A deep learning model to reduce agent dose for contrast-enhanced MRI of the cerebellopontine angle cistern

2025-11-25

AI Summary

Excessive contrast agent administration in contrast-enhanced MRI of the cerebellopontine angle cistern poses safety risks and necessitates dose reduction. Method: We propose a deep learning–based low-dose image reconstruction framework, trained on multicenter retrospective T1-weighted contrast-enhanced (T1ce) MRI data. A synthetic low-dose dataset (10%–30% of standard dose) was generated to train an end-to-end network that reconstructs high-fidelity standard-dose images from ultra-low-dose inputs. Contribution/Results: At 10% dose, our method achieves a structural similarity index of 0.639, improves tumor segmentation Dice score to 0.734, and reduces mean surface distance to 0.59 mm—while preserving diagnostic accuracy. Blinded radiologist evaluation confirms excellent image quality and clinically sufficient lesion detectability. This is the first study to enable reliable contrast-enhanced imaging and precise tumor segmentation in the cerebellopontine angle cistern at an ultra-low dose (10%), establishing a generalizable technical pathway for safer, more efficient neuroimaging.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Objectives: To evaluate a deep learning (DL) model for reducing the agent dose of contrast-enhanced T1-weighted MRI (T1ce) of the cerebellopontine angle (CPA) cistern. Materials and methods: In this multi-center retrospective study, T1 and T1ce of vestibular schwannoma (VS) patients were used to simulate low-dose T1ce with varying reductions of contrast agent dose. DL models were trained to restore standard-dose T1ce from the low-dose simulation. The image quality and segmentation performance of the DL-restored T1ce were evaluated. A head and neck radiologist was asked to rate DL-restored images in multiple aspects, including image quality and diagnostic characterization. Results: 203 MRI studies from 72 VS patients (mean age, 58.51 pm 14.73, 39 men) were evaluated. As the input dose increased, the structural similarity index measure of the restored T1ce increased from 0.639 pm 0.113 to 0.993 pm 0.009, and the peak signal-to-noise ratio increased from 21.6 pm 3.73 dB to 41.4 pm 4.84 dB. At 10% input dose, using DL-restored T1ce for segmentation improved the Dice from 0.673 to 0.734, the 95% Hausdorff distance from 2.38 mm to 2.07 mm, and the average surface distance from 1.00 mm to 0.59 mm. Both DL-restored T1ce from 10% and 30% input doses showed excellent images, with the latter being considered more informative. Conclusion: The DL model improved the image quality of low-dose MRI of the CPA cistern, which makes lesion detection and diagnostic characterization possible with 10% - 30% of the standard dose.

Problem

• Reducing contrast agent dose for cerebellopontine angle MRI using deep learning
• Restoring standard-dose image quality from low-dose contrast-enhanced MRI scans
• Enabling lesion detection with 10-30% of standard contrast agent dosage

Innovation

• Deep learning model reduces contrast agent dose for MRI
• Simulated low-dose images restored to standard-dose quality
• Improved image quality enables lesion detection with minimal dose