Novel deep learning method for coronary artery tortuosity detection through coronary angiography
Abstract Coronary artery tortuosity is usually an undetected condition in patients undergoing coronary angiography. This condition requires a longer examination by the specialist to be detected. Yet, detailed knowledge of the morphology of coronary arteries is essential for planning any intervention...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-37868-6 |
| _version_ | 1827875561386541056 |
|---|---|
| author | Miriam Cobo Francisco Pérez-Rojas Constanza Gutiérrez-Rodríguez Ignacio Heredia Patricio Maragaño-Lizama Francisca Yung-Manriquez Lara Lloret Iglesias José A. Vega |
| author_facet | Miriam Cobo Francisco Pérez-Rojas Constanza Gutiérrez-Rodríguez Ignacio Heredia Patricio Maragaño-Lizama Francisca Yung-Manriquez Lara Lloret Iglesias José A. Vega |
| author_sort | Miriam Cobo |
| collection | DOAJ |
| description | Abstract Coronary artery tortuosity is usually an undetected condition in patients undergoing coronary angiography. This condition requires a longer examination by the specialist to be detected. Yet, detailed knowledge of the morphology of coronary arteries is essential for planning any interventional treatment, such as stenting. We aimed to analyze coronary artery tortuosity in coronary angiography with artificial intelligence techniques to develop an algorithm capable of automatically detecting this condition in patients. This work uses deep learning techniques, in particular, convolutional neural networks, to classify patients into tortuous or non-tortuous based on their coronary angiography. The developed model was trained both on left (Spider) and right (45°/0°) coronary angiographies following a fivefold cross-validation procedure. A total of 658 coronary angiographies were included. Experimental results demonstrated satisfactory performance of our image-based tortuosity detection system, with a test accuracy of (87 ± 6)%. The deep learning model had a mean area under the curve of 0.96 ± 0.03 over the test sets. The sensitivity, specificity, positive predictive values, and negative predictive values of the model for detecting coronary artery tortuosity were (87 ± 10)%, (88 ± 10)%, (89 ± 8)%, and (88 ± 9)%, respectively. Deep learning convolutional neural networks were found to have comparable sensitivity and specificity with independent experts’ radiological visual examination for detecting coronary artery tortuosity for a conservative threshold of 0.5. These findings have promising applications in the field of cardiology and medical imaging. |
| first_indexed | 2024-03-12T17:08:40Z |
| format | Article |
| id | doaj.art-d815f88031a845559e63f62c243dcf3a |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-12T17:08:40Z |
| publishDate | 2023-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-d815f88031a845559e63f62c243dcf3a2023-08-06T11:14:41ZengNature PortfolioScientific Reports2045-23222023-07-011311810.1038/s41598-023-37868-6Novel deep learning method for coronary artery tortuosity detection through coronary angiographyMiriam Cobo0Francisco Pérez-Rojas1Constanza Gutiérrez-Rodríguez2Ignacio Heredia3Patricio Maragaño-Lizama4Francisca Yung-Manriquez5Lara Lloret Iglesias6José A. Vega7Advanced Computing and e-Science Research Group, Institute of Physics of Cantabria (IFCA), CSIC - UCFacultad de Medicina, Universidad Católica del MauleFacultad de Ciencias de la Salud, Universidad Autónoma de ChileAdvanced Computing and e-Science Research Group, Institute of Physics of Cantabria (IFCA), CSIC - UCDepartment of Hemodynamics, Talca Regional HospitalFacultad de Ciencias de la Salud, Universidad Autónoma de ChileAdvanced Computing and e-Science Research Group, Institute of Physics of Cantabria (IFCA), CSIC - UCDepartamento de Morfología y Biología Celular, Grupo de Investigación SINPOS, Universidad de OviedoAbstract Coronary artery tortuosity is usually an undetected condition in patients undergoing coronary angiography. This condition requires a longer examination by the specialist to be detected. Yet, detailed knowledge of the morphology of coronary arteries is essential for planning any interventional treatment, such as stenting. We aimed to analyze coronary artery tortuosity in coronary angiography with artificial intelligence techniques to develop an algorithm capable of automatically detecting this condition in patients. This work uses deep learning techniques, in particular, convolutional neural networks, to classify patients into tortuous or non-tortuous based on their coronary angiography. The developed model was trained both on left (Spider) and right (45°/0°) coronary angiographies following a fivefold cross-validation procedure. A total of 658 coronary angiographies were included. Experimental results demonstrated satisfactory performance of our image-based tortuosity detection system, with a test accuracy of (87 ± 6)%. The deep learning model had a mean area under the curve of 0.96 ± 0.03 over the test sets. The sensitivity, specificity, positive predictive values, and negative predictive values of the model for detecting coronary artery tortuosity were (87 ± 10)%, (88 ± 10)%, (89 ± 8)%, and (88 ± 9)%, respectively. Deep learning convolutional neural networks were found to have comparable sensitivity and specificity with independent experts’ radiological visual examination for detecting coronary artery tortuosity for a conservative threshold of 0.5. These findings have promising applications in the field of cardiology and medical imaging.https://doi.org/10.1038/s41598-023-37868-6 |
| spellingShingle | Miriam Cobo Francisco Pérez-Rojas Constanza Gutiérrez-Rodríguez Ignacio Heredia Patricio Maragaño-Lizama Francisca Yung-Manriquez Lara Lloret Iglesias José A. Vega Novel deep learning method for coronary artery tortuosity detection through coronary angiography Scientific Reports |
| title | Novel deep learning method for coronary artery tortuosity detection through coronary angiography |
| title_full | Novel deep learning method for coronary artery tortuosity detection through coronary angiography |
| title_fullStr | Novel deep learning method for coronary artery tortuosity detection through coronary angiography |
| title_full_unstemmed | Novel deep learning method for coronary artery tortuosity detection through coronary angiography |
| title_short | Novel deep learning method for coronary artery tortuosity detection through coronary angiography |
| title_sort | novel deep learning method for coronary artery tortuosity detection through coronary angiography |
| url | https://doi.org/10.1038/s41598-023-37868-6 |
| work_keys_str_mv | AT miriamcobo noveldeeplearningmethodforcoronaryarterytortuositydetectionthroughcoronaryangiography AT franciscoperezrojas noveldeeplearningmethodforcoronaryarterytortuositydetectionthroughcoronaryangiography AT constanzagutierrezrodriguez noveldeeplearningmethodforcoronaryarterytortuositydetectionthroughcoronaryangiography AT ignacioheredia noveldeeplearningmethodforcoronaryarterytortuositydetectionthroughcoronaryangiography AT patriciomaraganolizama noveldeeplearningmethodforcoronaryarterytortuositydetectionthroughcoronaryangiography AT franciscayungmanriquez noveldeeplearningmethodforcoronaryarterytortuositydetectionthroughcoronaryangiography AT laralloretiglesias noveldeeplearningmethodforcoronaryarterytortuositydetectionthroughcoronaryangiography AT joseavega noveldeeplearningmethodforcoronaryarterytortuositydetectionthroughcoronaryangiography |