Traditional supervised denoisers are trained using pairs of noisy input and clean target images. They learn to predict a central tendency of the posterior distribution over possible clean images. When, e.g., trained with the popular quadratic loss function, the network's output will correspond to the minimum mean square error (MMSE) estimate. Unsupervised denoisers based on Variational AutoEncoders (VAEs) have succeeded in achieving state-of-the-art results while requiring only unpaired noisy data as training input. In contrast to the traditional supervised approach, unsupervised denoisers do not directly produce a single prediction, such as the MMSE estimate, but allow us to draw samples from the posterior distribution of clean solutions corresponding to the noisy input. To approximate the MMSE estimate during inference, unsupervised methods have to create and draw a large number of samples - a computationally expensive process - rendering the approach inapplicable in many situations. Here, we present an alternative approach that trains a deterministic network alongside the VAE to directly predict a central tendency. Our method achieves results that surpass the results achieved by the unsupervised method at a fraction of the computational cost.
Most unsupervised denoising methods are based on the assumption that imaging noise is either pixel-independent, i.e., spatially uncorrelated, or signal-independent, i.e., purely additive. However, in practice many imaging setups, especially in microscopy, suffer from a combination of signal-dependent noise (e.g. Poisson shot noise) and axis-aligned correlated noise (e.g. stripe shaped scanning or readout artifacts). In this paper, we present the first unsupervised deep learning-based denoiser that can remove this type of noise without access to any clean images or a noise model. Unlike self-supervised techniques, our method does not rely on removing pixels by masking or subsampling so can utilize all available information. We implement a Variational Autoencoder (VAE) with a specially designed autoregressive decoder capable of modelling the noise component of an image but incapable of independently modelling the underlying clean signal component. As a consequence, our VAE's encoder learns to encode only underlying clean signal content and to discard imaging noise. We also propose an additional decoder for mapping the encoder's latent variables back into image space, thereby sampling denoised images. Experimental results demonstrate that our approach surpasses existing methods for self- and unsupervised image denoising while being robust with respect to the size of the autoregressive receptive field. Code for this project can be found at https://github.com/krulllab/DVLAE.
We present a fresh perspective on shot noise corrupted images and noise removal. By viewing image formation as the sequential accumulation of photons on a detector grid, we show that a network trained to predict where the next photon could arrive is in fact solving the minimum mean square error (MMSE) denoising task. This new perspective allows us to make three contributions: We present a new strategy for self-supervised denoising, We present a new method for sampling from the posterior of possible solutions by iteratively sampling and adding small numbers of photons to the image. We derive a full generative model by starting this process from an empty canvas. We call this approach generative accumulation of photons (GAP). We evaluate our method quantitatively and qualitatively on 4 new fluorescence microscopy datasets, which will be made available to the community. We find that it outperforms supervised, self-supervised and unsupervised baselines or performs on-par.
Light microscopy is routinely used to look at living cells and biological tissues at sub-cellular resolution. Components of the imaged cells can be highlighted using fluorescent labels, allowing biologists to investigate individual structures of interest. Given the complexity of biological processes, it is typically necessary to look at multiple structures simultaneously, typically via a temporal multiplexing scheme. Still, imaging more than 3 or 4 structures in this way is difficult for technical reasons and limits the rate of scientific progress in the life sciences. Hence, a computational method to split apart (decompose) superimposed biological structures acquired in a single image channel, i.e. without temporal multiplexing, would have tremendous impact. Here we present {\mu}Split, a dedicated approach for trained image decomposition. We find that best results using regular deep architectures is achieved when large image patches are used during training, making memory consumption the limiting factor to further improving performance. We therefore introduce lateral contextualization (LC), a memory efficient way to train deep networks that operate well on small input patches. In later layers, additional image context is fed at adequately lowered resolution. We integrate LC with Hierarchical Autoencoders and Hierarchical VAEs.For the latter, we also present a modified ELBO loss and show that it enables sound VAE training. We apply {\mu}Split to five decomposition tasks, one on a synthetic dataset, four others derived from two real microscopy datasets. LC consistently achieves SOTA results, while simultaneously requiring considerably less GPU memory than competing architectures not using LC. When introducing LC, results obtained with the above-mentioned vanilla architectures do on average improve by 2.36 dB (PSNR decibel), with individual improvements ranging from 0.9 to 3.4 dB.
