Accurate Patient Alignment without Unnecessary Imaging Dose via Synthesizing Patient-specific 3D CT Images from 2D kV Images

TL;DR

This paper introduces a real-time deep learning framework that synthesizes accurate 3D CT images from 2D kV images, improving patient alignment in radiotherapy while reducing unnecessary imaging dose.

Contribution

It presents a dual-model hierarchical ViT-based framework capable of generating full 3D CT from a single 2D kV image in real time, which is a significant advancement over previous proof-of-concept methods.

Findings

Achieved MAE of less than 45 HU in synthesized CT images.

Gamma passing rate over 97% for dosimetric accuracy.

Shift error less than 0.4 mm in patient positioning.

Abstract

In radiotherapy, 2D orthogonally projected kV images are used for patient alignment when 3D-on-board imaging(OBI) unavailable. But tumor visibility is constrained due to the projection of patient's anatomy onto a 2D plane, potentially leading to substantial setup errors. In treatment room with 3D-OBI such as cone beam CT(CBCT), the field of view(FOV) of CBCT is limited with unnecessarily high imaging dose, thus unfavorable for pediatric patients. A solution to this dilemma is to reconstruct 3D CT from kV images obtained at the treatment position. Here, we propose a dual-models framework built with hierarchical ViT blocks. Unlike a proof-of-concept approach, our framework considers kV images as the solo input and can synthesize accurate, full-size 3D CT in real time(within milliseconds). We demonstrate the feasibility of the proposed approach on 10 patients with head and neck (H&N) cancer using image quality(MAE: <45HU), dosimetrical accuracy(Gamma passing rate (2%/2mm/10%)>97%) and patient position uncertainty(shift error: <0.4mm). The proposed framework can generate accurate 3D CT faithfully mirroring real-time patient position, thus significantly improving patient setup accuracy, keeping imaging dose minimum, and maintaining treatment veracity.