Enhancing the Diagnostic Utility of ASL Imaging in Temporal Lobe Epilepsy through FlowGAN: An ASL to PET Image Translation Framework.

Background and Significance: Positron Emission Tomography (PET) using fluorodeoxyglucose (FDG-PET) is a standard imaging modality for detecting areas of hypometabolism associated with the seizure onset zone (SOZ) in temporal lobe epilepsy (TLE). However, FDG-PET is costly and involves the use of a radioactive tracer. Arterial Spin Labeling (ASL) offers an MRI-based quantification of cerebral blood flow (CBF) that could also help localize the SOZ, but its performance in doing so, relative to FDG-PET, is limited. In this study, we seek to improve ASL's diagnostic performance by developing a deep learning framework for synthesizing FDG-PET-like images from ASL and structural MRI inputs. Methods: We included 68 epilepsy patients, out of which 36 had well lateralized TLE. We compared the coupling between FDG-PET and ASL CBF values in different brain regions, as well as the asymmetry of these values across the brain. We additionally assessed each modality's ability to lateralize the SOZ across brain regions. Using our paired PET-ASL data, we developed FlowGAN, a generative adversarial neural network (GAN) that synthesizes PET-like images from ASL and T1-weighted MRI inputs. We tested our synthetic PET images against the actual PET images of subjects to assess their ability to reproduce clinically meaningful hypometabolism and asymmetries in TLE. Results: We found variable coupling between PET and ASL CBF values across brain regions. PET and ASL had high coupling in neocortical temporal and frontal brain regions (Spearman's r > 0.30, p < 0.05) but low coupling in mesial temporal structures (Spearman's r < 0.30, p > 0.05). Both whole brain PET and ASL CBF asymmetry values provided good separability between left and right TLE subjects, but PET (AUC = 0.96, 95% CI: [0.88, 1.00]) outperformed ASL (AUC = 0.81; 95% CI: [0.65, 0.96]). FlowGAN-generated images demonstrated high structural similarity to actual PET images (SSIM = 0.85). Globally, asymmetry values were better correlated between synthetic PET and original PET than between ASL CBF and original PET, with a mean correlation increase of 0.15 (95% CI: [0.07, 0.24], p <0.001, Cohen's d = 0.91). Furthermore, regions that had poor ASL-PET correlation (e.g. mesial temporal structures) showed the greatest improvement with synthetic PET images. Conclusions: FlowGAN improves ASL's diagnostic performance, generating synthetic PET images that closely mimic actual FDG-PET in depicting hypometabolism associated with TLE. This approach could improve non-invasive SOZ localization, offering a promising tool for epilepsy presurgical assessment. It potentially broadens the applicability of ASL in clinical practice and could reduce reliance on FDG-PET for epilepsy and other neurological disorders.

Should patients with lumbar stenosis and grade I spondylolisthesis be treated differently based on spinopelvic alignment? A retrospective, two-year, propensity matched, comparison of patient-reported outcome measures and clinical outcomes from multiple sites within a single health system.

