Peripheral Nerve Segmentation Using Speckle Removal and Bayesian Shape Models

• Published in: Pattern Recognition and Image Analysis Vol. 9117; pp. 387 - 394
• Main Authors: García, Hernán F., Giraldo, Juan J., Álvarez, Mauricio A., Orozco, Álvaro A., Salazar, Diego
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2015; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Bayesian shape models; Computer vision; Image processing; Pattern recognition; Peripheral nerve segmentaion; Speckle removal
• ISBN: 3319193899; 9783319193892
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-19390-8_44

In the field of medicine, ultrasound images have become a useful tool for visualizing nerve structures in the process of anesthesiology. Although, these images are commonly used in medical procedures such as peripheral nerve blocks. Their poor intelligibility makes it difficult for the anesthesiologists to perform this process accurately. Therefore, an automated segmentation methodology of the peripheral nerves can assist the experts in improving accuracy. This paper proposes a peripheral nerve segmentation method in medical ultrasound images, based on Speckle removal and Bayesian shape models. The method allows segmenting efficiently a given nerve by performing a Bayesian shape fitting. The experimental results show that performing a speckle removal before fitting the model, improves the accuracy due to the enhancement of the image to segment.