Search

Micro-computed tomography (micro-CT) is a non-destructive imaging technique that offers highly detailed, 3D visualizations of a target specimen. In the context of breast cancer, micro-CT has emerged as a promising tool for analyzing microcalcifications (MCs), tiny calcium deposits that can indicate at an early stage the presence of cancer. This review aimed to explore the current applications of micro-CT in analyzing breast MCs (ex vivo, animal models, and phantoms) and to identify potential avenues in scientific research. We followed PRISMA guidelines for scoping reviews, yielding 18 studies that met our criteria. The studies varied in their purposes: feasibility and optimization of micro-CT for breast cancer imaging and MC analysis/diagnosis, comparison with other imaging modalities, development of micro-CT scanners and processing algorithms, enhancement of MC detection through contrast agents, etc. In conclusion, micro-CT offers superior image quality and detailed visualization of breast tissue (especially tumor masses and MCs), surpassing traditional methods like mammography and approaching the level of detail of histology. It holds great potential to enhance our understanding of MC characteristics and breast pathologies when used as a supplementary tool. Further research will solidify its role in clinical practice and potentially expand its applications in breast cancer studies.

The integration of Deep Learning (DL) models with the HoloLens2 Augmented Reality (AR) headset has enormous potential for real-time AR medical applications. Currently, most applications execute the models on an external server that communicates with the headset via Wi-Fi. This client-server architecture introduces undesirable delays and lacks reliability for real-time applications. However, due to HoloLens2’s limited computation capabilities, running the DL model directly on the device and achieving real-time performances is not trivial. Therefore, this study has two primary objectives: (i) to systematically evaluate two popular frameworks to execute DL models on HoloLens2—Unity Barracuda and Windows Machine Learning (WinML)—using the inference time as the primary evaluation metric; (ii) to provide benchmark values for state-of-the-art DL models that can be integrated in different medical applications (e.g., Yolo and Unet models). In this study, we executed DL models with various complexities and analyzed inference times ranging from a few milliseconds to seconds. Our results show that Unity Barracuda is significantly faster than WinML (p-value < 0.005). With our findings, we sought to provide practical guidance and reference values for future studies aiming to develop single, portable AR systems for real-time medical assistance.

In recent years, the successful application of Deep Learning methods to classification problems has had a huge impact in many domains. (1) Background: In biomedical engineering, the problem of gesture recognition based on electromyography is often addressed as an image classification problem using Convolutional Neural Networks. Recently, a specific class of these models called Temporal Convolutional Networks (TCNs) has been successfully applied to this task. (2) Methods: In this paper, we approach electromyography-based hand gesture recognition as a sequence classification problem using TCNs. Specifically, we investigate the real-time behavior of our previous TCN model by performing a simulation experiment on a recorded sEMG dataset. (3) Results: The proposed network trained with data augmentation yields a small improvement in accuracy compared to our existing model. However, the classification accuracy is decreased in the real-time evaluation, showing that the proposed TCN architecture is not suitable for such applications. (4) Conclusions: The real-time analysis helps in understanding the limitations of the model and exploring new ways to improve its performance.

The range of applications of electromyography-based gesture recognition has increased over the last years. A common problem regularly encountered in literature is the inadequate data availability. Data augmentation, which aims at generating new synthetic data from the existing ones, is the most common approach to deal with this data shortage in other research domains. In the case of surface electromyography (sEMG) signals, there is limited research in augmentation methods and quite regularly the results differ between available studies. In this work, we provide a detailed evaluation of existing (i.e., additive noise, overlapping windows) and novel (i.e., magnitude warping, wavelet decomposition, synthetic sEMG models) strategies of data augmentation for electromyography signals. A set of metrics (i.e., classification accuracy, silhouette score, and Davies–Bouldin index) and visualizations help with the assessment and provides insights about their performance. Methods like signal magnitude warping and wavelet decomposition yield considerable increase (up to 16%) in classification accuracy across two benchmark datasets. Particularly, a significant improvement of 1% in the classification accuracy of the state-of-the-art model in hand gesture recognition is achieved.

Optoelectronic devices are the gold standard for 3D evaluation in clinics, but due to the complexity of this kind of hardware and the lack of access for patients, affordable, transportable, and easy-to-use systems must be developed to be largely used in daily clinics. The KinectTM sensor has various advantages compared to optoelectronic devices, such as its price and transportability. However, it also has some limitations: (in)accuracy of the skeleton detection and tracking as well as the limited amount of available points, which makes 3D evaluation impossible. To overcome these limitations, a novel method has been developed to perform 3D evaluation of the upper limbs. This system is coupled to rehabilitation exercises, allowing functional evaluation while performing physical rehabilitation. To validate this new approach, a two-step method was used. The first step was a laboratory validation where the results obtained with the KinectTM were compared with the results obtained with an optoelectronic device; 40 healthy young adults participated in this first part. The second step was to determine the clinical relevance of this kind of measurement. Results of the healthy subjects were compared with a group of 22 elderly adults and a group of 10 chronic stroke patients to determine if different patterns could be observed. The new methodology and the different steps of the validations are presented in this paper.