Kerstin Hammernik

Learning a Variational Network for Reconstruction of Accelerated MRI Data

To allow fast and high‐quality reconstruction of clinical accelerated multi‐coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning.

A multi-center milestone study of clinical vertebral CT segmentation☆

A multiple center milestone study of clinical vertebra segmentation is presented in this paper. Vertebra segmentation is a fundamental step for spinal image analysis and intervention. The first half of the study was conducted in the spine segmentation challenge in 2014 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Computational Spine Imaging (CSI 2014). The objective was to evaluate the performance of several state-of-the-art vertebra segmentation algorithms on computed tomography (CT) scans using ten training and five testing dataset, all healthy cases; the second half of the study was conducted after the challenge, where additional 5 abnormal cases are used for testing to evaluate the performance under abnormal cases. Dice coefficients and absolute surface distances were used as evaluation metrics. Segmentation of each vertebra as a single geometric unit, as well as separate segmentation of vertebra substructures, was evaluated. Five teams participated in the comparative study. The top performers in the study achieved Dice coefficient of 0.93 in the upper thoracic, 0.95 in the lower thoracic and 0.96 in the lumbar spine for healthy cases, and 0.88 in the upper thoracic, 0.89 in the lower thoracic and 0.92 in the lumbar spine for osteoporotic and fractured cases. The strengths and weaknesses of each method as well as future suggestion for improvement are discussed. This is the first multi-center comparative study for vertebra segmentation methods, which will provide an up-to-date performance milestone for the fast growing spinal image analysis and intervention.

Learning joint demosaicing and denoising based on sequential energy minimization

Demosaicing is an important first step for color image acquisition. For practical reasons, demosaicing algorithms have to be both efficient and yield high quality results in the presence of noise. The demosaicing problem poses several challenges, e.g. zippering and false color artifacts as well as edge blur. In this work, we introduce a novel learning based method that can overcome these challenges. We formulate demosaicing as an image restoration problem and propose to learn efficient regularization inspired by a variational energy minimization framework that can be trained for different sensor layouts. Our algorithm performs joint demosaicing and denoising in close relation to the real physical mosaicing process on a camera sensor. This is achieved by learning a sequence of energy minimization problems composed of a set of RGB filters and corresponding activation functions. We evaluate our algorithm on the Microsoft Demosaicing data set in terms of peak signal to noise ratio (PSNR) and structured similarity index (SSIM). Our algorithm is highly efficient both in image quality and run time. We achieve an improvement of up to 2.6 dB over recent state-of-the-art algorithms.

Vertebrae Segmentation in 3D CT Images based on a Variational Framework

Automatic segmentation of 3D vertebrae is a challenging task in medical imaging. In this paper, we introduce a total variation (TV) based framework that incorporates an a priori model, i.e., a vertebral mean shape, image intensity and edge information. The algorithm was evaluated using leave-one-out cross validation on a data set containing ten computed tomography scans and ground truth segmentations provided for the CSI MICCAI 2014 spine and vertebrae segmentation challenge. We achieve promising results in terms of the Dice Similarity Coefficient (DSC) of \(0.93 \pm 0.04\) averaged over the whole data set.

A Deep Learning Architecture for Limited-Angle Computed Tomography Reconstruction

Limited-angle computed tomography suffers from missing data in the projection domain, which results in intensity inhomogeneities and streaking artifacts in the image domain. We address both challenges by a two-step deep learning architecture: First, we learn compensation weights that account for the missing data in the projection domain and correct for intensity changes. Second, we formulate an image restoration problem as a variational network to eliminate coherent streaking artifacts. We perform our experiments on realistic data and we achieve superior results for destreaking compared to state-of-the-art non-linear filtering methods in literature. We show that our approach eliminates the need for manual tuning and enables joint optimization of both correction schemes.

Variational Networks: Connecting Variational Methods and Deep Learning

In this paper, we introduce variational networks (VNs) for image reconstruction. VNs are fully learned models based on the framework of incremental proximal gradient methods. They provide a natural transition between classical variational methods and state-of-the-art residual neural networks. Due to their incremental nature, VNs are very efficient, but only approximately minimize the underlying variational model. Surprisingly, in our numerical experiments on image reconstruction problems it turns out that giving up exact minimization leads to a consistent performance increase, in particular in the case of convex models.

Variational Photoacoustic Image Reconstruction with Spatially Resolved Projection Data

In this work, we explore different reconstruction algorithms for photoacoustic image reconstruction of spatially resolved projection data. While the commonly used back-projected reconstruction is efficient and fast to compute, it cannot deal with noise that arises during measurements. Therefore, we formulate photoacoustic image reconstruction in a variational framework where we add prior knowledge in terms of Total Generalized Variation. Using this prior knowledge, we can reduce measurement noise and improve the visibility of vessel structures.

Assessment of the generalization of learned image reconstruction and the potential for transfer learning

Although deep learning has shown great promise for MR image reconstruction, an open question regarding the success of this approach is the robustness in the case of deviations between training and test data. The goal of this study is to assess the influence of image contrast, SNR, and image content on the generalization of learned image reconstruction, and to demonstrate the potential for transfer learning.

Trainable Regularization for Multi-frame Superresolution

In this paper, we present a novel method for multi-frame superresolution (SR). Our main goal is to improve the spatial resolution of a multi-line scan camera for an industrial inspection task. High resolution output images are reconstructed using our proposed SR algorithm for multi-channel data, which is based on the trainable reaction-diffusion model. As this is a supervised learning approach, we simulate ground truth data for a real imaging scenario. We show that learning a regularizer for the SR problem improves the reconstruction results compared to an iterative reconstruction algorithm using TV or TGV regularization. We test the learned regularizer, trained on simulated data, on images acquired with the real camera setup and achieve excellent results.

Automatic Intervertebral Disc Localization and Segmentation in 3D MR Images Based on Regression Forests and Active Contours

We introduce a fully automatic localization and segmentation pipeline for three-dimensional (3D) intervertebral discs (IVDs), consisting of a regression-based prediction of vertebral bodies and IVD positions as well as a 3D geodesic active contour segmentation delineating the IVDs. The approach was evaluated on the data set of the challenge in conjunction with the 3rd MICCAI Workshop & Challenge on Computational Methods and Clinical Applications for Spine Imaging - MICCAI–CSI2015, that consists of 15 magnetic resonance images of the lumbar spine with given ground truth segmentations. Based on a localization accuracy of \(3.9 \pm 1.6\) mm, we achieve segmentation results in terms of the Dice similarity coefficient of \(89.1 \pm 2.9\,\%\) averaged over the whole data set.