Deep Learning-Based Automatic Delineation of Liver Domes in kV Triggered Images for Online Breath-hold Reproducibility Verification of Liver Stereotactic Body Radiation Therapy

TL;DR

This study introduces a deep learning pipeline using U-Net to automatically delineate liver domes in kV images, enabling rapid online breath-hold verification in liver SBRT with high accuracy and efficiency.

Contribution

We developed and validated a deep learning-based method for automatic liver dome delineation in kV images, improving speed and accuracy for breath-hold reproducibility verification in liver SBRT.

Findings

U-Net segmentation trained in under 30 minutes

Automatic delineation takes less than one second per image

Achieved RMSE of 6.4-7.7 mm and detection rates over 76%

Abstract

Stereotactic Body Radiation Therapy (SBRT) can be a precise, minimally invasive treatment method for liver cancer and liver metastases. However, the effectiveness of SBRT relies on the accurate delivery of the dose to the tumor while sparing healthy tissue. Challenges persist in ensuring breath-hold reproducibility, with current methods often requiring manual verification of liver dome positions from kV-triggered images. To address this, we propose a proof-of-principle study of a deep learning-based pipeline to automatically delineate the liver dome from kV-planar images. From 24 patients who received SBRT for liver cancer or metastasis inside liver, 711 KV-triggered images acquired for online breath-hold verification were included in the current study. We developed a pipeline comprising a trained U-Net for automatic liver dome region segmentation from the triggered images followed by extraction of the liver dome via thresholding, edge detection, and morphological operations. The performance and generalizability of the pipeline was evaluated using 2-fold cross validation. The training of the U-Net model for liver region segmentation took under 30 minutes and the automatic delineation of a liver dome for any triggered image took less than one second. The RMSE and rate of detection for Fold1 with 366 images was (6.4 +/- 1.6) mm and 91.7%, respectively. For Fold2 with 345 images, the RMSE and rate of detection was (7.7 +/- 2.3) mm and 76.3% respectively.