Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis

• URL: http://arxiv.org/abs/2605.00448v1
• Date: Fri, 01 May 2026 06:35:53 GMT
• Title: Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis
• Abstract summary: Feature Attention Style Transfer Transfer (FAST) is a novel framework that transfers from high-fidelity CT representations to a visual encoder operating on compressed inputs.<n>Structured Factorized Projection (SFP) is a parameter-efficient alternative to dense projection layers, reducing parameters by almost half.<n>Our contrastive learning pipeline, CT-Lite, integrates these components with a SigLIP-based objective alignment objective.
• Score: 0.18352113484137622
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The deployment of artificial intelligence in medical imaging is hindered by high computational complexity and resource-intensive processing of volumetric data. Although chest computed tomography (CT) volumes offer richer diagnostic information than projection radiography, their use in AI-based diagnosis remains limited due to the computational burden of processing uncompressed volumetric images (typically stored in NIfTI or DICOM format). Addressing the growing need for low-resource deployment and efficient electronic data transfer, we investigate the utilization of JPEG-compressed chest CT volumes for thoracic abnormality detection. We propose Feature Attention Style Transfer (FAST), a novel distillation framework that transfers both activation patterns and structural relationships from high-fidelity CT representations to a spatiotemporal visual encoder operating on compressed inputs. By combining Gram-matrix-based attention style preservation with dual-attention feature alignment, FAST enables robust feature extraction from degraded volumes. Furthermore, we introduce Structured Factorized Projection (SFP), leveraging Block Tensor Train decomposition as a parameter-efficient alternative to dense projection layers, reducing projection-head parameters by almost half. Our contrastive learning pipeline, CT-Lite, integrates these components with a SigLIP-based multimodal alignment objective. Experiments on CT-RATE, NIDCH, and Rad-ChestCT demonstrate that CT-Lite achieves AUROC within 5-7\% of the uncompressed-input baseline across all three datasets, despite operating on compressed inputs with significantly fewer parameters, paving the way for AI-based clinical evaluation under resource constraints.

Related papers

• 3D Ultrasound-Derived Pseudo-CT Synthesis Using a Transformer-Augmented Residual Network for Real-Time Operator Guidance [0.0]
  Ultrasound (US) is non-ionizing and widely accessible; however, it is highly operator dependent and lacks quantitative tissue characterization.<n>This work presents a 3D ultrasound-derived pseudo-CT framework that generates CT-like anatomical reference volumes inferred from US.<n>The proposed method outperforms established baselines in structural fidelity and perceptual image quality.
  arXiv  Detail & Related papers  (2026-05-06T12:52:59Z)
• Distilling Photon-Counting CT into Routine Chest CT through Clinically Validated Degradation Modeling [51.330452704464925]
  We train a latent diffusion model on 1,046 PCCTs and 405,379 EICTs from 145 hospitals.<n>We construct a large-scale dataset of over 17,316 publicly available EICTs enhanced to PCCT-like quality.<n>Our results suggest emerging imaging advances can be systematically distilled into routine EICT using limited high-quality scans as reference.
  arXiv  Detail & Related papers  (2026-04-08T17:47:35Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• Resolution-Independent Neural Operators for Multi-Rate Sparse-View CT [67.14700058302016]
  Deep learning methods achieve high-fidelity reconstructions but often overfit to a fixed acquisition setup.<n>We propose Computed Tomography neural Operator (CTO), a unified CT reconstruction framework that extends to continuous function space.<n>CTO enables consistent multi-sampling-rate and cross-resolution performance, with on average >4dB PSNR gain over CNNs.
  arXiv  Detail & Related papers  (2025-12-13T08:31:46Z)
• Accelerating 3D Photoacoustic Computed Tomography with End-to-End Physics-Aware Neural Operators [74.65171736966131]
  Photoacoustic computed tomography (PACT) combines optical contrast with ultrasonic resolution, achieving deep-tissue imaging beyond the optical diffusion limit.<n>Current implementations require dense transducer arrays and prolonged acquisition times, limiting clinical translation.<n>We introduce Pano, an end-to-end physics-aware model that directly learns the inverse acoustic mapping from sensor measurements to volumetric reconstructions.
  arXiv  Detail & Related papers  (2025-09-11T23:12:55Z)
• CAPRI-CT: Causal Analysis and Predictive Reasoning for Image Quality Optimization in Computed Tomography [2.422970122886921]
  CAPRI-CT is a causal-aware deep learning framework for Causal Analysis and Predictive Reasoning for Image Quality Optimization in CT imaging.<n>It integrates image data with acquisition metadata to model the underlying causal relationships that influence image quality.<n>It is trained and validated using an ensemble learning approach, achieving strong predictive performance.
  arXiv  Detail & Related papers  (2025-07-23T11:23:02Z)
• Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation [18.113659670915474]
  We propose a large language model (LLM) based CTRG method with recurrent visual feature extraction and stereo attentions for hierarchical feature modeling.<n>Specifically, we use a vision Transformer to recurrently process each slice in a CT volume, and employ a set of attentions over the encoded slices from different perspectives to obtain important visual information.<n>Experiment results and further analysis on the benchmark M3D-Cap dataset show that our method outperforms strong baseline models.
  arXiv  Detail & Related papers  (2025-06-24T14:29:06Z)
• CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers [66.15847237150909]
  We introduce a self-supervised deep learning architecture to segment catheters in longitudinal ultrasound images. The network architecture builds upon AiAReSeg, a segmentation transformer built with the Attention in Attention mechanism. We validated our model on a test dataset, consisting of unseen synthetic data and images collected from silicon aorta phantoms.
  arXiv  Detail & Related papers  (2024-03-21T15:13:36Z)
• Feature-oriented Deep Learning Framework for Pulmonary Cone-beam CT (CBCT) Enhancement with Multi-task Customized Perceptual Loss [9.59233136691378]
  Cone-beam computed tomography (CBCT) is routinely collected during image-guided radiation therapy. Recent deep learning-based CBCT enhancement methods have shown promising results in suppressing artifacts. We propose a novel feature-oriented deep learning framework that translates low-quality CBCT images into high-quality CT-like imaging.
  arXiv  Detail & Related papers  (2023-11-01T10:09:01Z)
• Self-Attention Generative Adversarial Network for Iterative Reconstruction of CT Images [0.9208007322096533]
  The aim of this study is to train a single neural network to reconstruct high-quality CT images from noisy or incomplete data. The network includes a self-attention block to model long-range dependencies in the data. Our approach is shown to have comparable overall performance to CIRCLE GAN, while outperforming the other two approaches.
  arXiv  Detail & Related papers  (2021-12-23T19:20:38Z)
• Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis [88.39466012709205]
  This paper builds a novel medical slice to increase the between-slice resolution. Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy. Our method outperforms state-of-the-art algorithms by clear margins.
  arXiv  Detail & Related papers  (2021-12-20T03:38:37Z)
• CT-SGAN: Computed Tomography Synthesis GAN [4.765541373485143]
  We propose the CT-SGAN model that generates large-scale 3D synthetic CT-scan volumes when trained on a small dataset of chest CT-scans. We show that CT-SGAN can significantly improve lung detection accuracy by pre-training a nodule on a vast amount of synthetic data.
  arXiv  Detail & Related papers  (2021-10-14T22:20:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.