From Pixels to Information: Artificial Intelligence in Fluorescence Microscopy

Introduction Serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN) often exhibit similar imaging features when evaluated with a single imaging modality. Differentiating between SCN and MCN typically necessitates the utilization of multiple imaging techniques, including computed tomography (CT), magnetic resonance imaging (MRI), and endoscopic ultrasonography (EUS). Recent research indicates that artificial intelligence (AI) can effectively distinguish between SCN and MCN using single-modal imaging. Despite these advancements, the diagnostic performance of AI has not yet reached an optimal level. This study compares the efficacy of AI in classifying SCN and MCN using multimodal imaging versus single-modal imaging. The objective was to assess the effectiveness of AI utilizing multimodal imaging with EUS, CT, and MRI to classify these two types of pancreatic cysts. Methods We retrospectively gathered data from 25 patients with surgically confirmed SCN and 24 patients with surgically confirmed MCN as part of a multicenter study. Imaging was conducted using four modalities: EUS, early-phase contrast-enhanced abdominal CT, T2-weighted MRI, and magnetic resonance pancreatography. Four images per modality were obtained for each tumor. Data augmentation techniques were utilized, resulting in a final dataset of 39,200 images per modality. An AI model with ResNet was employed to categorize the cysts as SCN or MCN, incorporating clinical features and combinations of imaging modalities (single, double, triple, and all four modalities). The classification outcomes were compared with those of five experienced gastroenterologists with over 10 years of experience. The comparison is based on three performance metrics: sensitivity, specificity, and accuracy. Results For AI utilizing a single imaging modality, the sensitivity, specificity, and accuracy were 87.0%, 92.7%, and 90.8%, respectively. Combining two imaging modalities improved the sensitivity, specificity, and accuracy to 95.3%, 95.1%, and 94.9%. With three modalities, AI achieved a sensitivity of 96.0%, a specificity of 99.0%, and an accuracy of 97.0%. Ultimately, employing all four imaging modalities resulted in AI achieving 98.0% sensitivity, 100% specificity, and 99.0% accuracy. In contrast, experts utilizing all four modalities attained a sensitivity of 78.0%, specificity of 82.0%, and accuracy of 81.0%. The AI models consistently outperformed the experts across all metrics. A continuous enhancement in performance was observed with each additional imaging modality, with AI utilizing three and four modalities significantly surpassing single-modal imaging AI. Conclusion AI utilizing multimodal imaging offers better performance compared to both single-modal imaging AI and experienced human experts in classifying SCN and MCN.

Biological intelligence is remarkable in its ability to produce complex behavior in many diverse situations through data efficient, generalizable, and transferable skill acquisition. It is believed that learning “good” sensory representations is important for enabling this, however there is little agreement as to what a good representation should look like. In this review article we are going to argue that symmetry transformations are a fundamental principle that can guide our search for what makes a good representation. The idea that there exist transformations (symmetries) that affect some aspects of the system but not others, and their relationship to conserved quantities has become central in modern physics, resulting in a more unified theoretical framework and even ability to predict the existence of new particles. Recently, symmetries have started to gain prominence in machine learning too, resulting in more data efficient and generalizable algorithms that can mimic some of the complex behaviors produced by biological intelligence. Finally, first demonstrations of the importance of symmetry transformations for representation learning in the brain are starting to arise in neuroscience. Taken together, the overwhelming positive effect that symmetries bring to these disciplines suggest that they may be an important general framework that determines the structure of the universe, constrains the nature of natural tasks and consequently shapes both biological and artificial intelligence.

Fluorescence microscope applies high-intensity light to illuminate the substance that emits fluorescence light. The present chapter describes the basic principle and applications of fluorescence microscopy. There are two types of fluorescence microscope: transmitted fluorescent microscope and incident fluorescent microscope. The working principles of both these types of microscopes are described. The confocal fluorescence microscopy (CFM) provides three-dimensional optical resolution. In CFM, at one time we see the image of the particular depth of the object at a small point. All the out-of-focus light is eliminated by passing the light through the pinhole. Multiple images at different depth are accumulated and then reconstructed to provide a three-dimensional image. The working principle and applications of CFM are discussed in the present chapter.

This viewpoint article first explores the ethical challenges associated with the future application of large language models (LLMs) in the context of medical education. These challenges include not only ethical concerns related to the development of LLMs, such as artificial intelligence (AI) hallucinations, information bias, privacy and data risks, and deficiencies in terms of transparency and interpretability but also issues concerning the application of LLMs, including deficiencies in emotional intelligence, educational inequities, problems with academic integrity, and questions of responsibility and copyright ownership. This paper then analyzes existing AI-related legal and ethical frameworks and highlights their limitations with regard to the application of LLMs in the context of medical education. To ensure that LLMs are integrated in a responsible and safe manner, the authors recommend the development of a unified ethical framework that is specifically tailored for LLMs in this field. This framework should be based on 8 fundamental principles: quality control and supervision mechanisms; privacy and data protection; transparency and interpretability; fairness and equal treatment; academic integrity and moral norms; accountability and traceability; protection and respect for intellectual property; and the promotion of educational research and innovation. The authors further discuss specific measures that can be taken to implement these principles, thereby laying a solid foundation for the development of a comprehensive and actionable ethical framework. Such a unified ethical framework based on these 8 fundamental principles can provide clear guidance and support for the application of LLMs in the context of medical education. This approach can help establish a balance between technological advancement and ethical safeguards, thereby ensuring that medical education can progress without compromising the principles of fairness, justice, or patient safety and establishing a more equitable, safer, and more efficient environment for medical education.

