Search Results (236)

Facial expression recognition (FER) is a critical research direction in artificial intelligence, which is widely used in intelligent interaction, medical diagnosis, security monitoring, and other domains. These applications highlight its considerable practical value and social significance. Face expression recognition models often need to run efficiently on mobile devices or edge devices, so the research on lightweight face expression recognition is particularly important. However, feature extraction and classification methods of lightweight convolutional neural network expression recognition algorithms mostly used at present are not specifically and fully optimized for the characteristics of facial expression images, yet fail to make full use of the feature information in face expression images. To address the lack of facial expression recognition models that are both lightweight and effectively optimized for expression-specific feature extraction, this study proposes a novel network design tailored to the characteristics of facial expressions. In this paper, we refer to the backbone architecture of MobileNet V2 network, and redesign LightExNet, a lightweight convolutional neural network based on the fusion of deep and shallow layers, attention mechanism, and joint loss function, according to the characteristics of the facial expression features. In the network architecture of LightExNet, firstly, deep and shallow features are fused in order to fully extract the shallow features in the original image, reduce the loss of information, alleviate the problem of gradient disappearance when the number of convolutional layers increases, and achieve the effect of multi-scale feature fusion. The MobileNet V2 architecture has also been streamlined to seamlessly integrate deep and shallow networks. Secondly, by combining the own characteristics of face expression features, a new channel and spatial attention mechanism is proposed to obtain the feature information of different expression regions as much as possible for encoding. Thus improve the accuracy of expression recognition effectively. Finally, the improved center loss function is superimposed to further improve the accuracy of face expression classification results, and corresponding measures are taken to significantly reduce the computational volume of the joint loss function. In this paper, LightExNet is tested on the three mainstream face expression datasets: Fer2013, CK+ and RAF-DB, respectively, and the experimental results show that LightExNet has 3.27 M Parameters and 298.27 M Flops, and the accuracy on the three datasets is 69.17%, 97.37%, and 85.97%, respectively. The comprehensive performance of LightExNet is better than the current mainstream lightweight expression recognition algorithms such as MobileNet V2, IE-DBN, Self-Cure Net, Improved MobileViT, MFN, Ada-CM, Parallel CNN(Convolutional Neural Network), etc. Experimental results confirm that LightExNet effectively improves recognition accuracy and computational efficiency while reducing energy consumption and enhancing deployment flexibility. These advantages underscore its strong potential for real-world applications in lightweight facial expression recognition. Full article

As multimedia technologies evolve, digital images have become increasingly prevalent across various fields, highlighting an urgent demand for robust image privacy and security mechanisms. However, existing image encryption algorithms (IEAs) still face limitations in balancing strong security, real-time performance, and computational efficiency. Therefore, we proposes a new IEA that integrates an improved chaotic map (Tent map), an improved Zigzag transform, and dynamic DNA coding. Firstly, a pseudo-wavelet transform (PWT) is applied to plain images to produce four sub-images $I_1$, $I_2$, $I_3$, and $I_4$. Secondly, the improved Zigzag transform and its three variants are used to rearrange the sub-image $I_1$, and then the scrambled sub-image is diffused using XOR operation. Thirdly, an inverse pseudo-wavelet transform (IPWT) is employed on the four sub-images to reconstruct the image, and then the reconstructed image is encoded into a DNA sequence utilizing dynamic DNA encoding. Finally, the DNA sequence is scrambled and diffused employing DNA-level index scrambling and dynamic DNA operations. The experimental results and performance evaluations, including chaotic performance evaluation and comprehensive security analysis, demonstrate that our IEA achieves high key sensitivity, low correlation, excellent entropy, and strong resistance to common attacks. This highlights its potential for deployment in real-time, high-security image cryptosystems, especially in fields such as medical image security and social media privacy. Full article

