The paper presents a multi-camera vision system designed for real-time applications. The system consists of six camera modules, which can be deployed at distances of up to approximately 15 meters from the central processing unit (host) without a significant loss in image quality. This configuration provides wide-angle coverage of the scene. The hardware design prioritizes cost-effectiveness and modularity. Each camera node is based, but not limited to, on the Raspberry Pi Camera Module 2, which integrates the Sony IMX219 CMOS sensor. The cameras were placed in enclosures that were self-designed and fabricated using 3D printing technology. The NVIDIA Jetson compute unit was used for image processing using artificial intelligence algorithms. This device enables the deployment of advanced computer vision models for real-time human pose estimation, such as YOLOv11 and OpenPose. Both frameworks are known for their high accuracy and low latency performance, making them suitable for time-sensitive applications. The use of on-device inference ensures efficient video data analysis while preserving low implementation costs and minimizing dependency on external processing infrastructure.

This study presents a specialized system for detecting textual data in medical images, aimed at enhancing the anonymization of sensitive patient information. Conventional OCR tools, such as EasyOCR and docTR, exhibit notable limitations in medical settings - particularly in handling complex imagery such as lung CT scans - resulting in high false positive rates and suboptimal recall. To overcome these challenges, we adapted the YOLOv11n object detection model for the task of text localization in medical images. The model was trained on a hybrid dataset comprising real CT images with annotated labels and synthetically generated samples, improving robustness under various imaging conditions. In a comparative evaluation, YOLOv11n achieved a precision of 100.00%, recall of 92.09% and F1 score of 95.86%, significantly outperforming EasyOCR (F1 = 66.9%) and docTR (F1 = 89.58%). In particular, YOLOv11n did not produce false positives in the test set, which makes it highly effective in preserving relevant diagnostic information while accurately detecting sensitive text regions. These results underscore the potential of adapting state-of-the-art object detection frameworks such as YOLO to specialized tasks in medical image processing and privacy preservation.

Nail disorders such as onychomycosis and nail psoriasis are common conditions that can significantly impact a patient's quality of life. Early detection and proper classification are essential for timely treatment; however, access to dermatological care may be limited. To address this challenge, we propose a mobile application designed to provide users with a preliminary diagnosis of nail plate disorders based on photographic input. The Android application uses deep learning to classify nail images. The core of the diagnostic system is trained on the publicly available “Nail Disease Image Classification Dataset” from Kaggle, which includes annotated images spanning three primary classes: healthy nails, nail psoriasis, and onychomycosis (fungal nail infection). Several CNN architectures were evaluated, with MobileNetV3Small selected for deployment due to its efficiency, achieving 93.0% test accuracy. The chosen model demonstrated high robustness and consistent performance across all three categories, making it suitable for real-world application. Moreover, MobileNetV3Small maintained a low validation loss of 0.1544 and a test loss of 0.2100, further confirming its generalization capabilities. This AI-powered mobile solution offers a user-friendly interface for self-assessment and could serve as a valuable tool for preliminary dermatological screening. Additionally, it has the potential to support healthcare professionals by assisting in triaging cases and raising awareness of potential nail disorders among patients.

The aim of this study was to develop a system capable of recognizing textual data in medical images and identifying which labels contain private information. We designed an intuitive, modular pipeline with extensibility in mind, allowing for the seamless integration or replacement of individual components as technologies evolve. This architecture ensures long-term adaptability to future advancements in OCR and machine learning. For text detection on images, we used a YOLO model fine-tuned on a specialized dataset of lung CT images. To improve text analysis, we integrated a large language model (LLM) into the workflow. Although effective, LLM introduces noticeable latency when processing numerous detected text regions, which may impact the overall image processing time. Nevertheless, with an accuracy of approximately 80% achieved on the test set, the system demonstrates robustness and scalability for the detection and interpretation of textual data in medical imaging contexts.

The paper presents preliminary analyses of pulse transit time (PTT) derived from photoplethysmography (PPG) measurements taken at the elbow, wrist, and finger. Data were collected from ten participants under the approval of a bioethics committee. The study examined the correlation coefficients of PTT between these locations using four fiducial points of the PPG signal. The results show strong dependence on the individual participant, the choice of fiducial point, and the sensor placement (the correlation coefficient varies from -0.69 to 1.00). These findings highlight the need for further analysis on a larger and more diverse population, including individuals with varying health conditions and broader ranges of blood pressure fluctuations.

The objective of this study is to develop and assess a mobile application that leverages artificial intelligence (AI) to support the rehabilitation of individuals with facial nerve paralysis. The application features two primary functionalities: assessing the paralysis severity and facilitating the monitoring of rehabilitation exercises. The AI algorithm employed for this purpose was Google's ML Kit “face-detection”. The classification of facial nerve palsy was achieved by measuring the asymmetry of the user's face using a proprietary algorithm developed specifically for this study. This approach not only enables a precise assessment of paralysis severity but also allows for a personalized rehabilitation experience. Furthermore, the monitoring of rehabilitation exercise adherence and correctness is conducted through algorithms crafted for this application to ensure that patients are performing their prescribed rehabilitation exercises effectively. This comprehensive system offers a tailored and interactive approach to the management of facial nerve paralysis through the integration of AI algorithms and user-friendly mobile technology.

