Computed Tomography

Also known as CT

Ask about this topic

Overview

Computed tomography (CT) research studies how to reconstruct internal structure from X-ray measurements and extract useful clinical or scientific information from scans. Approaches range from physics-based iterative reconstruction and learned unrolling to diffusion and flow-matching priors, CNN and Transformer segmentation, and vision-language systems for image interpretation and reporting. Work spans low-dose, sparse-view, cone-beam, and spectral CT, with evaluations on benchmarks such as AAPM Mayo, LoDoPaB-CT, and CT-RATE as well as multi-center cohorts. A central challenge is balancing speed and image quality with data consistency, anatomical fidelity, robustness across scanners and populations, and clinically meaningful evaluation.

Latest papers

CardsList

275 papers27 papers in the last four weeks, up 35% on the four weeks before. 0.2% of all new papers.

Apr 14, 2026

Representation geometry shapes task performance in vision-language modeling for CT enterography

Computed tomography (CT) enterography is a primary imaging modality for assessing inflammatory bowel disease (IBD), yet the representational choices that best support automated analysis of this modality are unknown. We present the first study of vision-language transfer learning on abdominal CT enterography and identify two main findings. First, mean pooling of slice embeddings gives better categorical disease assessment (59.2% three-class accuracy), whereas attention pooling gives better cross-modal retrieval (0.235 text-to-image MRR). This pattern holds across all LoRA configurations tested and suggests that the two aggregators emphasize different properties of the learned representation. Second, per-slice tissue contrast matters more than broader spatial coverage: multi-window RGB encoding, which maps complementary Hounsfield Unit windows to RGB channels, outperforms all strategies that increase spatial coverage through multiplanar sampling, and in this setting adding coronal and sagittal views reduces classification performance. For report generation, fine-tuning without retrieval context yields within-1 severity accuracy at the prevalence-matched chance level (70.4% vs.\ 71% random), suggesting little learned ordering beyond the class distribution. Retrieval-augmented generation (RAG) improves this across all configurations, scoring 7--14 percentage points above the chance baseline and improving ordinal MAE from 0.98 to 0.80--0.89. A three-teacher pseudolabel framework enables all comparisons without expert annotations. Together, these findings provide the first baselines for this underexplored modality and offer practical guidance for building vision-language systems for volumetric medical imaging.

Cristian Minoccheri, Emily Wittrup, Kayvan Najarian +1

Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan, 1109 Geddes Avenue, Ann Arbor, 48104, MI, USA. · Department of Emergency Medicine, University of Michigan, 1109 Geddes Avenue, Ann Arbor, 48104, MI, USA. · Department of Electrical Engineering and Computer Science, University of Michigan, 1109 Geddes Avenue, Ann Arbor, 48104, MI, USA. +1

Medical VLMsMedical Image ClassificationComputed TomographyImage-Text Retrieval
AskPDF
Apr 12, 2026

Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance

Vision--language models (VLMs) for radiology report generation (RRG) can produce long-form chest CT reports from volumetric scans and show strong potential to improve radiology workflow efficiency and consistency. However, existing methods face two key limitations: (i) training supervision is often coarse, aligning a whole CT volume with a full free-text report without explicit alignment for fine-grained attributes or pathology locations; and (ii) evaluation is typically holistic (lexical overlap, entity matching, or LLM-as-a-judge scores) and not diagnostic for spatial grounding. We propose Discriminative Cue-Prompting with Prompt Dropout (DCP-PD), a plug-and-play framework that distills fine-grained cues from free-text reports and uses them to guide report generation while mitigating shortcut reliance via prompt dropout. DCP-PD achieves state-of-the-art performance on CT-RATE, improving macro F1 from =0.501=0.501 to 0.6030.603 (20% relative), and substantially boosts out-of-distribution performance on Rad-ChestCT from F1 =0.266=0.266 to 0.5030.503 (89% relative). Finally, we introduce a hierarchical, location-aware question-set protocol (presence →\rightarrow laterality →\rightarrow lobe) to directly assess pathology-location grounding, showing that fine-grained spatial localization remains challenging even for models that score highly on current benchmarks.

Chenyu Wang, Weicheng Dai, Han Liu +2

Boston University, Boston, MA, USA · Siemens Healthineers, Princeton, NJ, USA

Radiology Report GenerationCT Report GenerationMedical Image GroundingComputed TomographyRadiology Report Evaluation
AskPDF
Apr 8, 2026

Distilling Photon-Counting CT into Routine Chest CT through Clinically Validated Degradation Modeling

Photon-counting CT (PCCT) provides superior image quality with higher spatial resolution and lower noise compared to conventional energy-integrating CT (EICT), but its limited clinical availability restricts large-scale research and clinical deployment. To bridge this gap, we propose SUMI, a simulated degradation-to-enhancement method that learns to reverse realistic acquisition artifacts in low-quality EICT by leveraging high-quality PCCT as reference. Our central insight is to explicitly model realistic acquisition degradations, transforming PCCT into clinically plausible lower-quality counterparts and learning to invert this process. The simulated degradations were validated for clinical realism by board-certified radiologists, enabling faithful supervision without requiring paired acquisitions at scale. As outcomes of this technical contribution, we: (1) train a latent diffusion model on 1,046 PCCTs, using an autoencoder first pre-trained on both these PCCTs and 405,379 EICTs from 145 hospitals to extract general CT latent features that we release for reuse in other generative medical imaging tasks; (2) construct a large-scale dataset of over 17,316 publicly available EICTs enhanced to PCCT-like quality, with radiologist-validated voxel-wise annotations of airway trees, arteries, veins, lungs, and lobes; and (3) demonstrate substantial improvements: across external data, SUMI outperforms state-of-the-art image translation methods by 15% in SSIM and 20% in PSNR, improves radiologist-rated clinical utility in reader studies, and enhances downstream top-ranking lesion detection performance, increasing sensitivity by up to 15% and F1 score by up to 10%. Our results suggest that emerging imaging advances can be systematically distilled into routine EICT using limited high-quality scans as reference.

