Pengfei Guo

Cheng Peng, Pengfei Guo, S. Kevin Zhou et al.

Magnetic Resonance (MR) image reconstruction from under-sampled acquisition promises faster scanning time. To this end, current State-of-The-Art (SoTA) approaches leverage deep neural networks and supervised training to learn a recovery model. While these approaches achieve impressive performances, the learned model can be fragile on unseen degradation, e.g. when given a different acceleration factor. These methods are also generally deterministic and provide a single solution to an ill-posed problem; as such, it can be difficult for practitioners to understand the reliability of the reconstruction. We introduce DiffuseRecon, a novel diffusion model-based MR reconstruction method. DiffuseRecon guides the generation process based on the observed signals and a pre-trained diffusion model, and does not require additional training on specific acceleration factors. DiffuseRecon is stochastic in nature and generates results from a distribution of fully-sampled MR images; as such, it allows us to explicitly visualize different potential reconstruction solutions. Lastly, DiffuseRecon proposes an accelerated, coarse-to-fine Monte-Carlo sampling scheme to approximate the most likely reconstruction candidate. The proposed DiffuseRecon achieves SoTA performances reconstructing from raw acquisition signals in fastMRI and SKM-TEA. Code will be open-sourced at www.github.com/cpeng93/DiffuseRecon.

Jeya Maria Jose Valanarasu, Pengfei Guo, Vibashan VS et al.

One major problem in deep learning-based solutions for medical imaging is the drop in performance when a model is tested on a data distribution different from the one that it is trained on. Adapting the source model to target data distribution at test-time is an efficient solution for the data-shift problem. Previous methods solve this by adapting the model to target distribution by using techniques like entropy minimization or regularization. In these methods, the models are still updated by back-propagation using an unsupervised loss on complete test data distribution. In real-world clinical settings, it makes more sense to adapt a model to a new test image on-the-fly and avoid model update during inference due to privacy concerns and lack of computing resource at deployment. To this end, we propose a new setting - On-the-Fly Adaptation which is zero-shot and episodic (i.e., the model is adapted to a single image at a time and also does not perform any back-propagation during test-time). To achieve this, we propose a new framework called Adaptive UNet where each convolutional block is equipped with an adaptive batch normalization layer to adapt the features with respect to a domain code. The domain code is generated using a pre-trained encoder trained on a large corpus of medical images. During test-time, the model takes in just the new test image and generates a domain code to adapt the features of source model according to the test data. We validate the performance on both 2D and 3D data distribution shifts where we get a better performance compared to previous test-time adaptation methods. Code is available at https://github.com/jeya-maria-jose/On-The-Fly-Adaptation

Yufan He, Pengfei Guo, Yucheng Tang et al.

Since the release of Segment Anything 2 (SAM2), the medical imaging community has been actively evaluating its performance for 3D medical image segmentation. However, different studies have employed varying evaluation pipelines, resulting in conflicting outcomes that obscure a clear understanding of SAM2's capabilities and potential applications. We shortly review existing benchmarks and point out that the SAM2 paper clearly outlines a zero-shot evaluation pipeline, which simulates user clicks iteratively for up to eight iterations. We reproduced this interactive annotation simulation on 3D CT datasets and provided the results and code~\url{https://github.com/Project-MONAI/VISTA}. Our findings reveal that directly applying SAM2 on 3D medical imaging in a zero-shot manner is far from satisfactory. It is prone to generating false positives when foreground objects disappear, and annotating more slices cannot fully offset this tendency. For smaller single-connected objects like kidney and aorta, SAM2 performs reasonably well but for most organs it is still far behind state-of-the-art 3D annotation methods. More research and innovation are needed for 3D medical imaging community to use SAM2 correctly.

Pengfei Guo, Can Zhao, Dong Yang et al.

Medical imaging analysis faces challenges such as data scarcity, high annotation costs, and privacy concerns. This paper introduces the Medical AI for Synthetic Imaging (MAISI), an innovative approach using the diffusion model to generate synthetic 3D computed tomography (CT) images to address those challenges. MAISI leverages the foundation volume compression network and the latent diffusion model to produce high-resolution CT images (up to a landmark volume dimension of 512 x 512 x 768 ) with flexible volume dimensions and voxel spacing. By incorporating ControlNet, MAISI can process organ segmentation, including 127 anatomical structures, as additional conditions and enables the generation of accurately annotated synthetic images that can be used for various downstream tasks. Our experiment results show that MAISI's capabilities in generating realistic, anatomically accurate images for diverse regions and conditions reveal its promising potential to mitigate challenges using synthetic data.

Pengfei Guo, Dong Yang, Ali Hatamizadeh et al.

Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. The inherent privacy-preserving property of FL algorithms makes them especially attractive to the medical field. However, in case of heterogeneous client data distributions, standard FL methods are unstable and require intensive hyperparameter tuning to achieve optimal performance. Conventional hyperparameter optimization algorithms are impractical in real-world FL applications as they involve numerous training trials, which are often not affordable with limited compute budgets. In this work, we propose an efficient reinforcement learning (RL)-based federated hyperparameter optimization algorithm, termed Auto-FedRL, in which an online RL agent can dynamically adjust hyperparameters of each client based on the current training progress. Extensive experiments are conducted to investigate different search strategies and RL agents. The effectiveness of the proposed method is validated on a heterogeneous data split of the CIFAR-10 dataset as well as two real-world medical image segmentation datasets for COVID-19 lesion segmentation in chest CT and pancreas segmentation in abdominal CT.

An Xu, Wenqi Li, Pengfei Guo et al.

Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years as it can resolve the critical issues of insufficient data, data privacy, and training efficiency. However, there can be a generalization gap between the model trained from FL and the one from centralized training. This important issue comes from the non-iid data distribution of the local data in the participating clients and is well-known as client drift. In this work, we propose a novel training framework FedSM to avoid the client drift issue and successfully close the generalization gap compared with the centralized training for medical image segmentation tasks for the first time. We also propose a novel personalized FL objective formulation and a new method SoftPull to solve it in our proposed framework FedSM. We conduct rigorous theoretical analysis to guarantee its convergence for optimizing the non-convex smooth objective function. Real-world medical image segmentation experiments using deep FL validate the motivations and effectiveness of our proposed method.

Xirui Hou, Pengfei Guo, Puyang Wang et al.

Cerebrovascular disease is a leading cause of death globally. Prevention and early intervention are known to be the most effective forms of its management. Non-invasive imaging methods hold great promises for early stratification, but at present lack the sensitivity for personalized prognosis. Resting-state functional magnetic resonance imaging (rs-fMRI), a powerful tool previously used for mapping neural activity, is available in most hospitals. Here we show that rs-fMRI can be used to map cerebral hemodynamic function and delineate impairment. By exploiting time variations in breathing pattern during rs-fMRI, deep learning enables reproducible mapping of cerebrovascular reactivity (CVR) and bolus arrive time (BAT) of the human brain using resting-state CO2 fluctuations as a natural 'contrast media'. The deep-learning network was trained with CVR and BAT maps obtained with a reference method of CO2-inhalation MRI, which included data from young and older healthy subjects and patients with Moyamoya disease and brain tumors. We demonstrate the performance of deep-learning cerebrovascular mapping in the detection of vascular abnormalities, evaluation of revascularization effects, and vascular alterations in normal aging. In addition, cerebrovascular maps obtained with the proposed method exhibited excellent reproducibility in both healthy volunteers and stroke patients. Deep-learning resting-state vascular imaging has the potential to become a useful tool in clinical cerebrovascular imaging.

Junqi Liu, Salena Song, Yuhan Wang et al.

Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form clinical question answering. However, existing medical agent benchmarks primarily evaluate final outputs, providing limited visibility into agent behavior within the research process. To address this gap, we present AutoMedBench, a workflow-aware benchmark for autonomous medical-AI research across diverse medical imaging and multimodal inference tasks, organizing agent execution into a unified five-stage workflow (S1-S5): Plan, Setup, Validate, Inference, and Submit. It comprises long-horizon tasks with each run averaging 33 agent turns, spanning five research tracks: segmentation, image enhancement, visual question answering (VQA), report generation, and lesion detection. Each task is evaluated under two difficulty tiers, Lite and Standard, which use the same data and metrics but differ in the amount of task-brief scaffolding, and each run is scored using both final task performance and S1-S5 stage scores, enabling stage-level analysis from the initial task brief to the final submitted artifact. Across thousands of recorded runs, stage-level scoring reveals that Validate is the weakest workflow stage on average, whereas Setup is the strongest, suggesting that current agents are better at making pipelines executable than at verifying their reliability. Post-run error analysis further shows that verification and submission failures dominate tagged errors, accounting for 37.7% and 38.1% of fired codes respectively, whereas task-understanding errors are rare at 0.9%, and runs with one fired error code have a 48% lower overall score than runs with no error code on average.

Yiqing Shen, Pengfei Guo, Jingpu Wu et al.