BACKGROUND: Degenerative lumbar spondylolisthesis is one of the most common pathologies addressed by surgeons. Recently, data demonstrated improved outcomes with fusion in conjunction with laminectomy compared to laminectomy alone. However, given not all degenerative spondylolistheses are clinically comparable, the best treatment option may depend on multiple parameters. Specifically, the impact of spinopelvic alignment on patient reported and clinical outcomes following fusion versus decompression for grade I spondylolisthesis has yet to be explored. PURPOSE: This study assessed two-year clinical outcomes and one-year patient reported outcomes following laminectomy with concomitant fusion versus laminectomy alone for management of grade I degenerative spondylolisthesis and stenosis. The present study is the first to examine the effect of spinopelvic alignment on patient-reported and clinical outcomes following decompression alone versus decompression with fusion. STUDY DESIGN/SETTING: Retrospective sub-group analysis of observational, prospectively collected cohort study. PATIENT SAMPLE: 679 patients treated with laminectomy with fusion or laminectomy alone for grade I degenerative spondylolisthesis and comorbid spinal stenosis performed by orthopaedic and neurosurgeons at three medical centers affiliated with a single, tertiary care center. OUTCOME MEASURES: The primary outcome was the change in Patient-Reported Outcome Measurement Information System (PROMIS), Global Physical Health (GPH), and Global Mental Health (GMH) scores at baseline and post-operatively at 4-6 and 10-12 months postoperatively. Secondary outcomes included operative parameters (estimated blood loss and operative time), and two-year clinical outcomes including reoperations, duration of postoperative physical therapy, and discharge disposition. METHODS: Radiographs/MRIs assessed stenosis, spondylolisthesis, pelvic incidence, lumbar lordosis, sacral slope, and pelvic tilt; from this data, two cohorts were created based on pelvic incidence minus lumbar lordosis (PILL), denoted as "high" and "low" mismatch. Patients underwent either decompression or decompression with fusion; propensity score matching (PSM) and coarsened exact matching (CEM) were used to create matched cohorts of "cases" (fusion) and "controls" (decompression). Binary comparisons used McNemar test; continuous outcomes used Wilcoxon rank-sum test. Between-group comparisons of changes in PROMIS GPH and GMH scores were analyzed using mixed-effects models; analyses were conducted separately for patients with high and low pelvic incidence-lumbar lordosis (PILL) mismatch. RESULTS: 49.9% of patients (339) underwent lumbar decompression with fusion, while 50.1% (340) received decompression. In the high PLL mismatch cohort at 10-12 months postoperatively, fusion-treated patients reported improved PROs, including GMH (26.61 vs. 20.75, p<0.0001) and GPH (23.61 vs. 18.13, p<0.0001). They also required fewer months of outpatient physical therapy (1.61 vs. 3.65, p<0.0001) and had lower 2-year reoperation rates (12.63% vs. 17.89%, p=0.0442) compared to decompression-only patients. In contrast, in the low PLL mismatch cohort, fusion-treated patients demonstrated worse endpoint PROs (GMH: 18.67 vs. 21.52, p<0.0001; GPH: 16.08 vs. 20.74, p<0.0001). They were also more likely to require skilled nursing/rehabilitation centers (6.86% vs. 0.98%, p=0.0412) and extended outpatient physical therapy (2.47 vs. 1.34 months, p<0.0001) and had higher 2-year reoperation rates (25.49% vs. 14.71%,p=0.0152). CONCLUSIONS: Lumbar laminectomy with fusion was superior to laminectomy in health-related quality of life and reoperation rate at two years postoperatively only for patients with sagittal malalignment, represented by high PILL mismatch. In contrast, the addition of fusion for patients with low-grade spondylolisthesis, spinal stenosis, and spinopelvic harmony (low PILL mismatch) resulted in worse quality of life outcomes and reoperation rates.

Multi-contrast high-field quality image synthesis for portable low-field MRI using generative adversarial networks and paired data.

Introduction: Portable low-field strength (64mT) MRI scanners promise to increase access to neuroimaging for clinical and research purposes, however these devices produce lower quality images compared to high-field scanners. In this study, we developed and evaluated a deep learning architecture to generate high-field quality brain images from low-field inputs using a paired dataset of multiple sclerosis (MS) patients scanned at 64mT and 3T. Methods: A total of 49 MS patients were scanned on portable 64mT and standard 3T scanners at Penn (n=25) or the National Institutes of Health (NIH, n=24) with T1-weighted, T2-weighted and FLAIR acquisitions. Using this paired data, we developed a generative adversarial network (GAN) architecture for low- to high-field image translation (LowGAN). We then evaluated synthesized images with respect to image quality, brain morphometry, and white matter lesions. Results: Synthetic high-field images demonstrated visually superior quality compared to low-field inputs and significantly higher normalized cross-correlation (NCC) to actual high-field images for T1 (p=0.001) and FLAIR (p<0.001) contrasts. LowGAN generally outperformed the current state-of-the-art for low-field volumetrics. For example, thalamic, lateral ventricle, and total cortical volumes in LowGAN outputs did not differ significantly from 3T measurements. Synthetic outputs preserved MS lesions and captured a known inverse relationship between total lesion volume and thalamic volume. Conclusions: LowGAN generates synthetic high-field images with comparable visual and quantitative quality to actual high-field scans. Enhancing portable MRI image quality could add value and boost clinician confidence, enabling wider adoption of this technology.