Pregnancy in a life of a woman, is an important time that is connected with both physiological and psychological changes. This paper aims at developing a digital twin application that allows to assess mother's health risk and help to diagnose them. The system presented in this paper includes models for three health outcomes: maternal health risk level, diagnosis of gestational diabetes mellitus (GDM), and diagnosis of late onset preeclampsia. The system included an examination of a data generation method. The model destined to assess the risk level achieved an accuracy of 83.5%. GDM model obtained a high precision of 97.2%. The analysis of preeclampsia data generation has shown a great potential for future use. The developed digital twin application serves to exhibit the mentioned models and offer an insight into the future diagnostic tool designed for maternal healthcare in the coming years.

Effective parking management is essential for ad-dressing the challenges of traffic congestion, city logistics, and air pollution in densely populated urban areas. This paper presents an algorithm designed to optimize parking management within city environments. The proposed system leverages deep learning models to accurately detect and classify street elements and events. Various algorithms, including automatic segmentation of urban landscapes, occupancy detection, and illegal parking violation detection, were developed and tested. To validate the system, cameras were installed facing streets and parking areas, and all algorithms were tested on real-world data. The segmentation network achieved a mean Average Precision (mAP) of 0.791. The occupancy detection algorithm showed a precision and recall of 0.97 on parking camera data, while the illegal parking violation detection system achieved precision and recall values of 0.971 and 0.958, respectively. This research contributes to smarter, more efficient urban parking solutions, enhancing overall city management.

This study aimed to develop and assess an application designed to enhance the management of a local client database consisting of mammographic images with a focus on ensuring that images are suitably and uniformly prepared for federated learning applications. The application supports a comprehensive approach, starting with a versatile image-loading function that supports DICOM files from various medical imaging devices and settings. It also aims to standardize the labeling and pre-processing of new images, statistical analysis and data visualization of mammographic images across all participating healthcare units. Initial image preprocessing is significantly enhanced through the use of Wiener and CLAHE filters, aimed at reducing noise and improving contrast, respectively, to ensure the highest quality of images for diagnostic purposes. Further refinement in the preprocessing pipeline is achieved with a U-Net model, trained on publicly available databases, which excels in segmenting the breast tissue from images, thereby eliminating irrelevant background and artifacts. This meticulous preparation of images not only standardizes data quality across multiple medical institutions but also facilitates collaborative model training within federated learning frameworks. The program allows for the review of images and their metadata, enables labeling of images with the ability to mark regions of interest (ROI), and utilize a pre-trained model for preliminary BI-RADS classification. A notable addition to the application is the integration of functionalities, thanks to the implementation of Grad-CAM model, designed to elucidate the decision-making processes of deep learning models. This integration further enriches the application's utility in supporting diagnostic and analytical tasks in mammography, providing clear insights into the interpretive reasoning behind model predictions.

(1) About 15-20% of couples struggle with the problem of infertility. 30 to 40% of these cases are caused by abnormalities in the structure and motility of sperm. Sometimes the only possibility for such people is to use the procedure of artificial insemination. CASA systems are used to increase the efficiency of this procedure by selecting the appropriate sperm cell. (2) This paper presents an approach to the sperm classification on the basis of its entire structure analysis, including flagella - often poorly visible and therefore ignored in the CASA systems element. The training of the Mask R-CNN architecture was performed on 2 publicly available and one specially created for this purpose sperm database. A 14-element feature vector was also proposed for the classification of 4 classes of typical head defects (amorphous, normal, tapered and pyriform) by the Support Vector Machine. (3) The sperm head (mAP 94.28%) and the whole flagellum (mAP 90.29%) were successfully detected. However, the flagella segmentation results were significantly lower (50.88%) than that the head segmentation (88.32%). Classification with SVM scored 82% accuracy. (4) Research has shown that segmentation and the use of a simple SVM classifier allow for quite good results in the classification of sperm defects. However, it is important to develop a larger whole sperm database, to improve the segmentation results.

In this paper, we summarize the results obtained from fire experiments. The aim of the work was to develop new methods of fire detection using IR thermal imaging cameras and dedicated image processing. We conducted 4 experiments in different configurations and with the use of different objects. The conducted experiments have shown the great usefulness of infrared cameras for detecting the seeds of a fire. Even cheap low-resolution bolometric detector modules can detect hot spots.

Automation or even computer assistance of the popular infertility treatment method: ICSI (Intracytoplasmic Sperm Injection) would speed up the whole process and improve the control of the results. This paper introduces a preliminary research for automatic spermatozoon injection into the oocyte cytoplasm. Here, the method for detection a correct orientation of the polar body of the oocyte is presented. Proposed method uses deep learning U-Net architecture for object segmentation. This solution proved to be universal and had no demand for numerous dataset or high-quality Images.