The synergy of long-range dependencies from transformers and local representations of image content from convolutional neural networks (CNNs) has led to advanced architectures and increased performance for various medical image analysis tasks due to their complementary benefits. However, compared with CNNs, transformers require considerably more training data, due to a larger number of parameters and an absence of inductive bias. The need for increasingly large datasets continues to be problematic, particularly in the context of medical imaging, where both annotation efforts and data protection result in limited data availability. In this work, inspired by the human decision-making process of correlating new evidence with previously memorized experience, we propose a Memorizing Vision Transformer (MoViT) to alleviate the need for large-scale datasets to successfully train and deploy transformer-based architectures. MoViT leverages an external memory structure to cache history attention snapshots during the training stage. To prevent overfitting, we incorporate an innovative memory update scheme, attention temporal moving average, to update the stored external memories with the historical moving average. For inference speedup, we design a prototypical attention learning method to distill the external memory into smaller representative subsets. We evaluate our method on a public histology image dataset and an in-house MRI dataset, demonstrating that MoViT applied to varied medical image analysis tasks, can outperform vanilla transformer models across varied data regimes, especially in cases where only a small amount of annotated data is available. More importantly, MoViT can reach a competitive performance of ViT with only 3.0% of the training data.

Zhitao Zeng, Mengya Xu, Jian Jiang et al.

Surgical intelligence has the potential to improve the safety and consistency of surgical care, yet most existing surgical AI frameworks remain task-specific and struggle to generalize across procedures and institutions. Although multimodal foundation models, particularly multimodal large language models, have demonstrated strong cross-task capabilities across various medical domains, their advancement in surgery remains constrained by the lack of large-scale, systematically curated multimodal data. To address this challenge, we introduce Surg$Σ$, a spectrum of large-scale multimodal data and foundation models for surgical intelligence. At the core of this framework lies Surg$Σ$-DB, a large-scale multimodal data foundation designed to support diverse surgical tasks. Surg$Σ$-DB consolidates heterogeneous surgical data sources (including open-source datasets, curated in-house clinical collections and web-source data) into a unified schema, aiming to improve label consistency and data standardization across heterogeneous datasets. Surg$Σ$-DB spans 6 clinical specialties and diverse surgical types, providing rich image- and video-level annotations across 18 practical surgical tasks covering understanding, reasoning, planning, and generation, at an unprecedented scale (over 5.98M conversations). Beyond conventional multimodal conversations, Surg$Σ$-DB incorporates hierarchical reasoning annotations, providing richer semantic cues to support deeper contextual understanding in complex surgical scenarios. We further provide empirical evidence through recently developed surgical foundation models built upon Surg$Σ$-DB, illustrating the practical benefits of large-scale multimodal annotations, unified semantic design, and structured reasoning annotations for improving cross-task generalization and interpretability.

Yufan He, Pengfei Guo, Mengya Xu et al.

Data scarcity remains a fundamental barrier to achieving fully autonomous surgical robots. While large scale vision language action (VLA) models have shown impressive generalization in household and industrial manipulation by leveraging paired video action data from diverse domains, surgical robotics suffers from the paucity of datasets that include both visual observations and accurate robot kinematics. In contrast, vast corpora of surgical videos exist, but they lack corresponding action labels, preventing direct application of imitation learning or VLA training. In this work, we aim to alleviate this problem by learning policy models from SurgWorld, a world model designed for surgical physical AI. We curated the Surgical Action Text Alignment (SATA) dataset with detailed action description specifically for surgical robots. Then we built SurgeWorld based on the most advanced physical AI world model and SATA. It's able to generate diverse, generalizable and realistic surgery videos. We are also the first to use an inverse dynamics model to infer pseudokinematics from synthetic surgical videos, producing synthetic paired video action data. We demonstrate that a surgical VLA policy trained with these augmented data significantly outperforms models trained only on real demonstrations on a real surgical robot platform. Our approach offers a scalable path toward autonomous surgical skill acquisition by leveraging the abundance of unlabeled surgical video and generative world modeling, thus opening the door to generalizable and data efficient surgical robot policies.

Pengfei Guo, Warren Richard Morningstar, Raviteja Vemulapalli et al.

Large machine learning models trained on diverse data have recently seen unprecedented success. Federated learning enables training on private data that may otherwise be inaccessible, such as domain-specific datasets decentralized across many clients. However, federated learning can be difficult to scale to large models when clients have limited resources. This challenge often results in a trade-off between model size and access to diverse data. To mitigate this issue and facilitate training of large models on edge devices, we introduce a simple yet effective strategy, Federated Layer-wise Learning, to simultaneously reduce per-client memory, computation, and communication costs. Clients train just a single layer each round, reducing resource costs considerably with minimal performance degradation. We also introduce Federated Depth Dropout, a complementary technique that randomly drops frozen layers during training, to further reduce resource usage. Coupling these two techniques enables us to effectively train significantly larger models on edge devices. Specifically, we reduce training memory usage by 5x or more in federated self-supervised representation learning and demonstrate that performance in downstream tasks is comparable to conventional federated self-supervised learning.

Puyang Wang, Pengfei Guo, Keyi Chai et al.

Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We introduce Scalable Deep Unrolled Model (SDUM), a universal framework combining a Restormer-based reconstructor, a learned coil sensitivity map estimator (CSME), sampling-aware weighted data consistency (SWDC), universal conditioning (UC) on cascade index and protocol metadata, and progressive cascade expansion training. SDUM exhibits foundation-model-like scaling behavior: reconstruction quality follows PSNR ${\sim}$ log(parameters) with correlation $r{=}0.986$ ($R^2{=}0.973$) up to 18 cascades, demonstrating predictable performance gains with model depth. A single SDUM trained on heterogeneous data achieves state-of-the-art results across all four CMRxRecon2025 challenge tracks--multi-center, multi-disease, 5T, and pediatric--without task-specific fine-tuning, surpassing specialized baselines by up to ${+}1.0$~dB. On CMRxRecon2024, SDUM outperforms the winning method PromptMR+ by ${+}0.55$~dB; on fastMRI brain, it exceeds PC-RNN by ${+}1.8$~dB. Ablations validate each component: SWDC ${+}0.43$~dB over standard DC, per-cascade CSME ${+}0.51$~dB, UC ${+}0.38$~dB. These results establish SDUM as a practical path toward universal, scalable MRI reconstruction.

Can Zhao, Pengfei Guo, Dong Yang et al.

Medical image synthesis is an important topic for both clinical and research applications. Recently, diffusion models have become a leading approach in this area. Despite their strengths, many existing methods struggle with (1) limited generalizability that only work for specific body regions or voxel spacings, (2) slow inference, which is a common issue for diffusion models, and (3) weak alignment with input conditions, which is a critical issue for medical imaging. MAISI, a previously proposed framework, addresses generalizability issues but still suffers from slow inference and limited condition consistency. In this work, we present MAISI-v2, the first accelerated 3D medical image synthesis framework that integrates rectified flow to enable fast and high quality generation. To further enhance condition fidelity, we introduce a novel region-specific contrastive loss to enhance the sensitivity to region of interest. Our experiments show that MAISI-v2 can achieve SOTA image quality with $33 \times$ acceleration for latent diffusion model. We also conducted a downstream segmentation experiment to show that the synthetic images can be used for data augmentation. We release our code, training details, model weights, and a GUI demo to facilitate reproducibility and promote further development within the community.

Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit et al.

Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architectures, and powerful pretrained models. This has enabled applications such as automated report generation and text-conditioned 3D image synthesis. Yet, current approaches struggle with high-resolution, long-sequence volumes: contrastive pretraining often yields vision encoders that are misaligned with clinical language, and slice-wise tokenization blurs fine anatomy, reducing diagnostic performance on downstream tasks. We introduce BTB3D (Better Tokens for Better 3D), a causal convolutional encoder-decoder that unifies 2D and 3D training and inference while producing compact, frequency-aware volumetric tokens. A three-stage training curriculum enables (i) local reconstruction, (ii) overlapping-window tiling, and (iii) long-context decoder refinement, during which the model learns from short slice excerpts yet generalizes to scans exceeding 300 slices without additional memory overhead. BTB3D sets a new state-of-the-art on two key tasks: it improves BLEU scores and increases clinical F1 by 40% over CT2Rep, CT-CHAT, and Merlin for report generation; and it reduces FID by 75% and halves FVD compared to GenerateCT and MedSyn for text-to-CT synthesis, producing anatomically consistent 512*512*241 volumes. These results confirm that precise three-dimensional tokenization, rather than larger language backbones alone, is essential for scalable vision-language modeling in 3D medical imaging. The codebase is available at: https://github.com/ibrahimethemhamamci/BTB3D

Yufan He, Pengfei Guo, Yucheng Tang et al.

Foundation models for interactive segmentation in 2D natural images and videos have sparked significant interest in building 3D foundation models for medical imaging. However, the domain gaps and clinical use cases for 3D medical imaging require a dedicated model that diverges from existing 2D solutions. Specifically, such foundation models should support a full workflow that can actually reduce human effort. Treating 3D medical images as sequences of 2D slices and reusing interactive 2D foundation models seems straightforward, but 2D annotation is too time-consuming for 3D tasks. Moreover, for large cohort analysis, it's the highly accurate automatic segmentation models that reduce the most human effort. However, these models lack support for interactive corrections and lack zero-shot ability for novel structures, which is a key feature of "foundation". While reusing pre-trained 2D backbones in 3D enhances zero-shot potential, their performance on complex 3D structures still lags behind leading 3D models. To address these issues, we present VISTA3D, Versatile Imaging SegmenTation and Annotation model, that targets to solve all these challenges and requirements with one unified foundation model. VISTA3D is built on top of the well-established 3D segmentation pipeline, and it is the first model to achieve state-of-the-art performance in both 3D automatic (supporting 127 classes) and 3D interactive segmentation, even when compared with top 3D expert models on large and diverse benchmarks. Additionally, VISTA3D's 3D interactive design allows efficient human correction, and a novel 3D supervoxel method that distills 2D pretrained backbones grants VISTA3D top 3D zero-shot performance. We believe the model, recipe, and insights represent a promising step towards a clinically useful 3D foundation model. Code and weights are publicly available at https://github.com/Project-MONAI/VISTA.

