[Clinical Application of Extraction and Analysis of the Key Frames Based on IVUS Sequences].

In this paper, we propose an image-based key frame gating method to reduce motion artifacts in intravascular ultrasound (IVUS) longitudinal cuts. The artifacts are mainly caused by the periodic relative displacement between blood vessels and the IVUS catheter due to cardiac motion. The method is achieved in four steps as following. Firstly, we convert IVUS image sequences to polar coordinates to cut down the amount of calculation. Secondly, we extracted a one-dimensional signal cluster reflecting cardiac motion by spectral analysis and filtering techniques. Thirdly, we designed a Butterworth band-pass filter for filtering the one-dimensional signal clusters. Fourthly, we retrieved the extremes of the filtered signal clusters to seek key frames to compose key-frames gated sequences. Experimental results showed that our algorithm was fast and the average frame processing time was 17ms. Observing the longitudinal viewpictures, we found that comparing to the original ones, the gated sequences had similar trend, less saw tooth shape, and good continuity. We selected 12 groups of clinical IVUS sequences [images (876 +/- 65 frames), coronary segments length (14.61 +/- 1.08 mm)] to calculate vessel volume, lumen volume, mean plaque burden of the original and gated sequences. Statistical results showed that, on one hand, both vessel volume and lumen volume measured of the gated sequences were significantly smaller than those of the original ones, and there was no significant difference on mean plaque burden between original and gated sequences, which met the need of the clinical diagnosis and treatment. On the other hand, variances of vessel area and lumen area of the gated sequences were significantly smaller than those of the original sequences, indicating that the gated sequences would be more stable than the original ones.

[Key frames extraction and application in intravascular ultrasound pullback sequences based on manifold learning].

OBJECTIVE: We propose an image-based key frames gating method for intravascular ultrasound (IVUS) sequence based on manifold learning to reduce motion artifacts in IVUS longitudinal cuts. METHODS: We achieved the gating with Laplacian eigenmaps, a manifold learning technique, to determine the low-dimensional manifold embedded in the high-dimensional image space. A distance function was constructed by the low-dimensional feature vectors to reflect the heart movement. The IVUS images were classified as end-diastolic and non-end-diastolic based on the distance function, and the IVUS images collected in end-diastolic stage constitutes the key frames gating sequences. RESULTS: We tested the algorithm on 13 in vivo clinical IVUS sequences (images 915±142 frames, coronary segments length 15.24±2.37 mm) to calculate the vessel volume, lumen volume, and the mean plaque burden of the original and gated sequences. Statistical results showed that both the vessel volume and lumen volume measured from the gated sequences were significantly smaller than the original ones, indicating that the gated sequences were more stable; the mean plaque burden was comparable between the original and gated sequences to meet the need in clinical diagnosis and treatment. In the longitudinal views, the gated sequences had less saw tooth shape than the original ones with a similar trend and a good continuity. We also compared our method with an existing gating method. CONCLUSION: The proposed algorithm is simple and robust, and the gating sequences can effectively reduce motion artifacts in IVUS longitudinal cuts.