ARTInp: CBCT-to-CT Image Inpainting and Image Translation in Radiotherapy

2025-02-07

AI Summary

In adaptive radiotherapy (ART), low-resolution cone-beam CT (CBCT) images with severe artifacts and anatomical discontinuities—particularly in total marrow/lymphoid irradiation (TMLI)—compromise dose verification reliability. To address this, we propose a dual-network collaborative framework: a coupled U-Net for CBCT volume completion and a customized generative adversarial network (GAN) for cross-modal CT synthesis. This is the first end-to-end solution enabling simultaneous CBCT void filling and high-fidelity synthetic CT generation specifically for whole-body radiotherapy scenarios like TMLI. Trained on the SynthRad 2023 paired dataset, our method achieves a 3.2 dB PSNR improvement and a 0.08 SSIM gain over baseline methods on an independent test set of 18 patients. The resulting synthetic CTs significantly enhance anatomical fidelity and dose calculation accuracy in CBCT-based ART, thereby improving treatment adaptation confidence and dosimetric reliability.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

A key step in Adaptive Radiation Therapy (ART) workflows is the evaluation of the patient's anatomy at treatment time to ensure the accuracy of the delivery. To this end, Cone Beam Computerized Tomography (CBCT) is widely used being cost-effective and easy to integrate into the treatment process. Nonetheless, CBCT images have lower resolution and more artifacts than CT scans, making them less reliable for precise treatment validation. Moreover, in complex treatments such as Total Marrow and Lymph Node Irradiation (TMLI), where full-body visualization of the patient is critical for accurate dose delivery, the CBCT images are often discontinuous, leaving gaps that could contain relevant anatomical information. To address these limitations, we propose ARTInp (Adaptive Radiation Therapy Inpainting), a novel deep-learning framework combining image inpainting and CBCT-to-CT translation. ARTInp employs a dual-network approach: a completion network that fills anatomical gaps in CBCT volumes and a custom Generative Adversarial Network (GAN) to generate high-quality synthetic CT (sCT) images. We trained ARTInp on a dataset of paired CBCT and CT images from the SynthRad 2023 challenge, and the performance achieved on a test set of 18 patients demonstrates its potential for enhancing CBCT-based workflows in radiotherapy.

Problem

• Improves CBCT image quality
• Fills anatomical gaps in CBCT
• Generates synthetic CT from CBCT

Innovation

• Deep-learning CBCT-to-CT translation
• Dual-network for image inpainting
• Generative Adversarial Network for sCT