Pengfei Guo, Yiqun Mei, Jinyuan Zhou et al.

Accelerating magnetic resonance image (MRI) reconstruction process is a challenging ill-posed inverse problem due to the excessive under-sampling operation in k-space. In this paper, we propose a recurrent transformer model, namely ReconFormer, for MRI reconstruction which can iteratively reconstruct high fertility magnetic resonance images from highly under-sampled k-space data. In particular, the proposed architecture is built upon Recurrent Pyramid Transformer Layers (RPTL), which jointly exploits intrinsic multi-scale information at every architecture unit as well as the dependencies of the deep feature correlation through recurrent states. Moreover, the proposed ReconFormer is lightweight since it employs the recurrent structure for its parameter efficiency. We validate the effectiveness of ReconFormer on multiple datasets with different magnetic resonance sequences and show that it achieves significant improvements over the state-of-the-art methods with better parameter efficiency. Implementation code will be available in https://github.com/guopengf/ReconFormer.

Pengfei Guo, Puyang Wang, Jinyuan Zhou et al.

Fast and accurate reconstruction of magnetic resonance (MR) images from under-sampled data is important in many clinical applications. In recent years, deep learning-based methods have been shown to produce superior performance on MR image reconstruction. However, these methods require large amounts of data which is difficult to collect and share due to the high cost of acquisition and medical data privacy regulations. In order to overcome this challenge, we propose a federated learning (FL) based solution in which we take advantage of the MR data available at different institutions while preserving patients' privacy. However, the generalizability of models trained with the FL setting can still be suboptimal due to domain shift, which results from the data collected at multiple institutions with different sensors, disease types, and acquisition protocols, etc. With the motivation of circumventing this challenge, we propose a cross-site modeling for MR image reconstruction in which the learned intermediate latent features among different source sites are aligned with the distribution of the latent features at the target site. Extensive experiments are conducted to provide various insights about FL for MR image reconstruction. Experimental results demonstrate that the proposed framework is a promising direction to utilize multi-institutional data without compromising patients' privacy for achieving improved MR image reconstruction. Our code will be available at https://github.com/guopengf/FLMRCM.

Vishwesh Nath, Wenqi Li, Dong Yang et al.

Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. In traditional computer vision tasks, creative or approximate answers may be acceptable, but in healthcare, precision is paramount.Current large multimodal models like Gemini and GPT-4o are insufficient for medical tasks due to their reliance on memorized internet knowledge rather than the nuanced expertise required in healthcare. VLMs are usually trained in three stages: vision pre-training, vision-language pre-training, and instruction fine-tuning (IFT). IFT has been typically applied using a mixture of generic and healthcare data. In contrast, we propose that for medical VLMs, a fourth stage of specialized IFT is necessary, which focuses on medical data and includes information from domain expert models. Domain expert models developed for medical use are crucial because they are specifically trained for certain clinical tasks, e.g. to detect tumors and classify abnormalities through segmentation and classification, which learn fine-grained features of medical data$-$features that are often too intricate for a VLM to capture effectively especially in radiology. This paper introduces a new framework, VILA-M3, for medical VLMs that utilizes domain knowledge via expert models. Through our experiments, we show an improved state-of-the-art (SOTA) performance with an average improvement of ~9% over the prior SOTA model Med-Gemini and ~6% over models trained on the specific tasks. Our approach emphasizes the importance of domain expertise in creating precise, reliable VLMs for medical applications.

Xinran Li, Yi Shuai, Chen Liu et al.

Tumor synthesis can generate examples that AI often misses or over-detects, improving AI performance by training on these challenging cases. However, existing synthesis methods, which are typically unconditional -- generating images from random variables -- or conditioned only by tumor shapes, lack controllability over specific tumor characteristics such as texture, heterogeneity, boundaries, and pathology type. As a result, the generated tumors may be overly similar or duplicates of existing training data, failing to effectively address AI's weaknesses. We propose a new text-driven tumor synthesis approach, termed TextoMorph, that provides textual control over tumor characteristics. This is particularly beneficial for examples that confuse the AI the most, such as early tumor detection (increasing Sensitivity by +8.5%), tumor segmentation for precise radiotherapy (increasing DSC by +6.3%), and classification between benign and malignant tumors (improving Sensitivity by +8.2%). By incorporating text mined from radiology reports into the synthesis process, we increase the variability and controllability of the synthetic tumors to target AI's failure cases more precisely. Moreover, TextoMorph uses contrastive learning across different texts and CT scans, significantly reducing dependence on scarce image-report pairs (only 141 pairs used in this study) by leveraging a large corpus of 34,035 radiology reports. Finally, we have developed rigorous tests to evaluate synthetic tumors, including Text-Driven Visual Turing Test and Radiomics Pattern Analysis, showing that our synthetic tumors is realistic and diverse in texture, heterogeneity, boundaries, and pathology.

