Robust and Fast Contrast Inflow Detection for 2D X-ray Fluoroscopy

Abstract

Abstract. 2D X-ray fluoroscopy is widely used in computer assisted and image guided interventions because of the real time visual guidance it can provide to the physicians. During cardiac interventions, acquisitions of angiography are often used to assist the physician in visualizing the blood vessel structures, guide wires, or catheters, localizing bifurcations, estimating severity of a lesion, or observing the blood flow. Computational algorithms often need to process differently to frames with or without contrast medium. In order to automate this process and streamline the clinical workflow, a fully automatic contrast inflow detection algorithm is proposed. The robustness of the algorithm is validated by more than 1300 real fluoroscopic scenes. The algorithm is computationally efficient; a sequence with 100 frames can be processed within a second.

Fast Prospective Detection of Contrast Inflow in X-ray Angiograms with Convolutional Neural Network and Recurrent Neural Network

“…The contrastenhanced frames are then detected via analysis of the feature. Learning-based approaches [8,9] train a classifier to detect contrast or non-contrast frames based on handcrafted image features. Among these works, [4,6,8] need an entire sequence to detect contrast inflow, and thus only work retrospectively.…”

“…Learning-based approaches [8,9] train a classifier to detect contrast or non-contrast frames based on handcrafted image features. Among these works, [4,6,8] need an entire sequence to detect contrast inflow, and thus only work retrospectively. [5] does not rely on a complete sequence, but retrospectively runs on a sliding segment of a few new X-ray frames, thus there is a trade-off between the possible delay of the contrast inflow detection and the overall processing efficiency.…”

“…To the best of our knowledge, this is the first work that applies deep learning for contrast inflow detection in X-ray images. To validate the detection, the position of the beginning contrast frame (BCF) [8,9] in a sequence (where contrast starts being visible) was used in the experiment.…”

Integrated spatiotemporal analysis for automatic contrast agent inflow detection on angiography and fluoroscopy during transcatheter aortic valve implantation

“…Unfortunately, there is scarce literature addressing the problem of detecting contrast agent inflow on x-ray images, mainly from two research groups. 8,9 In the first method, Condurache et al 8 proposed to use the 98th percentile of image histograms as the feature for contrast agent inflow detection. However, this simple threshold can vary significantly due to a variety of factors, including varying backgrounds, different xray radiation dose, or changes in the volume and density of the injected contrast agent.…”

“…Recently, a second learning-based method was proposed to detect contrast media injection into the coronary artery. 9 This method focuses on the vessel structures, and, more specifically, the region around the coronary artery ostia, which make it difficult to extend to TAVI applications due to the lack of a prominent feature such as the "vesselness measure" as the basis for training.…”