Discrimination between emboli and artifacts for outpatient transcranial Doppler ultrasound data
- 220 Downloads
This paper addresses the detection of emboli in transcranial Doppler ultrasound data acquired from an original portable device. The challenge is the removal of several artifacts (motion and voice) intrinsically related to long-duration (up to 1 h 40 mn per patient) outpatient signals monitoring from this device, as well as high intensities due to the stochastic nature of blood flow. This paper proposes an adapted removal procedure. This firstly consists of reducing the background noise and detecting the blood flow in the time–frequency domain using a likelihood method for contour detection. Then, a hierarchical extraction of features from magnitude and bounding boxes is achieved for the discrimination of emboli and artifacts. After processing of the long-duration outpatient signals, the number of artifacts predicted as emboli is considerably reduced (by 92% for some parameter values) between the first and the last step of our algorithm.
KeywordsEmboli detection Transcranial Doppler Ultrasound Time–frequency approach Likelihood Spectral kurtosis Artifacts rejection
This work was funded by the ANR-13-LAB3-0006-01 LabCom AtysCrea and was supported by the LABEX CELYA (ANR-10-LABX-0060) and PRIMES (ANR-11-LABX-0063) of Université de Lyon, within the program “Investissements d’Avenir” (ANR-11-IDEX-0007) operated by the French National Research Agency (ANR).
- 3.Biard M, Kouamé D, Girault JM, Patat F (2003) Discrimination between emboli and artifacts during transcranial doppler. In: Proceedings of the world congress on ultrasonics, société française d’acoustique, WCU. pp 1101–1104Google Scholar
- 5.Caruana R, Niculescu-Mizil A (2006) An empirical comparison of supervised learning algorithms. In: Proceedings of the 23rd international conference on machine learning, ICML ’06. ACM, New York, pp 161–168Google Scholar
- 9.Gencer M, Bilgin G, Aydin N (2013) Embolic doppler ultrasound signal detection via fractional fourier transform. In: Engineering in Medicine and Biology Society (EMBC), 35th annual international conference of the IEEE. pp 3050–3053Google Scholar
- 11.Huang YM, xin Du S (2005) Weighted support vector machine for classification with uneven training class sizes. In: Proceedings of 2005 international conference on machine learning and cybernetics, vol 7. pp 4365–4369Google Scholar
- 13.Karahoca A, Kucur T, Aydin N (2007) Data mining usage in emboli detection. In: ECSIS symposium on bio-inspired, learning, and intelligent systems for security, BLISS 2007. pp 159–162Google Scholar
- 16.Menigot S, Dreibine L, Meziati N, Girault J (2009) Automatic detection of microemboli by means of a synchronous linear prediction technique. In: Ultrasonics symposium (IUS), 2009 IEEE International. pp 2371–2374Google Scholar
- 18.Millioz F, Martin N (2010) Estimation of a white Gaussian noise in the short time Fourier transform based on the spectral kurtosis of the minimal statistics: application to underwater noise. In: IEEE international conference on acoustics speech and signal processing (ICASSP). pp 5638–5641Google Scholar
- 20.Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 11(285–296):23–27Google Scholar
- 22.Paschoal FM, de Almeida Lins Ronconi K, de Lima Oliveira M, Nogueira RdC, Paschoal EHA, Teixeira MJ, Figueiredo EG, Bor-Seng-Shu E (2015) Embolic signals during routine transcranial doppler ultrasonography in aneurysmal subarachnoid hemorrhage. BioMed research international 2015Google Scholar
- 24.Sciolla B, Ceccato P, Dambry T, Guibert B, Delachartre P (2015) A comparison of non-parametric segmentation methods. In: GRETSI, Lyon. https://hal.archives-ouvertes.fr/hal-01307318