Focal hyperintensity in the dorsal brain stem of patients with cerebellopontine angle tumor: A high-resolution 3 T MRI study

Brainstem hyperintensity in patients with vestibular schwannoma is associated with labyrinth signal on magnetic resonance imaging but not vestibulocochlear tests

OBJECTIVES

Focal hyperintensity in the dorsal brainstem (HDB) has been described in large cerebellopontine angle tumours and is thought to represent vestibular nuclei degeneration, but its functional significance has not been thoroughly investigated. Our aim was to analyse its relationship to imaging characteristics of the tumour and inner-ear structures and to vestibulocochlear functional tests.

METHODS

We retrospectively reviewed 54 patients with a histological diagnosis of vestibular schwannoma (VS). Magnetic resonance imaging tumour characteristics (size, cystic composition and distance from the cochlear aperture), signal intensity ratio of the cochlea and vestibule in fluid-attenuated inversion recovery (FLAIR) and fast imaging employing steady-state acquisition (FIESTA)/fast spin-echo imaging with variable flip angles (CUBE) and vestibulocochlear function tests (audiometry, auditory brainstem response (ABR) and video head impulse testing (vHIT)) were obtained. Statistical analyses were performed to evaluate their relation to focal HDB.

RESULTS

Focal HDB was found in 22% of VS. It was significantly associated with large (p < 0.001) and cystic (p = 0.004) tumours and also with tumours located further from the cochlear aperture (p = 0.039). The signal intensity ratio of the cochlea on FLAIR was higher in patients with HDB (p < 0.014), but this difference was not observed in FIESTA/CUBE (p = 0.981). Audiometry, ABR and vHIT results did not significantly differ in patients with HDB, but ABR results were worse in patients with higher cochlear signal intensity on FLAIR sequences (p = 0.026).

CONCLUSIONS

Focal HDB in patients with VS was associated with increased signal intensity ratio of the cochlea on FLAIR in patients with VS but not directly to the results of vestibulocochlear function tests.

Deep Learning Based Noise Reduction for Brain MR Imaging: Tests on Phantoms and Healthy Volunteers

Purpose:

To test whether our proposed denoising approach with deep learning-based reconstruction (dDLR) can effectively denoise brain MR images.

Methods:

In an initial experimental study, we obtained brain images from five volunteers and added different artificial noise levels. Denoising was applied to the modified images using a denoising convolutional neural network (DnCNN), a shrinkage convolutional neural network (SCNN), and dDLR. Using these brain MR images, we compared the structural similarity (SSIM) index and peak signal-to-noise ratio (PSNR) between the three denoising methods. Two neuroradiologists assessed the image quality of the three types of images. In the clinical study, we evaluated the denoising effect of dDLR in brain images with different levels of actual noise such as thermal noise. Specifically, we obtained 2D-T₂-weighted image, 2D-fluid-attenuated inversion recovery (FLAIR) and 3D-magnetization-prepared rapid acquisition with gradient echo (MPRAGE) from 15 healthy volunteers at two different settings for the number of image acquisitions (NAQ): NAQ2 and NAQ5. We reconstructed dDLR-processed NAQ2 from NAQ2, then compared with SSIM and PSNR. Two neuroradiologists separately assessed the image quality of NAQ5, NAQ2 and dDLR-NAQ2. Statistical analysis was performed in the experimental and clinical study. In the clinical study, the inter-observer agreement was also assessed.

Results:

In the experimental study, PSNR and SSIM for dDLR were statistically higher than those of DnCNN and SCNN (P < 0.001). The image quality of dDLR was also superior to DnCNN and SCNN. In the clinical study, dDLR-NAQ2 was significantly better than NAQ2 images for SSIM and PSNR in all three sequences (P < 0.05), except for PSNR in FLAIR. For all qualitative items, dDLR-NAQ2 had equivalent or better image quality than NAQ5, and superior quality to that of NAQ2 (P < 0.05), for all criteria except artifact. The inter-observer agreement ranged from substantial to near perfect.

Conclusion:

dDLR reduces image noise while preserving image quality on brain MR images.