Close

Fully Unsupervised Probabilistic Noise2Void

Mangal Prakash, Manan Lalit, Pavel Tomancak, Alexander Krull, Florian Jug

Preprint posted on 11 January 2020 https://arxiv.org/abs/1911.12291v1

Advancing image denoising: Improvements to Probabilistic Noise2Void (PN2V), a method to train convolutional neural networks for image denoising.

Selected by Mariana De Niz

Background

Image denoising is the first step in many biomedical image analysis pipelines, and it boils down to separating an image into its two components: the signal s, and the signal-degrading noise n. For this purpose, discriminative deep learning based methods are currently best performing. Previously, methods achieved denoising by training on pairs of noisy images, and corresponding clean target images. Later, a method was proposed which is capable of using independent pairs of noisy images: Noise2Noise (N2N). This approach has the advantage that it removes the need for strenuous collection of clean data. An improvement towards making this step more efficient, came in early 2019 with a method called Noise2Void (N2V) (1), which is a self-supervised training scheme, namely, it does not require noisy image pairs, nor clean target images. It allows training directly on the body of data to be denoised. This method was applied to various types of biomedical images, including fluorescence microscopy, and cryo-EM. A couple of limitations identified in N2V were a) the assumed predictability of signal s – (i.e. if a pixel’s signal is difficult to predict from its surroundings, more errors will appear in N2V predictions); and b) that N2V could not distinguish between the signal and structured noise that violates the assumption that for any given signal the noise is pixel-wise independent (1). Furthermore, the fact that self-supervised methods such as N2V are not competitive with models trained on image pairs raised the question how they could further be improved.

This is because self-supervised training assumes that the noise is pixel-wise independent given the ground-truth signal, and that the true intensity of the pixel can be predicted from local image context, excluding blind spots (single missing pixels) (1). To address this, Laine et al  (2) proposed using a Gaussian noise model and predicting Gaussian intensity distributions per pixel. With a method called Probabilistic Noise 2 Void (PN2V), Laine et al (2) and Krug et al (3) proposed a way to leverage information to the network’s blind spots. PN2V puts a probabilistic model for each pixel in place, from which it is possible to infer better denoising results after choose a statistical estimator,i.e. MMSE. The required PN2V noise models are generated from a sequence of noisy calibration images, and characterize the distribution of noisy pixels around their respective ground truth signal value.  The current preprint by Prakash et al. goes yet another step further, making PN2V fully unsupervised, hence not requiring to image calibration data any more (4). (Figure 1).

Figure 1. GMM bootstrapping method does not require paired training or calibration data.

 

Key findings and developments

General summary

The current work is an improvement over Noise2Void, Noise2Self, and Probabilistic Noise2Void. The previously published Probabilistic Noise2Void (PN2V) required additional noise models for which calibration data is required. The improvement to PN2V presented here replaces histogram based noise models by parametric noise models (using Gaussian Mixture Models (GMM)), and shows how suitable noise models can be created even in the absence of calibration data (i.e. Bootstrapped PN2V), hence rendering PN2V fully unsupervised.

The GMM-based variation of PN2V noise models can lead to higher reconstruction quality, even with imperfect calibration data. The bootstrapping scheme allows PN2V to be trained fully unsupervised, making use of only the data to be denoised. The denoising quality of bootstrapped PN2V was close to fully supervised CARE and outperformed N2V notably.

The authors applied the model to three image sets including a Convalaria dataset, a mouse skull nuclei dataset and a mouse actin dataset, all consisting of calibration and denoised sets. Consistent with open science, the authors make the calibration data and noisy image data publicly available together with the code.

The improvement to PN2V will help to make high quality deep learning-based denoising an easily applicable tool that does not require the acquisition of paired training data or calibration data. This is particularly relevant to experiments where photosensitivity or fast dynamics hinder the acquisition of image pairs.

What I like about this paper

I liked most about this paper the usefulness of the tool presented, and the continuity they give to the work they had previously presented. This is a tool useful to many labs across the biomedical science community. I like the fact that their development is a good example of open science, and of considering the needs of the scientific community- as the authors discuss the process since this tools’ predecessors. I also like that the full datasets are made available, and that the full basis of the improvements to PN2V are explained in detail.

