Precision Learning: Towards Use of Known Operators in Neural Networks

Maier, Andreas; Schebesch, Frank; Syben, Christopher; Würfl, Tobias; Steidl, Stefan; Choi, Jang-Hwan; Fahrig, Rebecca

doi:10.1109/icpr.2018.8545553

Cited by 31 publications

(33 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also other physical processes have been investigated using deep learning. In [60] a material decomposition using deep learning embedding prior physical operators using precision learning is proposed. Also physically less plausible interrelations are attempted.…”

Section: Physical Simulationmentioning

confidence: 99%

A gentle introduction to deep learning in medical image processing

Maier

Syben

Lasser

et al. 2019

Zeitschrift für Medizinische Physik

Self Cite

381

201

View full text Add to dashboard Cite

This paper tries to give a gentle introduction to deep learning in medical image processing, proceeding from theoretical foundations to applications. We first discuss general reasons for the popularity of deep learning, including several major breakthroughs in computer science. Next, we start reviewing the fundamental basics of the perceptron and neural networks, along with some fundamental theory that is often omitted. Doing so allows us to understand the reasons for the rise of deep learning in many application domains. Obviously medical image processing is one of these areas which has been largely affected by this rapid progress, in particular in image detection and recognition, image segmentation, image registration, and computer-aided diagnosis. There are also recent trends in physical simulation, modelling, and reconstruction that have led to astonishing results. Yet, some of these approaches neglect prior knowledge and hence bear the risk of producing implausible results. These apparent weaknesses highlight current limitations of deep learning. However, we also briefly discuss promising approaches that might be able to resolve these problems in the future.

show abstract

Section: Physical Simulationmentioning

confidence: 99%

A gentle introduction to deep learning in medical image processing

Maier

Syben

Lasser

et al. 2019

Zeitschrift für Medizinische Physik

Self Cite

381

201

View full text Add to dashboard Cite

show abstract

“…As the method allows considering arbitrary orbital angulations of the x‐ray source, tracking of the dose administered over the course of a procedure is possible, therefore allowing for an advanced monitoring of distribution of cumulative dose deposited in the patients skin. Furthermore, implementation of the RC simulation as a known operator in the neural network is conceivable . To increase the overall performance of the dose regression, various existing strategies could be tested.…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, implementation of the RC simulation as a known operator in the neural network is conceivable. 43 To increase the overall performance of the dose regression, various existing strategies could be tested. On the one hand, the spatial connectivity between different slices of the same anatomic site can be established by using 3D convolutions or a conditional random field.…”

Section: Discussionmentioning

confidence: 99%

Physics‐driven learning of x‐ray skin dose distribution in interventional procedures

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose Radiation doses accumulated during very complicated image‐guided x‐ray procedures have the potential to cause stochastic, but also deterministic effects, such as skin rashes or even hair loss. To monitor and reduce radiation‐related risks to patients’ skin, x‐ray imaging devices are equipped with online air kerma monitoring components. Traditionally, such measurements have been used to estimate skin entrance dose by (a) estimating air kerma at the interventional reference point (IRP), (b) forward projecting the dose distribution, and (c) considering a backscatter factor among other correction factors. Unfortunately, the complicated interaction between incident x‐ray photons, secondary electrons, and skin tissue cannot be properly accounted for by assuming a linear relationship between forward projected air kerma and a backscatter factor. Gold standard skin dose models are therefore determined using Monte Carlo (MC) techniques. However, MC simulations are computationally complex in general and possible acceleration mainly depends on the employed hardware and variance reduction techniques. To obtain reliable and fast dose estimates, we propose to combine MC‐based simulations with learning‐based methods. Methods The basic idea of our method is to approximate the radiation physics to calculate a first‐order exposure estimate quickly. This initial estimate is then refined using prior knowledge derived from MC simulations. To this end, the primary photon propagation inside a voxelized patient model is estimated using a less accurate but fast photon ray casting (RC) simulation based on the Beer–Lambert law. The results of the RC simulation are then fed into a convolutional neural network (CNN), which maps the propagation of primary photons to the dose deposition inside the patient model. Additionally, the patient model itself including anatomy and material properties, such as mass density and mass energy‐absorption coefficients, are fed into the CNN as well. The CNN is trained using smoothed results of MC simulations as output and RC simulations of identical imaging settings and patient models as input. Results In total, 163 MC and associated RC simulations are carried out for the head, thorax, abdomen, and pelvis in three different voxel phantoms. We used 108 or 109 primarily emitted photons sampled from a 125 kV peak voltage spectrum, respectively. Edge‐preserving smoothing (EPS) is applied to reduce (a) general stochastic uncertainties and (b) stochastic uncertainty concerning MC simulations of less primary photons. The CNN is trained using seven imaging settings of the abdomen in a single phantom. Testing its performance on the remaining datasets, the CNN is capable of estimating skin dose with an error of below 10% for the majority of test cases. Conclusion The combination of deep neural networks and MC simulation of particle physics has the potential to decrease the computational complexity of accurate skin dose estimation. The proposed approach can provide dose distributions in under one second when runni...

show abstract

“…We adopt generalized max pooling as a trainable neural network layer following the known-operator paradigm [30]. This allows for an end-to-end training given images and a loss function, such as softmax or triplet loss.…”

Section: B Deep Gmp Layermentioning

confidence: 99%

Deep Generalized Max Pooling

Christlein

Spranger

Seuret

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

Self Cite

View full text Add to dashboard Cite

Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They are used to aggregate activations of spatial locations to produce a fixed-size vector in several state-of-the-art CNNs. Global average pooling or global max pooling are commonly used for converting convolutional features of variable size images to a fix-sized embedding. However, both pooling layer types are computed spatially independent: each individual activation map is pooled and thus activations of different locations are pooled together. In contrast, we propose Deep Generalized Max Pooling that balances the contribution of all activations of a spatially coherent region by re-weighting all descriptors so that the impact of frequent and rare ones is equalized. We show that this layer is superior to both average and max pooling on the classification of Latin medieval manuscripts (CLAMM'16, CLAMM'17), as well as writer identification (Historical-WI'17).

show abstract

Precision Learning: Towards Use of Known Operators in Neural Networks

Cited by 31 publications

References 20 publications

A gentle introduction to deep learning in medical image processing

A gentle introduction to deep learning in medical image processing

Physics‐driven learning of x‐ray skin dose distribution in interventional procedures

Deep Generalized Max Pooling

Contact Info

Product

Resources

About