Artificial intelligence (AI) has already played a significant role in the healthcare sector, particularly in image-based medical diagnosis. Deep learning models have produced satisfactory and useful results for accurate decision-making. Among the various types of medical images, magnetic resonance imaging (MRI) is frequently utilized in deep learning applications to analyze detailed structures and organs in the body, using advanced intelligent software. However, challenges related to performance and data privacy often arise when using medical data from patients and healthcare institutions. To address these issues, new approaches have emerged, such as federated learning. This technique ensures the secure exchange of sensitive patient and institutional data. It enables machine learning or deep learning algorithms to establish a client–server relationship, whereby specific parameters are securely shared between models while maintaining the integrity of the learning tasks being executed. Federated learning has been successfully applied in medical settings, including diagnostic applications involving medical images such as MRI data. This research introduces an analytical intelligence system based on an Internet of Medical Things (IoMT) framework that employs federated learning to provide a safe and effective diagnostic solution for brain tumor identification. By utilizing specific brain MRI datasets, the model enables multiple local capsule networks (CapsNet) to achieve improved classification results. The average accuracy rate of the CapsNet model exceeds 97%. The precision rate indicates that the CapsNet model performs well in accurately predicting true classes. Additionally, the recall findings suggest that this model is effective in detecting the target classes of meningiomas, pituitary tumors, and gliomas. The integration of these components into an analytical intelligence system that supports the work of healthcare personnel is the main contribution of this work. Evaluations have shown that this approach is effective for diagnosing brain tumors while ensuring data privacy and security. Moreover, it represents a valuable tool for enhancing the efficiency of the medical diagnostic process. Full article

This study proposes an optimized footprint recognition model based on an enhanced StarNet architecture for biometric identification in the security, medical, and criminal investigation fields. Conventional image recognition algorithms exhibit limitations in processing barefoot footprint images characterized by concentrated feature distributions and rich texture patterns. To address this, our framework integrates an improved StarNet into the backbone of YOLOv8 architecture. Leveraging the unique advantages of element-wise multiplication, the redesigned backbone efficiently maps inputs to a high-dimensional nonlinear feature space without increasing channel dimensions, achieving enhanced representational capacity with low computational latency. Subsequently, an Encoder layer facilitates feature interaction within the backbone through multi-scale feature fusion and attention mechanisms, effectively extracting rich semantic information while maintaining computational efficiency. In the feature fusion part, a feature modulation block processes multi-scale features by synergistically combining global and local information, thereby reducing redundant computations and decreasing both parameter count and computational complexity to achieve model lightweighting. Experimental evaluations on a proprietary barefoot footprint dataset demonstrate that the proposed model exhibits significant advantages in terms of parameter efficiency, recognition accuracy, and computational complexity. The number of parameters has been reduced by 0.73 million, further improving the model’s speed. Gflops has been reduced by 1.5, lowering the performance requirements for computational hardware during model deployment. Recognition accuracy has reached 99.5%, with further improvements in model precision. Future research will explore how to capture shoeprint images with complex backgrounds from shoes worn at crime scenes, aiming to further enhance the model’s recognition capabilities in more forensic scenarios. Full article

Digital images have been widely applied in fields such as mobile devices, the Internet of Things, and medical imaging. Although significant progress has been made in image encryption technology, it still faces many challenges, such as attackers using powerful computing resources and advanced algorithms to crack encryption systems. To address these challenges, this paper proposes a novel image encryption algorithm based on one-dimensional sawtooth wave chaotic system (1D-SAW) and the three-strand structure of DNA. Firstly, a new 1D-SAW chaotic system was designed. By introducing nonlinear terms and periodic disturbances, this system is capable of generating chaotic sequences with high randomness and initial value sensitivity. Secondly, a new diffusion rule based on the three-strand structure of DNA is proposed. Compared with the traditional DNA encoding and XOR operation, this rule further enhances the complexity and anti-attack ability of the encryption process. Finally, the security and randomness of the 1D-SAW and image encryption algorithms were verified through various tests. Results show that this method exhibits better performance in resisting statistical attacks and differential attacks. Full article