Open questions

1.  In your preprint you touch on the question why self-supervised methods are not competitive with models trained on image pairs. Can you expand further on your explanation?

2.  You tested the improvements you made on images acquired from spinning disc and point scanning confocal microscopy with great success. Do you expect equal success on images obtained by MRI or EM (as you showed in your previous paper, where you first introduced PN2V)?

3.  What are general limitations you would expect using different types of samples (eg. live vs. fixed; strong markers vs. weak), or different imaging methods (eg. MRI, EM, cryo-EM, SR, etc)?

4.  Are there specific cases where your improved PN2V model is still unsuccessful and image pairs are still necessary?

5.  Could you expand further on the way Gaussian Mixture Models work, for non-specialists?

 

References

  1. Krull A, Vicar T, Jug F, Probabilistic Noise2Void: Unsupervised content-aware denoising (2019), arXiv:1906.00651v2
  2. Laine S, Karras T, Lehtinen J, Aila T, High-quality self-supervised deep image denoising (2019), arXiv:1901.10277
  3. Krull A, Buchholz TO, Jug F, Noise2Void – Learning denoising from single noisy images (2018), arXiv:1811.10980v2
  4. Prakash M, Lalit M, Tomancak P, Krull A, Jug F, Fully unsupervised probabilistic Noise2Void (2019), arXiv:1911.12291v1
  5. Weigert M, Schmidt U, Boothe T, Müller A, Dibrov A, Jain A, Wilhelm B, Schmidt D, Broaddus C, Culley S, Rocha-Martins M, Segovia-Miranda F, Norden C, Henriques R, Zerial M, Solimena M, Rink J, Tomancak P, Royer L, Jug F, Myers EW, Content-aware image restoration: pushing the limits of fluorescence microscopy, (2018), Nature Methods, 15(12):1090-1097, doi: 10.1038/s41592-018-0216-7.

Acknowledgement

I thank Mate Palfy for his feedback on this preLight highlight, and to Florian Jug, Alexander Krull, Mangal Prakash, and Manan Lalit for their feedback and kindly answering questions related to their preprint.

 

Posted on: 11 January 2020

doi: https://doi.org/10.1242/prelights.16203

Read preprint (No Ratings Yet)

Author's response

Mangal Prakash, Manan Lalit, Alexander Krull, Florian Jug shared

1. In your preprint you touch on the question why self-supervised methods are not competitive with models trained on image pairs. Can you expand further on your explanation?

This is an interesting question and it is important to answer with respect to the problem one intends to address. N2V, PN2V, and Bootstapped PN2V are methods to remove pixel-noises from image data. Supervised methods, such as the original CARE (5) or methods based on Noise2Noise training, can address various other image restoration problems as well. These problems include deconvolution, upsampling, superimposed text removal, or joint denoising and image projections. For all such tasks PN2V is not applicable and therefore, by definition, not competitive.
Still, if the goal is to remove pixel-noises from your images, i.e. photon shot-noise or readout-noise, we show on multiple examples that PN2V (as well as Bootstrapped PN2V) are now absolutely competitive with the best supervised methods that require ground-truth data during training.

2.  You tested the improvements you made on images acquired from spinning disc and point scanning confocal microscopy with great success. Do you expect equal success on images obtained by MRI or EM (as you showed in your previous paper, where you first introduced PN2V)?

Our methods do not care about the nature of the physical image formation process and will always learn to remove pixel-noises by extracting a content-aware prior from the signal surrounding any given pixel. Hence, N2V and PN2V will work out-of-the-box on, working on lots of data modalities, including TEM projections or SEM images. The same is not true for MRI volumina because their noise is of a very different kind. This is also true for EM tomograms, where we need Noise2Noise training in order to obtain useful image restoration models (see e.g. our cryoCARE method for more details).

3.  What are general limitations you would expect using different types of samples (eg. live vs. fixed; strong markers vs. weak), or different imaging methods (eg. MRI, EM, cryo-EM, SR, etc)?

As we described above, N2V, PN2V, and Boostrapped PN2V will do their job (removing pixel-noises) independent of the type of hardware that acquired the images one desires to denoise.