Junqi Liu, Xinze Zhou, Wenxuan Li +10

Johns Hopkins University · University of California, San Francisco · Harvard Medical School +3

Medical Image SynthesisComputed TomographyImage-to-Image TranslationDiffusion Models for Image Restoration
AskPDF
Apr 8, 2026

Balancing Efficiency and Restoration: Lightweight Mamba-Based Model for CT Metal Artifact Reduction

In computed tomography imaging, metal implants frequently generate severe artifacts that compromise image quality and hinder diagnostic accuracy. There are three main challenges in the existing methods: the deterioration of organ and tissue structures, dependence on sinogram data, and an imbalance between resource use and restoration efficiency. Addressing these issues, we introduce MARMamba, which effectively eliminates artifacts caused by metals of different sizes while maintaining the integrity of the original anatomical structures of the image. Furthermore, this model only focuses on CT images affected by metal artifacts, thus negating the requirement for additional input data. The model is a streamlined UNet architecture, which incorporates multi-scale Mamba (MS-Mamba) as its core module. Within MS-Mamba, a flip mamba block captures comprehensive contextual information by analyzing images from multiple orientations. Subsequently, the average maximum feed-forward network integrates critical features with average features to suppress the artifacts. This combination allows MARMamba to reduce artifacts efficiently. The experimental results demonstrate that our model excels in reducing metal artifacts, offering distinct advantages over other models. It also strikes an optimal balance between computational demands, memory usage, and the number of parameters, highlighting its practical utility in the real world. The code of the presented model is available at: https://github.com/RICKand-MORTY/MARMamba.

Weikai Qu, Sijun Liang, Xianfeng Li +7

New York University, America · BaiyunPort, China · University of Technology Sydney, Australia +6

Image RestorationComputed TomographyMambaU-Net
AskPDF
Apr 7, 2026

Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction

Metal artifacts from high-attenuation implants severely degrade CT image quality, obscuring critical anatomical structures and posing a challenge for standard deep learning methods that require extensive paired training data. We propose a paradigm shift: reframing artifact reduction as an in-context reasoning task by adapting a general-purpose vision-language diffusion foundation model via parameter-efficient Low-Rank Adaptation (LoRA). By leveraging rich visual priors, our approach achieves effective artifact suppression with only 16 to 128 paired training examples reducing data requirements by two orders of magnitude. Crucially, we demonstrate that domain adaptation is essential for hallucination mitigation; without it, foundation models interpret streak artifacts as erroneous natural objects (e.g., waffles or petri dishes). To ground the restoration, we propose a multi-reference conditioning strategy where clean anatomical exemplars from unrelated subjects are provided alongside the corrupted input, enabling the model to exploit category-specific context to infer uncorrupted anatomy. Extensive evaluation on the AAPM CT-MAR benchmark demonstrates that our method achieves state-of-the-art performance on perceptual and radiological-feature metrics . This work establishes that foundation models, when appropriately adapted, offer a scalable alternative for interpretable, data-efficient medical image reconstruction. Code is available at https://github.com/ahmetemirdagi/CT-EditMAR.

Ahmet Rasim Emirdagi, Süleyman Aslan, Mısra Yavuz +5

Codeway AI Research

Computed TomographyImage ReconstructionDiffusion Models for Image RestorationVision Foundation Model Adaptation
AskPDF
Apr 6, 2026

3D Gaussian Splatting for Annular Dark Field Scanning Transmission Electron Microscopy Tomography Reconstruction

Analytical Dark Field Scanning Transmission Electron Microscopy (ADF-STEM) tomography reconstructs nanoscale materials in 3D by integrating multi-view tilt-series images, enabling precise analysis of their structural and compositional features. Although integrating more tilt views improves 3D reconstruction, it requires extended electron exposure that risks damaging dose-sensitive materials and introduces drift and misalignment, making it difficult to balance reconstruction fidelity with sample preservation. In practice, sparse-view acquisition is frequently required, yet conventional ADF-STEM methods degrade under limited views, exhibiting artifacts and reduced structural fidelity. To resolve these issues, in this paper, we adapt 3D GS to this domain with three key components. We first model the local scattering strength as a learnable scalar field, denza, to address the mismatch between 3DGS and ADF-STEM imaging physics. Then we introduce a coefficient γγ to stabilize scattering across tilt angles, ensuring consistent denza via scattering view normalization. Finally, We incorporate a loss function that includes a 2D Fourier amplitude term to suppress missing wedge artifacts in sparse-view reconstruction. Experiments on 45-view and 15-view tilt series show that DenZa-Gaussian produces high-fidelity reconstructions and 2D projections that align more closely with original tilts, demonstrating superior robustness under sparse-view conditions.

Beiyuan Zhang, Hesong Li, Ruiwen Shao +1

Beijing Institute of Technology

Scanning Transmission Electron MicroscopyComputed TomographySparse-View 3D ReconstructionMicroscopy Image Analysis3D Gaussian Splatting
AskPDF
Apr 5, 2026

Learning Robust Visual Features in Computed Tomography Enables Efficient Transfer Learning for Clinical Tasks

There is substantial interest in developing artificial intelligence systems to support radiologists across tasks ranging from segmentation to report generation. Existing computed tomography (CT) foundation models have largely focused on building generalist vision-language systems capable of tasks such as question answering and report generation. However, training reliable vision-language systems requires paired image-text data at a scale that remains unavailable in CT. Moreover, adapting the underlying visual representations to downstream tasks typically requires partial or full backbone fine-tuning, a computationally demanding process inaccessible to many research groups. Instead, foundation models should prioritise learning robust visual representations that enable efficient transfer to new tasks with minimal labelled data and without backbone fine-tuning. We present VoxelFM, a 3D CT foundation model trained with self-distillation using the DINO framework, which learns semantically rich features without language supervision. We evaluated VoxelFM across seven categories of clinically relevant downstream tasks using frozen backbone representations with lightweight probes: classification, regression, survival analysis, instance retrieval, localisation, segmentation, and report generation. VoxelFM matched or outperformed four existing CT foundation models across all task categories. Despite receiving no language supervision during pre-training, VoxelFM surpassed models explicitly trained with language-alignment objectives, including on report generation. Our results indicate that current CT foundation models perform significantly better as feature extractors for lightweight probes rather than as vision encoders for vision-language models. Model weights and training code are publicly available.

