This paper presents a novel robust and accurate normal-assisted learning-based rigid point set registration approach, i.e., Deep Bi-directional Hybrid Mixture Registration (DeepBHMR), where normal vectors are used in both correspondence and transformation computational stages while the bi-directional registration processes are considered. DeepBHMR consists of three components, 1) the correspondence estimation network that predicts the correspondence probabilities; 2) the posterior estimation module that computes the HMMs parameters; 3) the transformation estimation module that calculates the rigid transformation matrix by utilizing the bidirectional optimization mechanism. DeepBHMR has been extensively validated on various medical data sets, outperforming state-of-the-art registration methods. For femur bones, the mean rotation error value is approximately 1 degrees (i.e, 1.01 degrees) and the translation error is less than 1 mm (i.e., 0.30 mm) respectively, which meets the requirement of computer-assisted orthopedic surgery. Furthermore, even 1) trained with femur data and tested on distinct shapes and 2) under the large transformation, the mean RMSE values of registration are 2.60 mm and 3.05 mm respectively, demonstrating DeepBHMR's favorable generalizability to different data shapes and great capability to handle global registration. Additionally, the individual significant contributions and computational efficiency of adopting normal vectors and utilizing the bidirectional mechanism have been validated in ablation studies. The results demonstrate the DeepBHMR's favorable generalizability from femur bones to hip bones and that DeepBHMR can successfully handle the large transformation or partial-to-full registration simultaneously. The code implementation of DeepBHMR has been made publicly available at https://github.com/zzyrobot/DeepBiHMM.git

In computer-assisted orthopedic surgery (CAOS), robust and accurate registration of the preoperative full bone model and the intraoperative partial point set is a prerequisite for reliable surgical navigation, yet remains highly challenging due to partial overlap, noise, and outliers. We propose the Overlap-Guided Bidirectional Hybrid Mixture Registration (OBHMR) framework for robust and accurate partial-to-full registration. First, geometric features (i.e., surface normals) extracted from raw point sets are incorporated in both correspondence estimation and transform computation. Meanwhile, we formulate a hybrid mixture model that jointly represents positions with Gaussian mixtures (GMMs) and normals with von Mises-Fisher (vMF) mixtures across the two generalized point sets. Second, a dual-branch overlap prediction network leverages feature similarity and geometric structure to provide accurate point-wise overlap scores that guide hybrid-mixture construction under partial overlap. Third, a correspondence module integrates rotation-invariant features, multi-level self-attention, and clustering-based refinement to enhance reliability under noise and misalignment. Finally, a bidirectional objective jointly aligns source-to-target and target-to-source mixtures, explicitly accounting for discrepancies induced by noise and outliers in both the preoperative and intraoperative point sets to achieve robust optimization. Extensive experiments on 1,399 femur and 1,301 hip models demonstrate superior performance over state-of-the-art methods across overlap ratios from 5% to 70%, under both isotropic and anisotropic noise and outlier ratios up to 100%, achieving errors as low as 1.27 degrees rotation and 1.18 mm translation at 50% overlap with 2.5 mm noise. Additional tests on liver and ModelNet40 confirm strong generalization across medical and non-medical data. Ablation studies further validate the contributions of normals, overlap estimation, and the bidirectional formulation. Note to Practitioners-Accurately aligning a full preoperative bone model with a partial intraoperative point set is difficult in real CAOS workflows because the two sets share limited overlap and both are corrupted by noise and outliers. We present Overlap-Guided Bidirectional Hybrid Mixture Registration (OBHMR), a rigid registration method tailored to these conditions. OBHMR uses surface normals together with positions and builds, for each set, a hybrid mixture model (HMM) that couples a Gaussian mixture on 3D positions with a Fisher (von Mises-Fisher) mixture on unit normals. An overlap-guided correspondence network (with STN-based standardization, PointNet-style MLPs plus multi-head self-attention, a clustering head for correspondences, and a dual-branch overlap estimator) predicts (i) point-to-HMM component responsibilities for both preoperative (full) and intraoperative (partial) sets and (ii) point-wise overlap scores on the preoperative set (the intraoperative set uses an all-ones overlap vector). These signals update the two overlap-guided HMMs, down-weighting non-overlapping or unreliable points during parameter estimation. Finally, OBHMR minimizes a bidirectional objective-the sum of the divergences between the forward-transformed source mixture and the target mixture, and between the inverse-transformed target mixture and the source mixture-thereby explicitly accounting for noise and outliers in both domains and producing robust, accurate partial-to-full registration suitable for intraoperative use.

The Segment Anything Model (SAM) is a powerful foundational model designed to generalize and automate image segmentation tasks. However, when directly applied to surgical images, SAM encounters several critical challenges including the imaging disparities between natural and medical images, its reliance on high-quality prompts, and the lack of support for multi-class segmentation. To address these limitations, we propose a novel approach Detection-SAM (DetSAM), which integrates a detection module with SAM. By leveraging the output of a detection module as a prompt for each individual class, fully automatic multi-class surgical instrument segmentation can be realized. Meanwhile, we also design a block-wise fine-tuned image encoder to extract image features. We have validated DetSAM on two standard public benchmark datasets (i.e., Endovis2017 and Endovis2018), achieving Ch_IoU scores of 77.53 https://github.com/JingsongWang04/DetSAM

Embedding biomechanical priors into medical image registration is essential to ensure physiologically credible soft-tissue motion. However, the optimal strategy for enforcing these priors within learning-based models re mains under-explored. In this work, we propose the Biome chanical Fields Prediction Physics-Informed Neural Net work (BFP-PINN) as a unified framework for prostate MR TRUS point-set registration. To systematically investigate the impact of different physics-embedding mechanisms, we instantiate and compare three distinct strategies within this backbone: (i) Deformation, which predicts displacement constrained by strong-form Navier-Cauchy residuals; (ii) Strain, which predicts both displacement and strain; and (iii) StressStrain, which jointly predicts displacement, stress, and strain. This controlled study isolates the effects of predicting intermediate physical fields versus direct reg ularization. Extensive experiments on simulated and clinical datasets show that the Deformation strategy provides the best overall balance between geometric accuracy and biomechanical plausibility in the evaluated setting. These findings suggest that while coupled-field predictions are theoretically rigorous, the direct residual constraint offers superior optimization stability for clinical registration tasks. Source codes are available at https://github.com/ Msx00/PINNs-for-Point-Set-Registration.git.

Stereo depth estimation has drawn widespread attention from the robotics and vision community due to its broad applications such as 3D reconstruction. Recently, stereo matching foundation models have made significant progress by being trained on the large-scale datasets containing natural images. However, directly leveraging these pretrained large models to minimally invasive surgery still remains challenging due to domain shifts in aspects of specular highlights and low-texture tissue. In this paper, we propose a parameter-efficient adaptation framework to address this gap. Specifically, we introduce Camera-Aware LoRA for fine-tuning FoundationStereo, using a camera-aware scaling gate computed from focal length and baseline to address intraoperative intrinsics drift arising from instrument self-heating and other thermal effects. We further develop a geometric consistency constraint and a spectral alignment regularizer that enforce cross-view depth agreement. Extensive experiments on the SCARED and Hamlyn datasets indicate that the proposed method achieves state-of-the-art performance. Notably, CaLoRA is easy to integrate into standard fine-tuning pipelines, requiring no backbone changes and only a small number of trainable parameters.

Biomechanical modelling of soft tissue provides a method for constraining medical image registration, such that the estimated spatial transformation is considered biophysically plausible. Existing methods either directly optimize the loss function containing the biomechanical-constrained regularization term over deformations, which takes much computational time, or are trained using biomechanically plausible data generated via finite element simulation, which is cumbersome. This work first instantiates the recently-proposed physics-informed neural networks (PINNs) to 3D elastic models that are used to establish the partial differential equations (PDEs) representing physics laws of biomechanical constraints to be satisfied. The registration algorithm that aligns point sets considering PINN-imposed biomechanics (i.e., the forward problem) is then formulated. In addition, the inverse problem and its algorithm of physical parameter (i.e., material property) estimation along with the registration are also formulated and developed. We carefully compare linear and nonlinear elasticity theories’ capabilities in solving both tasks of forward registration and inverse physical parameter identification under PINNs respectively. Furthermore, two specific network configurations that leverage one common branch or two individual branches to predict deformation vectors and biomechanical states are also constructed and compared. The proposed PINNs-based registration approaches have been extensively evaluated with three experiments, that is single and multiple patient MRI-US registration using clinical MRI-US pairs, and registration using pairs of undeformed MR images from clinical cases of prostate cancer biopsy and deformed counterparts with finite-element-computed ground-truth deformation. Results demonstrate that the proposed methods achieve state-of-the-art performances compared to biomechanical-model-based and learning-based registration approaches, and the biomechanical constraints of soft tissues have been successfully warranted after registration. The codes are available at https://github.com/ZheMin-1992/Registration_PINNs.

PURPOSE:In image-guided liver surgery (IGLS), the preoperative information can be overlaid onto the intraoperative scene by registering the 3D preoperative model with the intraoperative surface reconstructed from the laparoscopic image. It enables doctors to accurately locate tumors and perform precise resections. However, accurate registration remains challenging due to significant tissue deformation and partial overlaps caused by the limited laparoscopic view. To address these challenges, we propose a coarse-to-fine non-rigid registration framework using point cloud completion, i.e., point cloud completion-based non-rigid registration (PCReg) framework to achieve accurate registration between the preoperative and intraoperative data. METHODS:PCReg consists of three consecutive stages: intraoperative point cloud completion, coarse registration, and fine registration. More specifically, we firstly utilize the point cloud completion network (PCN)-based method to complete the intraoperative point set. Then, we also develop an improved optimal transport (OT)-based coarse registration method that takes the preoperative and completed intraoperative point set as inputs and predicts the initial displacement field. Finally, a fine registration step is introduced to further refine the coarse alignment result. RESULTS:Experimental results on simulated and real-world datasets demonstrate that PCReg achieves state-of-the-art performance, significantly outperforming existing methods in handling complex tissue deformations and varying overlap ratios. CONCLUSIONS:This work introduces PCReg, a novel point cloud registration framework for image-guided liver surgery. It achieves superior registration accuracy in low-overlapping scenarios and offers a promising solution for registration in image-guided liver surgery.

Monocular depth estimation serves as a core technique in endoscopic applications such as 3D reconstruction and localization. However, most existing methods focus primarily on in-domain depth estimation, which limits their robustness and prevents them from delivering impressive cross-domain performance, due to variations in depth distributions, illumination conditions, and texture patterns. In this work, we propose Depth Any Endoscopy (DAE), a novel self-supervised framework for generalizable depth estimation in monocular endoscopy. To specify, we develop a dual-level Mixture-of-Experts (MoE) adaptation paradigm that effectively tailors Vision Foundation Models to diverse endoscopic procedures, such as laparoscopy and colonoscopy, accounting for the challenges posed by varying environments. Internally, we integrate LoRA and Adapter modules within the MoE architecture, allowing the model to flexibly adapt to the characteristics of input data. Externally, a mixture of domain-specific experts provides customized guidance to enhance the training stability. In addition, we introduce a learnable gradient harmonization mechanism to dynamically balance the optimization between the depth and pose networks, along with a semantic distribution calibration module that strengthens the semantic consistency of depth predictions. Extensive experiments demonstrate that the proposed DAE achieves state-of-the-art performance in both zero-shot and in-domain depth estimation scenarios.

Accurate prostate zonal segmentation on MRI is crucial for prostate cancer (PCa) detection and treatment. Traditional CNN-based methods, though effective in single-center training, often lack global context awareness and generalize poorly to external datasets, especially in the peripheral zone (PZ) with fuzzy boundaries. Recently, foundation models like the Segment Anything Model (SAM) have shown strong segmentation ability, but domain gaps and limited medical annotations hinder their direct use in medical imaging. To address these challenges, we propose ProZoneSAM2, a region-constrained fine-tuning segmentation method built upon SAM2. ProZoneSAM2 fine-tunes only the memory encoder and mask decoder (5.58 M parameters) and introduces a Region-Constrained Loss Mechanism (RCLM) to enforce anatomical consistency among PZ and central gland (CG) by constraining their spatial complementarity within the whole gland (WG). ProZoneSAM2 achieves Dice scores of 94.46%, 92.74 %, and 80.07 % on the internal test (from Prostate158, PROSTATEx, and MSD) and $94.37 \%, 91.91 \%$, and 79.96 % on the external test (NCI-ISBI 2013) for WG, CG, and PZ, outperforming CNN-based and SAM-based methods.

In recent times, geometric foundation models have demonstrated remarkable performance in depth estimation tasks, benefiting from exposure to large-scale data that enables the learning of intricate geometric structures and spatial dependencies. However, their large parameter sizes and high computational complexity pose significant challenges in meeting the efficiency requirements of downstream surgical applications. Consequently, the design of a high-performance yet lightweight monocular depth estimator has become a focal point of research. To this end, we harness the rich geometric priors encoded in geometric foundation models and introduce a novel trinity distillation scheme that transfers geometric knowledge across three complementary dimensions, namely spatial, spectral and gradient, into a compact depth estimator. To further enhance prediction quality, we develop a semantic distribution alignment strategy to effectively suppress pseudo-texture artifacts arising from the limited semantic representation capability of the lightweight estimator. Extensive experiments on the SCARED, SERV-CT, Hamlyn, and C3VD datasets demonstrate that the proposed method either surpasses or achieves comparable performance to previous state-of-the-art competitors, with a smaller model size and reduced computational overhead. Code will be available at: https://github.com/ShuweiShao/LiteNet.

In computer-assisted orthopedic surgery (CAOS), accurately registering sparse and partial intraoperative point sets with a complete preoperative model remains highly challenging due to limited overlap, extreme sparsity, and point localisation noise. In this paper, we propose a novel end-to-end completion–registration framework, to accurately register partial and sparse point sets in CAOS. First, we develop a three-branch network that separately encodes intraoperative pose and geometry, while extracting rotation-invariant geometric priors from the preoperative model in a canonical space. This structure-aware design provides strong and beneficial cues for completing missing regions using sparse and partial data. Second, to address the sensitivity of the completion to random input poses, the completion is specifically conducted in a canonical frame and a learned SE(3) transform maps the output back to the observed intraoperative space. Third, we introduce a probabilistic registration module based on a bidirectional hybrid mixture model that aligns the completed intraoperative and preoperative point sets in distribution space by jointly optimizing the source-to-target and target-to-source objectives, addressing density mismatch and geometric inconsistencies that may arise from completion. Finally, we present the individual loss formulations for both supervised and unsupervised learning paradigms respectively, enabling robust end-to-end optimization of the entire pipeline. We systematically validate our approach on (1,757) femur, (1,301) hip, and (397) tibia models, as well as real-world phantom experiments. Our method achieves state-of-the-art performance under low overlap (15–30%), sparse observations (64–128 points), and large initial misalignments (up to ([-180, 180]^circ) rotation and ([-100, 100]mm) translation), demonstrating strong robustness and generalization.

Non-rigid registration is essential for augmented reality-guided laparoscopic liver surgery, as it enables the fusion of preoperative information such as tumor location and vascular structures into the limited intraoperative view, thereby enhancing surgical navigation. A prerequisite is the accurate prediction of intraoperative liver deformation, which remains highly challenging due to factors such as large deformation caused by pneumoperitoneum, respiration and tool interaction as well as noisy intraoperative data, and limited field of view due to occlusion and constrained camera movement. To address these challenges, we introduce PIVOTS, a Preoperative to Intraoperative VOlume-To-Surface registration neural network that directly takes point clouds as input for deformation prediction. The geometric feature extraction encoder allows multi-resolution feature extraction, and the decoder, comprising inter-modality cross attention modules, enables information exchange between pre- and intraoperative features and accurate multi-level displacement prediction. We train the neural network on a large synthetic dataset created using a biomechanical simulation pipeline that explicitly targets the mentioned intraoperative challenges and validate its performance on both synthetic and real datasets. Results demonstrate superior registration performance of our method compared to baseline methods, exhibiting strong robustness against high amounts of noise, large deformation, and various levels of intraoperative visibility. The network is fast enough to run multiple times per second and directly generalizes to new patients without retraining. We publish training and test sets as evaluation benchmarks in an effort to contribute to the development of more robust liver registration methods based on volume-to-surface data. Code, docker container and datasets are available athttps://github.com/pengliu-nct/PIVOTS.

In this paper, we present a novel curve-to-surface registration method, termed Bi-directional Hybrid Mixture Model Registration based on Dual-constrained Tangent and Normal Vectors (BiHMM-DTN), where two different tangent vectors at the intraoperative point are simultaneously used with the normal vector at the corresponding preoperative point to construct the geometric constraints. While hybrid registration models incorporating tangent and normal vectors (HMM-TN) demonstrate success, their geometric constraints prove inadequate or inappropriate for sparse intraoperative point sets, frequently yielding suboptimal optimization outcomes. By critically revisiting the geometric constraints of HMM-TN, we propose a dual-constraints-based hybrid mixture model registration framework with enhanced intraoperative point set acquisition protocols. To deal with noise and outliers in preoperative and intraoperative point sets—caused by reconstruction inaccuracies and tracking errors, respectively—our approach employs a bi-directional registration mechanism for curve-to-surface registration. We provide rigorous proofs validating the geometric completeness of the dual constraints within this mechanism. The BiHMM-DTN framework is formulated as a maximum likelihood estimation (MLE) problem and optimized using an expectation-maximization (EM) algorithm. Furthermore, to enhance convergence stability and accelerate optimization, the rotation matrix is updated iteratively through successive incremental steps. Extensive experiments on human femur and hip models demonstrate that our method outperforms state-of-the-art approaches, including both traditional optimization and deep learning methods, under various noise and outlier conditions. Furthermore, real-world phantom experiments highlight the potential clinical value of our method for surgical navigation applications. The codes and data are available at https://github.com/sam-zyzhang/BiHMM-DTN.git.

3D point cloud registration is an essential problem in computer vision, robotics, surgical navigation and augmented reality. Accurate registration of partially overlapped intraoperative point clouds (e.g., femoral reconstruction) remains critical yet challenging in orthopedic navigation due to incomplete overlap and dynamic noise. In this study, we propose a partial-to-partial point cloud registration framework based on directional spatial consistency. First, we extract overlapped areas from partially overlapping point clouds and leverage the point registration graph matching module to calculate the hard point matching matrix. Second, we sample nodes from the source point cloud and generate translation-invariant edge vectors (direction/scale-preserving) via their k-nearest neighbors, guided by predicted point correspondences. This bypasses translation ambiguities by encoding spatial consistency through edges, reducing pose estimation to 3DoF alignment (rotation). The loss explicitly couples point-level matches with edge-level geometric constraints for dual optimization. Building upon this framework, we extract reliable overlapping edge representations and prune their similarity matrix by thresholding low-confidence scores, effectively suppressing spurious matches. The proposed edge-aware matching mechanism further exploits the translation invariance of local structures to refine point correspondences with enhanced accuracy. Finally, we introduce a bidirectional registration mechanism to reinforce optimization stability, achieving state-of-the-art performance across benchmarks. Extensive experiments on ModelNet40, ShapeNet, and MedShapeNet validate our method under diverse scenarios: partial-to-partial, unseen categories, partial-to-full, and cross-dataset generalization, surpassing existing methods in registration accuracy. The codes are available at https://github.com/pidan0824/DSCGM.

The switch from oxidative phosphorylation to glycolysis is crucial for microglial activation. Recent studies highlight that histone lactylation promotes macrophage homeostatic gene expression via transcriptional regulation, but its role in microglia activation in Parkinson’s disease (PD) remains unclear. Here, we demonstrated that inhibiting glycolysis with 2-deoxy-d-glucose alleviates microgliosis, neuroinflammation and dopaminergic neurons damage by reducing lactate accumulation in PD mice. Notably, we observed a marked increase in histone lactylation, particularly H3K9 lactylation, in microglia in the substantia nigra of PD mice. Mechanistically, CUT&Tag and Chip-qPCR analyses revealed that H3K9 lactylation enriched at the SLC7A11promoter and activated its expression. Importantly, inhibiting SLC7A11 by sulfasalazine mitigated microglia-mediated neuroinflammation and improved motor function in PD mice. Moreover, we found that lactate-induce histone lactylation is dependent on P300/CBP. Collectively, our findings demonstrate that glycolysis-derived lactate promotes microglial activation via histone lactylation and provide a potential therapeutic strategy for PD.

In this paper, we propose a novel medical image registration framework called Det-SAMReg, aiming to fully leverage foundation vision models while minimizing training efforts. More specifically, the Grounding DINO-based detection module is first used to predict the target organ (e.g., prostate)’s bounding box using engineered text prompts specific to the anatomy-of-interest, with which the SAM-based segmentation module then automatically generates organ masks for both the moving and fixed images. These pairs of segmented masks are subsequently fed into an iterative optimization-based registration process to estimate the voxel-wise dense displacement field. Furthermore, it is found that fine-tuning detection and segmentation modules with substantially fewer samples achieved comparable performance to using the full training set. The impact of noise in localising bounding boxes on detection, segmentation and registration performances is also investigated. Experimental results of MRI-to-US registration demonstrate that Det-SAMReg significantly outperforms competitive learning-based methods, achieving a Dice Similarity Coefficient (DSC) of 0.867 and a Target Registration Error (TRE) of 5.548 mm, compared to those being 0.724 and 8.897 mm achieved by the strongest tested baseline method TransMorph ( p <0.001 ). Det-SAMReg remarkably maintains superior performance and significantly outperforms ( p <0.001 ) compared methods in MRI-to-US registration when detection and segmentation modules are fine-tuned with only 14 training samples. The source codes have been released at: https://github.com/ymttt111/Det-SAMReg.git .

Surgical video synthesis offers a cost-effective way to expand training data and enhance the performance of machine learning models in computer-assisted surgery. However, existing video translation methods often produce video sequences with large illumination changes across different views, disrupting the temporal consistency of the videos. Additionally, these methods typically synthesize videos with a monotonous style, whereas diverse synthetic data is desired to improve the generalization ability of downstream machine learning models. To address these challenges, we propose a novel Controllable Illumination Invariant Generative Adversarial Network (CIIGAN) for generating diverse, illumination-consistent video sequences. CIIGAN fuses multi-scale illumination-invariant features from a novel controllable illumination-invariant (CII) image space with multi-scale texture-invariant features from self-constructed 3D scenes. The CII image space, along with the 3D scenes, allows CIIGAN to produce diverse and temporally-consistent video or image translations. Extensive experiments demonstrate that CIIGAN achieves more realistic and illumination-consistent translations compared to previous state-of-the-art baselines. Furthermore, the segmentation networks trained on our diverse synthetic data outperform those trained on monotonous synthetic data. Our source code, well-trained models, and 3D simulation scenes are public available at https://github.com/LongChenCV/CIIGAN.