4.  Are there specific cases where your improved PN2V model is still unsuccessful and image pairs are still necessary?

Most of the original CARE applications (5) are, for example, not possible to with N2V or PN2V. The same holds true for other applications that go beyond the removal of pixel-noises. The future will tell in what ways one can continue to improve self-supervised image restoration methods. We are certainly looking forward to seeing new ideas being proposed and are clearly planning to continue working in this exciting research direction ourselves.

5.  Could you expand further on the way Gaussian Mixture Models work, for non-specialists?

Gaussian Mixture Models are a powerful tool for approximating arbitrary probability distributions. A GMM is simply the combination of multiple normal distributions, each having their own mean and standard deviation, as well as a weight that determines its influence on the mixture. It is important to note that a GMM can be used to approximate quite complex functions, in our case the measured distribution of noisy pixels intensities.
An excellent and comprehensive introduction to GMMs can be found in https://towardsdatascience.com/gaussian-mixture-models-explained-6986aaf5a95.

Have your say

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Sign up to customise the site to your preferences and to receive alerts

Register here

preLists in the bioinformatics category:

‘In preprints’ from Development 2022-2023

A list of the preprints featured in Development's 'In preprints' articles between 2022-2023

 



List by Alex Eve, Katherine Brown

9th International Symposium on the Biology of Vertebrate Sex Determination

This preList contains preprints discussed during the 9th International Symposium on the Biology of Vertebrate Sex Determination. This conference was held in Kona, Hawaii from April 17th to 21st 2023.

 



List by Martin Estermann

Alumni picks – preLights 5th Birthday

This preList contains preprints that were picked and highlighted by preLights Alumni - an initiative that was set up to mark preLights 5th birthday. More entries will follow throughout February and March 2023.

 



List by Sergio Menchero et al.

Fibroblasts

The advances in fibroblast biology preList explores the recent discoveries and preprints of the fibroblast world. Get ready to immerse yourself with this list created for fibroblasts aficionados and lovers, and beyond. Here, my goal is to include preprints of fibroblast biology, heterogeneity, fate, extracellular matrix, behavior, topography, single-cell atlases, spatial transcriptomics, and their matrix!

 



List by Osvaldo Contreras

Single Cell Biology 2020

A list of preprints mentioned at the Wellcome Genome Campus Single Cell Biology 2020 meeting.

 



List by Alex Eve

Antimicrobials: Discovery, clinical use, and development of resistance

Preprints that describe the discovery of new antimicrobials and any improvements made regarding their clinical use. Includes preprints that detail the factors affecting antimicrobial selection and the development of antimicrobial resistance.

 



List by Zhang-He Goh

Also in the cell biology category:

‘In preprints’ from Development 2022-2023

A list of the preprints featured in Development's 'In preprints' articles between 2022-2023

 



List by Alex Eve, Katherine Brown

preLights peer support – preprints of interest

This is a preprint repository to organise the preprints and preLights covered through the 'preLights peer support' initiative.

 



List by preLights peer support

The Society for Developmental Biology 82nd Annual Meeting

This preList is made up of the preprints discussed during the Society for Developmental Biology 82nd Annual Meeting that took place in Chicago in July 2023.

 



List by Joyce Yu, Katherine Brown

CSHL 87th Symposium: Stem Cells

Preprints mentioned by speakers at the #CSHLsymp23

 



List by Alex Eve

Journal of Cell Science meeting ‘Imaging Cell Dynamics’

This preList highlights the preprints discussed at the JCS meeting 'Imaging Cell Dynamics'. The meeting was held from 14 - 17 May 2023 in Lisbon, Portugal and was organised by Erika Holzbaur, Jennifer Lippincott-Schwartz, Rob Parton and Michael Way.

 



List by Helen Zenner

9th International Symposium on the Biology of Vertebrate Sex Determination

This preList contains preprints discussed during the 9th International Symposium on the Biology of Vertebrate Sex Determination. This conference was held in Kona, Hawaii from April 17th to 21st 2023.

 



List by Martin Estermann

Alumni picks – preLights 5th Birthday

This preList contains preprints that were picked and highlighted by preLights Alumni - an initiative that was set up to mark preLights 5th birthday. More entries will follow throughout February and March 2023.

