Capsule networks for segmentation of small intravascular ultrasound image datasets

Purpose Intravascular ultrasound (IVUS) imaging is crucial for planning and performing percutaneous coronary interventions. Automatic segmentation of lumen and vessel wall in IVUS images can thus help streamlining the clinical workflow. State-of-the-art results in image segmentation are achieved with data-driven methods like convolutional neural networks (CNNs). These need large amounts of training data to perform sufficiently well but medical image datasets are often rather small. A possibility to overcome this problem is exploiting alternative network architectures like capsule networks. Methods We systematically investigated different capsule network architecture variants and optimized the performance on IVUS image segmentation. We then compared our capsule network with corresponding CNNs under varying amounts of training images and network parameters. Results Contrary to previous works, our capsule network performs best when doubling the number of capsule types after each downsampling stage, analogous to typical increase rates of feature maps in CNNs. Maximum improvements compared to the baseline CNNs are 20.6% in terms of the Dice coefficient and 87.2% in terms of the average Hausdorff distance. Conclusion Capsule networks are promising candidates when it comes to segmentation of small IVUS image datasets. We therefore assume that this also holds for ultrasound images in general. A reasonable next step would be the investigation of capsule networks for few- or even single-shot learning tasks.

Calcification detection for intravascular ultrasound image using direct acyclic graph architecture: pre-trained model for 1-channel image

Coronary artery calcification is a calcium buildup within the walls of the arteries. It is considered a predominant marker for coronary artery disease. Thus many approaches have been developed for the automatic detection of calcification. The previous calcification detection was on segmentation of other structures as pre-processing steps or using the fact that the calcification often appears as a bright region. In this paper, an automated system proposed using a deep learning approach to detect the calcification absence and calcification presence in coronary artery IVUS image. A useful advantage of deep learning, compared to other methods is, it uses representations and features directly from the raw data, bypassing the need to manually extract features, a common that required in the traditional machine learning framework. The type of deep learning architecture used is 27 layers of convolutional neural networks (CNNs) using Direct Acyclic Graph. The proposed system used 2175 images and achieved an accuracy of 98.16% for Cartesian coordinate images and 99.08% for Polar Reconstructed Coordinate images.

Performance Assessment of K-Means and KNN Algorithm for the Detection of Borders and Extraction of Plaque Area from IVUS Images

The coronary artery vascular disease of atherosclerosis, which made the blood vessel artery wall harden and narrow. The vascular wall disease quantitatively analyzed and diagnosed by an intravascular ultrasound (IVUS) image. The quantitative investigations of coronary atherosclerosis by means of IVUS and manual recognition of wall and plaque borders are restricted by the need for observers with considerable understanding and the tedious environment of manual border detection. To improve and provide more detailed vessel and plaque information for better diagnosis and assessment go for an automated segmentation. An automated construction for the purpose of perceiving lumen and media-adventitia borders in IVUS images was effectively formulated. An effectual unsupervised K-Means clustering scheme refine the borders with morphological operations, later an IVUS data samples area classified using supervised KNN(K-Nearest Neighbor) classifier to extract the plaque feature. The performance of contour metric measurements in terms of Jaccard Index (JI), percentage area difference (PAD), area error (AE), dice index (DI), false positive ratio (RFP), in addition to false negative ratio (RFN) are computed for evaluation and variation.

IVUS Image Segmentation Using Superpixel-Wise Fuzzy Clustering and Level Set Evolution