Rubén Moreno-Aguado, Alba Magallón, Victor Moreno +2

Bioengineering Department and Imperial-X, Imperial College London, London, UK · Department of Computer Science, University of Manchester, Manchester, UK · Oncology Data Analytics Program, Catalan Institute of Oncology, Barcelona, Spain +6

Medical Imaging Foundation ModelsMedical Image Representation LearningComputed TomographySelf-Supervised Visual Representation Learning
AskPDF
Apr 4, 2026

Shower-Aware Dual-Stream Voxel Networks for Structural Defect Detection in Cosmic-Ray Muon Tomography

We present SA-DSVN, a 3D convolutional architecture for voxel-level segmentation of structural defects in reinforced concrete using cosmic-ray muon tomography. Unlike conventional reconstruction methods (POCA, MLSD) that rely solely on muon scattering angles, our approach jointly processes scattering kinematics (9 channels) and secondary electromagnetic shower multiplicities (40 channels) through independent encoder streams fused via cross-attention. Training data were generated using Vega, a cloud-native Geant4 simulation framework, producing 4.5 million muon events across 900 volumes containing four defect types - honeycombing, shear fracture, corrosion voids, and delamination - embedded within a dense 7x7 rebar cage. A five-variant ablation study demonstrates that the shower multiplicity stream alone accounts for the majority of discriminative power, raising defect-mean Dice from 0.535 (scattering only) to 0.685 (shower only). On 60 independently simulated validation volumes, the model achieves 96.3% voxel accuracy, per-defect Dice scores of 0.59-0.81, and 100% volume-level detection sensitivity at 10 ms inference per volume. These results establish secondary shower multiplicity as a previously unexploited but highly effective feature for learned muon tomographic reconstruction.

Parthiv Dasgupta, Sambhav Agarwal, Palash Dutta +2

Department of Computer Science and Engineering, Heritage Institute of Technology, Kolkata, India

Fault DetectionComputed Tomography3D Semantic Segmentation
AskPDF
Apr 3, 2026

HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis

Non-contrast chest CTs offer a rich opportunity for both conventional pulmonary and opportunistic extra-pulmonary screening. While Multi-Task Learning (MTL) can unify these diverse tasks, standard hard-parameter sharing approaches are often suboptimal for modeling distinct pathologies. We propose HyperCT, a framework that dynamically adapts a Vision Transformer backbone via a Hypernetwork. To ensure computational efficiency, we integrate Low-Rank Adaptation (LoRA), allowing the model to regress task-specific low-rank weight updates rather than full parameters. Validated on a large-scale dataset of radiological and cardiological tasks, \method{} outperforms various strong baselines, offering a unified, parameter-efficient solution for holistic patient assessment. Our code is available at https://github.com/lfb-1/HyperCT.

Fengbei Liu, Sunwoo Kwak, Hao Phung +6

Cornell Tech and Cornell University · Columbia University Irving Medical Center · Weill Cornell Medicine

Multi-Task LearningHypernetworksComputed TomographyVision Transformer
AskPDF
Apr 2, 2026

FaCT-GS: Fast and Scalable CT Reconstruction with Gaussian Splatting

Gaussian Splatting (GS) has emerged as a dominating technique for image rendering and has quickly been adapted for the X-ray Computed Tomography (CT) reconstruction task. However, despite its growing popularity, the benefits of GS are typically not substantial enough to motivate a transition from well-established reconstruction algorithms. This paper addresses the most significant remaining limitations of the GS-based approach by introducing FaCT-GS, a framework for fast and flexible CT reconstruction. Enabled by an in-depth optimization of the voxelization and rasterization pipelines, our new method is significantly faster than its predecessors and scales well with projection and output volume size. Furthermore, the improved voxelization enables rapid fitting of Gaussians to pre-existing volumes, which can serve as a prior for warm-starting the reconstruction, or simply as an alternative, compressed representation. FaCT-GS is over 4X faster than the State of the Art GS CT reconstruction on standard 512x512 projections, and over 13X faster on 2k projections. Implementation and data available through: https://github.com/PaPieta/fact-gs.

Pawel Tomasz Pieta, Rasmus Juul Pedersen, Sina Borgi +3

Technical University of Denmark, Kgs. Lyngby, Denmark

Computed Tomography3DGS Acceleration3D Gaussian Splatting
AskPDF
Apr 2, 2026

Robust Multi-Source Covid-19 Detection in CT Images

Deep learning models for COVID-19 detection from chest CT scans generally perform well when the training and test data originate from the same institution, but they often struggle when scans are drawn from multiple centres with differing scanners, imaging protocols, and patient populations. One key reason is that existing methods treat COVID-19 classification as the sole training objective, without accounting for the data source of each scan. As a result, the learned representations tend to be biased toward centres that contribute more training data. To address this, we propose a multi-task learning approach in which the model is trained to predict both the COVID-19 diagnosis and the originating data centre. The two tasks share an EfficientNet-B7 backbone, which encourages the feature extractor to learn representations that hold across all four participating centres. Since the training data is not evenly distributed across sources, we apply a logit-adjusted cross-entropy loss [1] to the source classification head to prevent underrepresented centres from being overlooked. Our pre-processing follows the SSFL framework with KDS [2], selecting eight representative slices per scan. Our method achieves an F1 score of 0.9098 and an AUC-ROC of 0.9647 on a validation set of 308 scans. The code is publicly available at https://github.com/Purdue-M2/-multisource-covid-ct.

Asmita Yuki Pritha, Jason Xu, Daniel Ding +4

Capstone School Dhaka, Bangladesh · Carmel High School, Carmel, Indiana, USA · Clarkstown High School South, West Nyack, New York, USA +2

Medical Image ClassificationDomain GeneralizationComputed Tomography
AskPDF
Apr 1, 2026

PHASOR: Anatomy- and Phase-Consistent Volumetric Diffusion for CT Virtual Contrast Enhancement

Contrast-enhanced computed tomography (CECT) is pivotal for highlighting tissue perfusion and vascularity, yet its clinical ubiquity is impeded by the invasive nature of contrast agents and radiation risks. While virtual contrast enhancement (VCE) offers an alternative to synthesizing CECT from non-contrast CT (NCCT), existing methods struggle with anatomical heterogeneity and spatial misalignment, leading to inconsistent enhancement patterns and incorrect details. This paper introduces PHASOR, a volumetric diffusion framework for high-fidelity CT VCE. By treating CT volumes as coherent sequences, we leverage a video diffusion model to enhance structural coherence and volumetric accuracy. To ensure anatomy-phase consistent synthesis, we introduce two complementary modules. First, anatomy-routed mixture-of-experts (AR-MoE) anchors distinct enhancement patterns to anatomical semantics, with organ-specific memory to capture salient details. Second, intensity-phase aware representation alignment (IP-REPA) highlights intricate contrast signals while mitigating the impact of imperfect spatial alignment. Extensive experiments across three datasets demonstrate that PHASOR significantly outperforms state-of-the-art methods in both synthesis quality and enhancement accuracy.