Pengfei Guo, Can Zhao, Dong Yang et al.

Generating 3D CT volumes from descriptive free-text inputs presents a transformative opportunity in diagnostics and research. In this paper, we introduce Text2CT, a novel approach for synthesizing 3D CT volumes from textual descriptions using the diffusion model. Unlike previous methods that rely on fixed-format text input, Text2CT employs a novel prompt formulation that enables generation from diverse, free-text descriptions. The proposed framework encodes medical text into latent representations and decodes them into high-resolution 3D CT scans, effectively bridging the gap between semantic text inputs and detailed volumetric representations in a unified 3D framework. Our method demonstrates superior performance in preserving anatomical fidelity and capturing intricate structures as described in the input text. Extensive evaluations show that our approach achieves state-of-the-art results, offering promising potential applications in diagnostics, and data augmentation.

Niklas Bubeck, Suprosanna Shit, Chen Chen et al.

Cardiac Magnetic Resonance (CMR) imaging is a critical tool for diagnosing and managing cardiovascular disease, yet its utility is often limited by the sparse acquisition of 2D short-axis slices, resulting in incomplete volumetric information. Accurate 3D reconstruction from these sparse slices is essential for comprehensive cardiac assessment, but existing methods face challenges, including reliance on predefined interpolation schemes (e.g., linear or spherical), computational inefficiency, and dependence on additional semantic inputs such as segmentation labels or motion data. To address these limitations, we propose a novel Cardiac Latent Interpolation Diffusion (CaLID) framework that introduces three key innovations. First, we present a data-driven interpolation scheme based on diffusion models, which can capture complex, non-linear relationships between sparse slices and improves reconstruction accuracy. Second, we design a computationally efficient method that operates in the latent space and speeds up 3D whole-heart upsampling time by a factor of 24, reducing computational overhead compared to previous methods. Third, with only sparse 2D CMR images as input, our method achieves SOTA performance against baseline methods, eliminating the need for auxiliary input such as morphological guidance, thus simplifying workflows. We further extend our method to 2D+T data, enabling the effective modeling of spatiotemporal dynamics and ensuring temporal coherence. Extensive volumetric evaluations and downstream segmentation tasks demonstrate that CaLID achieves superior reconstruction quality and efficiency. By addressing the fundamental limitations of existing approaches, our framework advances the state of the art for spatio and spatiotemporal whole-heart reconstruction, offering a robust and clinically practical solution for cardiovascular imaging.

Sampath Rapuri, Lalithkumar Seenivasan, Dominik Schneider et al.

A surgical world model capable of generating realistic surgical action videos with precise control over tool-tissue interactions can address fundamental challenges in surgical AI and simulation -- from data scarcity and rare event synthesis to bridging the sim-to-real gap for surgical automation. However, current video generation methods, the very core of such surgical world models, require expensive annotations or complex structured intermediates as conditioning signals at inference, limiting their scalability. Other approaches exhibit limited temporal consistency across complex laparoscopic scenes and do not possess sufficient realism. We propose Surgical Action World (SAW) -- a step toward surgical action world modeling through video diffusion conditioned on four lightweight signals: language prompts encoding tool-action context, a reference surgical scene, tissue affordance mask, and 2D tool-tip trajectories. We design a conditional video diffusion approach that reformulates video-to-video diffusion into trajectory-conditioned surgical action synthesis. The backbone diffusion model is fine-tuned on a custom-curated dataset of 12,044 laparoscopic clips with lightweight spatiotemporal conditioning signals, leveraging a depth consistency loss to enforce geometric plausibility without requiring depth at inference. SAW achieves state-of-the-art temporal consistency (CD-FVD: 199.19 vs. 546.82) and strong visual quality on held-out test data. Furthermore, we demonstrate its downstream utility for (a) surgical AI, where augmenting rare actions with SAW-generated videos improves action recognition (clipping F1-score: 20.93% to 43.14%; cutting: 0.00% to 8.33%) on real test data, and (b) surgical simulation, where rendering tool-tissue interaction videos from simulator-derived trajectory points toward a visually faithful simulation engine.

