Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network

• URL: http://arxiv.org/abs/2407.03239v2
• Date: Mon, 15 Jul 2024 08:53:44 GMT
• Title: Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
• Authors: Rui Li, Mikhail Kudryashev, Artur Yakimovich,
• Abstract summary: Traditional explicit methods in light microscopy (LM) rely on the point spread function (PSF) during image acquisition. We propose an innovative physics-informed neural network Multi-Stage Residual-BCR Net (m-rBCR) to approximate the optic deconvolution. In contrast to the explicit deconvolution methods (e.g. Richardson-Lucy) and other state-of-the-art NN models, the m-rBCR model demonstrates superior performance to other candidates.
• Score: 1.7916466820108048
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optic deconvolution in light microscopy (LM) refers to recovering the object details from images, revealing the ground truth of samples. Traditional explicit methods in LM rely on the point spread function (PSF) during image acquisition. Yet, these approaches often fall short due to inaccurate PSF models and noise artifacts, hampering the overall restoration quality. In this paper, we approached the optic deconvolution as an inverse problem. Motivated by the nonstandard-form compression scheme introduced by Beylkin, Coifman, and Rokhlin (BCR), we proposed an innovative physics-informed neural network Multi-Stage Residual-BCR Net (m-rBCR) to approximate the optic deconvolution. We validated the m-rBCR model on four microscopy datasets - two simulated microscopy datasets from ImageNet and BioSR, real dSTORM microscopy images, and real widefield microscopy images. In contrast to the explicit deconvolution methods (e.g. Richardson-Lucy) and other state-of-the-art NN models (U-Net, DDPM, CARE, DnCNN, ESRGAN, RCAN, Noise2Noise, MPRNet, and MIMO-U-Net), the m-rBCR model demonstrates superior performance to other candidates by PSNR and SSIM in two real microscopy datasets and the simulated BioSR dataset. In the simulated ImageNet dataset, m-rBCR ranks the second-best place (right after MIMO-U-Net). With the backbone from the optical physics, m-rBCR exploits the trainable parameters with better performances (from ~30 times fewer than the benchmark MIMO-U-Net to ~210 times than ESRGAN). This enables m-rBCR to achieve a shorter runtime (from ~3 times faster than MIMO-U-Net to ~300 times faster than DDPM). To summarize, by leveraging physics constraints our model reduced potentially redundant parameters significantly in expertise-oriented NN candidates and achieved high efficiency with superior performance.