Zilong Li, Dongyang Li, Chenglong Ma +6

Z. Li and J. Zhang are with the Shanghai Key Lab of Intelligent Information Processing, School of Computer Science and Artificial Intelligence, Fudan University, Shanghai 200433, China. · Z. Li, D. Li, D. Jin, H. Luo, and F. Wang are with Alibaba DAMO Academy, China. · C. Ma and H. Shan are with the Institute of Science and Technology for Brain-inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University, Shanghai 200433, China, and also with Shanghai Center for Brain Science and Brain-inspired Technology, Shanghai 201602, China. +1

Medical Image SynthesisImage EnhancementComputed Tomography
AskPDF
Apr 1, 2026

HICT: High-precision 3D CBCT reconstruction from a single X-ray

Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single low-dose panoramic X-ray is a promising alternative but remains challenging due to geometric inconsistencies and limited accuracy. We propose HiCT, a two-stage framework that first generates geometrically consistent multi-view projections from a single panoramic image using a video diffusion model, and then reconstructs high-fidelity CBCT from the projections using a ray-based dynamic attention network and an X-ray sampling strategy. To support this, we built XCT, a large-scale dataset combining public CBCT data with 500 paired PX-CBCT cases. Extensive experiments show that HiCT achieves state-of-the-art performance, delivering accurate and geometrically consistent reconstructions for clinical use.

Wen Ma, Jiaxiang Liu, Zikai Xiao +3

Zhejiang University · Angelalign Technology Inc.

Dental ImagingMedical ImagingSingle-View 3D ReconstructionCone-Beam CTComputed Tomography
AskPDF
Mar 30, 2026

MRI-to-CT synthesis using drifting models

Accurate MRI-to-CT synthesis could enable MR-only pelvic workflows by providing CT-like images with bone details while avoiding additional ionizing radiation. In this work, we investigate recently proposed drifting models for synthesizing pelvis CT images from MRI and benchmark them against convolutional neural networks (UNet, VAE), a generative adversarial network (WGAN-GP), a physics-inspired probabilistic model (PPFM), and diffusion-based methods (FastDDPM, DDIM, DDPM). Experiments are performed on two complementary datasets: Gold Atlas Male Pelvis and the SynthRAD2023 pelvis subset. Image fidelity and structural consistency are evaluated with SSIM, PSNR, and RMSE, complemented by qualitative assessment of anatomically critical regions such as cortical bone and pelvic soft-tissue interfaces. Across both datasets, the proposed drifting model achieves high SSIM and PSNR and low RMSE, surpassing strong diffusion baselines and conventional CNN-, VAE-, GAN-, and PPFM-based methods. Visual inspection shows sharper cortical bone edges, improved depiction of sacral and femoral head geometry, and reduced artifacts or over-smoothing, particularly at bone-air-soft tissue boundaries. Moreover, the drifting model attains these gains with one-step inference and inference times on the order of milliseconds, yielding a more favorable accuracy-efficiency trade-off than iterative diffusion sampling while remaining competitive in image quality. These findings suggest that drifting models are a promising direction for fast, high-quality pelvic synthetic CT generation from MRI and warrant further investigation for downstream applications such as MRI-only radiotherapy planning and PET/MR attenuation correction.

Qing Lyu, Jianxu Wang, Jeremy Hudson +2

Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT · Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY

Medical Image SynthesisDrifting ModelsMagnetic Resonance ImagingComputed Tomography
AskPDF
Mar 29, 2026

3-D Representations for Hyperspectral Flame Tomography

Flame tomography is a compelling approach for extracting large amounts of data from experiments via 3-D thermochemical reconstruction. Recent efforts employing neural-network flame representations have suggested improved reconstruction quality compared with classical tomography approaches, but a rigorous quantitative comparison with the same algorithm using a voxel-grid representation has not been conducted. Here, we compare a classical voxel-grid representation with varying regularizers to a continuous neural representation for tomographic reconstruction of a simulated pool fire. The representations are constructed to give temperature and composition as a function of location, and a subsequent ray-tracing step is used to solve the radiative transfer equation to determine the spectral intensity incident on hyperspectral infrared cameras, which is then convolved with an instrument lineshape function. We demonstrate that the voxel-grid approach with a total-variation regularizer reproduces the ground-truth synthetic flame with the highest accuracy for reduced memory intensity and runtime. Future work will explore more representations and under experimental configurations.

Nicolas Tricard, Zituo Chen, Sili Deng

Department of Mechanical Engineering, Massachusetts Institute of Technology 77 Massachusetts Ave, Cambridge, MA 02139, United States

Computed TomographyImplicit Neural Representations3D Representation LearningHyperspectral Imaging
AskPDF
Mar 27, 2026

Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays

Computed tomography (CT) provides rich 3D anatomical detail but is often constrained by high radiation exposure, substantial costs, and limited availability. Standard chest X-rays are cost-effective and widely accessible, but provide only 2D projections with limited pathological information. Reconstructing 3D CT volumes from 2D X-rays could markedly increase diagnostic accessibility, yet existing methods rely predominantly on synthetic X-ray projections, limiting clinical generalization. We propose AXON, a multi-stage diffusion-based framework that reconstructs 3D CT volumes directly from real X-rays with substantially improved fidelity over existing approaches. AXON follows a coarse-to-fine paradigm: a Brownian Bridge diffusion model first captures global anatomical structure, and a ControlNet-guided refinement stage then enhances local intensity detail and anatomical realism. To alleviate the depth ambiguity inherent in 2D-to-3D reconstruction, AXON incorporates bi-planar X-ray views, enabling more accurate spatial reasoning and structural recovery. A dedicated super-resolution module further increases the spatial resolution of the generated volumes. Experiments on public and external datasets show that AXON consistently surpasses state-of-the-art approaches while generalizing across diverse clinical distributions. At our highest-resolution bi-planar setting, AXON achieves an 11.9% improvement in PSNR and an 11.0% increase in SSIM over the strongest baseline evaluated at that resolution. In the 1283128^3 single-planar setting, it maintains a lead of 7.8% in PSNR on LIDC-IDRI, with larger margins on the external clinical dataset of 8.0% in PSNR and 16.9% in SSIM. Our code is available at https://github.com/ai-med/AXON/.

