Clinical Utility of a Novel Ultrafast T2-Weighted Sequence for Spine Imaging

Deep learning-based reconstruction can improve canine thoracolumbar magnetic resonance image quality and reduce slice thickness

In veterinary practice, thin-sliced thoracolumbar MRI is useful in detecting small lesions, especially in small-breed dogs. However, it is challenging due to the partial volume averaging effect and increase in scan time. Currently, deep learning-based reconstruction (DLR), a part of artificial intelligence, has been applied in diagnostic imaging. We hypothesized that the diagnostic performance of thin-slice thoracolumbar MRI with DLR would be superior to conventional MRI. This prospective, method comparison study aimed to determine the adequate slice thickness of a deep learning model for thin-slice thoracolumbar MRI. Sagittal and transverse T2-weighted MRI at the thoracolumbar region were performed on 12 clinically healthy beagle dogs; the images obtained were categorized into five groups according to slice thickness: conventional thickness of 3 mm (3 CON) and thicknesses of 3, 2, 1.5, and 1 mm with DLR (3 DLR, 2 DLR, 1.5 DLR, and 1 DLR, respectively). Quantitative analysis was performed using signal-to-noise ratio (SNR) and contrast-to-noise ratio. Qualitative analysis involved the evaluation of perceived SNR, structural visibility, and overall image quality using a four-point scale. Moreover, nerve root visibility was evaluated using transverse images. Quantitative and qualitative values were compared among the five groups. Compared with the 3 CON group, the 3 DLR, 2 DLR, and 1.5 DLR groups exhibited significantly higher quantitative and qualitative values. Nerve root visibility was significantly higher in 2 DLR, 1.5 DLR, and 1 DLR images than in 3 DLR and 3 CON images. Compared with conventional MRI, DLR reduced the slice thickness by up to one-half and improved image quality in this sample of clinically healthy beagles.

The Role of Advanced Imaging in Neurosurgical Diagnosis

Neurosurgery as a specialty has developed at a rapid pace as a result of the continual advancements in neuroimaging modalities. With more sophisticated imaging options available to the modern neurosurgeon, diagnoses become more accurate and at a faster rate, allowing for greater surgical planning and precision. Herein, the authors review the current heavily used imaging modalities within neurosurgery, weighing their strengths and weaknesses, and provide a look into new advances and imaging options within the field. Of the many imaging modalities currently available to the practicing neurosurgeon, magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), and ultrasonography (US) are used most heavily within the field for appropriate diagnosis of neuropathologies in question. For each, their strengths are weighed regarding appropriate capabilities in accurate diagnosis of cranial or spinal lesions. Reasoning for choosing one over the other for various pathologies is also reviewed. Current limitations of each is also assessed, providing insight for possible improvement for each. New advancements in imaging options are subsequently reviewed for best uses within neurosurgery, including the new utilization of FIESTA sequencing, glymphatic mapping, black-blood MRI, and functional MRI. The specialty of neurosurgery will continue to heavily rely on improvements within imaging options available for improved diagnosis and greater surgical outcomes for the patients treated. The synthesis of techniques provided herein may provide meaningful guidance for neurosurgeons in effectively diagnosing neurological pathologies while also helping guide future efforts in neuroimaging developments.

Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Background

Several deep learning-based methods have been proposed for addressing the long scanning time of magnetic resonance imaging. Most are trained using brain 3T magnetic resonance images, but is unclear whether performance is affected when applying these methods to different anatomical sites and at different field strengths.

Purpose

To validate the denoising performance of deep learning-based reconstruction method trained by brain and knee 3T magnetic resonance images when applied to lumbar 1.5T magnetic resonance images.

Material and Methods

Using a 1.5T scanner, we obtained lumber T2-weighted sequences in 10 volunteers using three different scanning times: 228 s (standard), 119 s (double-fast), and 68 s (triple-fast). We compared the images obtained by the standard sequence with those obtained by the deep learning-based reconstruction-applied faster sequences.

Results

Signal-to-noise ratio values were significantly higher for deep learning-based reconstruction-double-fast than for standard and did not differ significantly between deep learning-based reconstruction-triple-fast and standard. Contrast-to-noise ratio values also did not differ significantly between deep learning-based reconstruction-triple-fast and standard. Qualitative scores for perceived signal-to-noise ratio and overall image quality were significantly higher for deep learning-based reconstruction-double fast and deep learning-based reconstruction-triple-fast than for standard. Average scores for sharpness, contrast, and structure visibility were equal to or higher for deep learning-based reconstruction-double-fast and deep learning-based reconstruction-triple-fast than for standard, but the differences were not statistically significant. The average scores for artifact were lower for deep learning-based reconstruction-double-fast and deep learning-based reconstruction-triple-fast than for standard, but the differences were not statistically significant.

Conclusion

The deep learning-based reconstruction method trained by 3T brain and knee images may reduce the scanning time of 1.5T lumbar magnetic resonance images by one-third without sacrificing image quality.