Does FLAIR super-resolution erase or hallucinate small white-matter lesions?
2026-08-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors studied how well super-resolution (SR) methods can improve brain scans that have thick slices and are used to detect white matter hyperintensities (WMH), which are linked to brain issues. They tested different ways to make these thick-slice scans look like high-resolution ones and checked if small WMH lesions were kept or lost. They found that SR often caused small real lesions to disappear rather than inventing false ones, though SR still helped detect lesions better than using the thick scans alone. Among the methods tested, ECLARE did the best job at preserving small lesion details, while some approaches didn't improve much over simple interpolation.
White matter hyperintensities (WMH)Fluid-attenuated Inversion Recovery (FLAIR)Super-resolution (SR)Isotropic resolutionAnisotropic scanLesion segmentationImplicit neural representation (INR)ECLARE modelCubic interpolation
Authors
Zahra Khodakarami, Yue Li, Pulkit Khandelwal, John Detre, Sandhitsu Das, Christopher Brown, David Wolk, Paul Yushkevich
Abstract
White matter hyperintensities (WMH), bright regions on Fluid-attenuated Inversion Recovery (FLAIR) scans are associated with cerebrovascular pathology and neurodegeneration. FLAIR is usually acquired with thick slices in clinical settings, giving it poor through-plane resolution. Super-resolution (SR) is a widely used method for recovering an isotropic volume from an anisotropic scan. Yet whether applying it prior to WMH segmentation preserves lesion content remains unknown: a model may erase small real lesions or hallucinate absent ones. We used 1-mm isotropic high-resolution (HR) FLAIR scans from 29 individuals in the ADNI cohort, each manually segmented for WMH by an expert. Then, we degraded each to simulated 3 and 5 mm through-plane acquisitions. Multi-contrast implicit neural representation (INR), a single-contrast self-supervised model (ECLARE), and cubic interpolation were used to upsample them onto the HR grid. WMH segmentation from a simulated thick slice and the original HR FLAIR set the floor and ceiling, respectively, for the per-lesion analysis. Of four WMH segmentation methods (WMH-SynthSeg, segcsvd, MARS-WMH, TrUE-Net), we ran the analysis under the most sensitive one to small lesions on HR (MARS-WMH) with the evaluation metrics of detection sensitivity, erasure rate (HR-detected lesions lost after reconstruction), and hallucination rate (predicted components absent from both the manual and HR segmentation). The dominant effect of SR was erasure of small real lesions, not hallucination, and it increased with slice thickness, though every reconstruction still improved lesion detection over the raw thick slice. ECLARE recovered small lesion signal best at both thicknesses, while the INR was no better than cubic interpolation.