First Organoid Intelligence (OI) workshop to form an OI community.

The brain is arguably the most powerful computation system known. It is extremely efficient in processing large amounts of information and can discern signals from noise, adapt, and filter faulty information all while running on only 20 watts of power. The human brain's processing efficiency, progressive learning, and plasticity are unmatched by any computer system. Recent advances in stem cell technology have elevated the field of cell culture to higher levels of complexity, such as the development of three-dimensional (3D) brain organoids that recapitulate human brain functionality better than traditional monolayer cell systems. Organoid Intelligence (OI) aims to harness the innate biological capabilities of brain organoids for biocomputing and synthetic intelligence by interfacing them with computer technology. With the latest strides in stem cell technology, bioengineering, and machine learning, we can explore the ability of brain organoids to compute, and store given information (input), execute a task (output), and study how this affects the structural and functional connections in the organoids themselves. Furthermore, understanding how learning generates and changes patterns of connectivity in organoids can shed light on the early stages of cognition in the human brain. Investigating and understanding these concepts is an enormous, multidisciplinary endeavor that necessitates the engagement of both the scientific community and the public. Thus, on Feb 22-24 of 2022, the Johns Hopkins University held the first Organoid Intelligence Workshop to form an OI Community and to lay out the groundwork for the establishment of OI as a new scientific discipline. The potential of OI to revolutionize computing, neurological research, and drug development was discussed, along with a vision and roadmap for its development over the coming decade.

Real-Time Optimization of Retinal Ganglion Cell Spatial Activity in Response to Epiretinal Stimulation.

Retinal prostheses aim to improve visual perception in patients blinded by photoreceptor degeneration. However, shape and letter perception with these devices is currently limited due to low spatial resolution. Previous research has shown the retinal ganglion cell (RGC) spatial activity and phosphene shapes can vary due to the complexity of retina structure and electrode-retina interactions. Visual percepts elicited by single electrodes differ in size and shapes for different electrodes within the same subject, resulting in interference between phosphenes and an unclear image. Prior work has shown that better patient outcomes correlate with spatially separate phosphenes. In this study we use calcium imaging, in vitro retina, neural networks (NN), and an optimization algorithm to demonstrate a method to iteratively search for optimal stimulation parameters that create focal RGC activation. Our findings indicate that we can converge to stimulation parameters that result in focal RGC activation by sampling less than 1/3 of the parameter space. A similar process implemented clinically can reduce time required for optimizing implant operation and enable personalized fitting of retinal prostheses.

An in silico hiPSC-Derived Cardiomyocyte Model Built With Genetic Algorithm.

The formulation of in silico biophysical models generally requires optimization strategies for reproducing experimentally observed phenomena. In electrophysiological modeling, robust nonlinear regressive methods are often crucial for guaranteeing high fidelity models. Human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs), though nascent, have proven to be useful in cardiac safety pharmacology, regenerative medicine, and in the implementation of patient-specific test benches for investigating inherited cardiac disorders. This study demonstrates the potency of heuristic techniques at formulating biophysical models, with emphasis on a hiPSC-CM model using a novel genetic algorithm (GA) recipe we proposed. The proposed GA protocol was used to develop a hiPSC-CM biophysical computer model by fitting mathematical formulations to experimental data for five ionic currents recorded in hiPSC-CMs. The maximum conductances of the remaining ionic channels were scaled based on recommendations from literature to accurately reproduce the experimentally observed hiPSC-CM action potential (AP) metrics. Near-optimal parameter fitting was achieved for the GA-fitted ionic currents. The resulting model recapitulated experimental AP parameters such as AP durations (APD50, APD75, and APD90), maximum diastolic potential, and frequency of automaticity. The outcome of this work has implications for validating the biophysics of hiPSC-CMs in their use as viable substitutes for human cardiomyocytes, particularly in cardiac safety pharmacology and in the study of inherited cardiac disorders. This study presents a novel GA protocol useful for formulating robust numerical biophysical models. The proposed protocol is used to develop a hiPSC-CM model with implications for cardiac safety pharmacology.

Convolutional Neural Network Based Breast Cancer Histopathology Image Classification.

Breast cancer is a global health concern, with approximately 30 million new cases projected to be reported by 2030. While efforts are being channeled into curative measures, preventive and diagnostic measures also need to be improved to curb the situation. Convolutional Neural Networks (CNNs) are a class of deep learning algorithms that have been widely adopted for the computerized classification of breast cancer histopathology images. In this work, we propose a set of training techniques to improve the performance of CNN-based classifiers for breast cancer identification. We combined transfer learning techniques with data augmentation and whole image training to improve the performance of the CNN classifier. Instead of conventional image patch extraction for training and testing, we employed a high-resolution whole-image training and testing on a modified network that was pre-trained on the Imagenet dataset. Despite the computational complexity, our proposed classifier achieved significant improvement over the previously reported studies on the open-source BreakHis dataset, with an average image level accuracy of about 91% and patient scores as high as 95%.Clinical Relevance- this work improves on the performance of CNN for breast cancer histopathology image classification. An improved Breast cancer image classification can be used for the preliminary examination of tissue slides in breast cancer diagnosis.

Genetic Algorithm For Fitting Cardiac Cell Biophysical Model Formulations.

Modeling cardiac cell electrophysiology relies on fitting model equations to experimental data obtained under voltage/current clamping conditions. The fitting procedure for these often-nonlinear ionic current equations are mostly executed by trial-and-error by hand or by gradient-based optimization approaches. These methods, though sometimes sufficient at converging at optimal solutions is based on the premise that the characteristic objective function is convex, which often does not apply to cardiac model equations. Meta-heuristic methods, such as evolutionary algorithms and particle swarm algorithms, have proven resilient against early convergence to local optima and saddle-point parameter solutions. This work presents a genetic algorithm-based approach for fitting the adult cardiomyocyte biophysical model formulations to the experimental data obtained in human induced pluripotent stem cell-derived cardiomyocyte (hiPSC-CM). Specifically, whole-cell patch clamp ionic current data of rapid delayed rectifier potassium current, IKr, transient outward potassium current, Ito and hyperpolarization-activated current, If, was used for fitting. Using a two-point crossover scheme along with initial population and mutation constraints randomly selected from a uniformly distributed constrained parameter space, near-optimal fitting was achieved with R2 values (n = 5) of 0.9960±0.0007, 0.9995±0.0002, and 0.9974±0.0014 for IKr, Ito and If respectively.