Cancer drug discovery is a complex process that requires identifying compounds that selectively target malignant cells. While high-throughput screening (HTS) is essential for testing large libraries, it generates vast datasets that are difficult to interpret. Recently, the integration of artificial intelligence (AI), particularly deep learning (DL), has significantly accelerated drug candidate selection. This review highlights the synergy between AI and HTS, emphasizing DL techniques such as convolutional neural networks for bioactivity prediction, recurrent neural networks for de novo design, and reinforcement learning for property optimization. These methods streamline preclinical research by enabling rapid multi-omics analysis and prediction of drug-target interactions. However, challenges regarding data quality, model interpretability, and ethics persist. Emerging paradigms like Explainable AI and federated learning aim to enhance transparency and collaboration while safeguarding privacy. Ultimately, overcoming these barriers through AI-HTS integration holds transformative potential to reduce development costs and improve clinical outcomes for cancer patients.

This study aims to analyze and describe robotic assisted surgery approach in colorectal cancer therapy and evaluate its effectiveness in comparison to the laparoscopic approach. Apart from assessing surgical metrics, such as intraoperative precision and complication rates, the study also explores broader aspects, including the impact on patients’ quality of life, the frequency of conversions to open surgery, and the oncological quality of resections. By incorporating these complementary factors, the analysis provides a comprehensive perspective on the role of robotic surgery in colorectal cancer treatment. A systematic literature search was conducted in PubMed, Embase, and Web of Science up to January 30, 2026. All records were imported into Mendeley, and duplicates were removed. Among the1,384 identified publications, 17 met the eligibility criteria. Robotic colorectal surgery (RCS) demonstrated superior intraoperative control, lower conversion rates, and enhanced lymphadenectomy precision, though with longer operative times and higher procedural costs compared to laparoscopic surgery (LS). Complication rates were generally lower in the robotic surgery (RS) group, particularly in major (Clavien–Dindo III–V) complications and anastomotic leaks. Patient-related metrics, such as pain scores, bowel function recovery, and hospital stay, consistently favored RS. Robotic-assisted surgery offers perioperative and functional benefits for patients with CRC, especially in anatomically challenging cases. While its superiority in long-term oncological outcomes remains inconclusive, when combined with advances in molecular therapy, RS may contribute to a more individualized and effective treatment paradigm.

Cerebral Palsy (CP) requires individualized interventions due to its complex nature affecting movement and coordination. Medical Human Digital Twin (MHDT) technology offers significant advancements in CP management by creating virtual representations of patients’ physical and neurological states. This paper reviews MHDT applications in CP diagnosis, therapy, and rehabilitation. Advanced imaging techniques and sensor integration enhance early and accurate diagnosis through detailed patient modeling. Therapeutic applications focus on personalized treatment plans using AI-driven models, VR/AR, and robotic-assisted devices, ensuring continuous optimization through real-time monitoring. Rehabilitation strategies benefit from immersive technologies and adaptive feedback, improving patient engagement and outcomes. The integration of human empathy with data-driven insights enables more precise and effective care. Ethical considerations, data management challenges, and future research directions, including interdisciplinary collaboration, are discussed. MHDTs present a transformative approach to CP care, promising improved patient outcomes and personalized healthcare solutions.

Over the past decade, there has been growing interest in the mechanical and electrical properties of cancer cells and their potential for improved diagnosis and treatment. Cancer cells exhibit unique mechanical and electrical properties, including altered stiffness, adhesion, charge, and shape, which distinguish them from normal cells. Researchers are exploring ways to use these properties to develop new diagnostic tools and therapeutic approaches that selectively target cancer cells while minimizing harm to healthy tissue. Recent advancements in machine learning (ML) have enhanced the analysis of cancer cell behavior, enabling more accurate identification based on electrical and mechanical "biomarkers" and offering the potential for early diagnosis and personalized treatment strategies. In this review, we will examine the most recent research on the mechanical and electrical properties of cancer cells and discuss their potential implications for enhancing the diagnosis and treatment of cancer.

