Authors: Norliza M Noor Joel C M Than Omar M Rijal Rosminah M Kassim Ashari Yunus Amir A Zeki Michele Anzidei Luca Saba Jasjit S Suri
Publish Date: 2015/02/10
Volume: 39, Issue: 3, Pages: 22-
Abstract
Interstitial Lung Disease ILD encompasses a wide array of diseases that share some common radiologic characteristics When diagnosing such diseases radiologists can be affected by heavy workload and fatigue thus decreasing diagnostic accuracy Automatic segmentation is the first step in implementing a Computer Aided Diagnosis CAD that will help radiologists to improve diagnostic accuracy thereby reducing manual interpretation Automatic segmentation proposed uses an initial thresholding and morphology based segmentation coupled with feedback that detects large deviations with a corrective segmentation This feedback is analogous to a control system which allows detection of abnormal or severe lung disease and provides a feedback to an online segmentation improving the overall performance of the system This feedback system encompasses a texture paradigm In this study we studied 48 males and 48 female patients consisting of 15 normal and 81 abnormal patients A senior radiologist chose the five levels needed for ILD diagnosis The results of segmentation were displayed by showing the comparison of the automated and ground truth boundaries courtesy of ImgTracer™ 10 AtheroPoint™ LLC Roseville CA USA The left lung’s performance of segmentation was 9652 for Jaccard Index and 9821 for Dice Similarity 061 mm for Polyline Distance Metric PDM −115 for Relative Area Error and 409 Area Overlap Error The right lung’s performance of segmentation was 9724 for Jaccard Index 9858 for Dice Similarity 061 mm for PDM −003 for Relative Area Error and 353 for Area Overlap Error The segmentation overall has an overall similarity of 984 The segmentation proposed is an accurate and fully automated systemWe would like to thank all the radiologists and clinicians for making this study a success We would like to express our gratitude to Mr Ng Chuen Rue for helping to edit this manuscript We are grateful to AtheroPoint™ LLC Roseville CA USA for gracefully letting us use ImgTracer™ 10 software for tracing the manual borders of the lung This study was partly funded by Universiti Teknologi Malaysia research fund 06H35
Keywords: