# Deep-learning-based sampling position selection on color Doppler sonography images during renal artery ultrasound scanning

## TL;DR

This study explores using deep learning to help select accurate sampling positions in renal artery ultrasound scans, showing promising results for improving accuracy.

## Contribution

The study introduces and evaluates deep learning object detection models for sampling position selection in renal artery ultrasound imaging.

## Key findings

- The Double Head R-CNN model achieved the highest average accuracies of 89.3 ± 0.6% and 88.5 ± 0.3% on parameter optimization and validation datasets.
- The model's predictive accuracy for all four types of CDS images was significantly higher than other methods on clinical validation data.
- DL object detection models can assist inexperienced physicians in improving sampling position selection accuracy during renal artery ultrasound.

## Abstract

Accurate selection of sampling positions is critical in renal artery ultrasound examinations, and the potential of utilizing deep learning (DL) for assisting in this selection has not been previously evaluated. This study aimed to evaluate the effectiveness of DL object detection technology applied to color Doppler sonography (CDS) images in assisting sampling position selection. A total of 2004 patients who underwent renal artery ultrasound examinations were included in the study. CDS images from these patients were categorized into four groups based on the scanning position: abdominal aorta (AO), normal renal artery (NRA), renal artery stenosis (RAS), and intrarenal interlobular artery (IRA). Seven object detection models, including three two-stage models (Faster R-CNN, Cascade R-CNN, and Double Head R-CNN) and four one-stage models (RetinaNet, YOLOv3, FoveaBox, and Deformable DETR), were trained to predict the sampling position, and their predictive accuracies were compared. The Double Head R-CNN model exhibited significantly higher average accuracies on both parameter optimization and validation datasets (89.3 ± 0.6% and 88.5 ± 0.3%, respectively) compared to other methods. On clinical validation data, the predictive accuracies of the Double Head R-CNN model for all four types of images were significantly higher than those of the other methods. The DL object detection model shows promise in assisting inexperienced physicians in improving the accuracy of sampling position selection during renal artery ultrasound examinations.