Accurate compensation for intra-operative brain shift remains a fundamental challenge in neurosurgical procedures, as misalignment between pre-operative and intra-operative images can lead to suboptimal surgical guidance. In this work, we propose a bidirectional, unsupervised 3D brain shift compensation framework for non-rigid MRI registration, designed to directly estimate dense deformation fields between pre-operative and intra-operative volumes. The proposed approach employs dual image-translation pathways coupled with a dedicated deformation field predictor, enabling robust alignment without requiring paired training data. A key component of the framework is the integration of bidirectional consistency constraints to enforce anatomical correspondence across domains, while deformation field estimation is explicitly optimized for registration accuracy. In addition, we incorporate a Haar wavelet-based perceptual similarity (HaarPSI) loss to improve the preservation of fine-scale anatomical structures during registration. The proposed method is evaluated against classical and state-of-the-art baselines, including Elastix, Voxelmorph, and several adversarial and GAN-based learning approaches adapted with comparable registration modules. Qualitative analyses of deformation fields and error maps further demonstrate improved alignment in regions most affected by brain shift. These results highlight the effectiveness of bidirectional deformation modeling combined with adversarial and perceptual constraints for accurate, physically plausible, and unsupervised 3D non-rigid registration in neurosurgical applications.
Background Thromboembolic events remain a periprocedural concern despite latest-generation flow diverters (FDs), including the Pipeline Embolization Device-Flex with Shield technology (PEDS). We examined the association between FD-to-parent artery (PA) diameter mismatch and postoperative diffusion-weighted imaging–positive lesions (DPLs) after PEDS treatment. Materials and methods This retrospective cohort study included patients with unruptured intracranial aneurysms who underwent PEDS treatment and postoperative MRI within 48 h at a single center (June 2019–February 2026). We evaluated the nonlinear association between the stent-to-distal PA diameter ratio (RDd) and DPL count. Results Overall, 58 patients with 61 aneurysms undergoing 64 procedures were analyzed. Segmented negative binomial regression demonstrated a nonlinear association between RDd and DPL count, with an exploratory breakpoint estimated at 1.25 (Davies test, P = 0.01). Procedures were classified into high (RDd ≥1.25; n = 23) and low (RDd <1.25; n = 41) ratio groups. The high-ratio group had more DPLs (median, 10 vs. 2; P < 0.001). After adjustment for sex and percutaneous transluminal angioplasty (PTA), RDd ≥1.25 was associated with higher DPL counts (adjusted incidence rate ratio, 4.12; 95% confidence interval [CI], 2.53–6.80; P < 0.001), whereas PTA was associated with fewer DPLs (adjusted incidence rate ratio, 0.59; 95% CI, 0.34–0.99; P = 0.05). RDd association remained consistent in sensitivity analyses excluding PTA from adjustment. Conclusions A higher stent-to-distal PA diameter ratio was associated with greater postoperative DPL burden after PEDS treatment, with an exploratory breakpoint near 1.25. Assessment of diameter mismatch may inform procedural risk evaluation, although the estimated breakpoint requires external validation.
