The correlation of features in detecting cardiovascular vulnerable plaque
| Autor: | Al Fazir Omar, Daniel Baumgarten, Eko Supriyanto, Jens Haueisen, Nor Nisha Nadhira Nazirun, Christine Pohl |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
medicine.medical_specialty
Modality (human–computer interaction) business.industry medicine.medical_treatment Feature extraction Context (language use) 02 engineering and technology Image segmentation 030204 cardiovascular system & hematology medicine.disease medicine.disease_cause Vulnerable plaque 03 medical and health sciences Stenosis 0302 clinical medicine Angioplasty 0202 electrical engineering electronic engineering information engineering Medical imaging Medicine 020201 artificial intelligence & image processing Computer vision Artificial intelligence Radiology business |
| Zdroj: | 2016 International Conference on Robotics, Automation and Sciences (ICORAS). |
| Popis: | The combination of different medical modalities from single or multiple sensors produces higher reliability in diagnosis, pre-surgical planning and surgical intervention. Multimodal fusion is an option to exploit medical images in the context of coronary plaques detection. It is most sensible to detect the vulnerability of plaque as diseases related to it are among the leading cause of death. CTA and ICA were chosen as both modalities can visualize the blood vessel anatomically and functionally in the images, which were taken at a certain point in time and during the angioplasty intervention. The cross-sectional diameter of the blood vessel in an ICA was measured thus detecting vessel narrowing due to stenosis. Meanwhile, the high intensity pixels in CTA image, which indicated the calcification of plaque, were calculated after applying multilevel threshold. The severity of stenosis in ICA correlating to the pixel coverage in CTA was investigated. Compared to the diagnosis from one modality alone, the feature correlation delivered more information and consumes less time. The research results will support cardiologists by providing enhanced diagnosis capabilities of cardiovascular vulnerable plaques to improve the quality of data interpretation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|