Background: Chest X-ray (CXR) remains the standard imaging modality in postoperative care after non-cardiac thoracic surgery. Lung ultrasound (LUS) showed promising results in CXR reduction. The aim of this review was to identify areas where the evaluation of LUS videos by artificial intelligence could improve the implementation of LUS in thoracic surgery. Methods: A literature review of the replacement of the CXR by LUS after thoracic surgery and the evaluation of LUS videos by artificial intelligence after thoracic surgery was conducted in Medline. Results: Here, eight out of 10 reviewed studies evaluating LUS in CXR reduction showed that LUS can reduce CXR without a negative impact on patient outcome after thoracic surgery. No studies on the evaluation of LUS signs by artificial intelligence after thoracic surgery were found. Conclusion: LUS can reduce CXR after thoracic surgery. We presume that artificial intelligence could help increase the LUS accuracy, objectify the LUS findings, shorten the learning curve, and decrease the number of inconclusive results. To confirm this assumption, clinical trials are necessary. This research is funded by the Slovak Research and Development Agency, grant number APVV 20-0232.
This research introduces an advanced robotic finger designed for future generalist robots, closely mimicking the natural structure of the human finger. The incorporation of rarely discussed anatomical structures, including tendon sheath, ligaments, and palmar plates, combined with the usage of anatomically proven 3D models of the finger, give rise to the highly accurate replication of human-like soft mechanical fingers. Benefiting from the accurate anatomy of muscle insertions with the utilization of Shape Memory Alloy (SMA) wires’ muscle-like actuation properties, the bonding in-between the flexor tendons and extensor tendons allows for the realization of the central and lateral band of the finger anatomy. Evaluated using the computer vision method, the proposed robotic finger demonstrates a range of motion (ROM) equivalent to 113%, 87% and 88% of the human dynamic ROM for the DIP, PIP and MCP joints, respectively. The proposed finger possesses a soft nature when relaxed and becomes firm when activated, pioneering a new approach in biomimetic robot design and offering a unique contribution to the future of generalist humanoid robots.
Lung ultrasound is used to detect various artifacts in the lungs that support the diagnosis of different conditions. There is ongoing research to support the automatic detection of such artifacts using machine learning. We propose a solution that uses analytical computer vision methods to detect two types of lung artifacts, namely A- and B-lines. We evaluate the proposed approach on the POCUS dataset and data acquired from a hospital. We show that by using the Fourier transform, we can analyze lung ultrasound images in real-time and classify videos with an accuracy above 70%. We also evaluate the method’s applicability for segmentation, showcasing its high success rate for B-lines (89% accuracy) and its shortcomings for A-line detection. We then propose a hybrid solution that uses a combination of neural networks and analytical methods to increase accuracy in horizontal line detection, emphasizing the pleura.
In this paper, we present Combined-CapsNet (C-CapsNet), a novel approach aimed at enhancing the performance and explainability of Capsule Neural Networks (CapsNets) in image classification tasks. Our method involves the integration of segmentation masks as reconstruction targets within the CapsNet architecture. This integration helps in better feature extraction by focusing on significant image parts while reducing the number of parameters required for accurate classification. C-CapsNet combines principles from Efficient-CapsNet and the original CapsNet, introducing several novel improvements such as the use of segmentation masks to reconstruct images and a number of tweaks to the routing algorithm, which enhance both classification accuracy and interoperability. We evaluated C-CapsNet using the Oxford-IIIT Pet and SIIM-ACR Pneumothorax datasets, achieving mean F1 scores of 93% and 67%, respectively. These results demonstrate a significant performance improvement over traditional CapsNet and CNN models. The method’s effectiveness is further highlighted by its ability to produce clear and interpretable segmentation masks, which can be used to validate the network’s focus during classification tasks. Our findings suggest that C-CapsNet not only improves the accuracy of CapsNets but also enhances their explainability, making them more suitable for real-world applications, particularly in medical imaging.
1 December 2025 in Acta Electrotechnica et Informatica
This study explores the application of optical flow techniques for the automated classification of lung sliding in lung ultrasound—a key indicator for assessing lung function and diagnosing pneumothorax. Optical flow is used to capture subtle pleural motion between frames. We evaluate both traditional machine learning models (Random Forest, Gradient Boosting) and deep learning architectures (CNN, ResNet-18), using various preprocessing methods to optimize flow representation. Among deep models, the CNN achieved the highest overall accuracy (80.8%) and F1-score (73.7%), while the more complex ResNet-18 reached a high recall (94.5%) but suffered from lower precision (62.6%), indicating a tendency to over-predict the positive class. These findings highlight the trade-offs between model complexity and generalization in limited-data scenarios. The results underline the importance of model selection and tailored preprocessing in improving diagnostic reliability.
1 March 2023 in Acta Electrotechnica et Informatica
Hand fine motor functions may be impaired by various conditions, from injury to neurodegenerative diseases. Previously, we developed a prototype called Rehapiano that used load cells to measure the force exerted by the individual fingers. Rehapiano could distinguish between Parkinson’s patients and healthy individuals by analysing the finger tremors. Based on the experiences with the prototype and consultations with experts, we developed a more advanced prototype, Rehabimano. We show here how we improved the ergonomics and electronics. In addition, we have performed experimental validation of the device and confirmed its ability to detect and measure frequencies of tremors. These results are a stepping stone for consecutive software development and pre-clinical trials.