# Radiation Dose Reduction and Image Quality Improvement of UHR CT of the Neck by Novel Deep-learning Image Reconstruction

## TL;DR

A new AI-based method improves image quality in ultra-high-resolution CT scans of the neck while significantly reducing radiation exposure.

## Contribution

A novel deep-learning reconstruction algorithm achieves superior image quality at reduced radiation doses for UHR CT of the neck.

## Key findings

- DL-2 significantly improved subjective and objective image quality compared to existing methods.
- Weight-adapted protocols enabled very low radiation doses (CTDIvol: 7.4 ± 4.2 mGy) without compromising image quality.
- DL-2 outperformed all other techniques across all evaluated parameters (p < 0.001).

## Abstract

We evaluated a dedicated dose-reduced UHR-CT for head and neck imaging, combined with a novel deep learning reconstruction algorithm to assess its impact on image quality and radiation exposure.

Retrospective analysis of ninety-eight consecutive patients examined using a new body weight-adapted protocol. Images were reconstructed using adaptive iterative dose reduction and advanced intelligent Clear-IQ engine with an already established (DL-1) and a newly implemented reconstruction algorithm (DL-2). Additional thirty patients were scanned without body-weight-adapted dose reduction (DL-1-SD). Three readers evaluated subjective image quality regarding image quality and assessment of several anatomic regions. For objective image quality, signal-to-noise ratio and contrast-to-noise ratio were calculated for temporalis and masseteric muscle and the floor of the mouth. Radiation dose was evaluated by comparing the computed tomography dose index (CTDIvol) values.

Deep learning-based reconstruction algorithms significantly improved subjective image quality (diagnostic acceptability: DL‑1 vs AIDR OR of 25.16 [6.30;38.85], p < 0.001 and DL‑2 vs AIDR 720.15 [410.14;> 999.99], p < 0.001). Although higher doses (DL-1-SD) resulted in significantly enhanced image quality, DL‑2 demonstrated significant superiority over all other techniques across all defined parameters (p < 0.001). Similar results were demonstrated for objective image quality, e.g. image noise (DL‑1 vs AIDR OR of 19.0 [11.56;31.24], p < 0.001 and DL‑2 vs AIDR > 999.9 [825.81;> 999.99], p < 0.001). Using weight-adapted kV reduction, very low radiation doses could be achieved (CTDIvol: 7.4 ± 4.2 mGy).

AI-based reconstruction algorithms in ultra-high resolution head and neck imaging provide excellent image quality while achieving very low radiation exposure.

The online version of this article (10.1007/s00062-025-01532-5) contains supplementary material, which is available to authorized users.