Martin Rath, Morteza Ghahremani, Yitong Li +3

Technical University of Munich (TUM), Germany · Munich Center for Machine Learning (MCML), Germany · University of Western Australia (UWA), Australia

3D ReconstructionMedical Image SynthesisConditional Diffusion ModelsComputed Tomography
AskPDF
Mar 26, 2026

DeepFAN, a transformer-based deep learning model for human-artificial intelligence collaborative assessment of incidental pulmonary nodules in CT scans: a multi-reader, multi-case trial

The widespread adoption of CT has notably increased the number of detected lung nodules. However, current deep learning methods for classifying benign and malignant nodules often fail to comprehensively integrate global and local features, and most of them have not been validated through clinical trials. To address this, we developed DeepFAN, a transformer-based model trained on over 10K pathology-confirmed nodules and further conducted a multi-reader, multi-case clinical trial to evaluate its efficacy in assisting junior radiologists. DeepFAN achieved diagnostic area under the curve (AUC) of 0.939 (95% CI 0.930-0.948) on an internal test set and 0.954 (95% CI 0.934-0.973) on the clinical trial dataset involving 400 cases across three independent medical institutions. Explainability analysis indicated higher contributions from global than local features. Twelve readers' average performance significantly improved by 10.9% (95% CI 8.3%-13.5%) in AUC, 10.0% (95% CI 8.9%-11.1%) in accuracy, 7.6% (95% CI 6.1%-9.2%) in sensitivity, and 12.6% (95% CI 10.9%-14.3%) in specificity (P<0.001 for all). Nodule-level inter-reader diagnostic consistency improved from fair to moderate (overall k: 0.313 vs. 0.421; P=0.019). In conclusion, DeepFAN effectively assisted junior radiologists and may help homogenize diagnostic quality and reduce unnecessary follow-up of indeterminate pulmonary nodules. Chinese Clinical Trial Registry: ChiCTR2400084624.

Zhenchen Zhu, Ge Hu, Weixiong Tan +16

Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. · Theranostics and Translational Research Center, National Infrastructures for Translational Medicine, Institute of Clinical Medicine, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. · Artificial Intelligence Lab, Deepwise Healthcare, Beijing, China. +9

Medical Image ClassificationHuman-AI CollaborationComputed Tomography
AskPDF
Mar 25, 2026

CORA: Generalizable coronary artery disease assessment and risk stratification from coronary CT angiography using pathology-centric representation learning

Coronary artery disease, a leading cause of cardiovascular mortality worldwide, can be assessed non-invasively by coronary computed tomography angiography (CCTA). Although deep learning has advanced automated CCTA analysis, clinical translation remains constrained by the scarcity of expert-annotated data and by the spatial sparsity of coronary pathology, which occupies only a small fraction of each scan. Widely used label-free pretraining strategies, such as masked image modeling and contrastive learning, optimize for global anatomical reconstruction and tend to under-represent these tiny localized pathological features. Here we present CORA, an annotation-efficient model for comprehensive coronary artery disease assessment. Rather than reconstructing background anatomy, CORA learns from volumetric CCTA through a synthesis-driven self-supervised strategy: an anatomy-guided engine inserts diverse synthetic calcified and non-calcified lesions into unlabeled scans, reframing pretraining as an abnormality-detection task that biases representation learning toward clinically relevant disease features. We pretrained CORA on 10,138 unlabeled CCTA volumes and evaluated it across datasets from nine independent hospitals. Across plaque characterization, stenosis detection, and coronary artery segmentation, CORA consistently outperformed strong self-supervised pretraining baselines, with the largest gains on external multi-center data, indicating robust generalization under distributional shift. Coupling the imaging encoder with structured clinical variables further enabled near-term major adverse cardiac event (MACE) risk stratification. Our results show that pathology-centric, synthesis-driven pretraining is an effective and scalable strategy for annotation-efficient coronary artery disease assessment from CCTA.

Jinkui Hao, Gorkem Durak, Halil Ertugrul Aktas +4

Department of Radiology, Northwestern University, Chicago, IL, USA · Department of Biomedical Engineering, Northwestern University, Evanston, IL, USA · Department of Cardiology, Northwestern University, Chicago, IL, USA +1

Synthetic Data PretrainingCoronary AngiographyMedical DiagnosisMedical Image Anomaly DetectionMedical Image SegmentationCoronary Artery Segmentation+3
AskPDF
Mar 25, 2026

Beyond Benchmarks: A Framework for Post Deployment Validation of CT Lung Nodule Detection AI

Background: Artificial intelligence (AI) assisted lung nodule detection systems are increasingly deployed in clinical settings without site-specific validation. Performance reported under benchmark conditions may not reflect real-world behavior when acquisition parameters differ from training data. Purpose: To propose and demonstrate a physics-guided framework for evaluating the sensitivity of a deployed lung nodule detection model to systematic variation in CT acquisition parameters. Methods: Twenty-one cases from the publicly available LIDC-IDRI dataset were evaluated using a MONAI RetinaNet model pretrained on LUNA16 (fold 0, no fine-tuning). Five imaging conditions were tested: baseline, 25% dose reduction, 50% dose reduction, 3 mm slice thickness, and 5 mm slice thickness. Dose reduction was simulated via image-domain Gaussian noise; slice thickness via moving average along the z-axis. Detection sensitivity was computed at a confidence threshold of 0.5 with a 15 mm matching criterion. Results: Baseline sensitivity was 45.2% (57/126 consensus nodules). Dose reduction produced slight degradation: 41.3% at 25% dose and 42.1% at 50% dose. The 5 mm slice thickness condition produced a marked drop to 26.2% - a 19 percentage point reduction representing a 42% relative decrease from baseline. This finding was consistent across confidence thresholds from 0.1 to 0.9. Per-case analysis revealed heterogeneous performance including two cases with complete detection failure at baseline. Conclusion: Slice thickness represents a more fundamental constraint on AI detection performance than image noise under the conditions tested. The proposed framework is reproducible, requires no proprietary scanner data, and is designed to serve as the basis for ongoing post-deployment QA in resource-constrained environment.

