DeepFLAIR: A neural network approach to mitigate signal and contrast loss in temporal lobes at 7 Tesla FLAIR images

BACKGROUND AND PURPOSE

Higher magnetic field strength introduces stronger magnetic field inhomogeneities in the brain, especially within temporal lobes, leading to image artifacts. Particularly, T2-weighted fluid-attenuated inversion recovery (FLAIR) images can be affected by these artifacts. Here, we aimed to improve the FLAIR image quality in temporal lobe regions through image processing of multiple contrast images via machine learning using a neural network.

METHODS

Thirteen drug-resistant MR-negative epilepsy patients (age 29.2 ± 9.4y, 5 females) were scanned on a 7 T MRI scanner. Magnetization-prepared (MP2RAGE) and saturation-prepared with 2 rapid gradient echoes, multi-echo gradient echo with four echo times, and the FLAIR sequence were acquired. A voxel-wise neural network was trained on extratemporal-lobe voxels from the acquired structural scans to generate a new FLAIR-like image (i.e., deepFLAIR) with reduced temporal lobe inhomogeneities. The deepFLAIR was evaluated in temporal lobes through signal-to-noise (SNR), contrast-to-noise (CNR) ratio, the sharpness of the gray-white matter boundary and joint-histogram analysis. Saliency mapping demonstrated the importance of each input image per voxel.

RESULTS

SNR and CNR in both gray and white matter were significantly increased (p < 0.05) in the deepFLAIR's temporal ROIs, compared to the FLAIR. The gray-white matter boundary sharpness was either preserved or improved in 10/13 right-sided temporal regions and was found significantly increased in the ROIs. Multiple image contrasts were influential for the deepFLAIR reconstruction with the MP2RAGE second inversion image being the most important.

CONCLUSIONS

The deepFLAIR network showed promise to restore the FLAIR signal and reduce contrast attenuation in temporal lobe areas. This may yield a valuable tool, especially when artifact-free FLAIR images are not available.

Advances in Image Processing for Epileptogenic Zone Detection with MRI

Focal epilepsy is a common and severe neurologic disorder. Neuroimaging aims to identify the epileptogenic zone (EZ), preferably as a macroscopic structural lesion. For approximately a third of patients with chronic drug-resistant focal epilepsy, the EZ cannot be precisely identified using standard 3.0-T MRI. This may be due to either the EZ being undetectable at imaging or the seizure activity being caused by a physiologic abnormality rather than a structural lesion. Computational image processing has recently been shown to aid radiologic assessments and increase the success rate of uncovering suspicious regions by enhancing their visual conspicuity. While structural image analysis is at the forefront of EZ detection, physiologic image analysis has also been shown to provide valuable information about EZ location. This narrative review summarizes and explains the current state-of-the-art computational approaches for image analysis and presents their potential for EZ detection. Current limitations of the methods and possible future directions to augment EZ detection are discussed.

Visual field deficits after epilepsy surgery: a new quantitative scoring method

Background

Anterior temporal lobectomy (ATL) as a treatment for drug-resistant temporal lobe epilepsy (TLE) frequently causes visual field deficits (VFDs). Reported VFD encompasses homonymous contralateral upper quadrantanopia. Its reported incidence ranges from 15 to 90%. To date, a quantitative method to evaluate postoperative VFD in static perimetry is not available. A method to quantify postoperative VFD, which allows for comparison between groups of patients, was developed.

Methods

Fifty-five patients with drug-resistant TLE, who underwent ATL with pre- and postoperative perimetry, were included. Temporal lobe resection length was measured on postoperative MRI. Percentage VFD was calculated for the total visual field, contralateral upper quadrant, or other three quadrants combined.

Results

Patients were divided into groups by resection size (< 45 and ≥ 45 mm) and side of surgery (right and left). We found significant higher VFD in the ≥ 45 vs. < 45 mm group (2.3 ± 4.4 vs. 0.7 ± 2.4%,p = 0.04) for right-sided ATL. Comparing VFD in both eyes, we found more VFD in the right vs. left eye following left-sided ATL (14.5 ± 9.8 vs. 12.9 ± 8.3%, p = 0.03). We also demonstrated significantly more VFD in the < 45 mm group for left- vs. right-sided surgery (6.7 ± 6.7 vs. 13.1 ± 7.0%, p = 0.016). A significant quantitative correlation between VFD and resection size for right-sided ATL was shown (r = 0.52, p < 0.01).

Conclusions

We developed a new quantitative scoring method for the assessment of postoperative visual field deficits after temporal lobe epilepsy surgery and assessed its feasibility for clinical use. A significant correlation between VFD and resection size for right-sided ATL was confirmed.