Literature DB >> 20549375

Automatic detection of abnormal vascular cross-sections based on density level detection and support vector machines.

Maria A Zuluaga1, Isabelle E Magnin, Marcela Hernández Hoyos, Edgar J F Delgado Leyton, Fernando Lozano, Maciej Orkisz.   

Abstract

PURPOSE: The goal is to automatically detect anomalous vascular cross-sections to attract the radiologist's attention to possible lesions and thus reduce the time spent to analyze the image volume.
MATERIALS AND METHODS: We assume that both lesions and calcifications can be considered as local outliers compared to a normal cross-section. Our approach uses an intensity metric within a machine learning scheme to differentiate normal and abnormal cross-sections. It is formulated as a Density Level Detection problem and solved using a Support Vector Machine (DLD-SVM). The method has been evaluated on 42 synthetic phantoms and on 9 coronary CT data sets annotated by 2 experts.
RESULTS: The specificity of the method was 97.57% on synthetic data, and 86.01% on real data, while its sensitivity was 82.19 and 81.23%, respectively. The agreement with the observers, measured by the kappa coefficient, was substantial (κ = 0.72). After the learning stage, which is performed off-line, the average processing time was within 10 s per artery.
CONCLUSIONS: To our knowledge, this is the first attempt to use the DLD-SVM approach to detect vascular abnormalities. Good specificity, sensitivity and agreement with experts, as well as a short processing time, show that our method can facilitate medical diagnosis and reduce evaluation time by attracting the reader's attention to suspect regions.

Entities:  

Mesh:

Year:  2010        PMID: 20549375     DOI: 10.1007/s11548-010-0494-8

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  11 in total

1.  Estimating the support of a high-dimensional distribution.

Authors:  B Schölkopf; J C Platt; J Shawe-Taylor; A J Smola; R C Williamson
Journal:  Neural Comput       Date:  2001-07       Impact factor: 2.026

2.  Carotid artery segmentation using an outlier immune 3D active shape models framework.

Authors:  Karim Lekadir; Guang-Zhong Yang
Journal:  Med Image Comput Comput Assist Interv       Date:  2006

3.  Segmentation and quantification of human vessels using a 3-D cylindrical intensity model.

Authors:  Stefan Wörz; Karl Rohr
Journal:  IEEE Trans Image Process       Date:  2007-08       Impact factor: 10.856

4.  An accurate and reproducible scheme for quantification of coronary artery calcification in CT scans.

Authors:  Jamshid Dehmeshki; Xujiong Ye; Frank Wang; Xin Yu Lin; M Abaei; M M Siddique; S D Qanadli
Journal:  Conf Proc IEEE Eng Med Biol Soc       Date:  2004

Review 5.  A review of 3D vessel lumen segmentation techniques: models, features and extraction schemes.

Authors:  David Lesage; Elsa D Angelini; Isabelle Bloch; Gareth Funka-Lea
Journal:  Med Image Anal       Date:  2009-08-12       Impact factor: 8.545

6.  The measurement of observer agreement for categorical data.

Authors:  J R Landis; G G Koch
Journal:  Biometrics       Date:  1977-03       Impact factor: 2.571

7.  Augmented vessels for quantitative analysis of vascular abnormalities and endovascular treatment planning.

Authors:  Wilbur C K Wong; Albert C S Chung
Journal:  IEEE Trans Med Imaging       Date:  2006-06       Impact factor: 10.048

8.  Three-dimensional blood vessel quantification via centerline deformation.

Authors:  Dong-Goo Kang; Dae Chul Suh; Jong Beom Ra
Journal:  IEEE Trans Med Imaging       Date:  2009-03       Impact factor: 10.048

9.  Detection of coronary calcifications from computed tomography scans for automated risk assessment of coronary artery disease.

Authors:  Ivana Isgum; Annemarieke Rutten; Mathias Prokop; Bram van Ginneken
Journal:  Med Phys       Date:  2007-04       Impact factor: 4.071

10.  Congenital aortic disease: 4D magnetic resonance segmentation and quantitative analysis.

Authors:  Fei Zhao; Honghai Zhang; Andreas Wahle; Matthew T Thomas; Alan H Stolpen; Thomas D Scholz; Milan Sonka
Journal:  Med Image Anal       Date:  2009-02-21       Impact factor: 8.545

View more
  6 in total

1.  Automatic segmentation, detection and quantification of coronary artery stenoses on CTA.

Authors:  Rahil Shahzad; Hortense Kirişli; Coert Metz; Hui Tang; Michiel Schaap; Lucas van Vliet; Wiro Niessen; Theo van Walsum
Journal:  Int J Cardiovasc Imaging       Date:  2013-08-08       Impact factor: 2.357

2.  Sequential Monte Carlo tracking of the marginal artery by multiple cue fusion and random forest regression.

Authors:  Kevin M Cherry; Brandon Peplinski; Lauren Kim; Shijun Wang; Le Lu; Weidong Zhang; Jianfei Liu; Zhuoshi Wei; Ronald M Summers
Journal:  Med Image Anal       Date:  2014-10-13       Impact factor: 8.545

3.  Voxelwise atlas rating for computer assisted diagnosis: Application to congenital heart diseases of the great arteries.

Authors:  Maria A Zuluaga; Ninon Burgos; Alex F Mendelson; Andrew M Taylor; Sébastien Ourselin
Journal:  Med Image Anal       Date:  2015-09-16       Impact factor: 8.545

4.  Automatic Coronary Wall and Atherosclerotic Plaque Segmentation from 3D Coronary CT Angiography.

Authors:  Ahmed M Ghanem; Ahmed H Hamimi; Jatin R Matta; Aaron Carass; Reham M Elgarf; Ahmed M Gharib; Khaled Z Abd-Elmoniem
Journal:  Sci Rep       Date:  2019-01-10       Impact factor: 4.379

Review 5.  Machine Learning for Assessment of Coronary Artery Disease in Cardiac CT: A Survey.

Authors:  Nils Hampe; Jelmer M Wolterink; Sanne G M van Velzen; Tim Leiner; Ivana Išgum
Journal:  Front Cardiovasc Med       Date:  2019-11-26

Review 6.  Findings from machine learning in clinical medical imaging applications - Lessons for translation to the forensic setting.

Authors:  Carlos A Peña-Solórzano; David W Albrecht; Richard B Bassed; Michael D Burke; Matthew R Dimmock
Journal:  Forensic Sci Int       Date:  2020-10-18       Impact factor: 2.395

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.