MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography

TL;DR

MInDI-3D is a novel 3D diffusion-based model that effectively reduces artifacts in sparse-view CBCT scans, enabling lower radiation doses while maintaining clinical image quality.

Contribution

This work extends the InDI concept to 3D, introduces a large pseudo-CBCT dataset for training, and demonstrates superior artifact removal and generalisation in real-world clinical settings.

Findings

Achieves nearly 13 dB PSNR gain over uncorrected scans.

Enables 8x reduction in radiation exposure.

Matches 3D U-Net performance on real-world data.

Abstract

We present MInDI-3D (Medical Inversion by Direct Iteration in 3D), the first 3D conditional diffusion-based model for real-world sparse-view Cone Beam Computed Tomography (CBCT) artefact removal, aiming to reduce imaging radiation exposure. A key contribution is extending the "InDI" concept from 2D to a full 3D volumetric approach for medical images, implementing an iterative denoising process that refines the CBCT volume directly from sparse-view input. A further contribution is the generation of a large pseudo-CBCT dataset (16,182) from chest CT volumes of the CT-RATE public dataset to robustly train MInDI-3D. We performed a comprehensive evaluation, including quantitative metrics, scalability analysis, generalisation tests, and a clinical assessment by 11 clinicians. Our results show MInDI-3D's effectiveness, achieving a 12.96 (6.10) dB PSNR gain over uncorrected scans with only 50 projections on the CT-RATE pseudo-CBCT (independent real-world) test set and enabling an 8x reduction in imaging radiation exposure. We demonstrate its scalability by showing that performance improves with more training data. Importantly, MInDI-3D matches the performance of a 3D U-Net on real-world scans from 16 cancer patients across distortion and task-based metrics. It also generalises to new CBCT scanner geometries. Clinicians rated our model as sufficient for patient positioning across all anatomical sites and found it preserved lung tumour boundaries well.