Image-based patient-specific modelling of hemodynamics are gaining increased popularity as a diagnosis and outcome prediction solution for a variety of cardiovascular diseases. While their potential to improve diagnostic capabilities and thereby clinical outcome is widely recognized, these methods require considerable computational resources since they are mostly based on conventional numerical methods such as computational fluid dynamics (CFD). As an alternative to the numerical methods, we propose a machine learning (ML) based approach to calculate patient-specific hemodynamic parameters. Compared to CFD based methods, our approach holds the benefit of being able to calculate a patient-specific hemodynamic outcome instantly with little need for computational power. In this proof-of-concept study, we present a deep artificial neural network (ANN) capable of computing hemodynamics for patients with aortic coarctation in a centerline aggregated (i.e., locally averaged) form. Considering the complex relation between vessels shape and hemodynamics on the one hand and the limited availability of suitable clinical data on the other, a sufficient accuracy of the ANN may however not be achieved with available data only. Another key aspect of this study is therefore the successful augmentation of available clinical data. Using a statistical shape model, additional training data was generated which substantially increased the ANN's accuracy, showcasing the ability of ML based methods to perform in-silico modelling tasks previously requiring resource intensive CFD simulations.

Detecting malignant pulmonary nodules at an early stage can allow medical interventions which may increase the survival rate of lung cancer patients. Using computer vision techniques to detect nodules can improve the sensitivity and the speed of interpreting chest CT for lung cancer screening. Many studies have used CNNs to detect nodule candidates. Though such approaches have been shown to outperform the conventional image processing based methods regarding the detection accuracy, CNNs are also known to be limited to generalize on under-represented samples in the training set and prone to imperceptible noise perturbations. Such limitations can not be easily addressed by scaling up the dataset or the models. In this work, we propose to add adversarial synthetic nodules and adversarial attack samples to the training data to improve the generalization and the robustness of the lung nodule detection systems. To generate hard examples of nodules from a differentiable nodule synthesizer, we use projected gradient descent (PGD) to search the latent code within a bounded neighbourhood that would generate nodules to decrease the detector response. To make the network more robust to unanticipated noise perturbations, we use PGD to search for noise patterns that can trigger the network to give over-confident mistakes. By evaluating on two different benchmark datasets containing consensus annotations from three radiologists, we show that the proposed techniques can improve the detection performance on real CT data. To understand the limitations of both the conventional networks and the proposed augmented networks, we also perform stress-tests on the false positive reduction networks by feeding different types of artificially produced patches. We show that the augmented networks are more robust to both under-represented nodules as well as resistant to noise perturbations.

Modeling of hemodynamics and artificial intelligence have great potential to support clinical diagnosis and decision making. While hemodynamics modeling is extremely time- and resource-consuming, machine learning (ML) typically requires large training data that are often unavailable. The aim of this study was to develop and evaluate a novel methodology generating a large database of synthetic cases with characteristics similar to clinical cohorts of patients with coarctation of the aorta (CoA), a congenital heart disease associated with abnormal hemodynamics. Synthetic data allows use of ML approaches to investigate aortic morphometric pathology and its influence on hemodynamics. Magnetic resonance imaging data (154 patients as well as of healthy subjects) of aortic shape and flow were used to statistically characterize the clinical cohort. The methodology generating the synthetic cohort combined statistical shape modeling of aortic morphometry and aorta inlet flow fields and numerical flow simulations. Hierarchical clustering and non-linear regression analysis were successfully used to investigate the relationship between morphometry and hemodynamics and to demonstrate credibility of the synthetic cohort by comparison with a clinical cohort. A database of 2652 synthetic cases with realistic shape and hemodynamic properties was generated. Three shape clusters and respective differences in hemodynamics were identified. The novel model predicts the CoA pressure gradient with a root mean square error of 4.6 mmHg. In conclusion, synthetic data for anatomy and hemodynamics is a suitable means to address the lack of large datasets and provide a powerful basis for ML to gain new insights into cardiovascular diseases.

We propose a novel Computer-Aided Detection (CAD) system for pulmonary nodules using multi-view convolutional networks (ConvNets), for which discriminative features are automatically learnt from the training data. The network is fed with nodule candidates obtained by combining three candidate detectors specifically designed for solid, subsolid, and large nodules. For each candidate, a set of 2-D patches from differently oriented planes is extracted. The proposed architecture comprises multiple streams of 2-D ConvNets, for which the outputs are combined using a dedicated fusion method to get the final classification. Data augmentation and dropout are applied to avoid overfitting. On 888 scans of the publicly available LIDC-IDRI dataset, our method reaches high detection sensitivities of 85.4% and 90.1% at 1 and 4 false positives per scan, respectively. An additional evaluation on independent datasets from the ANODE09 challenge and DLCST is performed. We showed that the proposed multi-view ConvNets is highly suited to be used for false positive reduction of a CAD system.

In the near future, cameras will be used everywhere as flexible sensors for numerous applications. For mobility and privacy reasons, the required image processing should be local on embedded computer platforms with performance requirements and energy constraints. Dedicated acceleration of Convolutional Neural Networks (CNN) can achieve these targets with enough flexibility to perform multiple vision tasks. A challenging problem for the design of efficient accelerators is the limited amount of external memory bandwidth. We show that the effects of the memory bottleneck can be reduced by a flexible memory hierarchy that supports the complex data access patterns in CNN workload. The efficiency of the on-chip memories is maximized by our scheduler that uses tiling to optimize for data locality. Our design flow ensures that on-chip memory size is minimized, which reduces area and energy usage. The design flow is evaluated by a High Level Synthesis implementation on a Virtex 6 FPGA board. Compared to accelerators with standard scratchpad memories the FPGA resources can be reduced up to 13× while maintaining the same performance. Alternatively, when the same amount of FPGA resources is used our accelerators are up to 11× faster