The industrial environment has gone through the fourth revolution, also called “Industry 4.0”, where the main aspect is digitalization. Each device employed in an industrial process is connected to a network called the industrial Internet of things (IIOT). With IIOT manufacturers being capable of tracking every device, it has become easier to prevent or quickly solve failures. Specifically, the large amount of available data has allowed the use of artificial intelligence (AI) algorithms to improve industrial applications in many ways (e.g., failure detection, process optimization, and abnormality detection). Although data are abundant, their access has raised problems due to privacy concerns of manufacturers. Censoring sensitive information is not a desired approach because it negatively impacts the AI performance. To increase trust, there is also the need to understand how AI algorithms make choices, i.e., to no longer regard them as black boxes. This paper focuses on recent advancements related to the challenges mentioned above, discusses the industrial impact of proposed solutions, and identifies challenges for future research. It also presents examples related to privacy-preserving and explainable AI solutions, and comments on the interaction between the identified challenges in the conclusions.

Cardiovascular disease (CVD) is the number one cause of death worldwide, and coronary artery disease (CAD) is the most prevalent CVD, accounting for 42% of these deaths. In view of the limitations of the anatomical evaluation of CAD, Fractional Flow Reserve (FFR) has been introduced as a functional diagnostic index. Herein, we evaluate the feasibility of using deep neural networks (DNN) in an ensemble approach to predict the invasively measured FFR from raw anatomical information that is extracted from optical coherence tomography (OCT). We evaluate the performance of various DNN architectures under different formulations: regression, classification—standard, and few-shot learning (FSL) on a dataset containing 102 intermediate lesions from 80 patients. The FSL approach that is based on a convolutional neural network leads to slightly better results compared to the standard classification: the per-lesion accuracy, sensitivity, and specificity were 77.5%, 72.9%, and 81.5%, respectively. However, since the 95% confidence intervals overlap, the differences are statistically not significant. The main findings of this study can be summarized as follows: (1) Deep-learning (DL)-based FFR prediction from reduced-order raw anatomical data is feasible in intermediate coronary artery lesions; (2) DL-based FFR prediction provides superior diagnostic performance compared to baseline approaches that are based on minimal lumen diameter and percentage diameter stenosis; and (3) the FFR prediction performance increases quasi-linearly with the dataset size, indicating that a larger train dataset will likely lead to superior diagnostic performance.

In this paper, two adaptive control methods introduced in literature (e.g. the gradient and Lyapunov stability methods) are applied on several theoretical examples considering the second order plant for different time varying parameters. Further on, two new adaptive control laws are proposed. The first one is based on MIT rule and Lyapunov stability combination to allow usage of the same value for all adaptation gains. The second one, based on the first one, is developed for perturbation rejection by adding an artificial perturbation at the plant's input. Using Matlab / Simulink, the preferred approach for each use case is showcased.

Osteoporosis is a skeletal disorder which leads to bone mass loss and to an increased fracture risk. Recently, physics-based models, employing finite element analysis, have shown great promise in being able to non-invasively estimate biomechanical quantities of interest in the context of osteoporosis. However, these models have high computational demand, limiting their clinical adoption. In this manuscript, we present a machine learning-based model for predicting average strain as an alternative to physics-based approaches. The model is trained on a large database of synthetically generated cancellous bone anatomies, where the target values are computed using the physics-based FEA model. The performance of the trained model was assessed by comparing the predictions against physics-based computations on a separate test data set. Correlation between machine learning and physics-based predictions was very good (0.842, p <; 0.001) and no systematic bias was found in Bland-Altman analysis. Compared to the physics based computation, average execution time was reduced by more than 300 times, leading to real-time assessment of average strain. Average execution time went down from 32.1 ± 3.0 seconds for the FE model to around 0.01 ± 0.005 seconds for the machine learning model on a workstation equipped with 3.0 GHz Intel i7 2-core processor.

Coronary computed tomography angiography (CCTA) is an effective imaging modality, increasingly accepted as a first-line test to diagnose coronary artery disease (CAD). The accurate segmentation of the coronary artery lumen on CCTA is important for the anatomical, morphological, and non-invasive functional assessment of stenoses. Hence, semi-automated approaches are currently still being employed. The processing time for a semi-automated lumen segmentation can be reduced by pre-selecting vessel locations likely to require manual inspection and by submitting only those for review to the radiologist. Detection of faulty lumen segmentation masks can be formulated as an Out-of-Distribution (OoD) detection problem. Two Normalizing Flows architectures are investigated and benchmarked herein: a Glow-like baseline, and a proposed one employing a novel coupling layer. Synthetic mask perturbations are used for evaluating and fine-tuning the learnt probability densities. Expert annotations on a separate test-set are employed to measure detection performance relative to inter-user variability. Regular coupling-layers tend to focus more on local pixel correlations and to disregard semantic content. Experiments and analyses show that, in contrast, the proposed architecture is capable of capturing semantic content and is therefore better suited for OoD detection of faulty lumen segmentations. When compared against expert consensus, the proposed model achieves an accuracy of 78.6% and a sensitivity of 76%, close to the inter-user mean of 80.9% and 79%, respectively, while the baseline model achieves an accuracy of 64.3% and a sensitivity of 48%.