Daniel Soliman

Lung Nodule DetectionMedical Image AnalysisComputed TomographyMedical Image Anomaly DetectionMedical Image Benchmarks
AskPDF
Mar 24, 2026

Curriculum-Driven 3D CT Report Generation via Language-Free Visual Grafting and Zone-Constrained Compression

Automated radiology report generation from 3D computed tomography (CT) volumes is challenging due to extreme sequence lengths, severe class imbalance, and the tendency of large language models (LLMs) to ignore visual tokens in favor of linguistic priors. We present Ker-VLJEPA-3B, a four-phase curriculum learning framework for free-text report generation from thoracic CT volumes. A phased training curriculum progressively adapts a Llama 3.2 3B decoder to ground its output in visual features from a frozen, self-supervised encoder. Our visual backbone (LeJEPA ViT-Large) is trained via self-supervised joint-embedding prediction on unlabeled CTs, without text supervision. Unlike contrastive models (CLIP, BiomedCLIP), this language-free backbone yields modality-pure representations. Vision-language alignment is deferred to the curriculum's bridge and generation phases. This modality-agnostic design can integrate any self-supervised encoder into an LLM without paired text during foundation training. Methodological innovations include: (1) zone-constrained cross-attention compressing slice embeddings into 32 spatially-grounded visual tokens; (2) PCA whitening of anisotropic LLM embeddings; (3) a positive-findings-only strategy eliminating posterior collapse; (4) warm bridge initialization transferring projection weights; and (5) selective cross-attention freezing with elastic weight consolidation to prevent catastrophic forgetting. Evaluated on the CT-RATE benchmark (2,984 validation volumes, 18 classes), Ker-VLJEPA-3B achieves a macro F1 of 0.429, surpassing the state-of-the-art (U-VLM, macro F1 = 0.414) by 3.6%, and reaching 0.448 (+8.2%) with threshold optimization. Ablation studies confirm 56.6% of generation quality derives from patient-specific visual content. Code and weights are available.

V. K. Cody Bumgardner, Mitchell A. Klusty, Mahmut S. Gokmen +1

Center for Applied Artificial Intelligence, University of Kentucky, Lexington, KY 40506 USA

CT Report GenerationRadiology Report GenerationComputed TomographyCurriculum Learning
AskPDF
Mar 24, 2026

HUydra: Full-Range Lung CT Synthesis via Multiple HU Interval Generative Modelling

Currently, a central challenge and bottleneck in the deployment and validation of computer-aided diagnosis (CAD) models within the field of medical imaging is data scarcity. For lung cancer, one of the most prevalent types worldwide, limited datasets can delay diagnosis and have an impact on patient outcome. Generative AI offers a promising solution for this issue, but dealing with the complex distribution of full Hounsfield Unit (HU) range lung CT scans is challenging and remains as a highly computationally demanding task. This paper introduces a novel decomposition strategy that synthesizes CT images one HU interval at a time, rather than modelling the entire HU domain at once. This framework focuses on training generative architectures on individual tissue-focused HU windows, then merges their output into a full-range scan via a learned reconstruction network that effectively reverses the HU-windowing process. We further propose multi-head and multi-decoder models to better capture textures while preserving anatomical consistency, with a multi-head VQVAE achieving the best performance for the generative task. Quantitative evaluation shows this approach significantly outperforms conventional 2D full-range baselines, achieving a 6.2% improvement in FID and superior MMD, Precision, and Recall across all HU intervals. The best performance is achieved by a multi-head VQVAE variant, demonstrating that it is possible to enhance visual fidelity and variability while also reducing model complexity and computational cost. This work establishes a new paradigm for structure-aware medical image synthesis, aligning generative modelling with clinical interpretation.

António Cardoso, Pedro Sousa, Tania Pereira +1

INESC TEC, Portugal · Faculty of Engineering, University of Porto, Portugal · Faculty of Sciences, University of Porto, Portugal

Medical Image SynthesisComputed TomographyVector-Quantized Variational Autoencoder
AskPDF
Mar 24, 2026

Image-Domain Poisson-Perturbation Robustness of NCCT Slice Classification

Image-domain Poisson perturbation may alter normalized NCCT appearance and downstream models. We evaluated classification of ischemic core/penumbra-bearing non-contrast CT (NCCT) slices under five simulated settings. The source cohort was CPAISD (112 hyperacute ischemic stroke patients); the test partition contained 10 patients and 809 slices. First, a fixed-checkpoint audit compared direct ResNet-18 classification (P1) with residual U-Net denoising followed by the classifier (P2). P1 average precision (AP) ranged from 0.694 to 0.901, whereas P2 AP ranged from 0.509 to 0.797 (substantially lower at settings 10-40). The fixed 0.5 threshold had 0-12.8% sensitivity for P1 and 0% for P2. Second, a prospectively locked de novo experiment compared direct noisy classification (DNC), joint denoising-classification (JDC-0), and the same joint model with privileged training-only lesion-boundary supervision (JDC-B). Across-setting mean AP was 0.861 +/- 0.028 for DNC, 0.840 +/- 0.038 for JDC-0, and 0.856 +/- 0.031 for JDC-B. Hierarchical paired-bootstrap differences were -0.021 (95% CI -0.063 to 0.019) for JDC-0 minus DNC, 0.016 (-0.019 to 0.054) for JDC-B minus JDC-0, and -0.005 (-0.041 to 0.026) for JDC-B minus DNC; none excluded zero. A frozen stress test on the 52-patient AISD partition also showed limited transportability. Thus, ordinary joint training did not demonstrate a classification benefit, and the boundary term recovered part of its point-estimate loss without a statistically supported advantage. Image fidelity, ranking, calibration, and clinical utility must be evaluated separately. This study does not validate acquired low-dose, portable, or cone-beam CT, nor patient-level stroke diagnosis.