Reliable detection of the media-adventitia border (MAB) and the lumen-intima border (LIB) in intravascular ultrasound (IVUS) images remains a challenging task that is of high clinical interest. In this paper, we propose a superpixel-wise fuzzy clustering technique modified by edges, followed by level set evolution (SFCME-LSE), for automatic border extraction in 40 MHz IVUS images. The contributions are three-fold. First, the usage of superpixels suppresses the influence of speckle noise in ultrasound images on the clustering results. Second, we propose a region of interest (ROI) assignment scheme to prevent the segmentation from being distracted by pathological structures and artifacts. Finally, the contour is converged towards the target boundary through LSE with an appropriately improved edge indicator. Quantitative evaluations on two IVUS datasets by the Jaccard measure (JM), the percentage of area difference (PAD), and the Hausdorff distance (HD) demonstrate the effectiveness of the proposed SFCME-LSE method. SFCME-LSE achieves the minimal HD of 1.20 ± 0.66 mm and 1.18 ± 0.70 mm for the MAB and LIB, respectively, among several state-of-the-art methods on a publicly available dataset.

Automatic Thin Cap Fibroatheroma Detection Using Fusion of Intravascular Ultrasound and Virtual Histology Images

Virtual Histology- Intravascular Ultrasound (VH-IVUS) image is an available method for visualizing plaque component to detect thin cap fibroatheroma. Nevertheless, this imaging modality has considerable limitations to extract the plaque component features and identifying the TCFA plaque. The aim of this paper is to improve the identification of TCFA using fusion of IVUS and VH-IVUS images. In order to generate the automatic technique for reducing the human interaction, a new method namely Active Contour based Plaque Border Detection (ACPB) is proposed. In order to perform the pixel wise classification, hybrid of K-means algorithm with Particle Swarm Optimization and Plaque based Minimum Euclidean Distance (KMPSO-PMED) method is presented to classify the plaque region as well. Moreover, to obtain more significant information of imaging modalities, fusion of two different images consisting of VH-IVUS and IVUS is performed. Therefore, geometric features are extracted from the plaque region and combine with IVUS features. Furthermore, different group of plaque features are divided by means of the histopathological studies. SVM classifiers is applied to detect the TCFA and non-TCFA plaques. The proposed method is applied on 566 in-vivo IVUS and their matching VH-IVUS images obtained from 9 patients. The best result of SVM illustrates the accuracy rates of 99.41% for classification of TCFA plaque. The results prove that the highest accuracy is achieved by integrated features of IVUS and VH-IVUS images.

Reconstruction of Intima and Adventitia Models into a State Undeformed by a Catheter by Using CT, IVUS, and Biplane X-Ray Angiogram Images

The number of studies on blood flow analysis using fluid-structure interaction (FSI) analysis is increasing. Though a 3D blood vessel model that includes intima and adventitia is required for FSI analysis, there are difficulties in generating it using only one type of medical imaging. In this paper, we propose a 3D modeling method for accurate FSI analysis. An intravascular ultrasound (IVUS) image is used with biplane X-ray angiogram images to calculate the position and orientation of the blood vessel. However, these images show that the blood vessel is deformed by the catheter inserted into the blood vessel for IVUS imaging. To eliminate such deformation, a CT image was added and the two models were registered. First, a 3D model of the undeformed intima was generated using a CT image. In the second stage, a model of intima and adventitia deformed by the catheter was generated by combining the IVUS image and the X-ray angiogram images. A 3D model of intima and adventitia with the deformation caused by insertion of the catheter eliminated was generated by matching these 3D blood vessel models in different states. In addition, a 3D blood vessel model including bifurcation was generated using the proposed method.

A Case of Cystic Adventitial Degeneration of the Left Popliteal Artery Diagnosed by Intravascular Ultrasound

An 87-year-old male was admitted with intermittent claudication of the left calf. We performed lower extremity angiography, which revealed stenosis of the left popliteal artery. Intravascular ultrasound (IVUS) image correctly identified the cystic appearance of visualized extravascular hypodensity, causing extrinsic compression of the lumen. We diagnosed the condition as cystic adventitial degeneration (CAD) of the popliteal artery. We operated a resection of a cyst with the artery and replaced the autovein graft (saphenous vein). After surgery, the patient was free of symptoms. CAD is a rare disease; thus, our IVUS findings may provide unique diagnostic clues in patients with CAD.