A universal medical imaging modality translation model in brain and head-and-neck radiotherapy.

Authors

Abstract

We developed a universal image translation model-Translate Any Modality (TAM) model to synthesize MRI sequences and CT for brain and head-and-neck radiotherapy, facilitating downstream clinical tasks including multimodal registration and treatment dose calculation. We retrospectively curated multi-modal imaging from 90 patients (43 brain, and 47 head-and-neck), each with up to eight MRI sequences and a paired CT. TAM uses a two-stage translation strategy: a 3D U-Net to firstly segment soft tissues and bones to serve as anatomical anchors; and a conditional diffusion model, guided by these masks, to synthesize the target modality from any available input modalities. We evaluated 46 MRI-to-MRI and MRI-to-CT translation tasks against two comparison methods, CycleGAN and UNIT, using Frechet Inception Distance (FID), peak signal-to-noise-ratio (PSNR), structural similarity index (SSIM), and Hounsfield unit (HU)-based mean absolute error (MAE). Clinical relevance was tested via multi-modality registration with simulated B-spline deformations and dose calculation using clinical plans with Gamma criteria 1 %/1 mm and 2 %/2 mm. TAM improved image quality (PSNR 30.0 ± 3.7; SSIM 0.973 ± 0.024) versus UNIT (27.0 ± 3.2; 0.958 ± 0.026) and CycleGAN (25.4 ± 4.1; 0.949 ± 0.037). For synthesized CT, TAM-based CT achieved average Gamma indices of 99.1 ± 1.7 % (2 %/2 mm) and 94.1 ± 6.4 % (1 %/1 mm) versus CycleGAN 93.1 ± 7.5 %/84.0 ± 9.5 % and UNIT 93.8 ± 7.0 %/86.3 ± 9.4 %, with dose-volume histograms closely matching real-CT plans. TAM is a novel any-to-any medical image modality translation model. It provides flexible, anatomically faithful translation among MRI sequences and CT, which subsequently improves the accuracy of downstream tasks, including registration and dose calculation.

Tags

Topics