Rhea Ghosal, Ronok Ghosal, Eileen Lou

Westlake High School, Austin, TX, United States · California Institute of Technology, Pasadena, CA, United States · Round Rock High School, Round Rock, TX, United States

Medical Image ClassificationNeuroimagingComputed TomographyImage Denoising
AskPDF
Mar 23, 2026

PIVM: Diffusion-Based Prior-Integrated Variation Modeling for Anatomically Precise Abdominal CT Synthesis

Abdominal CT data are limited by high annotation costs and privacy constraints, which hinder the development of robust segmentation and diagnostic models. We present a Prior-Integrated Variation Modeling (PIVM) framework, a diffusion-based method for anatomically accurate CT image synthesis. Instead of generating full images from noise, PIVM predicts voxel-wise intensity variations relative to organ-specific intensity priors derived from segmentation labels. These priors and labels jointly guide the diffusion process, ensuring spatial alignment and realistic organ boundaries. Unlike latent-space diffusion models, our approach operates directly in image space while preserving the full Hounsfield Unit (HU) range, capturing fine anatomical textures without smoothing. Source code is available at https://github.com/BZNR3/PIVM.

Dinglun He, Baoming Zhang, Xu Wang +3

Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA · Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA · Department of Radiation Oncology, Washington University in St. Louis, MO, USA +2

Medical Image SynthesisComputed TomographyDiffusion-Based Image Generation
AskPDF
Mar 21, 2026

TAFG-MAN: Timestep-Adaptive Frequency-Gated Latent Diffusion for Efficient and High-Quality Low-Dose CT Image Denoising

Low-dose computed tomography (LDCT) reduces radiation exposure but also introduces substantial noise and structural degradation, making it difficult to suppress noise without erasing subtle anatomical details. In this paper, we present TAFG-MAN, a latent diffusion framework for efficient and high-quality LDCT image denoising. The framework combines a perceptually optimized autoencoder, conditional latent diffusion restoration in a compact latent space, and a lightweight Timestep-Adaptive Frequency-Gated (TAFG) conditioning design. TAFG decomposes condition features into low- and high-frequency components, predicts timestep-adaptive gates from the current denoising feature and timestep embedding, and progressively releases high-frequency guidance in later denoising stages before cross-attention. In this way, the model relies more on stable structural guidance at early reverse steps and introduces fine details more cautiously as denoising proceeds, improving the balance between noise suppression and detail preservation. Experiments show that TAFG-MAN achieves a favorable quality-efficiency trade-off against representative baselines. Compared with its base variant without TAFG, it further improves detail preservation and perceptual quality while maintaining essentially the same inference cost, and ablation results confirm the effectiveness of the proposed conditioning mechanism.

Tangtangfang Fang, Yang Jiao, Xiangjian He +2

University of Nottingham Ningbo China, Ningbo, Zhejiang, China

LDCT DenoisingDiffusion Models for Image RestorationComputed TomographyLatent Diffusion ModelsConditional Diffusion Models
AskPDF
Mar 19, 2026

Benchmarking CNN-based Models against Transformer-based Models for Abdominal Multi-Organ Segmentation on the RATIC Dataset

Accurate multi-organ segmentation in abdominal CT scans is essential for computer-aided diagnosis and treatment. While convolutional neural networks (CNNs) have long been the standard approach in medical image segmentation, transformer-based architectures have recently gained attention due to their ability to model long-range dependencies. In this study, we systematically benchmark the three hybrid transformer-based models UNETR, SwinUNETR, and UNETR++ against a strong CNN baseline, SegResNet, for volumetric multi-organ segmentation on the heterogeneous RATIC dataset. The dataset comprises 206 annotated CT scans from 23 institutions worldwide, covering five abdominal organs. All models were trained and evaluated under identical preprocessing and training conditions using the Dice Similarity Coefficient (DSC) as the primary metric. The results show that the CNN-based SegResNet achieves the highest overall performance, outperforming all hybrid transformer-based models across all organs. Among the transformer-based approaches, UNETR++ delivers the most competitive results, while UNETR demonstrates notably faster convergence with fewer training iterations. These findings suggest that, for small- to medium-sized heterogeneous datasets, well-optimized CNN architectures remain highly competitive and may outperform hybrid transformer-based designs.

Lukas Bayer, Sheethal Bhat, Andreas Maier

Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg

Medical Image SegmentationHybrid CNN-Transformer ArchitecturesConvolutional Neural NetworksMedical Image BenchmarksComputed Tomography
AskPDF
Mar 16, 2026

Towards Fair and Robust Volumetric CT Classification via KL-Regularised Group Distributionally Robust Optimisation

Automated diagnosis from chest computed tomography (CT) scans faces two persistent challenges in clinical deployment: distribution shift across acquisition sites and performance disparity across demographic subgroups. We address both simultaneously across two complementary tasks: binary COVID-19 classification from multi-site CT volumes (Task 1) and four-class lung pathology recognition with gender-based fairness constraints (Task 2). Our framework combines a lightweight MobileViT-XXS slice encoder with a two-layer SliceTransformer aggregator for volumetric reasoning, and trains with a KL-regularised Group Distributionally Robust Optimisation (Group DRO) objective that adaptively upweights underperforming acquisition centres and demographic subgroups. Unlike standard Group DRO, the KL penalty prevents group weight collapse, providing a stable balance between worst-case protection and average performance. For Task 2, we define groups at the granularity of gender class, directly targeting severely underrepresented combinations such as female Squamous cell carcinoma. On Task 1, our best configuration achieves a challenge F1 of 0.835, surpassing the best published challenge entry by +5.9. On Task 2, Group DRO with α = 0.5 achieves a mean per-gender macro F1 of 0.815, outperforming the best challenge entry by +11.1 pp and improving Female Squamous F1 by +17.4 over the Focal Loss baseline.

