Dual‐Sensitivity Multiple Sclerosis Lesion and CSF Segmentation for Multichannel 3T Brain MRI

Abstract

BACKGROUND AND PURPOSEA pipeline for fully automated segmentation of 3T brain MRI scans in multiple sclerosis (MS) is presented. This 3T morphometry (3TM) pipeline provides indicators of MS disease progression from multichannel datasets with high‐resolution 3‐dimensional T1‐weighted, T2‐weighted, and fluid‐attenuated inversion‐recovery (FLAIR) contrast. 3TM segments white (WM) and gray matter (GM) and cerebrospinal fluid (CSF) to assess atrophy and provides WM lesion (WML) volume.METHODSTo address nonuniform distribution of noise/contrast (eg, posterior fossa in 3D‐FLAIR) of 3T magnetic resonance imaging, the method employs dual sensitivity (different sensitivities for lesion detection in predefined regions). We tested this approach by assigning different sensitivities to supratentorial and infratentorial regions, and validated the segmentation for accuracy against manual delineation, and for precision in scan‐rescans.RESULTSIntraclass correlation coefficients of .95, .91, and .86 were observed for WML and CSF segmentation accuracy and brain parenchymal fraction (BPF). Dual sensitivity significantly reduced infratentorial false‐positive WMLs, affording increases in global sensitivity without decreasing specificity. Scan‐rescan yielded coefficients of variation (COVs) of 8% and .4% for WMLs and BPF and COVs of .8%, 1%, and 2% for GM, WM, and CSF volumes. WML volume difference/precision was .49 ± .72 mL over a range of 0–24 mL. Correlation between BPF and age was r = .62 (P = .0004), and effect size for detecting brain atrophy was Cohen's d = 1.26 (standardized mean difference vs. healthy controls).CONCLUSIONSThis pipeline produces probability maps for brain lesions and tissue classes, facilitating expert review/correction and may provide high throughput, efficient characterization of MS in large datasets.

Neurofilament light chain serum levels correlate with 10‐year MRI outcomes in multiple sclerosis

“…The output provided brain T2 hyperintense lesion volume (T2LV) and brain parenchymal fraction (BPF), a surrogate of whole brain atrophy. This pipeline showed high accuracy and reliability 23. Intraclass correlation coefficients of 0.95, 0.91, and 0.86 were obtained for T2LV, CSF, and BPF accuracy.…”

“…This pipeline showed high accuracy and reliability. 23 Intraclass correlation coefficients of 0.95, 0.91, and 0.86 were obtained for T2LV, CSF, and BPF accuracy. A scan-rescan reliability experiment showed coefficients of variation (COVs) of 8%, 2%, and 0.4% for T2LV, CSF volume, and BPF.…”

“…The sequences were optimized in contrast for depicting brain‐cerebrospinal fluid (CSF) interfaces and white matter lesions. The main steps of the fully automated quantitative analysis pipeline were outlined in Meier et al23 Key steps were co‐registration of the three MR sequences, anatomical parcellation with heuristic misclassification correction, and an expectation‐maximization algorithm. The output provided brain T2 hyperintense lesion volume (T2LV) and brain parenchymal fraction (BPF), a surrogate of whole brain atrophy.…”

Salient Central Lesion Volume: A Standardized Novel Fully Automated Proxy for Brain FLAIR Lesion Volume in Multiple Sclerosis

“…This is a more elegant way to handle spatial variation in detectability than our proposed centrality criterion, but requires full anatomic coverage for template registration, as well as the presence of multimodal input data. A potentially even more promising newer approach is the use of deep learning in the form of convolutional neural networks (CNNs), which are capable of incorporating data from tremendously large training sets to self‐learn complex pattern recognition algorithms in a manner similar to the way the human visual system works . CNNs have consistently topped recent general lesion segmentation challenges like those hosted by the Medical Image Computing and Computer Aided Intervention (MICCAI) society .…”

Faster RCNN‐based detection of cervical spinal cord injury and disc degeneration

“…Previous studies focused primarily on brain diseases compared to diseases of the spinal cord because MRI has been successful in diagnosing brain‐related illness. In addition, spinal cord diseases exhibit more variations in their morphology and signals in sagittal MRI 12–15 . Only a few studies have investigated spinal cord diseases on MRI using CNN models.…”