Magnetic resonance (MR) tagging is an imaging technique for noninvasively tracking tissue motion in vivo by creating a visible pattern of magnetization saturation (tags) that deforms with the tissue. Due to longitudinal relaxation and progression to steady-state, the tags and tissue brightnesses change over time, which makes tracking with optical flow methods error-prone. Although Fourier methods can alleviate these problems, they are also sensitive to brightness changes as well as spectral spreading due to motion. To address these problems, we introduce the brightness-invariant tracking estimation (BRITE) technique for tagged MRI. BRITE disentangles the anatomy from the tag pattern in the observed tagged image sequence and simultaneously estimates the Lagrangian motion. The inherent ill-posedness of this problem is addressed by leveraging the expressive power of denoising diffusion probabilistic models to represent the probabilistic distribution of the underlying anatomy and the flexibility of physics-informed neural networks to estimate biologically-plausible motion. A set of tagged MR images of a gel phantom was acquired with various tag periods and imaging flip angles to demonstrate the impact of brightness variations and to validate our method. The results show that BRITE achieves more accurate motion and strain estimates as compared to other state of the art methods, while also being resistant to tag fading.

Whole Slide Images (WSIs) in histopathology present a significant challenge for large-scale medical image analysis due to their high resolution, large size, and complex tile relationships. Existing Multiple Instance Learning (MIL) methods, such as Graph Neural Networks (GNNs) and Transformer-based models, face limitations in scalability and computational cost. To bridge this gap, we propose the WSI-GMamba framework, which synergistically combines the relational modeling strengths of GNNs with the efficiency of Mamba, the State Space Model designed for sequence learning. The proposed GMamba block integrates Message Passing, Graph Scanning & Flattening, and feature aggregation via a Bidirectional State Space Model (Bi-SSM), achieving Transformer-level performance with 7* fewer FLOPs. By leveraging the complementary strengths of lightweight GNNs and Mamba, the WSI-GMamba framework delivers a scalable solution for large-scale WSI analysis, offering both high accuracy and computational efficiency for slide-level classification.

Medical image segmentation is vital for clinical diagnosis, yet current deep learning methods often demand extensive expert effort, i.e., either through annotating large training datasets or providing prompts at inference time for each new case. This paper introduces a zero-shot and automatic segmentation pipeline that combines off-the-shelf vision-language and segmentation foundation models. Given a medical image and a task definition (e.g., "segment the optic disc in an eye fundus image"), our method uses a grounding model to generate an initial bounding box, followed by a visual prompt boosting module that enhance the prompts, which are then processed by a promptable segmentation model to produce the final mask. To address the challenges of domain gap and result verification, we introduce a test-time adaptation framework featuring a set of learnable adaptors that align the medical inputs with foundation model representations. Its hyperparameters are optimized via Bayesian Optimization, guided by a proxy validation model without requiring ground-truth labels. Our pipeline offers an annotation-efficient and scalable solution for zero-shot medical image segmentation across diverse tasks. Our pipeline is evaluated on seven diverse medical imaging datasets and shows promising results. By proper decomposition and test-time adaptation, our fully automatic pipeline performs competitively with weakly-prompted interactive foundation models.

Accurate prediction of prognosis and postoperative radiotherapy response is critical for personalized treatment in head and neck squamous cell carcinoma (HNSCC). We developed a multimodal deep learning model (MDLM) integrating computed tomography, whole-slide images, and clinical features from 1087 HNSCC patients across multiple centers. The MDLM exhibited good performance in predicting overall survival (OS) and disease-free survival in external test cohorts. Additionally, the MDLM outperformed unimodal models. Patients with a high-risk score who underwent postoperative radiotherapy exhibited prolonged OS compared to those who did not (P = 0.016), whereas no significant improvement in OS was observed among patients with a low-risk score (P = 0.898). Biological exploration indicated that the model may be related to changes in the cytochrome P450 metabolic pathway, tumor microenvironment, and myeloid-derived cell subpopulations. Overall, the MDLM effectively predicts prognosis and postoperative radiotherapy response, offering a promising tool for personalized HNSCC therapy.

Glaucoma is a group of serious eye diseases that can cause incurable blindness. Despite the critical need for early detection, over 60% of cases remain undiagnosed, especially in less developed regions. Glaucoma diagnosis is a costly task and some models have been proposed to automate diagnosis based on images of the retina, specifically the area known as the optic cup and the associated disc where retinal blood vessels and nerves enter and leave the eye. However, diagnosis is complicated because both normal and glaucoma-affected eyes can vary greatly in appearance. Some normal cases, like glaucoma, exhibit a larger cup-to-disc ratio, one of the main diagnostic criteria, making it challenging to distinguish between them. We propose a deep learning model with domain features (DLMDF) to combine unstructured and structured features to distinguish between glaucoma and physiologic large cups. The structured features were based upon the known cup-to-disc ratios of the four quadrants of the optic discs in normal, physiologic large cups, and glaucomatous optic cups. We segmented each cup and disc using a fully convolutional neural network and then calculated the cup size, disc size, and cup-to-disc ratio of each quadrant. The unstructured features were learned from a deep convolutional neural network. The average precision (AP) for disc segmentation was 98.52%, and for cup segmentation it was also 98.57%. Thus, the relatively high AP values enabled us to calculate the 15 reliable features from each segmented disc and cup. In classification tasks, the DLMDF outperformed other models, achieving superior accuracy, precision, and recall. These results validate the effectiveness of combining deep learning-derived features with domain-specific structured features, underscoring the potential of this approach to advance glaucoma diagnosis.

