There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

https://www.zora.uzh.ch/id/eprint/146170/1/1-s2.0-S1078588416301782-main.pdf

Editor's Choice - Management of Descending Thoracic Aorta Diseases: Clinical Practice Guidelines of the European Society for Vascular Surgery (ESVS)

One of the most promising areas of health innovation is the application of artificial intelligence (AI), primarily in medical imaging. This article provides basic definitions of terms such as “machine/deep learning” and analyses the integration of AI into radiology. Publications on AI have drastically increased from about 100–150 per year in 2007–2008 to 700–800 per year in 2016–2017. Magnetic resonance imaging and computed tomography collectively account for more than 50% of current articles. Neuroradiology appears in about one-third of the papers, followed by musculoskeletal, cardiovascular, breast, urogenital, lung/thorax, and abdomen, each representing 6–9% of articles. With an irreversible increase in the amount of data and the possibility to use AI to identify findings either detectable or not by the human eye, radiology is now moving from a subjective perceptual skill to a more objective science. Radiologists, who were on the forefront of the digital era in medicine, can guide the introduction of AI into healthcare. Yet, they will not be replaced because radiology includes communication of diagnosis, consideration of patient’s values and preferences, medical judgment, quality assurance, education, policy-making, and interventional procedures. The higher efficiency provided by AI will allow radiologists to perform more value-added tasks, becoming more visible to patients and playing a vital role in multidisciplinary clinical teams.

/pdf/artificial-intelligence-in-medical-imaging-threat-or-2fzcyw9ypc.pdf

Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine

Embodiments include a system for determining cardiovascular information for a patient. The system may include at least one computer system configured to receive patient-specific data regarding a geometry of the patient's heart, and create a three-dimensional model representing at least a portion of the patient's heart based on the patient-specific data. The at least one computer system may be further configured to create a physics-based model relating to a blood flow characteristic of the patient's heart and determine a fractional flow reserve within the patient's heart based on the three-dimensional model and the physics-based model.

Method and system for patient-specific modeling of blood flow

In recent years, powered by state-of-the-art achievements in a broad range of areas, machine learning has received considerable attention from the healthcare sector. Despite their ability to provide solutions within personalized medicine, strict regulations on the confidentiality of patient health information have in many cases hindered the adoption of deep learning-based solutions in clinical workflows. To allow for the processing of sensitive health information without disclosing the underlying data, we propose a solution based on fully homomorphic encryption (FHE). The considered encryption scheme, MORE (Matrix Operation for Randomization or Encryption), enables the computations within a neural network model to be directly performed on floating point data with a relatively small computational overhead. We consider the well-known MNIST digit recognition problem to evaluate the feasibility of the proposed method and show that performance does not decrease when deep learning is applied on MORE homomorphic data. To further evaluate the suitability of the method for healthcare applications, we first train a model on encrypted data to estimate the outputs of a whole-body circulation (WBC) hemodynamic model and then provide a solution for classifying encrypted X-ray coronary angiography medical images. The findings highlight the potential of the proposed privacy-preserving deep learning methods to outperform existing approaches by providing, within a reasonable amount of time, results equivalent to those achieved by unencrypted models. Lastly, we discuss the security implications of the encryption scheme and show that while the considered cryptosystem promotes efficiency and utility at a lower security level, it is still applicable in certain practical use cases.

/pdf/applying-deep-neural-networks-over-homomorphic-encrypted-4j57zgcfts.pdf

Applying Deep Neural Networks over Homomorphic Encrypted Medical Data.

A method and system for non-invasive hemodynamic assessment of coronary artery stenosis based on medical image data is disclosed. Patient-specific anatomical measurements of the coronary arteries are extracted from medical image data of a patient. Patient-specific boundary conditions of a computational model of coronary circulation representing the coronary arteries are calculated based on the patient-specific anatomical measurements of the coronary arteries. Blood flow and pressure in the coronary arteries are simulated using the computational model of coronary circulation and the patient-specific boundary conditions and coronary autoregulation is modeled during the simulation of blood flow and pressure in the coronary arteries. A wave-free period is identified in a simulated cardiac cycle, and an instantaneous wave-Free Ratio (iFR) value is calculated for a stenosis region based on simulated pressure values in the wave-free period.

Method and System for Non-Invasive Computation of Hemodynamic Indices for Coronary Artery Stenosis

A method and system for non-invasive hemodynamic assessment of aortic coarctation from medical image data, such as magnetic resonance imaging (MRI) data is disclosed. Patient-specific lumen anatomy of the aorta and supra-aortic arteries is estimated from medical image data of a patient, such as contrast enhanced MRI. Patient-specific aortic blood flow rates are estimated from the medical image data of the patient, such as velocity encoded phase-contrasted MRI cine images. Patient-specific inlet and outlet boundary conditions for a computational model of aortic blood flow are calculated based on the patient-specific lumen anatomy, the patient-specific aortic blood flow rates, and non-invasive clinical measurements of the patient. Aortic blood flow and pressure are computed over the patient-specific lumen anatomy using the computational model of aortic blood flow and the patient-specific inlet and outlet boundary conditions.

Method and system for hemodynamic assessment of aortic coarctation from medical image data

A method and system for prediction of post-stenting hemodynamic metrics for treatment planning of arterial stenosis is disclosed. A pre-stenting patient-specific anatomical model of the coronary arteries is extracted from medical image data of a patient Blood flow is simulated in the pre-stenting patient-specific anatomical model of the coronary arteries with a modified pressure-drop model that simulates an effect of stenting on a target stenosis region used to compute a pressure drop over the target stenosis region. Parameter values for the modified pressure-drop model are set without modifying the pre-stenting patient-specific anatomical model of the coronary arteries. A predicted post-stenting hemodynamic metric for the target stenosis region, such as fractional flow reserve (FFR), is calculated based on the pressure-drop over the target stenosis region computed using the modified pressure-drop model.

Method and System for Prediction of Post-Stenting Hemodynamic Metrics for Treatment Planning of Arterial Stenosis

We propose a numerical implementation based on a Graphics Processing Unit (GPU) for the acceleration of the execution time of the Lattice Boltzmann Method (LBM). The study focuses on the application of the LBM for patient-specific blood flow computations, and hence, to obtain higher accuracy, double precision computations are employed. The LBM specific operations are grouped into two kernels, whereas only one of them uses information from neighboring nodes. Since for blood flow computations regularly only 1/5 or less of the nodes represent fluid nodes, an indirect addressing scheme is used to reduce the memory requirements. Three GPU cards are evaluated with different 3D benchmark applications (Poisseuille flow, lid-driven cavity flow and flow in an elbow shaped domain) and the best performing card is used to compute blood flow in a patient-specific aorta geometry with coarctation. The speed-up over a multi-threaded CPU code is of 19.42x. The comparison with a basic GPU based LBM implementation demonstrates the importance of the optimization activities.

/pdf/gpu-accelerated-blood-flow-computation-using-the-lattice-kkt1xyxz1q.pdf

Lucian Mihai Itu

Papers

Applying Deep Neural Networks over Homomorphic Encrypted Medical Data.

Method and System for Non-Invasive Computation of Hemodynamic Indices for Coronary Artery Stenosis

Method and system for hemodynamic assessment of aortic coarctation from medical image data

Method and System for Prediction of Post-Stenting Hemodynamic Metrics for Treatment Planning of Arterial Stenosis

GPU accelerated blood flow computation using the Lattice Boltzmann Method