Contrast enhancement in cerebral adrenoleukodystrophy: a comparison of T1 TSE and MPRAGE sequences

Performance Test of a Well-Trained Model for Meningioma Segmentation in Health Care Centers: Secondary Analysis Based on Four Retrospective Multicenter Data Sets

BACKGROUND

Convolutional neural networks (CNNs) have produced state-of-the-art results in meningioma segmentation on magnetic resonance imaging (MRI). However, images obtained from different institutions, protocols, or scanners may show significant domain shift, leading to performance degradation and challenging model deployment in real clinical scenarios.

OBJECTIVE

This research aims to investigate the realistic performance of a well-trained meningioma segmentation model when deployed across different health care centers and verify the methods to enhance its generalization.

METHODS

This study was performed in four centers. A total of 606 patients with 606 MRIs were enrolled between January 2015 and December 2021. Manual segmentations, determined through consensus readings by neuroradiologists, were used as the ground truth mask. The model was previously trained using a standard supervised CNN called Deeplab V3+ and was deployed and tested separately in four health care centers. To determine the appropriate approach to mitigating the observed performance degradation, two methods were used: unsupervised domain adaptation and supervised retraining.

RESULTS

The trained model showed a state-of-the-art performance in tumor segmentation in two health care institutions, with a Dice ratio of 0.887 (SD 0.108, 95% CI 0.903-0.925) in center A and a Dice ratio of 0.874 (SD 0.800, 95% CI 0.854-0.894) in center B. Whereas in the other health care institutions, the performance declined, with Dice ratios of 0.631 (SD 0.157, 95% CI 0.556-0.707) in center C and 0.649 (SD 0.187, 95% CI 0.566-0.732) in center D, as they obtained the MRI using different scanning protocols. The unsupervised domain adaptation showed a significant improvement in performance scores, with Dice ratios of 0.842 (SD 0.073, 95% CI 0.820-0.864) in center C and 0.855 (SD 0.097, 95% CI 0.826-0.886) in center D. Nonetheless, it did not overperform the supervised retraining, which achieved Dice ratios of 0.899 (SD 0.026, 95% CI 0.889-0.906) in center C and 0.886 (SD 0.046, 95% CI 0.870-0.903) in center D.

CONCLUSIONS

Deploying the trained CNN model in different health care institutions may show significant performance degradation due to the domain shift of MRIs. Under this circumstance, the use of unsupervised domain adaptation or supervised retraining should be considered, taking into account the balance between clinical requirements, model performance, and the size of the available data.

Interval between contrast administration and T1-weighted MRI for cerebral adrenoleukodystrophy: a single-case observation

In adrenoleukodystrophy (ALD), contrast enhancement (CE) is a disease activity marker, but there is uncertainty about the optimal delay, if any, between contrast injection and magnetic resonance imaging (MRI) acquisition to avoid false-negative results. We acquired axial two-dimensional (2D) and three-dimensional (3D) T1-weighted gradient-echo every 6 min from 0 to 36 min after contrast administration (gadobutrol 0.1 mmol/kg) in an ALD patient with enlarging white matter lesions and progressive neuropsychological symptoms, using a 3-T magnet. The image signal over time was qualitatively assessed and measured in two regions of interest. On 3D sequences, no definite CE was appreciated, whereas on 2D sequences, CE was noticed after 6 min and definitely evident after 12 min, when 73% of the maximum signal intensity was measured. In ALD subjects, contrast-enhanced 2D T1-weighted gradient-echo sequences acquired at least 10 min after contrast injection may be considered to reduce false negative results.Relevance statementOur report is the first attempt to find an optimal delay between contrast administration and T1-weighted acquisition in cALD patients in order to correctly detect disease activity and avoid false negative results.Key points• The optimal time between contrast injection and image acquisition for MRI of adrenoleukodystrophy is unknown.• Contrast enhancement predicts adrenoleukodystrophy progression and could help patient's selection for the therapy.• We acquired two post-contrast T1-GRE-2D/3D sequences several times to find the best injection-time.• T1-weighted 2D GRE resulted more sensitive than T1-weighted 3D GRE even after long intervals from injection.• A delay of about 10 min may minimize false negatives.