Andriy Myronenko, Dong Yang, Baris Turkbey et al.

Vision-language models (VLMs) have shown strong promise for medical image analysis, but most remain opaque, offering predictions without the transparent, stepwise reasoning clinicians rely on. We present a framework that brings chain-of-thought (CoT) reasoning to chest X-ray interpretation. Inspired by reasoning-first training paradigms, our approach is designed to learn how experts reason, not just what they conclude, by aligning intermediate steps with observable image evidence and radiology workflow. Beyond accuracy, the explicit reasoning traces support clinical auditability: they reveal why a conclusion was reached, which alternatives were considered, and where uncertainty remains, enabling quality assurance, error analysis, and safer human-AI collaboration. Our model couples high-fidelity visual encoding with a two-stage training recipe: a reasoning-style supervised fine-tuning (SFT) followed by reinforcement learning (RL) that uses verifiable rewards over a list of X-ray abnormalities. The model outputs reasoning that mirrors radiologists systematic thought process, uncertainty, and differential diagnosis. In out-of-distribution evaluation, the approach achieves competitive multi-label classification while improving interpretability. In a reader study with expert radiologists, full reasoning traces increased confidence, supported error auditing, and reduced time to finalize reports. We release code and the model NV-Reason-CXR-3B to support community progress toward trustworthy, explainable AI in chest radiography and other medical imaging tasks where reasoning quality is as critical as prediction quality.

Yiqun Mei, Pengfei Guo, Vishal M. Patel

In Heterogeneous Face Recognition (HFR), the objective is to match faces across two different domains such as visible and thermal. Large domain discrepancy makes HFR a difficult problem. Recent methods attempting to fill the gap via synthesis have achieved promising results, but their performance is still limited by the scarcity of paired training data. In practice, large-scale heterogeneous face data are often inaccessible due to the high cost of acquisition and annotation process as well as privacy regulations. In this paper, we propose a new face hallucination paradigm for HFR, which not only enables data-efficient synthesis but also allows to scale up model training without breaking any privacy policy. Unlike existing methods that learn face synthesis entirely from scratch, our approach is particularly designed to take advantage of rich and diverse facial priors from visible domain for more faithful hallucination. On the other hand, large-scale training is enabled by introducing a new federated learning scheme to allow institution-wise collaborations while avoiding explicit data sharing. Extensive experiments demonstrate the advantages of our approach in tackling HFR under current data limitations. In a unified framework, our method yields the state-of-the-art hallucination results on multiple HFR datasets.

Pengfei Guo, Vishal M. Patel

Deep Learning (DL) based methods for magnetic resonance (MR) image reconstruction have been shown to produce superior performance in recent years. However, these methods either only leverage under-sampled data or require a paired fully-sampled auxiliary modality to perform multi-modal reconstruction. Consequently, existing approaches neglect to explore attention mechanisms that can transfer textures from reference fully-sampled data to under-sampled data within a single modality, which limits these approaches in challenging cases. In this paper, we propose a novel Texture Transformer Module (TTM) for accelerated MRI reconstruction, in which we formulate the under-sampled data and reference data as queries and keys in a transformer. The TTM facilitates joint feature learning across under-sampled and reference data, so the feature correspondences can be discovered by attention and accurate texture features can be leveraged during reconstruction. Notably, the proposed TTM can be stacked on prior MRI reconstruction approaches to further improve their performance. Extensive experiments show that TTM can significantly improve the performance of several popular DL-based MRI reconstruction methods.

Pengfei Guo, Jeya Maria Jose Valanarasu, Puyang Wang et al.

Reconstructing magnetic resonance (MR) images from undersampled data is a challenging problem due to various artifacts introduced by the under-sampling operation. Recent deep learning-based methods for MR image reconstruction usually leverage a generic auto-encoder architecture which captures low-level features at the initial layers and high-level features at the deeper layers. Such networks focus much on global features which may not be optimal to reconstruct the fully-sampled image. In this paper, we propose an Over-and-Under Complete Convolutional Recurrent Neural Network (OUCR), which consists of an overcomplete and an undercomplete Convolutional Recurrent Neural Network(CRNN). The overcomplete branch gives special attention in learning local structures by restraining the receptive field of the network. Combining it with the undercomplete branch leads to a network which focuses more on low-level features without losing out on the global structures. Extensive experiments on two datasets demonstrate that the proposed method achieves significant improvements over the compressed sensing and popular deep learning-based methods with less number of trainable parameters.

Lucie Lévêque, Ji Yang, Xiaohan Yang et al.

