Segmentation of Lumen and External Elastic Laminae in Intravascular Ultrasound Images Using Ultrasonic Backscattering Physics Initialized Multiscale Random Walks

Abstract

Coronary artery disease accounts for a large number of deaths across the world and clinicians generally prefer using x-ray computed tomography or magnetic resonance imaging for localizing vascular pathologies. Interventional imaging modalities like intravascular ultrasound (IVUS) are used to adjunct diagnosis of atherosclerotic plaques in vessels, and help assess morphological state of the vessel and plaque, which play a significant role for treatment planning. Since speckle intensity in IVUS images are inherently stochastic in nature and challenge clinicians with accurate visibility of the vessel wall boundaries, it requires automation. In this paper we present a method for segmenting the lumen and external elastic laminae of the artery wall in IVUS images using random walks over a multiscale pyramid of Gaussian decomposed frames. The seeds for the random walker are initialized by supervised learning of ultrasonic backscattering and attenuation statistical mechanics from labelled training samples. We have experimentally evaluated the performance using 77 IVUS images acquired at 40 MHz that are available in the IVUS segmentation challenge dataset 4 to obtain a Jaccard score of 0.89 ± 0.14 for lumen and 0.85 ± 0.12 for external elastic laminae segmentation over a 10-fold cross-validation study.

SpeckleGAN: a generative adversarial network with an adaptive speckle layer to augment limited training data for ultrasound image processing

“…This leads to the conclusion that realistic speckle does not play an important role for segmentation of the lumen when dealing with 20 MHz IVUS images. Comparing [1,3,22] and the results of scenario 2, it can be seen that our approach nearly reached state-of-the-art performance, although our training set was smaller and no special care was taken about optimization of the segmentation network used in this work (see "Segmentation evaluation" section).…”

Real-time element position tracking of flexible array transducer for ultrasound beamforming

“…Ultrasound (US) imaging in biomedical applications such as image-guided radiotherapy (IGRT) has increased in the last decade because of its non-ionizing nature and real-time imaging capability [1][2][3][4][5][6][7][8][9][10][11][12][13] . The use of other imaging modalities has been more common [14][15][16][17][18][19][20][21][22][23][24] than the use of US-based techniques in clinical applications of IGRT due to the rigid architecture of traditional US probe transducers.…”

Performance analysis of various denoising filters on intravascular ultrasound coronary artery images

“…This interference results in unpredictable patterns because the spacing between scatters varies with the type of tissues present, thereby producing a constructive pattern (generating a bright spot in the image) at some locations and a destructive pattern (generating a dark spot) at other locations. The result is the “grainy” speckle pattern 3,4 …”

“…The result is the "grainy" speckle pattern. 3,4 The presence of speckle noise in medical ultrasound images is still a major issue, and the need to efficaciously suppress speckle noise is very important. Various despeckling techniques for medical ultrasound images are studied in the literature.…”