An Inverse Scattering Algorithm for the Segmentation of the Luminal Border on Intravascular Ultrasound Data E. Gerardo Mendizabal-Ruiz 1 , George Biros 2 , and Ioannis A. Kakadiaris 1 1 Computational Biomedicine Lab, Departments of Computer Science, Electrical and Computer Engineering, and Biomedical Engineering, University of Houston, Houston, TX 2 Department of Biomedical Engineering and School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA Abstract. Intravascular ultrasound (IVUS) is a catheter-based medical imaging technique that produces cross-sectional images of blood vessels and is particu- larly useful for studying atherosclerosis. In this paper, we present a novel method for segmentation of the luminal border on IVUS images using the radio frequency (RF) raw signal based on a scattering model and an inversion scheme. The scat- tering model is based on a random distribution of point scatterers in the vessel. The per-scatterer signal uses a differential backscatter cross-section coefficient (DBC) that depends on the tissue type. Segmentation requires two inversions: a calibration inversion and a reconstruction inversion. In the calibration step, we use a single manually segmented frame and then solve an inverse problem to re- cover the DBC for the lumen and vessel wall (κ l and κ w , respectively) and the width of the impulse signal σ. In the reconstruction step, we use the parameters from the calibration step to solve a new inverse problem: for each angle Θi of the IVUS data, we reconstruct the lumen-vessel wall interface. We evaluated our method using three 40MHz IVUS sequences by comparing with manual segmen- tations. Our preliminary results indicate that it is possible to segment the luminal border by solving an inverse problem using the IVUS RF raw signal with the scatterer model. 1 Introduction Intravascular ultrasound (IVUS) is an invasive catheter imaging technique capable of providing high-resolution, cross-sectional images of the interior of human blood ves- sels. The IVUS catheter consists of a solid-state or mechanically-rotated transducer that emits ultrasound pulses and receives acoustic echoes (i.e., A-line) at a discrete set of angles (commonly 240 to 360). The envelopes of the received signals are computed, log-compressed, and then geometrically transformed to obtain the disc-shaped B-mode IVUS image. Segmentation of IVUS images refers to the delineation of the lumen/intima and me- dia/adventita borders. This process is necessary for assessing the vessel and plaque characteristics. Given that IVUS sequences may be hundreds to thousands of frames long, manual segmentation of a complete sequence is prohibitively time-consuming. Thus, methods for automatic segmentation of IVUS images are needed. Contributions. In this paper, we present a novel method for segmentation of the luminal border on IVUS data. using the radio frequency (RF) raw signal based on a scattering G.-Z. Yang et al. (Eds.): MICCAI 2009, Part II, LNCS 5762, pp. 885–892, 2009. c  Springer-Verlag Berlin Heidelberg 2009