Implantable cardioverter-defibrillators (ICDs) present several challenges regarding their detection, localization, and continuous monitoring within patients’ bodies. These challenges include maintaining the integrity of electrodes, preventing local tissue irritation, avoiding device displacement, and ensuring compatibility with MRI. Continuous monitoring is critical to ensure patient safety and the functional integrity of the devices. This paper systematically reviews approaches for the comprehensive monitoring of Cardiac Implantable Electronic Devices (CIEDs) over the past ten years, focusing on the CaRDIA-X procedure. We examine advanced protocols and integrated algorithms designed for this purpose. Specifically, we introduce the CaRDIA-X protocol, a manual method for identifying CIEDs based on the analysis of device patterns and the arrangement of elements on X-ray images. We compare this protocol with alternative detection methods, including artificial intelligence algorithms, and emphasize the field’s most significant studies and comprehensive comparative analyses. In conclusion, we propose improvements to the classic CaRDIA-X algorithm, focusing on automating the CaRDIA-X procedure, which holds significant potential for enhancing patient management and therapeutic efficacy. This integrated proposition offers a holistic perspective on CIED performance and potential issues.

Healthcare and medicine applications, which use motion tracking technology to support operators, effective address the problems of navigating in complex surgical spaces and smooth and flexible navigation of medical of instruments. This research focuses on the applications of Augmented Reality (AR) and Mixed Reality systems. We explore the use of the Microsoft HoloLens 2 to facilitate and enhance medical procedures that use motion tracking technology. Test experiments were realized to evaluate the effectiveness of motion tracking in AR using the HoloLens 2 equipment. Based on the results and the experience gained during the tests, conclusions and future directions were formulated. The conducted tests showed that motion tracking based on optical see-through Head Mounted Display technology still requires improvements and research, before they can be used in healthcare and medical applications.

Synovitis, characterized by inflammation of the synovial membrane in human joints, poses significant diagnostic and treatment challenges. This review presents methods and recent machine learning (ML) developments to analyze synovial arthritis in joints that help overcome these challenges. The methods described in the review include traditional ML algorithms, novel deep learning architectures and recent medical imaging techniques. Key challenges are discussed including the need for large and diverse datasets, model interpretability, generalization to different patient populations, dealing with data variability, and reducing computational complexity. The review also examines integrating multimodal data sources, advances in transfer learning, and developing robust, interpretable models as future directions. It includes enhancing early diagnostic capabilities, leveraging joint-on-a-chip simulations, and investigating signaling pathways in rheumatoid arthritis. This study aims to provide a consolidated resource for interdisciplinary researchers, clinicians and practitioners in the fields of rheumatology and medical imaging as it synthesizes current research to understand better ML methods in the detection of synovitis in human joints, paving the way for improved diagnostic and care capabilities over the patient.

This study aims to analyze and compare classical and deep learning-based methods for medical image segmentation, focusing on chest X-ray images containing cardiac implantable electronic devices. A complete processing pipeline was developed, including mask extraction, data preprocessing, and model training and evaluation. Several deep learning architectures were implemented and tested, such as DeepLabv3+ with a ResNet-50 backbone, U-Net, MONAI-based U-Net, and SegResNet, along with classical image processing techniques including deconvolution, contrast enhancement, and edge detection. The model’s performance was evaluated using standard segmentation metrics, including mean Intersection over Union (mIoU), Dice coefficient, pixel accuracy, and Specificity. The results demonstrate that the U-Net architecture combined with extended preprocessing achieved the highest overall segmentation accuracy, while the ResNet-50-based model obtained the best Specificity, reducing false positives. In contrast, the MONAI-based U-Net performed the weakest across all tested configurations. Furthermore, preprocessing techniques such as CLAHE and morphological transformations have enhanced segmentation quality, particularly for low-contrast and complex anatomical structures. The findings highlight the importance of data preparation and model selection in biomedical image segmentation tasks and confirm the potential of integrating classical preprocessing with deep learning approaches to improve the detection of medical device leads in X-ray imaging.

Synovitis is the inflammation of a synovial membrane surrounding a joint. Its assessment is an important step in the diagnosis and treatment of rheumatoid arthritis. Joint detection is the first stage of an automated method of assessment of a degree of synovitis, from an Ultrasound (USG) image of a finger joint and its surrounding area. A joint detector consists of three parts: image preprocessing, feature extraction, and classification. Each part contains adjustable parameters that must be set experimentally to ensure the proper operation of the detector. Both the structure of a joint detector and a procedure for finding a near-optimal configuration of the adjustable parameters are described. The optimization process is based on two evaluation measures: Area Under the Receiver Operating Characteristic Curve (AUC) and False Positive Count (FPC). The optimization process decreases the number of pictures with multiple detections, which was the main point of works presented in this paper. This was achieved by increasing the number of components of the homogeneous mixed-SURF descriptor which has the greatest influence on the final result. Non-SURF descriptors achieve poorer classification results. Our research led to the creation of a better joint detector which could positively influence the final results of inflammation level classification.