Samuel Johnny, Blessed Guda, Goodness Obasi +2

Carnegie Mellon University Africa, Kigali, Rwanda · Carnegie Mellon University, Pittsburgh, USA

Group Distributionally Robust OptimizationMedical Image ClassificationFairness in Medical Image ClassificationDistributionally Robust OptimizationAlgorithmic FairnessComputed Tomography
AskPDF
Mar 16, 2026

NAMD: Virtual Follow-up Computed Tomography Synthesis via Nodule-Aligned Multimodal Diffusion Models for Early Lung Cancer Diagnosis

Lung cancer remains the leading cause of cancer-related mortality worldwide, with survival outcomes critically dependent on early and accurate detection. When low-dose computed tomography (LDCT) findings are indeterminate, clinicians typically defer diagnosis pending follow-up CT imaging obtained up to 12 months later, inevitably delaying treatment for patients with malignant nodules. To address this clinical gap, we propose Nodule-Aligned Multimodal (Latent) Diffusion (NAMD), a novel generative framework that synthesizes one-year follow-up nodule CT images conditioned on the baseline CT scan, quantitative nodule biomarkers, and patient-level Electronic Health Records (EHR), enabling timely prediction of nodule malignant progression without requiring actual follow-up scans. NAMD introduces two key contributions: (i) a nodule-aligned latent space regularized so that embedding distances reflect clinically meaningful biomarker changes, and (ii) an LLM-driven multimodal conditioning mechanism encoding heterogeneous EHR data into the diffusion backbone. Evaluated on the National Lung Screening Trial (NLST), our method's synthetic follow-up images achieve an AUROC of 0.805 and an AUPRC of 0.346 for lung nodule malignancy prediction, outperforming both the baseline LDCT performance without virtual follow-up generation, and existing state-of-the-art conditional generation methods, while maintaining competitive image quality. These findings suggest that NAMD enables earlier and more accurate lung cancer diagnosis by capturing clinically meaningful features of nodule progression.

James Song, Yifan Wang, Chuan Zhou +1

University of Michigan · University of Michigan Medical School

Medical Image AnalysisLongitudinal Medical Image AnalysisMedical Image SynthesisComputed TomographyMultimodal Diffusion Models
AskPDF
Mar 16, 2026

Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report Generation

Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this limitation stems from a representational bottleneck: contrastive 3D CT embeddings encode discriminative pathology signals, yet exhibit severe dimensional concentration, with as few as 2 effective dimensions out of 512. Corroborating this, scaling the language model yields no measurable improvement, suggesting that the bottleneck lies in the visual representation rather than the generator. This bottleneck limits both generation and retrieval; naive static retrieval fails to improve clinical efficacy and can even degrade performance. We propose AdaRAG-CT, an adaptive augmentation framework that compensates for this visual bottleneck by introducing supplementary textual information through controlled retrieval and selectively integrating it during generation. On the CT-RATE benchmark, AdaRAG-CT achieves state-of-the-art clinical efficacy, improving Clinical F1 from 0.420 (CT-Agent) to 0.480 (+6 points); ablation studies confirm that both the retrieval and generation components contribute to the improvement. Code is available at https://github.com/renjie-liang/Adaptive-RAG-for-3DCT-Report-Generation.

Renjie Liang, Yiling Ma, Yang Xing +6

University of Florida · Yale University · University of Southern California

HealthcareMultimodal RAGRetrieval-Augmented GenerationRadiology Report GenerationAdaptive RAGComputed Tomography+1
AskPDF
Mar 16, 2026

One CT Unified Model Training Framework to Rule All Scanning Protocols

Non-ideal measurement computed tomography (NICT), which lowers radiation at the cost of image quality, is expanding the clinical use of CT. Although unified models have shown promise in NICT enhancement, most methods require paired data, which is an impractical demand due to inevitable organ motion. Unsupervised approaches attempt to overcome this limitation, but their assumption of homogeneous noise neglects the variability of scanning protocols, leading to poor generalization and potential model collapse. We further observe that distinct scanning protocols, which correspond to different physical imaging processes, produce discrete sub-manifolds in the feature space, contradicting these assumptions and limiting their effectiveness. To address this, we propose an Uncertainty-Guided Manifold Smoothing (UMS) framework to bridge the gaps between sub-manifolds. A classifier in UMS identifies sub-manifolds and predicts uncertainty scores, which guide the generation of diverse samples across the entire manifold. By leveraging the classifier's capability, UMS effectively fills the gaps between discrete sub-manifolds, and promotes a continuous and dense feature space. Due to the complexity of the global manifold, it's hard to directly model it. Therefore, we propose to dynamically incorporate the global- and sub-manifold-specific features. Specifically, we design a global- and sub-manifold-driven architecture guided by the classifier, which enables dynamic adaptation to subdomain variations. This dynamic mechanism improves the network's capacity to capture both shared and domain-specific features, thereby improving reconstruction performance. Extensive experiments on public datasets are conducted to validate the effectiveness of our method across different generation paradigms.

Fengzhi Xu, Ziyuan Yang, Zexin Lu +4

Sichuan University, Chengdu, China · City University of Hong Kong, Hong Kong, China · Fudan University, Shanghai, China

Computed TomographyImage ReconstructionLDCT DenoisingUnsupervised Domain Adaptation
AskPDF
Mar 15, 2026

A Heterogeneous Ensemble for Multi-Center COVID-19 Classification from Chest CT Scans

The COVID-19 pandemic exposed critical limitations in diagnostic workflows: RT-PCR tests suffer from slow turnaround times and high false-negative rates, while CT-based screening offers faster complementary diagnosis but requires expert radiological interpretation. Deploying automated CT analysis across multiple hospital centres introduces further challenges, as differences in scanner hardware, acquisition protocols, and patient populations cause substantial domain shift that degrades single-model performance. To address these challenges, we present a heterogeneous ensemble of nine models spanning three inference paradigms: (1) a self-supervised DINOv2 Vision Transformer with slice-level sigmoid aggregation, (2) a RadImageNet-pretrained DenseNet-121 with slice-level sigmoid averaging, and (3) seven Gated Attention Multiple Instance Learning models using EfficientNet-B3, ConvNeXt-Tiny, and EfficientNetV2-S backbones with scan-level softmax classification. Ensemble diversity is further enhanced through random-seed variation and Stochastic Weight Averaging. We address severe overfitting, reducing the validation-to-training loss ratio from 35x to less than 3x, through a combination of Focal Loss, embedding-level Mixup, and domain-aware augmentation. Model outputs are fused via score-weighted probability averaging and calibrated with per-source threshold optimization. The final ensemble achieves an average macro F1 of 0.9280 across four hospital centres, outperforming the best single model (F1=0.8969) by +0.031, demonstrating that heterogeneous architectures combined with source-aware calibration are essential for robust multi-site medical image classification.

Aadit Nilay, Bhavesh Thapar, Anant Agrawal +1

University of Maryland, College Park

Medical Image ClassificationDomain GeneralizationDeep EnsemblesComputed Tomography
AskPDF