Low-quality pseudo labels pose a significant obstacle in semi-supervised medical image segmentation (SSMIS), impeding consistency learning on unlabeled data. Leveraging vision-language model (VLM) holds promise in ameliorating pseudo label quality by employing textual prompts to delineate segmentation regions, but it faces the challenge of cross-modal alignment uncertainty due to multiple correspondences (multiple images/texts tend to correspond to one text/image). Existing VLMs address this challenge by modeling semantics as distributions but such distributions lead to semantic degradation. To address these problems, we propose Alignment-Multiplicity Aware Vision-Language Model (AMVLM), a new VLM pre-training paradigm with two novel similarity metric strategies. (i) Cross-modal Similarity Supervision (CSS) proposes a probability distribution transformer to supervise similarity scores across fine-granularity semantics through measuring cross-modal distribution disparities, thus learning cross-modal multiple alignments. (ii) Intra-modal Contrastive Learning (ICL) takes into account the similarity metric of coarse-fine granularity information within each modality to encourage cross-modal semantic consistency. Furthermore, using the pretrained AMVLM, we propose a pioneering text-guided SSMIS network to compensate for the quality deficiencies of pseudo-labels. This network incorporates a text mask generator to produce multimodal supervision information, enhancing pseudo label quality and the model's consistency learning. Extensive experimentation validates the efficacy of our AMVLM-driven SSMIS, showcasing superior performance across four publicly available datasets. The code will be available at: https://github.com/QingtaoPan/AMVLM.

Medical image segmentation faces persistent challenges due to severe class imbalance and the frequency-specific distribution of anatomical structures. Most conventional CNN-based methods operate in the spatial domain and struggle to capture minority class signals, often affected by frequency aliasing and limited spectral selectivity. Transformer-based models, while powerful in modeling global dependencies, tend to overlook critical local details necessary for fine-grained segmentation. To overcome these limitations, we propose FreqU-FNet, a novel U-shaped segmentation architecture operating in the frequency domain. Our framework incorporates a Frequency Encoder that leverages Low-Pass Frequency Convolution and Daubechies wavelet-based downsampling to extract multi-scale spectral features. To reconstruct fine spatial details, we introduce a Spatial Learnable Decoder (SLD) equipped with an adaptive multi-branch upsampling strategy. Furthermore, we design a frequency-aware loss (FAL) function to enhance minority class learning. Extensive experiments on multiple medical segmentation benchmarks demonstrate that FreqU-FNet consistently outperforms both CNN and Transformer baselines, particularly in handling under-represented classes, by effectively exploiting discriminative frequency bands.

Medical image reconstruction from measurement data is a vital but challenging inverse problem. Deep learning approaches have achieved promising results, but often requires paired measurement and high-quality images, which is typically simulated through a forward model, i.e., retrospective reconstruction. However, training on simulated pairs commonly leads to performance degradation on real prospective data due to the retrospective-to-prospective gap caused by incomplete imaging knowledge in simulation. To address this challenge, this paper introduces imaging Knowledge-Informed Dynamic Optimal Transport (KIDOT), a novel dynamic optimal transport framework with optimality in the sense of preserving consistency with imaging physics in transport, that conceptualizes reconstruction as finding a dynamic transport path. KIDOT learns from unpaired data by modeling reconstruction as a continuous evolution path from measurements to images, guided by an imaging knowledge-informed cost function and transport equation. This dynamic and knowledge-aware approach enhances robustness and better leverages unpaired data while respecting acquisition physics. Theoretically, we demonstrate that KIDOT naturally generalizes dynamic optimal transport, ensuring its mathematical rationale and solution existence. Extensive experiments on MRI and CT reconstruction demonstrate KIDOT's superior performance.

This paper presents a novel method for monocular patient-to-image intraoperative registration, specifically designed to operate without any external hardware tracking equipment or fiducial point markers. Leveraging a synthetic microscopy surgical scene dataset with a wide range of transformations, our approach directly maps preoperative CT scans to 2D intraoperative surgical frames through a lightweight neural network for real-time cochlear implant surgery guidance via a zero-shot learning approach. Unlike traditional methods, our framework seamlessly integrates with monocular surgical microscopes, making it highly practical for clinical use without additional hardware dependencies and requirements. Our method estimates camera poses, which include a rotation matrix and a translation vector, by learning from the synthetic dataset, enabling accurate and efficient intraoperative registration. The proposed framework was evaluated on nine clinical cases using a patient-specific and cross-patient validation strategy. Our results suggest that our approach achieves clinically relevant accuracy in predicting 6D camera poses for registering 3D preoperative CT scans to 2D surgical scenes with an angular error within 10 degrees in most cases, while also addressing limitations of traditional methods, such as reliance on external tracking systems or fiducial markers.

Medical image segmentation, particularly in multi-domain scenarios, requires precise preservation of anatomical structures across diverse representations. While deep learning has advanced this field, existing models often struggle with accurate boundary representation, variability in organ morphology, and information loss during downsampling, limiting their accuracy and robustness. To address these challenges, we propose the Context Enhancement Network (CENet), a novel segmentation framework featuring two key innovations. First, the Dual Selective Enhancement Block (DSEB) integrated into skip connections enhances boundary details and improves the detection of smaller organs in a context-aware manner. Second, the Context Feature Attention Module (CFAM) in the decoder employs a multi-scale design to maintain spatial integrity, reduce feature redundancy, and mitigate overly enhanced representations. Extensive evaluations on both radiology and dermoscopic datasets demonstrate that CENet outperforms state-of-the-art (SOTA) methods in multi-organ segmentation and boundary detail preservation, offering a robust and accurate solution for complex medical image analysis tasks. The code is publicly available at https://github.com/xmindflow/cenet.