Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

Malignant melanomas resembling seborrheic keratosis (SK-like MMs) are atypical, challenging to diagnose melanoma cases that carry the risk of delayed diagnosis and inadequate treatment. On the other hand, SK may mimic melanoma, producing a ‘false positive’ with unnecessary lesion excisions. The present study proposes a computer-based approach using dermoscopy images for the characterization of SΚ-like MMs. Dermoscopic images were retrieved from the International Skin Imaging Collaboration archive. Exploiting image embeddings from pretrained convolutional network VGG16, we trained a support vector machine (SVM) classification model on a data set of 667 images. SVM optimal hyperparameter selection was carried out using the Bayesian optimization method. The classifier was tested on an independent data set of 311 images with atypical appearance: MMs had an absence of pigmented network and had an existence of milia-like cysts. SK lacked milia-like cysts and had a pigmented network. Atypical MMs were characterized with a sensitivity and specificity of 78.6% and 84.5%, respectively. The advent of deep learning in image recognition has attracted the interest of computer science towards improved skin lesion diagnosis. Open-source, public access archives of skin images empower further the implementation and validation of computer-based systems that might contribute significantly to complex clinical diagnostic problems such as the characterization of SK-like MMs.

The Effect of Hyperparameter Selection on the Personification of Customer Population Data

We explore the effects of hyperparameter selections on the personification accuracy of customer analytics data from a corporate YouTube channel with an audience in the hundreds of thousands and customer interactions in the tens of millions. Using non-negative matrix factorization, we generate personas sets from 5 to 15 using the customer analytics data, with the number of personas being the changing hyperparameter. We then compare the gender, age, nationality, and topical interests of the personas across each of the 11 persona sets using the average of the 110 generated personas as the baseline. This analysis shows that hyperparameter selection significantly alters the personification of the analytics data, with the effect most apparent with age representation. The set of 10 personas provides one of the most accurate representations across all attributes, indicating that this may be a good default hyperparameter for personification. Future research can explore other personification attributes with other customer analytics datasets.

Benchmarking the performance of Bayesian optimization across multiple experimental materials science domains

Bayesian optimization (BO) has been leveraged for guiding autonomous and high-throughput experiments in materials science. However, few have evaluated the efficiency of BO across a broad range of experimental materials domains. In this work, we quantify the performance of BO with a collection of surrogate model and acquisition function pairs across five diverse experimental materials systems. By defining acceleration and enhancement metrics for materials optimization objectives, we find that surrogate models such as Gaussian Process (GP) with anisotropic kernels and Random Forest (RF) have comparable performance in BO, and both outperform the commonly used GP with isotropic kernels. GP with anisotropic kernels has demonstrated the most robustness, yet RF is a close alternative and warrants more consideration because it is free from distribution assumptions, has smaller time complexity, and requires less effort in initial hyperparameter selection. We also raise awareness about the benefits of using GP with anisotropic kernels in future materials optimization campaigns.

Improving the efficiency of reinforcement learning for a spacecraft powered descent with Q-learning

Reinforcement learning entails many intuitive and useful approaches to solving various problems. Its main premise is to learn how to complete tasks by interacting with the environment and observing which actions are more optimal with respect to a reward signal. Methods from reinforcement learning have long been applied in aerospace and have more recently seen renewed interest in space applications. Problems in spacecraft control can benefit from the use of intelligent techniques when faced with significant uncertainties—as is common for space environments. Solving these control problems using reinforcement learning remains a challenge partly due to long training times and sensitivity in performance to hyperparameters which require careful tuning. In this work we seek to address both issues for a sample spacecraft control problem. To reduce training times compared to other approaches, we simplify the problem by discretising the action space and use a data-efficient algorithm to train the agent. Furthermore, we employ an automated approach to hyperparameter selection which optimises for a specified performance metric. Our approach is tested on a 3-DOF powered descent problem with uncertainties in the initial conditions. We run experiments with two different problem formulations—using a ‘shaped’ state representation to guide the agent and also a ‘raw’ state representation with unprocessed values of position, velocity and mass. The results show that an agent can learn a near-optimal policy efficiently by appropriately defining the action-space and state-space. Using the raw state representation led to ‘reward-hacking’ and poor performance, which highlights the importance of the problem and state-space formulation in successfully training reinforcement learning agents. In addition, we show that the optimal hyperparameters can vary significantly based on the choice of loss function. Using two sets of hyperparameters optimised for different loss functions, we demonstrate that in both cases the agent can find near-optimal policies with comparable performance to previously applied methods.

A Cost-Aware DNN-Based FDI Technology for Solenoid Pumps

Fluid Pumps serve a critical function in hydraulic and thermodynamic systems, and this often exposes them to prolonged use, leading to fatigue, stress, contamination, filter clogging, etc. On one hand, vibration monitoring for hydraulic components has shown reliable efficiencies in fault detection and isolation (FDI) practices. On the other hand, signal processing techniques provide reliable FDI parameters for artificial intelligence (AI)-based data-driven diagnostics (and prognostics) and have recently attracted global interest across different disciplines and applications. Particularly for cost-aware systems, the choice of diagnostic parameters determines the reliability of an FDI/diagnostic model. By extracting (and selecting) discriminative spectral and transient features from solenoid pump vibration signals, accurate diagnostics across operating conditions can be achieved using AI-based FDI algorithms. This study employs a deep neural network (DNN) for fault diagnosis after a correlation-based selection of discriminative spectral and transient features. To solve the problem of hyperparameter selection for the proposed model, a grid search technique was employed for optimal search for parameters (number of layers, neurons, activation function, weight optimizer, etc.) on different network architectures.The results reveal the high accuracy of a three-layer DNN with ReLU activation function, with a test accuracy of 99.23% and a minimal false alarm rate on a case study.

The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective

Image-based navigation is widely considered the next frontier of minimally invasive surgery. It is believed that image-based navigation will increase the access to reproducible, safe, and high-precision surgery as it may then be performed at acceptable costs and effort. This is because image-based techniques avoid the need of specialized equipment and seamlessly integrate with contemporary workflows. Furthermore, it is expected that image-based navigation techniques will play a major role in enabling mixed reality environments, as well as autonomous and robot-assisted workflows. A critical component of image guidance is 2D/3D registration, a technique to estimate the spatial relationships between 3D structures, e.g., preoperative volumetric imagery or models of surgical instruments, and 2D images thereof, such as intraoperative X-ray fluoroscopy or endoscopy. While image-based 2D/3D registration is a mature technique, its transition from the bench to the bedside has been restrained by well-known challenges, including brittleness with respect to optimization objective, hyperparameter selection, and initialization, difficulties in dealing with inconsistencies or multiple objects, and limited single-view performance. One reason these challenges persist today is that analytical solutions are likely inadequate considering the complexity, variability, and high-dimensionality of generic 2D/3D registration problems. The recent advent of machine learning-based approaches to imaging problems that, rather than specifying the desired functional mapping, approximate it using highly expressive parametric models holds promise for solving some of the notorious challenges in 2D/3D registration. In this manuscript, we review the impact of machine learning on 2D/3D registration to systematically summarize the recent advances made by introduction of this novel technology. Grounded in these insights, we then offer our perspective on the most pressing needs, significant open problems, and possible next steps.