Combining a large collection of patient data and advanced technology, healthcare organizations can excel in medical research and increase the quality of patient care. At the same time, health records present serious privacy and security challenges because they are confidential and can be breached through networks. Even traditional methods with federated learning are used to share data, patient information might still be at risk of interference while updating the model. This paper proposes the Privacy-Preserving Federated Learning with Homomorphic Encryption (PPFLHE) framework, which strongly supports secure cooperation in healthcare and at the same time providing symmetric privacy protection among participating institutions. Everyone in the collaboration used the same EfficientNet-B0 architecture and training conditions and keeping the model symmetrical throughout the network to achieve a balanced learning process and fairness. All the institutions used CKKS encryption symmetrically for their models to keep data concealed and stop any attempts at inference. Our federated learning process uses FedAvg on the server to symmetrically aggregate encrypted model updates and decrease any delays in our server communication. We attained a classification accuracy of 83.19% and 81.27% when using the APTOS 2019 Blindness Detection dataset and MosMedData CT scan dataset, respectively. Such findings confirm that the PPFLHE framework is generalizable among the broad range of medical imaging methods. In this way, patient data are kept secure while encouraging medical research and treatment to move forward, helping healthcare systems cooperate more effectively. Full article

Background/Objectives: Artificial intelligence (AI) holds great potential to reshape the academic paradigm. They can process large volumes of information, assist in academic literature reviews, and augment the overall quality of scientific discourse. This narrative review examines the application of various AI tools in surgical research, its present capabilities, future directions, and potential challenges. Methods: A search was performed by two independent authors for relevant studies on PubMed, Cochrane Library, Web of Science, and EMBASE databases from January 1901 until March 2025. Studies were included if they were written in English and discussed the use of AI tools in surgical research. They were excluded if they were not in English and discussed the use of AI tools in medical research. Results: Forty-two articles were included in this review. The findings underscore a range of AI tools such as writing enhancers, LLMs, search engine optimizers, image interpreters and generators, content organization and search systems, and audio analysis tools, along with their influence on medical research. Despite the multitude of benefits presented by AI tools, risks such as data security, inherent biases, accuracy, and ethical dilemmas are of concern and warrant attention. Conclusions: AI could offer significant contributions to medical research in the form of superior data analysis, predictive abilities, personalized treatment strategies, enhanced diagnostic accuracy, amplified research, educational, and publication processes. However, to unlock the full potential of AI in surgical research, we must institute robust frameworks and ethical guidelines. Full article

Medical clinical images have a larger number of bits, and real-time and robust medical encryption systems with a high security level, a large key space, high unpredictability, better bifurcation behavior, low computational complexity, and good encryption outcomes are significant design challenges. Chaotic medical image encryption (MIE) has become an important research area in advanced MIE strategies. Chaotic MIE technology can be used in medical image storage systems, cloud-based medical systems, healthcare systems, telemedicine, mHealth, picture archiving and communication systems, digital imaging and communication in medicine, and telehealth. This study focuses on several basic frameworks for chaos-based MIE. Multiple chaotic maps, robust chaos-based techniques, and fast and simple chaotic system designs of chaos-based MIE are demonstrated. The major technical notes, features and effectiveness of chaos-based MIE are investigated for future research directions. The chaotic maps of MIE are illustrated, and security evaluation methods for chaos-based MIE are explored. Design issues in the implementation of chaos-based MIE are demonstrated. The findings can inspire researchers to design an innovative, advanced chaos-based MIE system to better protect MIs against attacks and ensure robust MIE. Full article

Medical images demand robust privacy protection, driving research into advanced image encryption (IE) schemes. However, current IE schemes still encounter certain challenges in both security and efficiency. Fractional-order Hopfield neural networks (HNNs) demonstrate unique advantages in IE. The introduction of fractional-order calculus operators enables them to possess more complex dynamical behaviors, creating more random and unpredictable keystreams. To enhance privacy protection, this paper introduces a high-performance medical IE scheme that integrates a novel 4D fractional-order HNN with a differentiated encryption strategy (MIES-FHNN-DE). Specifically, MIES-FHNN-DE leverages this 4D fractional-order HNN alongside a 2D hyperchaotic map to generate keystreams collaboratively. This design not only capitalizes on the 4D fractional-order HNN’s intricate dynamics but also sidesteps the efficiency constraints of recent IE schemes. Moreover, MIES-FHNN-DE boosts encryption efficiency through pixel bit splitting and weighted accumulation, ensuring robust security. Rigorous evaluations confirm that MIES-FHNN-DE delivers cutting-edge security performance. It features a large key space ($2^{383}$), exceptional key sensitivity, extremely low ciphertext pixel correlations (<0.002), excellent ciphertext entropy values (>7.999 bits), uniform ciphertext pixel distributions, outstanding resistance to differential attacks (with average NPCR and UACI values of $99.6096\%$ and $33.4638\%$, respectively), and remarkable robustness against data loss. Most importantly, MIES-FHNN-DE achieves an average encryption rate as high as 102.5623 Mbps. Compared with recent leading counterparts, MIES-FHNN-DE better meets the privacy protection demands for medical images in emerging fields like medical intelligent analysis and medical cloud services. Full article

