Hippocampal Sclerosis Detection with NeuroQuant Compared with Neuroradiologists

Abstract

Background and purpose: NeuroQuant is an FDA-approved software that performs automated MR imaging quantitative volumetric analysis. This study aimed to compare the accuracy of NeuroQuant analysis with visual MR imaging analysis by neuroradiologists with expertise in epilepsy in identifying hippocampal sclerosis.

Materials and methods: We reviewed 144 adult patients who underwent presurgical evaluation for temporal lobe epilepsy. The reference standard for hippocampal sclerosis was defined by having hippocampal sclerosis on pathology (n = 61) or not having hippocampal sclerosis on pathology (n = 83). Sensitivities, specificities, positive predictive values, and negative predictive values were compared between NeuroQuant analysis and visual MR imaging analysis by using a McNemar paired test of proportions and the Bayes theorem.

Results: NeuroQuant analysis had a similar specificity to neuroradiologist visual MR imaging analysis (90.4% versus 91.6%; P = .99) but a lower sensitivity (69.0% versus 93.0%, P < .001). The positive predictive value of NeuroQuant analysis was comparable with visual MR imaging analysis (84.0% versus 89.1%), whereas the negative predictive value was not comparable (79.8% versus 95.0%).

Conclusions: Visual MR imaging analysis by a neuroradiologist with expertise in epilepsy had a higher sensitivity than did NeuroQuant analysis, likely due to the inability of NeuroQuant to evaluate changes in hippocampal T2 signal or architecture. Given that there was no significant difference in specificity between NeuroQuant analysis and visual MR imaging analysis, NeuroQuant can be a valuable tool when the results are positive, particularly in centers that lack neuroradiologists with expertise in epilepsy, to help identify and refer candidates for temporal lobe epilepsy resection. In contrast, a negative test could justify a case referral for further evaluation to ensure that false-negatives are detected.

Fig 1.

NeuroQuant triage brain atrophy report provides volumetric percentiles of left and right regions of the brain.

Fig 2.

NeuroQuant hippocampal atrophy report provides volumetric percentiles of the left and right regions of the hippocampus as well as the normative percentile of the hippocampus compared with the normative control group of patients.

Fig 3.

PPV of visual MR imaging analysis and NeuroQuant analysis results as the prevalence of HS increases. In our study, HS had a prevalence of 42.4% (black dotted line), NeuroQuant analysis had a PPV of 84%, and MR imaging had a PPV of 89.1%. With a decreased prevalence of HS, both MR imaging and NeuroQuant (NQ) have a decreased PPV, whereas an increased prevalence of HS results in a higher PPV for both analytic methods.

Fig 4.

NPV of visual MR imaging analysis and NeuroQuant analysis results as the prevalence of HS increases. In our study, HS had a prevalence of 42.4% (black dotted line). In areas with a lower prevalence of HS than our institution, the NPV increases for both MR imaging and NeuroQuant.