Utilizing Uncertainty Estimation in Deep Learning Segmentation of Fluorescence Microscopy Images with Missing Markers

@article{Gomariz2021UtilizingUE,
  title={Utilizing Uncertainty Estimation in Deep Learning Segmentation of Fluorescence Microscopy Images with Missing Markers},
  author={Alvaro Gomariz and Raphael Egli and Tiziano Portenier and C{\'e}sar Nombela-Arrieta and Orcun Goksel},
  journal={2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)},
  year={2021},
  pages={371-374}
}
Fluorescence microscopy images contain several channels, each indicating a marker staining the sample. Since many different marker combinations are utilized in practice, it has been challenging to apply deep learning based segmentation models, which expect a predefined channel combination for all training samples as well as at inference for future application. Recent work circumvents this problem using a modality attention approach to be effective across any possible marker combination. However… 

Figures from this paper

Probabilistic spatial analysis in quantitative microscopy with uncertainty-aware cell detection using deep Bayesian regression

This work proposes a framework that can operate on large microscopy images and output probabilistic predictions by integrating deep Bayesian learning for the regression of uncertainty-aware density maps and learning a mapping from prediction proposals to a Probabilistic space that accurately represents the chances of a successful prediction.

References

SHOWING 1-10 OF 11 REFERENCES

Modality Attention and Sampling Enables Deep Learning with Heterogeneous Marker Combinations in Fluorescence Microscopy

This work substantially ameliorates the use of deep learning in fluorescence microscopy analysis, and can also be utilized in other fields with incomplete data acquisitions and missing modalities.

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

A Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty is presented, which makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks.

U-Net: deep learning for cell counting, detection, and morphometry

An ImageJ plugin is presented that enables non-machine-learning experts to analyze their data with U-Net on either a local computer or a remote server/cloud service.

Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference

This work presents an efficient Bayesian CNN, offering better robustness to over-fitting on small data than traditional approaches, and approximate the model's intractable posterior with Bernoulli variational distributions.

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

A new theoretical framework is developed casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes, which mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy.

Automated Muscle Segmentation from Clinical CT Using Bayesian U-Net for Personalized Musculoskeletal Modeling

We propose a method for automatic segmentation of individual muscles from a clinical CT. The method uses Bayesian convolutional neural networks with the U-Net architecture, using Monte Carlo dropout

Deep Ensembles: A Loss Landscape Perspective

Developing the concept of the diversity--accuracy plane, it is shown that the decorrelation power of random initializations is unmatched by popular subspace sampling methods and the experimental results validate the hypothesis that deep ensembles work well under dataset shift.

Adam: A Method for Stochastic Optimization

This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

Dropout: a simple way to prevent neural networks from overfitting

It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.

Imaging and spatial analysis of hematopoietic stem cell niches

Hematopoietic stem cells (HSCs) have been long proposed to reside in defined anatomical locations within bone marrow (BM) tissues in direct contact or close proximity to nurturing cell types. Imaging