With the dynamic development of imaging technologies and increasing demands in various industrial fields, neural networks are playing a crucial role in advanced design, monitoring, and analysis techniques. This review article presents the latest research advancements in neural network-based imaging, thermal, infrared, and X-ray technologies from 2005 to 2024. It focuses on two main research categories: ‘Technology’ and ‘Application’. The ‘Technology’ category includes neural network-enhanced image sensors, thermal imaging, infrared detectors, and X-ray technologies, while the ‘Application’ category is divided into image processing, robotics and design, object recognition, medical imaging, and security systems. In image processing, significant progress has been made in classification, segmentation, digital image storage, and information classification using neural networks. Robotics and design have seen advancements in mobile robots, navigation, and machine design through neural network integration. Object recognition technologies include neural network-based object detection, face recognition, and pattern recognition. Medical imaging has benefited from innovations in diagnosis, imaging techniques, and disease detection using neural networks. Security systems have improved in terms of monitoring and efficiency through neural network applications. This review aims to provide a comprehensive understanding of the current state and future directions of neural network-based imaging, thermal, infrared, and X-ray technologies. Full article

In this study, Lu_2.5Y_0.5(Al_2.5Ga_2.5)O₁₂ (LuYAGG) single-crystal scintillators doped with terbium ions (Tb³⁺) at concentrations of 0.5, 1, 5, and 10 mol% were successfully synthesized using the floating zone method. The structural, optical, photoluminescence (PL), and scintillation properties of the Tb³⁺-doped crystals were systematically investigated with a focus on their potential for high-performance scintillator applications. X-ray diffraction (XRD) confirmed the formation of a pure garnet phase without any secondary phases, indicating the successful incorporation of Tb³⁺ into the LuYAGG lattice. Optical transmittance spectra revealed high transparency in the visible range. Photoluminescence measurements showed characteristic Tb³⁺ emission peaks, with the strongest green emission observed from the ⁵D₄ → ⁷F₅ transition, particularly for the 5 mol% sample. The PL decay curves further confirmed that this concentration offers a favorable balance between radiative efficiency and minimal non-radiative losses. Under γ-ray excitation, the 5 mol% Tb³⁺-doped crystal exhibited the highest light yield, surpassing the performance of other concentrations and even outperforming Bi₄Ge₃O₁₂ (BGO) in relative comparison, with an estimated yield of approximately 60,000 photons/MeV. Scintillation decay time analysis revealed that the 5 mol% sample also possessed the fastest decay component, indicating its superior capability for radiation detection. Although 10 mol% Tb³⁺ still showed good performance, slight quenching effects were observed, while lower concentrations (0.5 and 1 mol%) suffered from longer decay and lower emission efficiency due to limited activator density. These findings clearly identify with 5 mol% Tb³⁺ as the optimal dopant level in LuYAGG single crystals, offering a synergistic combination of high light yield and excellent optical transparency. This work highlights the strong potential of LuYAGG:Tb³⁺ as a promising candidate for the next-generation scintillator materials used in medical imaging, security scanning, and high-energy physics applications. Full article