Research on image quality assessment (IQA) remains limited mainly due to our incomplete knowledge about human visual perception. Existing IQA algorithms have been designed or trained with insufficient subjective data with a small degree of stimulus variability. This has led to challenges for those algorithms to handle complexity and diversity of real-world digital content. Perceptual evidence from human subjects serves as a grounding for the development of advanced IQA algorithms. It is thus critical to acquire reliable subjective data with controlled perception experiments that faithfully reflect human behavioural responses to distortions in visual signals. In this paper, we present a new study of image quality perception where subjective ratings were collected in a controlled lab environment. We investigate how quality perception is affected by a combination of different categories of images and different types and levels of distortions. The database will be made publicly available to facilitate calibration and validation of IQA algorithms.

Pengfei Guo, Puyang Wang, Rajeev Yasarla et al.

Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas in neuro-oncology, especially with the help of standard anatomic and advanced molecular MR images. However, data quantity and quality remain a key determinant of, and a significant limit on, the potential of such applications. In our previous work, we explored synthesis of anatomic and molecular MR image network (SAMR) in patients with post-treatment malignant glioms. Now, we extend it and propose Confidence Guided SAMR (CG-SAMR) that synthesizes data from lesion information to multi-modal anatomic sequences, including T1-weighted (T1w), gadolinium enhanced T1w (Gd-T1w), T2-weighted (T2w), and fluid-attenuated inversion recovery (FLAIR), and the molecular amide proton transfer-weighted (APTw) sequence. We introduce a module which guides the synthesis based on confidence measure about the intermediate results. Furthermore, we extend the proposed architecture for unsupervised synthesis so that unpaired data can be used for training the network. Extensive experiments on real clinical data demonstrate that the proposed model can perform better than the state-of-theart synthesis methods.

He Chen, Pengfei Guo, Pengfei Li et al.

Epipolar constraints are at the core of feature matching and depth estimation in current multi-person multi-camera 3D human pose estimation methods. Despite the satisfactory performance of this formulation in sparser crowd scenes, its effectiveness is frequently challenged under denser crowd circumstances mainly due to two sources of ambiguity. The first is the mismatch of human joints resulting from the simple cues provided by the Euclidean distances between joints and epipolar lines. The second is the lack of robustness from the naive formulation of the problem as a least squares minimization. In this paper, we depart from the multi-person 3D pose estimation formulation, and instead reformulate it as crowd pose estimation. Our method consists of two key components: a graph model for fast cross-view matching, and a maximum a posteriori (MAP) estimator for the reconstruction of the 3D human poses. We demonstrate the effectiveness and superiority of our proposed method on four benchmark datasets.

Pengfei Guo, Puyang Wang, Jinyuan Zhou et al.

Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas for patients with malignant gliomas in neuro-oncology with the help of conventional and advanced molecular MR images. However, the lack of sufficient annotated MRI data has vastly impeded the development of such automatic methods. Conventional data augmentation approaches, including flipping, scaling, rotation, and distortion are not capable of generating data with diverse image content. In this paper, we propose a method, called synthesis of anatomic and molecular MR images network (SAMR), which can simultaneously synthesize data from arbitrary manipulated lesion information on multiple anatomic and molecular MRI sequences, including T1-weighted (T1w), gadolinium enhanced T1w (Gd-T1w), T2-weighted (T2w), fluid-attenuated inversion recovery (FLAIR), and amide proton transfer-weighted (APTw). The proposed framework consists of a stretch-out up-sampling module, a brain atlas encoder, a segmentation consistency module, and multi-scale label-wise discriminators. Extensive experiments on real clinical data demonstrate that the proposed model can perform significantly better than the state-of-the-art synthesis methods.

Pengfei Guo, Dawei Li, Xingde Li

We customize an end-to-end image compression framework for retina OCT images based on deep convolutional neural networks (CNNs). The customized compression scheme consists of three parts: data Preprocessing, compression CNNs, and reconstruction CNNs. Data preprocessing module reduces the speckle noise of the OCT images and the segments out the region of interest. We added customized skip connections between the compression CNNs and the reconstruction CNNs to reserve the detail information and trained the two nets together with the semantic segmented image patches from data preprocessing module. To train the two networks sensitive to both low frequency information and high frequency information, we adopted an objective function with two parts: A PatchGAN discriminator to judge the high frequency information and a differentiable MS-SSIM penalty to evaluate the low frequency information. The proposed framework was trained and evaluated on a publicly available OCT dataset. The evaluation showed above 99% similarity in terms of multi-scale structural similarity (MS-SSIM) when the compression ratio is as high as 40. Furthermore, the reconstructed images of compression ratio 80 from the proposed framework even have better quality than that of compression ratio 20 from JPEG by visual comparison. The testing result outperforms JPEG in term of both of MS-SSIM and visualization, which is more obvious as the increase of compression ratio. Our preliminary result indicates the huge potential of deep neural networks on customized medical image compression.