# A bias field correction workflow based on generative adversarial network for abdominal cancers treated with 0.35T MR‐LINAC

## TL;DR

This paper introduces a new workflow using GANs to correct bias field artifacts in MRI images for abdominal cancer patients treated with a 0.35T MR-LINAC system, improving image quality and segmentation accuracy.

## Contribution

The novel workflow enhances GAN-based bias field correction for 0.35T MR-LINAC abdominal cancer imaging, improving generalizability and segmentation performance.

## Key findings

- The proposed workflow outperformed GAN and N4ITK in bias field correction with lower RMSE and higher PSNR and SSIM values.
- Segmentation accuracy improved for fat and soft tissue masks using the proposed workflow compared to N4ITK.
- The workflow shows potential to enhance clinical utility for MRI-guided radiotherapy in abdominal cancers.

## Abstract

In this study, a bias field correction workflow was proposed to improve the flexibility and generalizability of the generative adversarial network (GAN) model for abdominal cancer patients treated with a 0.35T magnetic resonance imaging linear accelerator (MR‐LINAC) system.

Model training was performed using brain MR images acquired on a 3T diagnostic scanner, while model testing was performed using abdominal MR images obtained using a 0.35T MR‐LINAC system. The performance of the proposed workflow was first compared with the GAN model using root‐mean‐square error (RMSE), peak signal‐to‐noise ratio (PSNR), and structural similarity index measure (SSIM). To assess the impact of the workflow on image segmentation, it was also compared with the N4ITK algorithm. Segmentation was performed using the k‐means clustering algorithm with three clusters corresponding to air, fat, and soft tissue. Segmentation accuracy was then evaluated using the Dice similarity coefficient (DSC).

The RMSE values were 30.59, 12.06, 10.37 for the bias field‐corrupted images (IIN), GAN‐corrected images (IGAN), and images corrected with the proposed workflow (IOUT), respectively. Corresponding PSNR values were 42.34, 46.04, 47.04 dB, and SSIM values were 0.84, 0.96, 0.98. For segmentation accuracy, the mean DSC for air masks was 0.95, 0.97, and 0.97; for fat masks, 0.61, 0.71, and 0.74; and for soft tissue masks, 0.60, 0.68, and 0.69, corresponding to IIN, N4ITK‐corrected images (IN4ITK), and IOUT, respectively

By effectively mitigating bias field artifacts, the proposed workflow has the potential to strengthen the clinical utility of MRI‐guided adaptive radiotherapy for abdominal cancers, ensuring safer and more accurate radiation delivery.