Background: Medical photography is widely used in dermatology referrals to secondary healthcare, yet concerns exist regarding image quality and data security. This study aimed to evaluate the quality of clinical photographs used in dermatology referrals, to identify discrepancies between specialties’ perceptions, and to determine the general awareness of proper storage and security of clinical photographs. Methods: A 43-question survey, based on previously validated questionnaires, was administered to general and family medicine (GFM) doctors and to dermatologists at an academic referral hospital in Porto, Portugal. The survey assessed demographics, photo-taking habits, perceived photo quality, adequacy of clinical information, and opinions on the role of photography in the referral process. Quantitative statistical methods were used to analyze questionnaire responses. Results: A total of 65 physicians participated (18 dermatologists and 47 GFM doctors). Significant differences were observed between the two groups. While 36.2% of GFMs rated their submitted photos as high- or very-high-quality, none of the dermatologists rated the received photos as high-quality, with 83.3% rating them as average (p = 0.012). Regarding clinical information, 46.8% of GFMs reported consistently sending enough information, while no dermatologists reported always receiving sufficient information (p < 0.001). Most respondents (76.9%) agreed that the quality of photographs is important in diagnosis and treatment. Conclusions: The findings reveal a discrepancy between GFM doctors’ and dermatologists’ perceptions of photograph quality and information sufficiency in dermatology referrals. Standardized guidelines and educational interventions are necessary to improve the quality and consistency of clinical photographs, thereby enhancing communication between healthcare providers and ensuring patient data privacy and security. Full article

Multimodal artificial intelligence (AI) is driving a paradigm shift in modern biomedicine by seamlessly integrating heterogeneous data sources such as medical imaging, genomic information, and electronic health records. This review explores the transformative impact of multimodal AI across three pivotal areas: biomaterials science, medical diagnostics, and personalized medicine. In the realm of biomaterials, AI facilitates the design of patient-specific solutions tailored for tissue engineering, drug delivery, and regenerative therapies. Advanced tools like AlphaFold have significantly improved protein structure prediction, enabling the creation of biomaterials with enhanced biological compatibility. In diagnostics, AI systems synthesize multimodal inputs combining imaging, molecular markers, and clinical data—to improve diagnostic precision and support early disease detection. For precision medicine, AI integrates data from wearable technologies, continuous monitoring systems, and individualized health profiles to inform targeted therapeutic strategies. Despite its promise, the integration of AI into clinical practice presents challenges such as ensuring data security, meeting regulatory standards, and promoting algorithmic transparency. Addressing ethical issues including bias and equitable access remains critical. Nonetheless, the convergence of AI and biotechnology continues to shape a future where healthcare is more predictive, personalized, and responsive. Full article

Introduction: Testicular cancer (TC) is diagnosed at a young age and carries a remarkably high cure rate. Hence, there is a sizeable population living in the survivorship phase. Many studies have highlighted the plight of TC survivors as a result of the late side-effects of the different therapeutic modalities used for the treatment of TC. This is the first study in Ireland to highlight the impact of TC on socio-economic health, sexual health, and fertility in survivors. Method: We performed a questionnaire-based survey, which was fully anonymised to encourage participation. Questionnaires were designed to measure the self-reported impact on social, sexual, and economic health on a five-point Likert scale (ranging from no effect to very significant effect), whereas any effect on fertility was investigated with questions regarding biological children before and after cancer with or without medical assistance. Results: A total of 83 TC survivors participated in the study. Almost half of our respondents revealed some effect on their performance at work and personal finances. Around one-third suffered an impact on career choice, job security, and their relationship with their partner. Regarding sexual health, the worst repercussions were noted on sex drive and body image perception, where close to half of the respondents reported at least some deterioration. Ejaculation and erectile function were affected in 30% of the participants. Of all participants, 17% reported issues with fertility, and the same proportion reported seeking medical help to conceive after diagnosis or treatment of TC. Conclusions: In conclusion, some TC survivors experience significant impact on their socio-economic and sexual health. Full article

Data security is critical, particularly in medical imaging, yet remains challenging. Many research efforts have focused on enhancing medical image security, particularly during network transmission. Ensuring confidentiality and authenticity is a key priority for researchers. However, traditional encryption methods are unsuitable for IoT environments due to data size limitations. Lightweight encryption algorithms that preserve confidentiality, integrity, and authenticity can address these limitations. This paper proposes an efficient, lightweight method to encrypt and authenticate medical images in healthcare systems. The approach splits images into diagonal and non-diagonal blocks, and then processes them in two phases: (1) non-diagonal blocks are permuted using inter-block differences and XORed with diagonal blocks for substitution; (2) diagonal blocks are encrypted via AES and enhanced CBC mode with a tag mechanism for integrity. Security tests (histograms, correlation, entropy, NPCR, UACI) verify the scheme’s robustness. The results show that the model outperforms existing techniques in efficacy and attack resistance, making it viable for medical IoT and smart surveillance. Full article