Determining the scanning range of coronary computed tomography angiography based on deep learning

Area of Science:

• Radiology
• Artificial Intelligence
• Medical Imaging

Background:

• Coronary computed tomography angiography (CCTA) is vital for diagnosing coronary artery disease.
• Manual determination of CCTA scan ranges is time-consuming and lacks automation.

Purpose of the Study:

• To develop and validate a deep learning model for automated CCTA scan range determination.
• Utilize anteroposterior scout images for efficient scan range estimation.

Main Methods:

• Retrospective analysis of 1388 patient chest CT datasets.
• Training a deep learning model on annotated anteroposterior scout images.
• Dataset split into training, validation, and testing sets for rigorous evaluation.

Main Results:

• The deep learning model achieved high accuracy in determining CCTA scan ranges.
• Mean average precision (mAP50) of 0.995 and mAP50-95 of 0.994 on the test set.

Conclusions:

• Anteroposterior scout images are effective for estimating CCTA scan ranges.
• The developed method allows for dynamic adjustment of scan ranges to suit diverse medical settings.