Disentangled Learning Improves Implicit Neural Representations for Medical Reconstruction

• URL: http://arxiv.org/abs/2605.04234v1
• Date: Tue, 05 May 2026 19:21:02 GMT
• Title: Disentangled Learning Improves Implicit Neural Representations for Medical Reconstruction
• Abstract summary: Implicit neural representations (INRs) have emerged as a powerful paradigm for medical imaging via physics-informed unsupervised learning.<n>We present DisINR, a novel INR framework that explicitly disentangles shared and subject-specific representations.
• Score: 32.058812894769616
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Implicit neural representations (INRs) have emerged as a powerful paradigm for medical imaging via physics-informed unsupervised learning. Classical INRs optimize an entire network from scratch for each subject, leading to inefficient training and suboptimal imaging quality. Recent initialization-based approaches attempt to inject population priors into pre-trained networks, yet they rely on high-quality images and often suffer from catastrophic forgetting during fine-tuning. We present DisINR, a novel INR framework that explicitly disentangles shared and subject-specific representations. DisINR introduces a shared encoder-decoder pair and subject-specific encoders, whose features are jointly decoded for image reconstruction. By integrating differentiable forward models, it pre-trains the shared modules directly from limited raw measurements, removing the need for pre-acquired high-quality images. During test-time adaptation, only the subject-specific encoder is optimized, while the shared pair remains frozen, effectively preserving learned priors. Extensive evaluations on three representative medical imaging tasks show that DisINR significantly outperforms state-of-the-art INRs in both reconstruction accuracy and efficiency.

Related papers

• Enhancing Implicit Neural Representations with Image Feature Embedding for Unsupervised Cardiac Cine MRI Reconstruction [2.92524552093165]
  Under-sampled k-space data is often used in cardiac cine MRI reconstruction.<n>Unsupervised methods eliminate the need for fully sampled reference data.<n>In this work, we propose an image-domain dual-branch INR framework, termed I-FP-INR.
  arXiv  Detail & Related papers  (2026-07-05T01:02:42Z)
• PrIINeR: Towards Prior-Informed Implicit Neural Representations for Accelerated MRI [2.2265038612930663]
  Implicit Neural Representations (INRs) show promise for MRI reconstruction, but struggle at high acceleration factors due to weak prior constraints.<n>We propose PrIINeR, an INR-based MRI reconstruction method that integrates prior knowledge from pre-trained deep learning models into the INR framework.
  arXiv  Detail & Related papers  (2025-08-11T14:59:09Z)
• NeRF-based CBCT Reconstruction needs Normalization and Initialization [53.58395475423445]
  NeRF-based methods suffer from a local-global training mismatch between their two key components: the hash encoder and the neural network.<n>We introduce a Normalized Hash, which enhances feature consistency and mitigates the mismatch.<n>The neural network exhibits improved stability during early training, enabling faster convergence and enhanced reconstruction performance.
  arXiv  Detail & Related papers  (2025-06-24T16:01:45Z)
• Regularization by Neural Style Transfer for MRI Field-Transfer Reconstruction with Limited Data [2.308563547164654]
  Regularization by Neural Style Transfer is a novel framework that integrates a neural style transfer engine with a denoiser to enable magnetic field-transfer reconstruction.<n>Our experiment results demonstrate RNST's ability to reconstruct high-quality images across diverse anatomical planes.
  arXiv  Detail & Related papers  (2023-08-21T18:26:35Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction [68.80715727288514]
  We show how to unfold an iterative MGDUN algorithm into a novel model-guided deep unfolding network by taking the MRI observation matrix. In this paper, we propose a novel Model-Guided interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction.
  arXiv  Detail & Related papers  (2022-09-15T03:58:30Z)
• Adaptive Diffusion Priors for Accelerated MRI Reconstruction [0.9895793818721335]
  Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Unconditional models instead learn generative image priors decoupled from the operator to improve reliability against domain shifts related to the imaging operator. Here we propose the first adaptive diffusion prior for MRI reconstruction, AdaDiff, to improve performance and reliability against domain shifts.
  arXiv  Detail & Related papers  (2022-07-12T22:45:08Z)
• Federated Learning of Generative Image Priors for MRI Reconstruction [5.3963856146595095]
  Multi-institutional efforts can facilitate training of deep MRI reconstruction models, albeit privacy risks arise during cross-site sharing of imaging data. We introduce a novel method for MRI reconstruction based on Federated learning of Generative IMage Priors (FedGIMP) FedGIMP leverages a two-stage approach: cross-site learning of a generative MRI prior, and subject-specific injection of the imaging operator.
  arXiv  Detail & Related papers  (2022-02-08T22:17:57Z)
• InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images [53.4351366246531]
  We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. We analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance.
  arXiv  Detail & Related papers  (2021-12-23T15:52:37Z)
• Implicit Neural Representations for Image Compression [103.78615661013623]
  Implicit Neural Representations (INRs) have gained attention as a novel and effective representation for various data types. We propose the first comprehensive compression pipeline based on INRs including quantization, quantization-aware retraining and entropy coding. We find that our approach to source compression with INRs vastly outperforms similar prior work.
  arXiv  Detail & Related papers  (2021-12-08T13:02:53Z)
• Adaptive Gradient Balancing for UndersampledMRI Reconstruction and Image-to-Image Translation [60.663499381212425]
  We enhance the image quality by using a Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing technique. In MRI, our method minimizes artifacts, while maintaining a high-quality reconstruction that produces sharper images than other techniques.
  arXiv  Detail & Related papers  (2021-04-05T13:05:22Z)
• Self-Organized Operational Neural Networks for Severe Image Restoration Problems [25.838282412957675]
  Discnative learning based on convolutional neural networks (CNNs) aims to perform image restoration by learning from training examples of noisy-clean image pairs. We claim that this is due to the inherent linear nature of convolution-based transformation, which is inadequate for handling severe restoration problems. We propose a self-organizing variant of ONNs, Self-ONNs, for image restoration, which synthesizes novel nodal transformations onthe-fly.
  arXiv  Detail & Related papers  (2020-08-29T02:19:41Z)

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.