Jonas Adler

Jonas Adler
  • PhD
  • Senior Research Scientist at Google DeepMind

About

32
Publications
22,593
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
38,674
Citations
Introduction
Working in the intersection between machine learning and the natural sciences.
Current institution
Google DeepMind
Current position
  • Senior Research Scientist
Additional affiliations
June 2019 - present
DeepMind
Position
  • Senior Researcher
December 2013 - June 2019
Elekta
Position
  • Researcher
Education
April 2015 - October 2019
KTH Royal Institute of Technology
Field of study
  • Applied Mathematics
August 2009 - December 2013
KTH Royal Institute of Technology
Field of study
  • Engineering Physics

Publications

Publications (32)
Article
Full-text available
We propose a partially learned approach for the solution of ill-posed inverse problems with not necessarily linear forward operators. The method builds on ideas from classical regularisation theory and recent advances in deep learning to perform learning while making use of prior information about the inverse problem encoded in the forward operator...
Article
Full-text available
We propose a Learned Primal-Dual algorithm for tomographic reconstruction. The algorithm includes the (possibly non-linear) forward operator in a deep neural network inspired by unrolled proximal primal-dual optimization methods, but where the proximal operators have been replaced with convolutional neural networks. The algorithm is trained end-to-...
Preprint
Full-text available
Wasserstein Generative Adversarial Networks (WGANs) can be used to generate realistic samples from complicated image distributions. The Wasserstein metric used in WGANs is based on a notion of distance between individual images, which induces a notion of distance between probability distributions of images. So far the community has considered l2 as...
Preprint
Full-text available
Characterizing statistical properties of solutions of inverse problems is essential for decision making. Bayesian inversion offers a tractable framework for this purpose, but current approaches are computationally unfeasible for most realistic imaging applications in the clinic. We introduce two novel deep learning based methods for solving large-s...
Article
Full-text available
Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1, 2, 3–4, the structures of around 100,000 unique proteins have been determined⁵, but this represents a small fraction of the billions of known protein sequences6,7. Structural cover...
Article
Full-text available
The introduction of AlphaFold 2¹ has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2, 3, 4, 5–6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure...
Article
Full-text available
We describe the operation and improvement of AlphaFold*, the system that was entered by the team AlphaFold2 to the “human” category in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The AlphaFold system entered in CASP14 is entirely different to the one entered in CASP13. It used a novel end-to-end deep neural network traine...
Article
Full-text available
The paper considers the problem of performing a post-processing task defined on a model parameter that is only observed indirectly through noisy data in an ill-posed inverse problem. A key aspect is to formalize the steps of reconstruction and post-processing as appropriate estimators (non-randomized decision rules) in statistical estimation proble...
Article
Full-text available
Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17% of the total residues in human protein sequences are covered by an experimentally-determined structure1. Here we dramatical...
Preprint
Full-text available
Cryo-electron microscopy (cryo-EM) has revolutionized experimental protein structure determination. Despite advances in high resolution reconstruction, a majority of cryo-EM experiments provide either a single state of the studied macromolecule, or a relatively small number of its conformations. This reduces the effectiveness of the technique for p...
Preprint
Full-text available
We propose several deep-learning accelerated optimization solvers with convergence guarantees. We use ideas from the analysis of accelerated forward-backward schemes like FISTA, but instead of the classical approach of proving convergence for a choice of parameters, such as a step-size, we show convergence whenever the update is chosen in a specifi...
Article
Full-text available
Three-dimensional reconstruction of the electron-scattering potential of biological macromolecules from electron cryo-microscopy (cryo-EM) projection images is an ill-posed problem. The most popular cryo-EM software solutions to date rely on a regularization approach that is based on the prior assumption that the scattering potential varies smoothl...
Preprint
Full-text available
Deep learning methods using convolutional neural networks (CNN) have been successfully applied to virtually all imaging problems, and particularly in image reconstruction tasks with ill-posed and complicated imaging models. In an attempt to put upper bounds on the capability of baseline CNNs for solving image-to-image problems we applied a widely u...
Article
Full-text available
Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times, the latter due to computationally expensive forward models. As a possibl...
Preprint
Full-text available
Three-dimensional reconstruction of the electron scattering potential of biological macromolecules from electron cryo-microscopy (cryo-EM) projection images is an ill-posed problem. The most popular cryo-EM software solutions to date rely on a regularisation approach that is based on the prior assumption that the scattering potential varies smoothl...
Preprint
Full-text available
Unpaired image-to-image translation has attracted significant interest due to the invention of CycleGAN, a method which utilizes a combination of adversarial and cycle consistency losses to avoid the need for paired data. It is known that the CycleGAN problem might admit multiple solutions, and our goal in this paper is to analyze the space of exac...
Preprint
Full-text available
Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times due to computationally expensive forward models. As a possible solution t...
Preprint
Full-text available
Over the last few years machine learning has demonstrated groundbreaking results in many areas of medical image analysis, including segmentation. A key assumption, however, is that the train- and test distributions match. We study a realistic scenario where this assumption is clearly violated, namely segmentation with missing input modalities. We d...
Presentation
Full-text available
There are occasions, perhaps due to hardware constraints, or to speed-up data acquisition, when it is helpful to be able to reconstruct a photoacoustic image from an under-sampled or incomplete data set. Here, we will show how Deep Learning can be used to improve image reconstruction in such cases. Deep Learning is a type of machine learning in whi...
Preprint
Full-text available
The paper considers the problem of performing a task defined on a model parameter that is only observed indirectly through noisy data in an ill-posed inverse problem. A key aspect is to formalize the steps of reconstruction and task as appropriate estimators (non-randomized decision rules) in statistical estimation problems. The implementation make...
Preprint
Full-text available
Digital breast tomosynthesis is rapidly replacing digital mammography as the basic x-ray technique for evaluation of the breasts. However, the sparse sampling and limited angular range gives rise to different artifacts, which manufacturers try to solve in several ways. In this study we propose an extension of the Learned Primal-Dual algorithm for d...
Preprint
Full-text available
In this work, we consider methods for solving large-scale optimization problems with a possibly nonsmooth objective function. The key idea is to first specify a class of optimization algorithms using a generic iterative scheme involving only linear operations and applications of proximal operators. This scheme contains many modern primal-dual first...
Article
Energy-dispersive X-ray spectroscopy (EDS) tomography is an advanced technique to characterize compositional information for nanostructures in three dimensions (3D). However, the application is hindered by the poor image quality caused by the low signal-to-noise ratios and the limited number of tilts, which are fundamentally limited by the insuffic...
Article
Full-text available
Recent advances in deep learning for tomographic reconstructions have shown great potential to create accurate and high quality images with a considerable speed-up. In this work we present a deep neural network that is specifically designed to provide high resolution 3D images from restricted photoacoustic measurements. The network is designed to r...
Article
Full-text available
We propose using the Wasserstein loss for training in inverse problems. In particular, we consider a learned primal-dual reconstruction scheme for ill-posed inverse problems using the Wasserstein distance as loss function in the learning. This is motivated by miss-alignments in training data, which when using standard mean squared error loss could...
Preprint
Recent advances in deep learning for tomographic reconstructions have shown great potential to create accurate and high quality images with a considerable speed-up. In this work we present a deep neural network that is specifically designed to provide high resolution 3D images from restricted photoacoustic measurements. The network is designed to r...
Code
ODL Operator Discretization Library (ODL) is a Python library for fast prototyping focusing on (but not restricted to) inverse problems. ODL is being developed at KTH Royal Institute of Technology, Stockholm, and Centrum Wiskunde & Informatica (CWI), Amsterdam. The main intent of ODL is to enable mathematicians and applied scientists to use differe...
Chapter
Full-text available
CBCT images suffer from acute shading artifacts primarily due to scatter. Numerous image-domain correction algorithms have been proposed in the literature that use patient-specific planning CT images to estimate shading contributions in CBCT images. However, in the context of radiosurgery applications such as gamma knife, planning images are often...

Network

Cited By