Electrical impedance tomographic imaging of a single cell electroporation.

A living cell placed in a high strength electric field, can undergo a process known as electroporation. It is believed that during electroporation nano-scale defects (pores) occur in the membrane of the cell, causing dramatic changes to the permeability of its membrane. Electroporation is an important technique in biotechnology and medicine and numerous methods are being developed to improve the understanding and use of the technology. We propose to extend the toolbox available for studying electroporation by generating impedance distribution images of the cell as it undergoes electroporation using Electrical Impedance Tomography (EIT). To investigate the feasibility of this concept, we develop a mathematical model of the process of electroporation in a single cell and of EIT of the process and show simulation results of a computer-based finite element model (FEM). Our work is an attempt to develop a new imaging tool for visualizing electroporation in a single cell, offering a different temporal and spatial resolution compared to the state of the art, which includes bulk measurements of electrical properties during single cell electroporation, patch clamp and voltage clamp measurement in single cells and optical imaging with colorimetric dyes during single cell electroporation. This paper is a preliminary theoretic feasibility study.

EHR-Safe: generating high-fidelity and privacy-preserving synthetic electronic health records.

Privacy concerns often arise as the key bottleneck for the sharing of data between consumers and data holders, particularly for sensitive data such as Electronic Health Records (EHR). This impedes the application of data analytics and ML-based innovations with tremendous potential. One promising approach for such privacy concerns is to instead use synthetic data. We propose a generative modeling framework, EHR-Safe, for generating highly realistic and privacy-preserving synthetic EHR data. EHR-Safe is based on a two-stage model that consists of sequential encoder-decoder networks and generative adversarial networks. Our innovations focus on the key challenging aspects of real-world EHR data: heterogeneity, sparsity, coexistence of numerical and categorical features with distinct characteristics, and time-varying features with highly-varying sequence lengths. Under numerous evaluations, we demonstrate that the fidelity of EHR-Safe is almost-identical with real data (<3% accuracy difference for the models trained on them) while yielding almost-ideal performance in practical privacy metrics.

Incidental cerebral aneurysms detected by a computer-assisted detection system based on artificial intelligence: A case series.

RATIONALE: Computer-assisted detection (CAD) systems based on artificial intelligence (AI) using convolutional neural network (CNN) have been successfully used for the diagnosis of unruptured cerebral aneurysms in experimental situations. However, it is yet unclear whether CAD systems can detect cerebral aneurysms effectively in real-life clinical situations. This paper describes the diagnostic efficacy of CAD systems for cerebral aneurysms and the types of cerebral aneurysms that they can detect. PATIENT CONCERNS: From March 7, 2017 to August 26, 2018 we performed brain magnetic resonance imaging (MRI) scans for 1623 subjects, to rule out intracranial diseases. We retrospectively reviewed the medical records including the history and images for each patient. DIAGNOSES, INTERVENTIONS AND OUTCOMES: Among them, we encountered 5 cases in whom the cerebral aneurysms had been overlooked in the first and second round of imaging, and were detected for the first time by CAD. All missed aneurysms were less than 2 mm in diameter. Of the 5 aneurysms, 2 were internal carotid artery (ICA) paraclinoid aneurysms, 2 were Internal carotid-posterior communicating artery (IC-PC) aneurysms and 1 was a distal middle cerebral artery (MCA) aneurysm. LESSONS: Our CAD system can detect very small aneurysms masked by the surrounding arteries and difficult for radiologists to detect. In the future, CAD systems might pave the way to substitute the workload of diagnostic radiologists and reduce the cost of human labor.

Electrical impedance tomography of electrolysis.

The primary goal of this study is to explore the hypothesis that changes in pH during electrolysis can be detected with Electrical Impedance Tomography (EIT). The study has relevance to real time control of minimally invasive surgery with electrolytic ablation. To investigate the hypothesis, we compare EIT reconstructed images to optical images acquired using pH-sensitive dyes embedded in a physiological saline agar gel phantom treated with electrolysis. We further demonstrate the biological relevance of our work using a bacterial E.Coli model, grown on the phantom. The results demonstrate the ability of EIT to image pH changes in a physiological saline phantom and show that these changes correlate with cell death in the E.coli model. The results are promising, and invite further experimental explorations.

Magnetic resonance imaging of electrolysis.

This study explores the hypothesis that Magnetic Resonance Imaging (MRI) can image the process of electrolysis by detecting pH fronts. The study has relevance to real time control of cell ablation with electrolysis. To investigate the hypothesis we compare the following MR imaging sequences: T1 weighted, T2 weighted and Proton Density (PD), with optical images acquired using pH-sensitive dyes embedded in a physiological saline agar solution phantom treated with electrolysis and discrete measurements with a pH microprobe. We further demonstrate the biological relevance of our work using a bacterial E. Coli model, grown on the phantom. The results demonstrate the ability of MRI to image electrolysis produced pH changes in a physiological saline phantom and show that these changes correlate with cell death in the E. Coli model grown on the phantom. The results are promising and invite further experimental research.

Combining Electrolysis and Electroporation for Tissue Ablation.

Electrolytic ablation is a method that operates by delivering low magnitude direct current to the target region over long periods of time, generating electrolytic products that destroy cells. This study was designed to explore the hypothesis stating that electrolytic ablation can be made more effective when the electrolysis-producing electric charges are delivered using electric pulses with field strength typical in reversible electroporation protocols. (For brevity we will refer to tissue ablation protocols that combine electroporation and electrolysis as E(2).) The mechanistic explanation of this hypothesis is related to the idea that products of electrolysis generated by E(2) protocols can gain access to the interior of the cell through the electroporation permeabilized cell membrane and therefore cause more effective cell death than from the exterior of an intact cell. The goal of this study is to provide a first-order examination of this hypothesis by comparing the charge dosage required to cause a comparable level of damage to a rat liver, in vivo, when using either conventional electrolysis or E(2) approaches. Our results show that E(2) protocols produce tissue damage that is consistent with electrolytic ablation. Furthermore, E(2) protocols cause damage comparable to that produced by conventional electrolytic protocols while delivering orders of magnitude less charge to the target tissue over much shorter periods of time.

Distributed network, wireless and cloud computing enabled 3-D ultrasound; a new medical technology paradigm.

Medical technologies are indispensable to modern medicine. However, they have become exceedingly expensive and complex and are not available to the economically disadvantaged majority of the world population in underdeveloped as well as developed parts of the world. For example, according to the World Health Organization about two thirds of the world population does not have access to medical imaging. In this paper we introduce a new medical technology paradigm centered on wireless technology and cloud computing that was designed to overcome the problems of increasing health technology costs. We demonstrate the value of the concept with an example; the design of a wireless, distributed network and central (cloud) computing enabled three-dimensional (3-D) ultrasound system. Specifically, we demonstrate the feasibility of producing a 3-D high end ultrasound scan at a central computing facility using the raw data acquired at the remote patient site with an inexpensive low end ultrasound transducer designed for 2-D, through a mobile device and wireless connection link between them. Producing high-end 3D ultrasound images with simple low-end transducers reduces the cost of imaging by orders of magnitude. It also removes the requirement of having a highly trained imaging expert at the patient site, since the need for hand-eye coordination and the ability to reconstruct a 3-D mental image from 2-D scans, which is a necessity for high quality ultrasound imaging, is eliminated. This could enable relatively untrained medical workers in developing nations to administer imaging and a more accurate diagnosis, effectively saving the lives of people.