Predicting lesion reversal in acute cerebral ischaemia via apparent diffusion coefficient threshold on diffusion-weighted MRI.

Abstract

Objectives: Diffusion-weighted imaging (DWI) quickly detects early ischaemic changes, but does not necessarily signify irreversible tissue damage, as DWI lesion reversal (DWI-R) can occur. Apparent diffusion coefficient (ADC) thresholds have been proposed to distinguish salvageable from irreversibly damaged tissue. This study aimed to evaluate the predictive value of a single ADC threshold for DWI-R following rapid and successful recanalization with voxel-level methodology.

Materials and methods: In this cohort study, we retrospectively analysed consecutive patients examined with DWI before and the day after endovascular therapy, with successful recanalization within 120 min of baseline MRI. DWI-R was assessed voxel-wise for ADC values between 200 mm²/s and 760 × 10^-6 mm²/s. Predictive accuracy of ADC thresholds was evaluated using receiver operating characteristic (ROC) analyses.

Results: Seventy-one patients with a mean baseline DWI lesion volume of 18.13 mL (IQR: 6.15, 26.25) were included. Median time from MRI to recanalization was 84.0 min (IQR: 72.0, 95.5). On average, 37.5% of voxels demonstrated reversal. The area under the curve for predicting reversal based on ADC was 0.708, and the optimal threshold was 555 × 10^-6 mm²/s (sensitivity 73.8%, specificity 58.6%). The voxel-wise probability of reversal declined with lower ADC, but even low ADC values exhibited some degree of reversal.

Conclusion: This study reinforces existing concerns about using fixed ADC thresholds to define irreversible injury. A single ADC cut-off showed only modest sensitivity and poor specificity for predicting DWI-R. No definitive lower ADC boundary was identified across clinically relevant ranges below which the likelihood of DWI-R became negligible.

Key points: Question Identifying penumbra from permanent ischaemic damage remains challenging, and the role of ADC evaluation before thrombectomy in predicting tissue viability is debated. Findings An ADC threshold of 555 × 10-6 mm²/s yielded moderate sensitivity (73.8%) and low specificity (58.6%) for predicting DWI-R (AUC 0.708). Clinical relevance A uniform ADC threshold has limited utility in identifying salvageable brain tissue in thrombectomy triage. Our findings emphasise the need for caution when excluding acute ischaemic stroke patients from recanalization therapy based on restrictive diffusion.