ABSTRACT
The detection of the media-adventitia (MA) border in intravascular ultrasound (IVUS) images is essential for vessel assessment and disease diagnosis. However, it remains a challenging task, considering the existence of plaque, calcification, and various artifacts. In this article, an effective method based on classification is proposed to extract the MA border in IVUS images. First, a novel morphologic feature describing the relative position of each structure relative to the MA border, called RPES for short, is proposed. Then, the RPES feature and other features are employed in a multiclass extreme learning machine (ELM) to classify IVUS images into nine classes including the MA border and other structures. At last, a modified snake model is employed to effectively detect the MA border in the rectangular domain, in which a modified external force field is constructed on the basis of local border appearances and classification results. The proposed method is evaluated on a public dataset with 77 IVUS images by three indicators in eight situations, such as calcification and a guide wire artifact. With the proposed RPES feature, detection performances are improved by more than 39 percent, which shows an apparent advantage in comparative experiments. Furthermore, compared with two other existing methods used on the same dataset, the proposed method achieves 18 of the best indicators among 24, demonstrating its higher capability in detecting the MA border.
Subject(s)
Adventitia/diagnostic imaging , Coronary Vessels/diagnostic imaging , Tunica Media/diagnostic imaging , Ultrasonography, Interventional/classification , Ultrasonography, Interventional/methods , Artifacts , Datasets as Topic , Humans , Image Processing, Computer-Assisted , Machine Learning , Plaque, Atherosclerotic/diagnostic imaging , Vascular Calcification/diagnostic imagingSubject(s)
Cardiac Catheterization , Fractional Flow Reserve, Myocardial , Percutaneous Coronary Intervention , Terminology as Topic , Ultrasonography, Interventional , Cardiac Catheterization/classification , Clinical Competence , Curriculum , Education, Medical, Graduate , Humans , Learning Curve , Percutaneous Coronary Intervention/classification , Percutaneous Coronary Intervention/education , Predictive Value of Tests , Ultrasonography, Interventional/classificationABSTRACT
Our Bioengineering Research Partnership grant, -High Frequency Ultrasound Arrays for Cardiac Imaging", including the individuals cited at the end of this paper - Douglas N. Stephens (UC Davis), Matthew O'Donnell (UW Seattle), Kai Thomenius (GE Global Research), Aaron M. Dentinger (GE Global Research), Douglas Wildes (GE Global Research), Peter Chen (St. Jude Medical), K. Kirk Shung (University of Southern California), Jonathan M. Cannata (University of Southern California), Butrus (Pierre) T. Khuri-Yakub (Stanford University), Omer Oralkan (Stanford University), Aman Mahajan (UCLA School of Medicine), Kalyanam Shivkumar (UCLA School of Medicine) and David J. Sahn (Oregon Health & Science University) - is in its sixth year of NIH funding, having proposed to develop a family of high frequency miniaturized forward and side-looking ultrasound imaging devices equipped with electrophysiology mapping and localization sensors and eventually to include a family of capactive micromachined ultrasonic transducer (cMUT) devices - a forward-looking cMUT MicroLinear array and a ring array capable of 3-dimensional imaging and a 5Fr lumen large enough to admit an electrode and ablation devices.
Subject(s)
Atrial Fibrillation/diagnostic imaging , Cardiac Catheterization/methods , Ultrasonography, Interventional/classification , Adult , Aged , Animals , Atrial Fibrillation/epidemiology , Body Surface Potential Mapping/instrumentation , Cardiac Catheterization/instrumentation , Electrophysiologic Techniques, Cardiac , Equipment Design , Heart Atria/diagnostic imaging , Humans , Middle Aged , Models, Animal , Pulmonary Veins/diagnostic imaging , Swine , Ultrasonography, Interventional/instrumentation , United States/epidemiologySubject(s)
Current Procedural Terminology , Ultrasonography/classification , Vocabulary, Controlled , Diagnosis, Computer-Assisted/classification , Diagnosis, Differential , Echocardiography, Stress/classification , Expert Systems , Germany , Humans , Image Processing, Computer-Assisted/classification , Radiology Information Systems/classification , Ultrasonic Therapy/classification , Ultrasonography, Interventional/classification , Video Recording/classificationABSTRACT
Many Emergency Departments (ED) use emergency ultrasonography of the right upper quadrant (RUQ) to capture images of the gallbladder in patients with suspected gallstones. It is unclear what impact this practice has on additional imaging performed by radiology. Patients were enrolled 24 h a day by ED residents and attending physicians who have completed an educational program in limited RUQ ultrasound. All ultrasounds were videotaped and later reviewed. According to the American College of Emergency Physicians' credentialing standards, 25 ultrasounds were required before using the results clinically. A total of 352 patients were enrolled by 42 physicians over a 1-year period. Two hundred twelve (60.2%) of the ultrasounds were performed clinically, with the rest performed for teaching purposes. One hundred seventy-nine (50.9%) of the ultrasounds were performed by credentialed physicians. One hundred forty-nine (70%) clinical and 29 (20.7%) teaching ultrasounds had additional imaging. The average time to follow up imaging after discharge from the ED was 8.51 days. Most patients receiving emergency ultrasound of their RUQ had follow-up imaging by radiology.
