A novel automated lumen segmentation and classification algorithm for detection of irregular protrusion after stents deployment

Abstract

Background: Clinically, irregular protrusions and blockages after stent deployment can lead to significant adverse outcomes such as thrombotic reocclusion or restenosis. In this study, we propose a novel fully automated method for irregular lumen segmentation and normal/abnormal lumen classification. Methods:The proposed method consists of a lumen segmentation, feature extraction, and lumen classification. In total, 92 features were extracted to classify normal/abnormal lumen. The lumen classification method is a combination of supervised learning algorithm and feature selection that is a partition-membership filter method.Results: As the results, our proposed lumen segmentation method obtained the average of dice similarity coefficient (DSC) and the accuracy of proposed features and the random forest (RF) for normal/abnormal lumen classification as 97.6% and 98.2%, respectively.Conclusions: Therefore, we can lead to better understanding of the overall vascular status and help to determine cardiovascular diagnosis. K E Y W O R D S cardiac, cardiology, heart, image analysis, vascular surgery, vessel

Multi-object segmentation of anatomical layers in intravascular polarization-sensitive optical coherence tomography using convolutional neural networks

“…Such segments were included in our data set merely to train the model to ignore the ensuing artifacts. Notably, there exists a distinct class of models designed to detect stent struts and verify correct stent deployment [24], [32], [34]).…”

“…While other graphical models such as Markov random field [32] tackle the vessel wall segmentation problem from a similar point of view, the counterpart physics-based methods simulate the segmentation as a physical problem. For example, Olender et al [33] proposed a model based on mechanical deformation that mimics active contour models [34].…”

Automated Coronary Optical Coherence Tomography Feature Extraction with Application to Three-Dimensional Reconstruction

“…To improve the ability to classify and segment the lumen in difficult regions, such as stented arteries and bifurcations, machine learning approaches show significant potential. Yang et al, compared the performance of six classifiers (RF, SVM, J48, Bagging, Naïve Bayes and adaptive boosting (AdaBoost) [ 81 , 82 , 83 ]) in difficult or irregular regions [ 84 ]. By identifying and classifying 92 features from 54 patients and 14,207 images (1857 images denoted as irregular) through supervised learning and a partition-membership filtering method, the RF classifier produced the best overall accuracy compared to the other five classifiers: RF 98.2%, SVM 98.1%, J48 97.3%, Bagging 96.6%, Naïve Bayes 88.8%, AdaBoost 88.7%.…”

Bio-Inspired and Smart Nanoparticles for Triple Negative Breast Cancer Microenvironment

“…Zhai et al constructed a cytotoxic T lymphocyte (CTL)-inspired nanovesicle (MPV) with a methylene blue (MB) and cisplatin (Pt)-loaded gelatin nanogel core and a RBC vesicle (RV)-derived shell [42]. Applying MPV along with NIR irradiation was part of a combinatorial design to induce TNBC cell death by photochemotherapy with a chance of tumor photoacoustic imaging [42,43]. According to in vitro studies in 4T1 cells, MPV plus NIR irradiation displayed a significant accumulation in tumor cells, showing no MB accumulation in the absence of NIR treatment.…”