Many microscopy applications are limited by the total amount of usable light and are consequently challenged by the resulting levels of noise in the acquired images. This problem is often addressed via (supervised) deep learning based denoising. Recently, by making assumptions about the noise statistics, self-supervised methods have emerged. Such methods are trained directly on the images that are to be denoised and do not require additional paired training data. While achieving remarkable results, self-supervised methods can produce high-frequency artifacts and achieve inferior results compared to supervised approaches. Here we present a novel way to improve the quality of self-supervised denoising. Considering that light microscopy images are usually diffraction-limited, we propose to include this knowledge in the denoising process. We assume the clean image to be the result of a convolution with a point spread function (PSF) and explicitly include this operation at the end of our neural network. As a consequence, we are able to eliminate high-frequency artifacts and achieve self-supervised results that are very close to the ones achieved with traditional supervised methods.
Deep Learning based methods have emerged as the indisputable leaders for virtually all image restoration tasks. Especially in the domain of microscopy images, various content-aware image restoration (CARE) approaches are now used to improve the interpretability of acquired data. But there are limitations to what can be restored in corrupted images, and any given method needs to make a sensible compromise between many possible clean signals when predicting a restored image. Here, we propose DivNoising -- a denoising approach based on fully-convolutional variational autoencoders, overcoming this problem by predicting a whole distribution of denoised images. Our method is unsupervised, requiring only noisy images and a description of the imaging noise, which can be measured or bootstrapped from noisy data. If desired, consensus predictions can be inferred from a set of DivNoising predictions, leading to competitive results with other unsupervised methods and, on occasion, even with the supervised state-of-the-art. DivNoising samples from the posterior enable a plethora of useful applications. We are (i) discussing how optical character recognition (OCR) applications could benefit from diverse predictions on ambiguous data, and (ii) show in detail how instance cell segmentation gains performance when using diverse DivNoising predictions.
Microscopy image analysis often requires the segmentation of objects, but training data for this task is typically scarce and hard to obtain. Here we propose DenoiSeg, a new method that can be trained end-to-end on only a few annotated ground truth segmentations. We achieve this by extending Noise2Void, a self-supervised denoising scheme that can be trained on noisy images alone, to also predict dense 3-class segmentations. The reason for the success of our method is that segmentation can profit from denoising, especially when performed jointly within the same network. The network becomes a denoising expert by seeing all available raw data, while co-learning to segment, even if only a few segmentation labels are available. This hypothesis is additionally fueled by our observation that the best segmentation results on high quality (very low noise) raw data are obtained when moderate amounts of synthetic noise are added. This renders the denoising-task non-trivial and unleashes the desired co-learning effect. We believe that DenoiSeg offers a viable way to circumvent the tremendous hunger for high quality training data and effectively enables few-shot learning of dense segmentations.
Deep learning (DL) has arguably emerged as the method of choice for the detection and segmentation of biological structures in microscopy images. However, DL typically needs copious amounts of annotated training data that is for biomedical projects typically not available and excessively expensive to generate. Additionally, tasks become harder in the presence of noise, requiring even more high-quality training data. Hence, we propose to use denoising networks to improve the performance of other DL-based image segmentation methods. More specifically, we present ideas on how state-of-the-art self-supervised CARE networks can improve cell/nuclei segmentation in microscopy data. Using two state-of-the-art baseline methods, U-Net and StarDist, we show that our ideas consistently improve the quality of resulting segmentations, especially when only limited training data for noisy micrographs are available.
Image denoising is the first step in many biomedical image analysis pipelines and Deep Learning (DL) based methods are currently best performing. A new category of DL methods such as Noise2Void or Noise2Self can be used fully unsupervised, requiring nothing but the noisy data. However, this comes at the price of reduced reconstruction quality. The recently proposed Probabilistic Noise2Void (PN2V) improves results, but requires an additional noise model for which calibration data needs to be acquired. Here, we present improvements to PN2V that (i) replace histogram based noise models by parametric noise models, and (ii) show how suitable noise models can be created even in the absence of calibration data. This is a major step since it actually renders PN2V fully unsupervised. We demonstrate that all proposed improvements are not only academic but indeed relevant.