Model-Based and Data-Driven Strategies in Medical Image Computing

@article{Rueckert2020ModelBasedAD,
  title={Model-Based and Data-Driven Strategies in Medical Image Computing},
  author={Daniel Rueckert and Julia Anne Schnabel},
  journal={Proceedings of the IEEE},
  year={2020},
  volume={108},
  pages={110-124}
}
Model-based approaches for image reconstruction, analysis, and interpretation have made significant progress over the past decades. Many of these approaches are based on either mathematical, physical, or biological models. A challenge for these approaches is the modeling of the underlying processes (e.g., the physics of image acquisition or the patho-physiology of a disease) with appropriate levels of detail and realism. With the availability of large amounts of imaging data and machine… Expand
Applications of artificial intelligence in cardiovascular imaging
TLDR
In cardiovascular imaging, AI algorithms are often purely data-driven but can be improved when associated with biophysical models of the heart, which enables the integration of pre-existing knowledge of human anatomy and physiology. Expand
Deep learning for fast MR imaging: A review for learning reconstruction from incomplete k-space data
TLDR
This survey aims to review deep learning based MR image reconstruction works from 2016- June 2020 and will discuss merits, limitations and challenges associated with such methods, as a starting point for researchers interested in contributing to this field. Expand
A Mixed Focal Loss Function for Handling Class Imbalanced Medical Image Segmentation
TLDR
The proposed Mixed Focal loss function is robust to significant class imbalance, and is associated with a better recall-precision balance, significantly outperforming the other loss functions in both binary and multi-class image segmentation. Expand
Designing deep learning studies in cancer diagnostics
TLDR
To reduce the risk of biased performance estimation of deep learning systems, this Perspective advocates evaluation in external cohorts and strongly advises that a primary analysis is predefined in a standardized protocol preferentially stored in an online repository. Expand
A Geometry-Informed Deep Learning Framework for Ultra-Sparse 3D Tomographic Image Reconstruction
TLDR
It is demonstrated that the seamless inclusion of known priors is essential to enhance the performance of 3D volumetric computed tomography imaging with ultra-sparse sampling and opens new avenues for data-driven biomedical imaging. Expand
Learning a Model-Driven Variational Network for Deformable Image Registration
TLDR
VR-Net is proposed, a novel cascaded variational network for unsupervised deformable image registration that outperforms state-of-the-art deep learning methods on registration accuracy, while maintains the fast inference speed of deep learning and the data-efficiency of variational model. Expand
Impact of hybrid supervision approaches on the performance of artificial intelligence for the classification of chest radiographs
TLDR
Extra supervision using a balance of annotated normal and abnormal cases applied to a weakly supervised model can minimize the number of false negative cases when classifying two-view chest radiographs. Expand
Learning Diffeomorphic and Modality-invariant Registration using B-splines
TLDR
This paper proposes to use a B-spline FFD parameterisation of Stationary Velocity Field (SVF) to in DL registration in order to achieve smooth diffeomorphic deformation while being computationally-efficient. Expand
Time-Varying Convex Optimization: Time-Structured Algorithms and Applications
TLDR
A broad class of state-of-the-art algorithms for time-varying optimization is reviewed, with an eye to performing both algorithmic development and performance analysis, to exemplify wide engineering relevance of analytical tools and pertinent theoretical foundations. Expand
Practical computer vision application to detect hip fractures on pelvic X-rays: a bi-institutional study
TLDR
A high-performing computer vision algorithm to detect hip fractures on PXR is refined and validated and a web application facilitates algorithm use at the bedside, but the benefit of using the algorithm to supplement decision-making is likely institution dependent. Expand
...
1
2
...

References

SHOWING 1-10 OF 126 REFERENCES
Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation
TLDR
This work proposes a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end and demonstrates how the learnt deep models of 3-D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies. Expand
Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation
TLDR
This study trained a CNN on legacy MR images of brain and evaluated the performance of the domain-adapted network on the same task with images from a different domain, substantially outperforming a similar network trained on the the same set of examples from scratch. Expand
A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction
TLDR
A framework for reconstructing dynamic sequences of 2-D cardiac magnetic resonance images from undersampled data using a deep cascade of convolutional neural networks (CNNs) to accelerate the data acquisition process is proposed and it is demonstrated that CNNs can learn spatio-temporal correlations efficiently by combining convolution and data sharing approaches. Expand
Clinically applicable deep learning for diagnosis and referral in retinal disease
TLDR
A novel deep learning architecture performs device-independent tissue segmentation of clinical 3D retinal images followed by separate diagnostic classification that meets or exceeds human expert clinical diagnoses of retinal disease. Expand
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks
TLDR
An automated analysis method based on a fully convolutional network achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Deformable models in medical image analysis: a survey
TLDR
The rapidly expanding body of work on the development and application of deformable models to problems of fundamental importance in medical image analysis, including segmentation, shape representation, matching and motion tracking is reviewed. Expand
Image reconstruction by domain-transform manifold learning
TLDR
A unified framework for image reconstruction—automated transform by manifold approximation (AUTOMAP)—which recasts image reconstruction as a data-driven supervised learning task that allows a mapping between the sensor and the image domain to emerge from an appropriate corpus of training data is presented. Expand
An Unsupervised Learning Model for Deformable Medical Image Registration
TLDR
The proposed method uses a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field, and demonstrates registration accuracy comparable to state-of-the-art 3D image registration, while operating orders of magnitude faster in practice. Expand
Deep learning cardiac motion analysis for human survival prediction
TLDR
A fully convolutional neural network is used to create time-resolved three-dimensional dense segmentations of heart images that can efficiently predict human survival. Expand
...
1
2
3
4
5
...