This research paper discusses the current state of Internet of Things (IoT) security in relation to smart bot technology and suggests actions to mitigate IoT weaponization threats. One of the most dangerous cyberattack activities is infecting IoT devices with malware to gain control of their operations. This allows attackers to combine the computational power of infected devices to form a botnet, which can then be used to carry out Distributed Denial of Service (DDoS) attacks against specified IP addresses. The aim is to overwhelm the target IP address servers with requests and prevent them from servicing legitimate requests from other users, thereby degrading the availability of the target's services and resources. This paper aims to analyze IoT DDoS attacks or weaponization of IoT to determine the most effective methods of eliminating such threats and preventing serious damage to IoT infrastructure and business-related data. We will describe what IoT weaponization malware is, outline its features, and discuss the most common IoT malware currently present on the Internet. We will then analyze the Mirai source code to fully understand its qualities, including attack types and operations, that allowed it to remain effective.

The paper deals with the issue of comparing trajectories in augmented and mixed realities incorporated in medical and healthcare systems. The comparison process brings to a sequence of comparing pairs of elements of these trajectories. We match up pairs using either time-domain mapping or projection in Euclidean space. The suitability of matched up pairs are assessed based on gold standard Dynamic Time Wrapping method. Finally, we propose two similarity relations which incorporate the idea of coordination space and position vectors.

The study of Japanese fencing and German Longsword Mastercuts based on exact motion measurements in specialist labs is summarized in this work. Based on a streamlined measuring technique, the need for a more thorough study has been suggested that might apply to the observation and evaluation of movement during training in a real-world setting. The requisite data sets and domain knowledge must be available to create motion analysis methods of human sword combat. Such information helps compare several algorithms and techniques, and develop and test new computational methods. In 2020, we created one of the world's first reference databases of fencing actions, which included five master long sword strikes with kinetic, kinematic, and video modalities. We were able to assess these movements and suggest potential study directions thanks to the created methods and algorithms. This paper proposes to extend the presented registration technologies for long swords and swordsmanship to similar combat, such as Japanese Kendo sword fencing.

Ultrashort electric pulses in the nanosecond range (nsPEF) can affect extra-and intracellular lipid structures and can also alternate cell functioning reversibly and irreversibly. Several of the nsPEF effects are due to the abrupt rise in intracellular free calcium levels and calcium ions influx from the outside. Calcium is one of the most important factors in cell proliferation, differentiation, and cell death (apoptosis or necrosis). Manipulating cal-cium levels using electroporation can have different effects on normal and malignant cells. This study aimed to examine the impact of nsPEFs, combined with 1 mM Ca2+ in human colon adenocarcinoma cell lines: sensitive-LoVo and drug resistant-LoVoDX. In this study 200 pulses of 10 ns and high voltage (12.5-50 kVcm(-1)) were used. Cell viability was determined by MTT and clonogenic assay. Proteasomal activity, GSH/GSSG assay, ROS pro-duction, and PALS-1 protein were evaluated as oxidative stress markers and protein damage. Cell morphology was visualized by AFM, SEM, and confocal microscopy imaging. The results revealed that nsPEF with 1 mM Ca2+ is cytotoxic, particularly for LoVoDX cells, and safe for normal cells. NsPEF provoked ROS release, altered cell polarity, and destabilized cell morphology. These results can be important for future protocols for colon adenocarcinoma using calcium nsPEF.

In today's world, it is becoming essential to be able to complete the authentication steps and provide the access to computer systems or other resources without having to require specific proximity or neutral expressions. Modern multiview facial authentication and access control often involve the ability to capture a face from the front or from the side and use these views for authentication and access control. This paper explores various cases of implementation of effective authentication and access control for human users without considering specific context, proximity, and environmental factors. Access control represents a crucial task in application areas such as surveillance, proof of identity, and tracking. While significant research has been conducted in the direction of human authentication and access control, completing authentication with an explainable process is still far from being perfect under the currently deployed techniques. This is mainly due to depending on machine learning to create behind-the-scene calculations that the user may not fully understand. Another issue is the requirement of distance approximation to the device and possibly a neutral posture or facial expressions of the user as discussed in discussed cases.

