Deep learning method for aortic root detection
| Autor: | José M. Carreira, Rafael Varela, Pablo G. Tahoces |
|---|---|
| Přispěvatelé: | Universidade de Santiago de Compostela. Departamento de Electrónica e Computación |
| Rok vydání: | 2021 |
| Předmět: |
0301 basic medicine
Computed Tomography Angiography Computer science Aortic root Health Informatics 03 medical and health sciences Deep Learning 0302 clinical medicine medicine Segmentation Aorta Computed tomography angiography medicine.diagnostic_test Landmarks business.industry Deep learning Pattern recognition Computer Science Applications Computed tomography angiography (CTA) Anatomical landmark Detection 030104 developmental biology Test set Fully automatic Benchmark (computing) Artificial intelligence Tomography X-Ray Computed business 030217 neurology & neurosurgery Vascular imaging |
| Zdroj: | Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela instname Minerva: Repositorio Institucional de la Universidad de Santiago de Compostela Universidad de Santiago de Compostela (USC) |
| ISSN: | 0010-4825 |
| Popis: | Background: Computed tomography angiography (CTA) is a preferred imaging technique for a wide range of vascular diseases. However, extensive manual analysis is required to detect and identify several anatomical landmarks for clinical application. This study demonstrates the feasibility of a fully automatic method for detecting the aortic root, which is a key anatomical landmark in this type of procedure. The approach is based on the use of deep learning techniques that attempt to mimic expert behavior. Methods: A total of 69 CTA scans (39 for training and 30 for validation) with different pathology types were selected to train the network. Furthermore, a total of 71 CTA scans were selected independently and applied as the test set to assess their performance. Results: The accuracy was evaluated by comparing the locations marked by the method with benchmark locations (which were manually marked by two experts). The interobserver error was 4.6 ± 2.3 mm. On an average, the differences between the locations marked by the two experts and those detected by the computer were 6.6 ± 3.0 mm and 6.8 ± 3.3 mm, respectively, when calculated using the test set. Conclusions: From an analysis of these results, we can conclude that the proposed method based on pre-trained CNN models can accurately detect the aortic root in CTA images without prior segmentation This work was partially financed by Consellería de Cultura, Educación e Universidade (reference 2019–2021, ED431C 2018/19) SI |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect