IEEE transactions on medical imaging最新文献

Immunohistochemistry (IHC) staining is crucial for determining tumor subtypes, obtaining protein expression information, and developing personalized treatment plans. But compared with hematoxylin and eosin (H&E) staining, IHC staining is more complex and expensive. With the advancement of deep learning, converting H&E stained images into IHC stained images has gradually emerged as a solution for obtaining IHC staining. However, current virtual staining processes suffer from difficulties in aligning pathological semantic features, posing significant challenges for network training, which poses significant challenges for network training. To solve these issues, we propose a multi-view multi-level pathology semantic perception learning method for H&E-to-IHC virtual staining (M2PL-GAN). Unlike prior approaches, M2PL-GAN introduces a comprehensive semantic learning paradigm from three views: structural contextual relations, feature distribution, and topology-aware fine-grained semantics. These correspond to the Context-aware Correlation Mechanism (CACM), the Local-aware Distribution Alignment Mechanism (LDAM), and the Graph-aware Bidirectional Contrastive Learning Mechanism (GBCLM) respectively. Among them, CACM enhances contextual consistency by establishing semantic correlations between virtual and real IHC images at local scales. LDAM ensures alignment of semantic feature distributions between virtual and real IHC images, mitigating semantic shifts caused by HE-IHC staining. GBCLM leverages graph neural network to capture topology-aware semantic representations and optimizes semantic feature alignment through bidirectional contrastive learning. Extensive experiments on both public and private datasets demonstrate that our method outperforms state-of-the-art approaches in both quantitative metrics and qualitative evaluations. Our code is available in https://github.com/Pikachu-one/M2PL-GAN.

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.

Precise cortical and cancellous bone segmentation is essential for safe laminectomy. However, it remains challenging due to limited annotations and high anatomical similarity. To mitigate these challenges, we propose MambaMatch, an end-to-end semi-supervised segmentation framework collaboratively optimized under a teacher-student paradigm. The student branch adopts an innovative Mamba-ASPP-Unet (MAU) module, which integrates multi-scale Atrous Spatial Pyramid Pooling (ASPP) with channel and spatial attention to actively extract global spinal structures and cortical boundary features, while the teacher branch guides the student through constraints imposed by the KL-divergence. To enhance feature diversity, a dual-stream perturbation strategy is employed, combining Correlation-Guided CutMix Augmentation (CGCA) on high-response regions with standard strong augmentations. Furthermore, to account for inter-class variations in pseudo-label reliability, dynamic thresholding and temperature scaling are further introduced to adaptively balance pseudo-label selection and the intensity of consistency loss. MambaMatch achieves an mIoU of 79.69% and a Dice of 83.57% on our clinically validated CT Cortical- Cancellous Dataset, and also shows strong robustness on MRI-SPIDER, SKIN-ISIC 2018, PH², and CT-VerSe datasets and the model remains lightweight and efficient. These results show that MambaMatch provides an efficient and accurate segmentation framework with clear potential to support clinical workflows in spinal surgery, while also demonstrating value across a broader range of clinical imaging scenarios.

Performing unsupervised anomaly detection in retinal optical coherence tomography (OCT) images involves training a model solely on anomaly-free samples and detecting anomalies during inference, which reduces the cost of collecting large-scale annotated anomalous data. However, retinal OCT images exhibit significant variations in shape, thickness, and orientation, and lesions often have similar reflectance signals as normal tissues, making anomaly localization highly challenging. Existing methods address these challenges by flattening retinal layers, normalizing thickness, or leveraging reflectance priors, but their reliance on complex pre- and post-processing introduces uncertainties and limits end-to-end clinical applicability. To overcome these issues, we propose a novel semantic augmentation variational autoencoder (SeAugVAE) for unsupervised anomaly detection in retinal OCT images. Specifically, to capture the anatomical variability of normal retinas and thereby enhance anomaly sensitivity, we introduce a self-supervised semantic data augmentation strategy that enforces dual distribution consistency in both image and feature spaces during VAE training. For precise anomaly localization, we develop structural-semantic anomaly attention maps in the inference phase to detect anomalies from both local and global perspectives, and combine them to calculate anomaly score maps as the metric for localizing anomalous regions in images. Extensive experiments on multiple publicly and privately collected Cirrus and Spectralis OCT datasets demonstrate the effectiveness of SeAugVAE in pixel-wise unsupervised anomaly detection across multiple retinal diseases. Our codes are available at https://github.com/xyzhou1121/SeAugVAE.

Histology image segmentation is a critical prerequisite to pathological diagnosis. Accurate segmentation of these images can significantly aid physicians by facilitating quicker and more precise diagnostic decisions. A notable challenge in this area arises from the fact that different objects within histology images require segmentation at varying magnifications. However, most existing models are typically limited to performing segmentation at one pre-determined magnification. In this paper, we propose a novel universal scale transformer model (UniScaleFormer), which employs a scale-aware approach and integrates textual input to uniformly segment objects in histology images across various magnifications. Our method adopts an end-to-end architecture and utilizes a candidate mask query mechanism, specifically designed to identify and distinguish objects at different image scales. Moreover, we develop a Scale-Aware Module that enhances our network's ability to recognize the magnification level of input histology images, by using a scale query with extracted visual features. Then the scale query is integrated with mask queries, facilitating the incorporation of scale information. Experimental results demonstrate that the proposed method effectively achieves competitive results on various segmentation benchmarks at different magnifications. The code will be released at https://github.com/lhaof/UniScale.

Generative diffusion models have received increasing attention in medical imaging, particularly in limited-angle computed tomography (LACT). Standard diffusion models achieve high-quality image reconstruction but require a large number of sampling steps during inference, imposing a heavy computational burden. Although skip-sampling strategies have been proposed to improve efficiency, they often lead to loss of fine structural details. To address this issue, we propose a Prior-aware Wavelet Diffusion for Efficient Dental Limited-angle CT Reconstruction (PWD). The PWD enables efficient sampling while preserving reconstruction fidelity in LACT, and effectively mitigates the degradation typically introduced by skip-sampling. Specifically, during the training phase, PWD maps the distribution of LACT images to that of fully sampled target images, enabling the model to learn structural correspondences between them. During inference, the LACT image serves as an prior-aware to guide the sampling trajectory, allowing for high-quality reconstruction with significantly fewer steps. In addition, PWD performs multi-scale feature fusion in the wavelet domain, effectively enhancing the reconstruction of fine details by leveraging both low-frequency and high-frequency information. Quantitative and qualitative evaluations on clinical dental arch CBCT and periapical datasets demonstrate that PWD outperforms existing methods under the same sampling condition. Using only 50 sampling steps, PWD achieves at least 1.7 dB improvement in PSNR and 10% gain in SSIM.

Accurate segmentation of cervical structures in transvaginal ultrasound (TVS) is critical for assessing the risk of spontaneous preterm birth (PTB), yet the scarcity of labeled data limits the performance of supervised learning approaches. This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation, hosted at ISBI 2025. FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images. Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2. The challenge attracted 10 teams with 82 participants submitting innovative solutions. The best-performing methods for each individual metric achieved 90.26% mDSC, 38.88 mHD, and 32.85 ms RT, respectively. FUGC establishes a standardized benchmark for cervical segmentation, demonstrates the efficacy of semi-supervised methods with limited labeled data, and provides a foundation for AI-assisted clinical PTB risk assessment.

Probing diffusion in myelin water using diffusion-weighted T₁-/T₂-selective MRI acquisitions enables noninvasive measurement of myelinated axon diameter. Its application for in vivo measurements requires numerical verification through diffusion simulations. Here, we propose the theory of myelin water diffusion as measured with a diffusion MRI pulse sequence with wide gradient pulses using the Gaussian phase approximation. We establish its applicability to axonal diameter mapping via Monte Carlo simulations in either infinitely thin cylindrical surfaces or concentric cylindrical shells of finite thickness, mimicking the micro-geometry of myelin sheaths. The estimated diameters are shown to be weighted more toward outer than inner calibers. Simulation results evaluate the theory of myelin water diffusion and axon diameter estimation using spherical mean diffusion signals, demonstrating its applicability at signal-to-noise ratio above 20 on the Connectome 2.0 MRI scanner equipped with maximum gradient strength of 500 mT/m and slew rate of 600 T/m/s. Measuring restricted diffusion of myelin water in-between myelin sheaths using diffusion MRI allows one to measure myelinated axon diameters in vivo. The protocol can potentially be adapted for clinically available high-gradient performance scanners.

Pseudo-healthy image synthesis aims to generate subject-specific, pathology-free images from pathological scans. Such images can be helpful in certain tasks, such as anomaly detection and understanding changes induced by pathology and disease. A participant cannot be "healthy" and "unhealthy" at the same time, and thus, directly obtaining pathological and healthy paired images of the same individual to train and evaluate supervised learning algorithms is infeasible. In addition, simultaneously meeting the requirements of subjects' "identity" preservation and pathology restoration performance is frequently difficult for existing unsupervised learning methods, especially for large or information-free pathological regions, such as postoperative cavities. In this study, we propose a novel pseudo-healthy synthesis framework that combines low-resolution residual decoupling with an edge-prior-guided super-resolution reconstruction module. We named this framework LRD-ESR-Net. In particular, by using a coarse-to-fine synthesis pipeline, the residual decoupling network first decouples information-rich tumor tissues or information-free resection cavities from healthy brain tissues in low-resolution pathological magnetic resonance images. Then, a residual-shifting diffusion network with Canny edge maps is employed to reconstruct low-resolution pseudo-healthy images to their original resolutions. We evaluate the proposed framework on one in-house brain dataset, two public brain datasets, and one public liver dataset, and validate its effectiveness on low-contrast lesion segmentation and pre-/postoperative brain tumor MRI registration. Results show that LRD-ESR-Net consistently outperforms state-of-the-art methods in pseudo-healthy image quality, anatomical preservation, and downstream task performance, demonstrating strong robustness and generalization across organs, modalities, and lesion types.

Direct parametric reconstruction algorithms have been developed to improve the statistical reliability of parametric images estimated from dynamic PET imaging data. However, these estimates are degraded by noise due to measurement error and noise propagation during reconstruction. In this study, we develop a deep image prior (DIP) regularized direct reconstruction method, where the DIP network is used to represent the estimated parametric image. By initializing the DIP with pre-trained weights and updating its network to learn the intermediate information during reconstruction, the DIP regularization leverages the available population and subject-specific features. The proposed method is applied to reconstruct K₁ from both simulated and patient data acquired by ⁸²Rb dynamic PET myocardial perfusion imaging. Benefiting from the nonlinear representation capability of the DIP network, the proposed method achieves superior noise versus bias/mean performance compared with the indirect and direct reconstruction methods with various regularizations formed by quadratic smoothness, dictionary learning, or fully-connected neural network. To summarize, the proposed method demonstrates its potential in improving the precision of dynamic PET imaging measurements, which will contribute to diagnostic accuracy and disease monitoring.