The paper presents a comprehensive overview of intelligent video analytics and human action recognition methods. The article provides an overview of the current state of knowledge in the field of human activity recognition, including various techniques such as pose-based, tracking-based, spatio-temporal, and deep learning-based approaches, including visual transformers. We also discuss the challenges and limitations of these techniques and the potential of modern edge AI architectures to enable real-time human action recognition in resource-constrained environments.

Nanosecond (ns) pulsed electric field (PEF) is a technology in which the application of ultra-short electrical pulses can be used to disrupt the barrier function of cell plasma and internal membranes. Disruptions of the membrane integrity cause a substantial imbalance in cell homeostasis in which oxidative stress is a principal component. In the present study, nsPEF-induced oxidative stress was investigated in two gastric adenocarcinoma cell lines (EPG85-257P and EPG85-257RDB) which differ by their sensitivity to daunorubicin. Cells were exposed to 200 pulses of 10 ns duration, with the amplitude and pulse repetition frequency at 1 kHz, with electric field intensity varying from 12.5 to 50 kV/cm. The electroporation buffer contained either 1 mM or 2 mM calcium chloride. CellMask DeepRed visualized cell plasma permeabilization, Fluo-4 was used to visualize internal calcium ions content, and F-actin was labeled with AlexaFluor®488 for the cytoskeleton. The cellular viability was determined by MTT assay. An alkaline and neutral comet assay was employed to detect apoptotic and necrotic cell death. The luminescent method estimated the modifications in GSSG/GSH redox potential and the imbalance of proteasomal activity (chymotrypsin-, trypsin- and caspase-like). The reactive oxygen species (ROS) level was measured by flow cytometry using dihydroethidium (DHE) dye. Morphological visualization indicated cell shrinkage, affected cell membranes (characteristic bubbles and changed cell shape), and the reorganization of actin fibers with sites of its dense concentration; the effect was more intense with the increasing electric field strength. The most significant decrease in cell viability and GSSG/GSH redox potential was noted at the highest amplitude of 50 kV/cm, and calcium ions amplified this effect. nsPEF, particularly with calcium ions, inhibited proteasomal activities, resulting in increased protein degradation. nsPEF increased the percentage of apoptotic cells and ROS levels. The EPG85-257 RDB cell line, which is resistant to standard chemotherapy, was more sensitive to applied nsPEF protocols. The applied nsPEF method disrupted the metabolism of cancer cells and induced apoptotic cell death. The nsPEF ability to cause apoptosis, oxidative stress, and protein degradation make the nsPEF methodology a suitable alternative to current anticancer pharmacological methods.

This paper discusses an application of motion capture in longsword fencing, a discipline experiencing rising popularity since the 1990s. Historical European Martial Arts alliance focuses on re-enacting the Late Middle Ages and Renaissance fighting styles. To popularize this art, novel research to automatically distinguish selected sword cutting techniques has been conducted. The fencing knowledge required for conducting this research was based on publications and consultation with experts in the field, and recordings. For this research, different movements from Masterstrikes such as Zornhau (Strike of Wrath), Schielhau (Squinting Strike), Zwerchhau (Cross Strike), Krumphau (Crooked Strike), Scheitelhau (Crown Strike) were selected. Motions performed by an adept fencer (acting expert) were used as patterns of correct strikes and compared with the movements of fencing amateurs. The main goal of this research was to measure the precision of movement while performing five different fencing strokes. Each movement was recorded with 39 unique full-body plug-in gait configurations initially designed for medical applications. During the exercise, 16 EMG electrodes configuration was used for the measurement of muscle activity.

Many health professionals do not use correct person transfer techniques in their daily practice. This results in damage to the paraspinal musculature over time, resulting in lower back pain and injuries. In this work, we propose an approach for the accurate multimodal measurement of people lifting and related motion patterns for ergonomic education regarding the application of correct patient transfer techniques. Several examples of person lifting were recorded and processed through accurate instrumentation and the well-defined measurements of kinematics, kinetics, surface electromyography of muscles as well as multicamera video. This resulted in a complete measurement protocol and unique reference datasets of correct and incorrect lifting schemes for caregivers and patients. This understanding of multimodal motion patterns provides insights for further independent investigations.

This work introduces the Extracted Tags - EXTags, a short form of data extracted from a massive amount of multimodal human motion data for efficient human motion analysis. EXTags describe the only crucial space-time features from motion data in a certain period. We demonstrate how such brief representation might be a handful in an analysis of the patient transport situation from the point of view of the ergonomics of transporting people.