In this paper, we propose a novel unsupervised learning-based non-rigid 3D point set registration method, Learning Coherent Point Drift Network (LCNet), for image-guided liver surgery. We reformulate the classical probabilistic registration approach, i.e., Coherent Point Drift (CPD) into a learning-based paradigm. We first utilise the feature extraction module (FEM) to extract the features of two original point sets, which are robust to rigid transformation. Subsequently, we establish reliable correspondences between the point sets using the optimal transport (OT) module by leveraging both original points and learned features. Then, rather than directly regressing displacement vectors, we compute the displacements by solving the involved matrix equation in the transformation module, where the point localization noise is explicitly considered. In addition, we present three variants of the proposed approach, i.e., LCNet, LCNet-ED and LCNet-WD. Among these, LCNet outperforms the other two, demonstrating the superiority of the Chamfer loss. We have extensively evaluated LCNet on the simulated and real datasets. Under experimental conditions with the rotation angle lies in the range of [-45(degrees),45(degrees)] and the translation in the range of [-30mm,30mm] , LCNet achieves the root-mean-square-error (rmse) value being 3.46 mm on the MedShapeNet dataset, while those using CPD and RoITr are 7.65 mm (p<0.001) and 6.71 mm (p<0.001) respectively. Experimental results show that LCNet exhibits significant improvements over existing state-of-the-art registration methods and shed light on its promising use in image-guided liver surgery.

This study conducts a comparative analysis of two types of augmented reality-assisted surgical navigation systems designed for orthopedic procedures. The first system is the Visual Tag-based navigation System (VTS), and the second is the External Optical tracker-based navigation System (EOS). This study aims to identify a more practical architecture for clinical use. Experiments conducted on a femur phantom assessed five registration algorithms, including ICP, CPD, BCPD, RANSAC, and PointNetLK. The VTS achieved an average target registration error of 9.37±4.68 mm and target visualization error of 9.31±3.20 mm, while the EOS attained a target registration error of 4.02±1.18 mm and a target visualization error of 8.40±0.81 mm. Although the EOS demonstrated a statistically significant advantage in target registration error (p< 0.001), no significant difference was observed in target visualization error (p > 0.05).

BACKGROUND:The diagnosis of Parkinson's disease (PD) lacks reliable biomarkers. This study investigated substantia nigra (SN) elasticity using shear wave elastography (SWE) as a novel diagnostic tool for PD. OBJECTIVES:To investigate the role of SN elasticity values in the diagnosis of PD and their correlation with disease severity, duration, and iron metabolism indicators. METHODS:This study included PD patients diagnosed and treated at Tongji Hospital's Neurology Department and healthy controls from January 2021 to December 2022. SWE was used to measure the elasticity of the SN and surrounding midbrain regions. Differences in elasticity between the two groups were analyzed, along with correlations between SN elasticity and age, hyperechoic area of SN, iron metabolism markers, and disease duration. RESULTS:A total of 90 patients with PD and 106 healthy controls who could undergo transcranial ultrasound elastography were enrolled. The PD group demonstrated significantly elevated SN elasticity values (20.43 ± 3.94 kPa vs. 10.72 ± 1.86 kPa, P < 0.001) compared with controls. The SN elasticity value demonstrated higher classification performance with an area under the curve (AUC) of 0.96 (95% CI: 0.87-0.98) compared with the hyperechogenic area of SN (AUC: 0.884, 95% CI: 0.85-0.92). The elasticity values of the SN in the PD group were positively correlated with disease duration (r = 0.503, P < 0.001). CONCLUSIONS:SN elasticity values are a promising classification biomarker for PD, showing a significant association with disease duration and improving classification performance. These findings highlight the potential of biomechanical properties in neurodegenerative disease assessment and call for further validation in larger cohorts. © 2025 International Parkinson and Movement Disorder Society.