Katharina Breininger

Some Investigations on Robustness of Deep Learning in Limited Angle Tomography

In computed tomography, image reconstruction from an insufficient angular range of projection data is called limited angle tomography. Due to missing data, reconstructed images suffer from artifacts, which cause boundary distortion, edge blurring, and intensity biases. Recently, deep learning methods have been applied very successfully to this problem in simulation studies. However, the robustness of neural networks for clinical applications is still a concern. It is reported that most neural networks are vulnerable to adversarial examples. In this paper, we aim to investigate whether some perturbations or noise will mislead a neural network to fail to detect an existing lesion. Our experiments demonstrate that the trained neural network, specifically the U-Net, is sensitive to Poisson noise. While the observed images appear artifact-free, anatomical structures may be located at wrong positions, e.g. the skin shifted by up to 1 cm. This kind of behavior can be reduced by retraining on data with simulated Poisson noise. However, we demonstrate that the retrained U-Net model is still susceptible to adversarial examples. We conclude the paper with suggestions towards robust deep-learning-based reconstruction.

Intraoperative stent segmentation in X-ray fluoroscopy for endovascular aortic repair

PurposeFusion of preoperative data with intraoperative X-ray images has proven the potential to reduce radiation exposure and contrast agent, especially for complex endovascular aortic repair (EVAR). Due to patient movement and introduced devices that deform the vasculature, the fusion can become inaccurate. This is usually detected by comparing the preoperative information with the contrasted vessel. To avoid repeated use of iodine, comparison with an implanted stent can be used to adjust the fusion. However, detecting the stent automatically without the use of contrast is challenging as only thin stent wires are visible.MethodWe propose a fast, learning-based method to segment aortic stents in single uncontrasted X-ray images. To this end, we employ a fully convolutional network with residual units. Additionally, we investigate whether incorporation of prior knowledge improves the segmentation.ResultsWe use 36 X-ray images acquired during EVAR for training and evaluate the segmentation on 27 additional images. We achieve a Dice coefficient of 0.933 (AUC 0.996) when using X-ray alone, and 0.918 (AUC 0.993) and 0.888 (AUC 0.99) when adding the preoperative model, and information about the expected wire width, respectively.ConclusionThe proposed method is fully automatic, fast and segments aortic stent grafts in fluoroscopic images with high accuracy. The quality and performance of the segmentation will allow for an intraoperative comparison with the preoperative information to assess the accuracy of the fusion.

Multiple Device Segmentation for Fluoroscopic Imaging Using Multi-task Learning

For endovascular aortic repair (EVAR), integrating preoperative information of the aortic anatomy with intraoperative fluoroscopy can aid in reducing radiation exposure, contrast agent and procedure time. However, the quality of this fusion may deteriorate over the course of the intervention due to patient movement or deformation of the vasculature caused by interventional tools. Automatically detecting the instruments present in the X-ray image can help to assess the degree of deterioration, trigger automatic re-registration or aid in automatic workflow phase detection and process modeling. In this work, we investigate a flexible approach to segment different devices based on fully convolutional neural networks using multi-task learning. We evaluate the proposed approach on a set of 38 X-ray images acquired during EVAR interventions by targeting the segmentation of aortic stents, stiff guidewires and pigtail catheters. We compare the results to the performance of single-task networks. We manage to keep similar performance compared to single-task networks with Dice coefficients between 0.95 and 0.80 depending on the device, while speeding up computation by a factor of two.

Abstract: Efficient Epipolar Consistency

Epipolar consistency (EC) is one of the simplest consistency conditions in cone-beam computed tomgraphy. It describes redundant line integrals between any two projection images. Its simplicity is an advantage for practical implementation and applications for calibration and motion correction in FDCT.

Deep Learning Fundamentals

Deep learning has received a lot of attention in the machine learning community. Successful applications from speech recognition or computer vision are already part of our daily life. Much effort has been devoted to transferring this success to medical image computing.

Rewiring of neuronal networks during synaptic silencing

Analyzing the connectivity of neuronal networks, based on functional brain imaging data, has yielded new insight into brain circuitry, bringing functional and effective networks into the focus of interest for understanding complex neurological and psychiatric disorders. However, the analysis of network changes, based on the activity of individual neurons, is hindered by the lack of suitable meaningful and reproducible methodologies. Here, we used calcium imaging, statistical spike time analysis and a powerful classification model to reconstruct effective networks of primary rat hippocampal neurons in vitro. This method enables the calculation of network parameters, such as propagation probability, path length, and clustering behavior through the measurement of synaptic activity at the single-cell level, thus providing a fuller understanding of how changes at single synapses translate to an entire population of neurons. We demonstrate that our methodology can detect the known effects of drug-induced neuronal inactivity and can be used to investigate the extensive rewiring processes affecting population-wide connectivity patterns after periods of induced neuronal inactivity.