تخمين حجم هواي ريه در بيماران COPD با استفاده از بخش بندي تصاوير CT سه بعدي

چكيده انگليسي :

Lung s Air Volume Estimation In COPD Patients Using Segmentation of 3D CT Images Hadi Moghadas Dastjerdi h moghadas@ec iut ac ir May 17 2017 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 IranSupervisors Dr Mohammadreza Ahmadzadeh ahmadzadeh@cc iut ac ir Dr Abbas Samani asamani@uwo ca Advisors Dr Mehdi Karami Dr Rassoul Amirfattahi Department Graduate Program Coordinator Dr Mohammadreza Taban Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Department of Electrical and Computer Engineering Department of Medical Biophysics Western University London Ontario N6A5B9 Canada Department of Radiology Isfahan University of Medical Sciences Isfahan 81746 73461 IranAbstract Lung air estimation using non invasive techniques can be used for assessment of the lung function and effective diag nosis of lung disease e g chronic obstructive pulmonary disease A novel technique is proposed to automatically estimatethe lung air volume and its variations throughout respiration cycle using 4D thoracic CT images The technique is basedon an advanced thresholding method which benefits from parenchyma tissue mechanical properties in addition to the lungimage data over the respiration cycle to determine the segmentation threshold values The technique was applied to CTscans of ex vivo porcine lung and to lung images of COPD patients Results indicate that the air volume estimated usingthe proposed method is significantly more accurate when AVPCs are used in the air volume estimation as mean errors ofonly 1 and less than 6 86 were obtained in the ex vivo lung and patient studies respectively Furthermore a novelexpert system technique is proposed to accurately assess COPD severity characterized by its stage through processing thepatient s thoracic CT images The technique inputs thoracic CT images to automatically extract 23 features of air volumevariation and distribution within the lung over respiration cycle Relationships between features and pulmonary functiontest PFT measurements were developed which indicated strong correlation Results obtained in this investigation showedan overall accuracy of over 84 which demonstrates its effectiveness in determining COPD stage merely based on CTimages and without using PFT measurements The performance characteristics of the proposed method including beingcompletely images based fully automatic combined with its demonstrated high accuracy makes it a strong candidate tocomplement replace pulmonary function diagnostic tests that involve experimental measurement of function parameters Key WordsAir Volume Estimation 3D CT Images Segmentation Lung Partial Volume Effect COPD Introduction According to the American Lung Association lung diseases are among the most common medical disordersin the world While death rates due to lung diseases are currently on the rise death rates due to other leadingcauses of death such as cancer stroke and heart disease are declining Among these diseases chronic obstructivepulmonary disease COPD is an increasingly prevalent disorder which is associated with airflow limitation inthe lung While it is currently the fourth leading cause of death in the world as it causes more than 3 milliondeaths per year while over 350 million people suffer from the disease worldwide it is expected to becomethe third leading cause of death by 2020 American Lung Association 2008 Rising mortality rates of lungdiseases has attracted the attention of many researchers to improve present diagnosis and treatment techniques As a heterogeneous disorder COPD consists of two pathological processes including functional airways diseaseand emphysematous lung tissue destruction in a variety of combinations to varying degrees of severity These

مقدس دستجردي، هادي

تخمين حجم هواي ريه در بيماران COPD با استفاده از بخش بندي تصاوير CT سه بعدي

تخمين حجم هوا , تصاوير CT سه بعدي , بخش بندي , ريه , اثر حجم جزئي , COPD