 



List by Sergio Menchero et al.

CellBio 2022 – An ASCB/EMBO Meeting

This preLists features preprints that were discussed and presented during the CellBio 2022 meeting in Washington, DC in December 2022.

 



List by Nadja Hümpfer et al.

Fibroblasts

The advances in fibroblast biology preList explores the recent discoveries and preprints of the fibroblast world. Get ready to immerse yourself with this list created for fibroblasts aficionados and lovers, and beyond. Here, my goal is to include preprints of fibroblast biology, heterogeneity, fate, extracellular matrix, behavior, topography, single-cell atlases, spatial transcriptomics, and their matrix!

 



List by Osvaldo Contreras

EMBL Synthetic Morphogenesis: From Gene Circuits to Tissue Architecture (2021)

A list of preprints mentioned at the #EESmorphoG virtual meeting in 2021.

 



List by Alex Eve

FENS 2020

A collection of preprints presented during the virtual meeting of the Federation of European Neuroscience Societies (FENS) in 2020

 



List by Ana Dorrego-Rivas

Planar Cell Polarity – PCP

This preList contains preprints about the latest findings on Planar Cell Polarity (PCP) in various model organisms at the molecular, cellular and tissue levels.

 



List by Ana Dorrego-Rivas

BioMalPar XVI: Biology and Pathology of the Malaria Parasite

[under construction] Preprints presented at the (fully virtual) EMBL BioMalPar XVI, 17-18 May 2020 #emblmalaria

 



List by Dey Lab, Samantha Seah

1

Cell Polarity

Recent research from the field of cell polarity is summarized in this list of preprints. It comprises of studies focusing on various forms of cell polarity ranging from epithelial polarity, planar cell polarity to front-to-rear polarity.

 



List by Yamini Ravichandran

TAGC 2020

Preprints recently presented at the virtual Allied Genetics Conference, April 22-26, 2020. #TAGC20

 



List by Maiko Kitaoka et al.

3D Gastruloids

A curated list of preprints related to Gastruloids (in vitro models of early development obtained by 3D aggregation of embryonic cells). Updated until July 2021.

 



List by Paul Gerald L. Sanchez and Stefano Vianello

ECFG15 – Fungal biology

Preprints presented at 15th European Conference on Fungal Genetics 17-20 February 2020 Rome

 



List by Hiral Shah

ASCB EMBO Annual Meeting 2019

A collection of preprints presented at the 2019 ASCB EMBO Meeting in Washington, DC (December 7-11)

 



List by Madhuja Samaddar et al.

EMBL Seeing is Believing – Imaging the Molecular Processes of Life

Preprints discussed at the 2019 edition of Seeing is Believing, at EMBL Heidelberg from the 9th-12th October 2019

 



List by Dey Lab

Autophagy

Preprints on autophagy and lysosomal degradation and its role in neurodegeneration and disease. Includes molecular mechanisms, upstream signalling and regulation as well as studies on pharmaceutical interventions to upregulate the process.

 



List by Sandra Malmgren Hill

Lung Disease and Regeneration

This preprint list compiles highlights from the field of lung biology.

 



List by Rob Hynds

Cellular metabolism

A curated list of preprints related to cellular metabolism at Biorxiv by Pablo Ranea Robles from the Prelights community. Special interest on lipid metabolism, peroxisomes and mitochondria.

 



List by Pablo Ranea Robles

BSCB/BSDB Annual Meeting 2019

Preprints presented at the BSCB/BSDB Annual Meeting 2019

 



List by Dey Lab

MitoList

This list of preprints is focused on work expanding our knowledge on mitochondria in any organism, tissue or cell type, from the normal biology to the pathology.

 



List by Sandra Franco Iborra

Biophysical Society Annual Meeting 2019

Few of the preprints that were discussed in the recent BPS annual meeting at Baltimore, USA

 



List by Joseph Jose Thottacherry

ASCB/EMBO Annual Meeting 2018

This list relates to preprints that were discussed at the recent ASCB conference.

 



List by Dey Lab, Amanda Haage
Close