Related papers

• Unrolled Networks are Conditional Probability Flows in MRI Reconstruction [13.185194525641478]
  We introduce flow ODEs to MRI reconstruction by theoretically proving that unrolled networks are discrete implementations of conditional probability flow ODEs.<n>This connection provides explicit formulations for parameters and clarifies how intermediate states should evolve.<n>We propose Flow-Aligned Training (FLAT), which derives unrolled parameters from the ODE discretization and aligns intermediate reconstructions with the ideal ODE trajectory to improve stability and convergence.
  arXiv  Detail & Related papers  (2025-12-02T18:48:10Z)
• In silico Deep Learning Protocols for Label-Free Super-Resolution Microscopy: A Comparative Study of Network Architectures and SNR Dependence [6.165323448459655]
  A key limitation often cited by optical microscopists refers to the limit of its lateral resolution.<n>This study seeks to evaluate an alternative & economical approach to achieving super-resolution (SR) optical microscopy.
  arXiv  Detail & Related papers  (2025-09-23T07:32:40Z)
• Self-Consistent Nested Diffusion Bridge for Accelerated MRI Reconstruction [22.589087990596887]
  We focus on the underexplored task of magnitude-image-based MRI reconstruction. Recent advancements in diffusion models, particularly denoising diffusion probabilistic models, have demonstrated strong capabilities in modeling image priors. We propose a novel Self-Consistent Nested Diffusion Bridge (SC-NDB) framework that models accelerated MRI reconstruction.
  arXiv  Detail & Related papers  (2024-12-13T09:35:34Z)
• LDPM: Towards undersampled MRI reconstruction with MR-VAE and Latent Diffusion Prior [4.499605583818247]
  Some works attempted to solve MRI reconstruction with diffusion models, but these methods operate directly in pixel space. Latent diffusion models, pre-trained on natural images with rich visual priors, are expected to solve the high computational cost problem in MRI reconstruction. A novel Latent Diffusion Prior-based undersampled MRI reconstruction (LDPM) method is proposed.
  arXiv  Detail & Related papers  (2024-11-05T09:51:59Z)
• Spherical convolutional neural networks can improve brain microstructure estimation from diffusion MRI data [0.35998666903987897]
  Diffusion magnetic resonance imaging is sensitive to the microstructural properties of brain tissue. Estimate clinically and scientifically relevant microstructural properties from the measured signals remains a highly challenging inverse problem that machine learning may help solve. We trained a spherical convolutional neural network to predict the ground-truth parameter values from efficiently simulated noisy data.
  arXiv  Detail & Related papers  (2022-11-17T20:52:00Z)
• Hybrid Parallel Imaging and Compressed Sensing MRI Reconstruction with GRAPPA Integrated Multi-loss Supervised GAN [2.7110495144693374]
  This paper proposes a novel Generative Adversarial Network (GAN) namely RECGAN-GR supervised with multi-modal losses for de-aliasing the reconstructed image. The proposed work contributes to significant improvement in the image quality for low retained data leading to 5x or 10x faster acquisition.
  arXiv  Detail & Related papers  (2022-09-19T07:26:45Z)
• 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)
• Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
  State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-28T17:50:19Z)
• Two-Stage Self-Supervised Cycle-Consistency Network for Reconstruction of Thin-Slice MR Images [62.4428833931443]
  The thick-slice magnetic resonance (MR) images are often structurally blurred in coronal and sagittal views. Deep learning has shown great potential to re-construct the high-resolution (HR) thin-slice MR images from those low-resolution (LR) cases. We propose a novel Two-stage Self-supervised Cycle-consistency Network (TSCNet) for MR slice reconstruction.
  arXiv  Detail & Related papers  (2021-06-29T13:29:18Z)
• Over-and-Under Complete Convolutional RNN for MRI Reconstruction [57.95363471940937]
  Recent deep learning-based methods for MR image reconstruction usually leverage a generic auto-encoder architecture. We propose an Over-and-Under Complete Convolu?tional Recurrent Neural Network (OUCR), which consists of an overcomplete and an undercomplete Convolutional Recurrent Neural Network(CRNN) The proposed method achieves significant improvements over the compressed sensing and popular deep learning-based methods with less number of trainable parameters.
  arXiv  Detail & Related papers  (2021-06-16T15:56:34Z)
• Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers [0.0]
  We introduce a novel unsupervised MRI reconstruction method based on zero-Shot Learned Adrial TransformERs (SLATER) A zero-shot reconstruction is performed on undersampled test data, where inference is performed by optimizing network parameters. Experiments on brain MRI datasets clearly demonstrate the superior performance of SLATER against several state-of-the-art unsupervised methods.
  arXiv  Detail & Related papers  (2021-05-15T02:01:21Z)
• 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)
• Deeply-Supervised Density Regression for Automatic Cell Counting in Microscopy Images [9.392002197101965]
  We propose a new density regression-based method for automatically counting cells in microscopy images. The proposed method processes two innovations compared to other state-of-the-art regression-based methods. Experimental studies evaluated on four datasets demonstrate the superior performance of the proposed method.
  arXiv  Detail & Related papers  (2020-11-07T04:02:47Z)
• Enhancing Fiber Orientation Distributions using convolutional Neural Networks [0.0]
  We learn improved FODs for commercially acquired MRI. We evaluate patch-based 3D convolutional neural networks (CNNs) Our approach may enable robust CSD model estimation on single-shell dMRI acquisition protocols.
  arXiv  Detail & Related papers  (2020-08-12T16:06:25Z)
• When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks [57.0502745301132]
  We propose Micro-Dense Nets, a novel architecture with global residual learning and local micro-dense aggregations. Our micro-dense block can be integrated with neural architecture search based models to boost their performance.
  arXiv  Detail & Related papers  (2020-04-19T08:34:52Z)

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.