Fully automatic cardiac T2* relaxation time estimation using marker-controlled watershed

作者: Kittichai Wantanajittikul , Suwit Saekho , Arintaya Phrommintikul , Nipon Theera-Umpon , Sansanee Auephanwiriyakul

DOI: 10.1109/ICCSCE.2015.7482215

关键词:

摘要: Heart failure due to iron-overload cardiomyopathy is one of the main causes mortality. The reversible if intensive iron chelation treatment done in time. However, diagnosis often delayed because cardiac deposition unpredictable and symptoms are lately detected. widely used method many countries by calculating a parameter called T2* (T2-star) from magnetic resonance (MR) image sequences. In order compute value, region interest (ROI) manually selected an expert which may require considerable time skills. aim this work hence develop fully automatic measurement using marker-controlled watershed for segmenting interventricular septum MR images. Mathematical morphologies also reduce some errors. Moreover, new approach evaluation suggested work. septa images all echo times (TE's) segmented calculate signal intensities (SI's) while classical segments only first TE. Thirty were segmentation performances evaluated precision recall 0.9 0.8 compared with two experts' opinions. It shows that results our proposed technique quite similar values carried out based on automatically ROI's. mean difference between opinions about 1 ms. This demonstrates close calculated experts.

参考文章(26)
Qian Zheng, Yanqiu Feng, Xiaping Wei, Meiyan Feng, Wufan Chen, Zhentai Lu, Yikai Xu, Hongwen Chen, Taigang He, Automated interventricular septum segmentation for black-blood myocardial T2* measurement in thalassemia. Journal of Magnetic Resonance Imaging. ,vol. 41, pp. 1242- 1250 ,(2015) , 10.1002/JMRI.24662
Tuan Anh Ngo, Gustavo Carneiro, Left ventricle segmentation from cardiac MRI combining level set methods with deep belief networks international conference on image processing. pp. 695- 699 ,(2013) , 10.1109/ICIP.2013.6738143
MM Hadhoud, Mohamed I Eladawy, Ahmed Farag, Franco M Montevecchi, Umberto Morbiducci, None, Left Ventricle Segmentation in Cardiac MRI Images American Journal of Biomedical Engineering. ,vol. 2, pp. 131- 135 ,(2012) , 10.5923/J.AJBE.20120203.07
Phalla Ou, Yansong Zhao, Sara El Fawal, Puja Banka, Andrew J. Powell, Cardiac T2 measurements in patients with iron overload: a comparison of imaging parameters and analysis techniques. Magnetic Resonance Imaging. ,vol. 30, pp. 641- 648 ,(2012) , 10.1016/J.MRI.2011.12.020
Caroline Petitjean, Jean-Nicolas Dacher, A review of segmentation methods in short axis cardiac MR images Medical Image Analysis. ,vol. 15, pp. 169- 184 ,(2011) , 10.1016/J.MEDIA.2010.12.004
Susanne Will, Petros Martirosian, Christian Würslin, Fritz Schick, Automated segmentation and volumetric analysis of renal cortex, medulla, and pelvis based on non-contrast-enhanced T1- and T2-weighted MR images Magnetic Resonance Materials in Physics Biology and Medicine. ,vol. 27, pp. 445- 454 ,(2014) , 10.1007/S10334-014-0429-4
Vincenzo Positano, Benedetta Salani, Alessia Pepe, Maria Filomena Santarelli, Daniele De Marchi, Anna Ramazzotti, Brunella Favilli, Eliana Cracolici, Massimo Midiri, Paolo Cianciulli, Massimo Lombardi, Luigi Landini, Improved T2* assessment in liver iron overload by magnetic resonance imaging. Magnetic Resonance Imaging. ,vol. 27, pp. 188- 197 ,(2009) , 10.1016/J.MRI.2008.06.004
Ekkarat Boonchieng, Khanita Duangchaemkarn, Myocardial iron measurement in thalassemia using cardiac magnetic resonance image processing software biomedical engineering international conference. pp. 1- 4 ,(2012) , 10.1109/BMEICON.2012.6465497
Fernand Meyer, Topographic distance and watershed lines Signal Processing. ,vol. 38, pp. 113- 125 ,(1994) , 10.1016/0165-1684(94)90060-4
Lin Xu, Huan Ma, Shengli Song, Qianjin Feng, Yanqiu Feng, Wufan Chen, Taigang He, Qian Zheng, Zhentai Lu, Minghui Zhang, Automatic Segmentation of Myocardium from Black-Blood MR Images Using Entropy and Local Neighborhood Information PLOS ONE. ,vol. 10, pp. e0120018- ,(2015) , 10.1371/JOURNAL.PONE.0120018