结点与血管的清晰度,且分离出骨骼和软组织可有效地帮助放射医生检测肺结点。

关键词: X光胸片, 肺结点, 计算机辅助检测, 人工神经网络

Abstract:

A large number of lung nodules are missed by radiologists because they are hidden behind ribs or clavicles in chest radiographs.The purpose of this study is to separate the bony structure,such as ribs and clavicles from soft tissue in CXRs.To achieve this goal,we developed a multiresolution massive training artificial neural network based on the wavelet transform.By this method,the visibility of nodules and lung vessels are guaranteed.And the separation of bones from the soft tissue would be potentially useful for radiologists in the detection of lung nodules.

Key words: chest radiography;lung nodules;computeraided diagnosis;artificial neural network

中图分类号:

TP391.41

陈胜,璩心波. 基于小波变换的多神经网络胸片骨骼分离[J]. , 2015, 28(5): 124-.

CHEN Sheng,QU Xinbo. Chest Bone Segmentation Based on Wavelet Transform and Massive Training Artificial Neural Network[J]. , 2015, 28(5): 124-.

参考文献

［1］Murphy G P.American cancer society textbook of clinical oncology［M］.2nd ed.Atlanta,Ga:The Society,1995.

［2］Austin J H.Missed bronchogenic carcinoma:radiographic findings in 27 patients with a potentially resectable lesion evident in retrospect［J］.Radiology,1992,182(6):115-122.
［3］Shah P K.Missed non-small cell lung cancer:radiographic findings of potentially resectable lesions evident only in retrospect［J］.Radiology,2003,226(2):235-241.

［4］Kido S,Kuriyama K,Hosomi N,et al.Detection of simulated pulmonary nodules by single-exposure dual-energy computed radiography of the chest:effect of a computer-aided diagnosis system［J］.Europe Journal of Radiology,2002,44(5):205-219.

［5］Kido S,Nakamura H,Ito W,et al.Computerized detection of pulmonary nodules by single-exposure dual-energy computed radiography of the chest［J］.Europe Journal of Radiology,2002,44(1):198-204.

［6］Clocker R,Frohnmayer W.Uber die rontgenspektroskopische bestimmung des gewichtsanteiles eines elementes in gememgen und verbindumgen［J］.Annalen der Physik,1925,76(6):369-395.

［7］Jacobson J,Mackay R S.Radiological contrast enhancing methods［J］.Advances in Biological and Medical Physics,1958(6):201-261.

［8］Loog M.Filter learning:application to suppression of bony structures from chest radiographs［J］.Medical Image Analysis,2006(10):826-840.

［9］Suzuki K.Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network(MTANN)［J］.IEEE Transactions on Medical Imaging,2006,25(3):406-16.

［10］Sheng Chen.Separation of bones from chest radiographs by means of anatomically specific multiple massive-training ANNs combined with total variation minimization smoothing and consistency processing［J］.IEEE Transactions on Medical Imaging Publication Information,2014,33(7):233-246.

[1]	周小波,邹任玲,卢旭华,王海滨,张俊翔. 基于人工神经网络的表面肌电信号分类器研究进展[J]. 电子科技, 2021, 34(2): 62-67.
[2]	何菁，陈胜. 一种全新的两步自动化医学图像分割方案[J]. , 2016, 29(7): 85-.
[3]	马立新,周磊,张海兵,栾健. 自适应智能化谐波电流检测方法[J]. , 2016, 29(2): 126-.
[4]	时广献, 李春辉, 李宏博. 基于联想神经网络算法的电力系统负荷预测[J]. , 2010, 23(12): 62-66.