Objective: The objective of this narrative review was to summarize and critically appraise current clinical applications of artificial intelligence (AI) in cardiology, with particular emphasis on arrhythmia detection and cardiovascular imaging modalities. Methods: A selective narrative review of peer-reviewed literature published between 2015 and 2025 was performed using PubMed, Scopus, and Web of Science. Studies were selected based on clinical relevance, validation methodology, and reported diagnostic or prognostic performance in human populations. Results: AI-based algorithms demonstrate diagnostic performance comparable to expert interpretation in atrial fibrillation (AF) detection as well as across echocardiography, coronary computed tomography angiography (CCTA), cardiac magnetic resonance imaging (CMR), and intravascular optical coherence tomography (OCT). Beyond diagnostic accuracy, AI has been shown to reduce analysis time and interobserver variability in controlled and retrospective study settings. However, the majority of available studies are retrospective, rely on curated datasets, and lack prospective validation demonstrating a direct impact on clinical outcomes. Conclusions: AI constitutes a valuable decision-support tool in contemporary cardiology, enhancing diagnostic efficiency and risk stratification across multiple imaging and electrophysiological modalities. Nevertheless, broader clinical adoption will require rigorous external validation, improved model interpretability, and prospective outcome-driven studies. This review uniquely integrates evidence across electrophysiology and multiple imaging modalities to identify shared translational challenges and near-term clinical opportunities for AI in cardiology.

Purpose. The study aims to understand artificial intelligence as a socio-cultural phenomenon and its impact on education, where the spiritual sphere of humanity, moral norms, values, and human cognitive abilities are preserved, transferred as well as reproduced. A new discourse on the interaction of artificial and authentic human intelligence becomes inevitable, which has led to a situation of uncertainty. Changes in the socio-cultural environment under the influence of artificial intelligence increase potential threats to the educational space, which stimulates to find the ways to eliminate them. Theoretical basis. Various approaches of classical and postmodern philosophical heritage were taken as a theoretical basis for the research. The originality of the study is in the interpretation of artificial intelligence as a modern form of alienation of essential human characteristics in the socio-cultural context of information technology. The expansion of artificial intelligence raises awareness of the existential threat to the basic socio-cultural, moral and ethical principles of humanism. It is proved that various forms of alienation in the current existing socio-cultural space are typical of our reality, which changes the system of values, moral principles, and social organization of the community. Conclusions. In conclusion, it is proved that AI is a natural stage of scientific and technological progress, which reflects its secondary, derivative nature from human (authentic) intelligence. Human intelligence will always have advantages over AI due to its ability to create, communicate socially and culturally, and be emotional. The dilemma of the counterbalance between human and artificial intelligence is perceived mainly at the emotional level of people. The millennial understanding of the primacy of the creator over his creation can traditionally overcome this contradiction. The universality of human thinking is an undeniable advantage of human intelligence and a guarantee of its, i.e. our, priority.

Background/Objectives: Artificial intelligence (AI) is rapidly transforming the landscape of modern medicine, offering advanced tools for diagnosing complex conditions. In the realm of venous pathologies such as chronic venous disease (CVD), venous reflux, and deep venous thrombosis (DVT), AI has shown tremendous potential to improve diagnostic accuracy, streamline workflows, and enhance clinical decision-making. This study aims to evaluate the efficacy and feasibility of AI algorithms in diagnosing venous diseases and explore their potential impact on clinical practice. Methods: This paper provides a comprehensive review of key studies documenting the use of AI in venous pathology diagnostics, with different electronic databases being searched, including MEDLINE/Pub Med, Web of Science, Scopus, Embase, ResearchGate, and Google Scholar. Results: Out of 52 reports assessed for eligibility, 43 were excluded according to the preset criteria; therefore, findings from nine major studies involving more than 1000 patients were analyzed. The evaluation shows that AI utilization in the diagnosis of venous pathologies has demonstrated significant improvements. Notably, AI algorithms have achieved an accuracy exceeding 90%, significantly reducing inter-observer variability and ensuring consistent interpretation of ultrasonographic images across different clinicians and settings. Additionally, AI has accelerated diagnostic workflows, decreasing the time required for image analysis by more than 50%. Furthermore, AI has proven capable of detecting subtle abnormalities, such as minor venous reflux or early-stage thrombi, which may be overlooked during manual evaluations. Conclusions: Artificial intelligence represents a transformative innovation in the diagnosis and management of venous diseases. By enhancing diagnostic accuracy, streamlining workflows, and enabling personalized care, AI has the potential to address current challenges in venous diagnostics and improve patient outcomes. The future of AI in venous diagnostics is promising, and several areas of development were noted, including AI algorithms embedding directly into ultrasound devices to provide instantaneous diagnostic insights during patient evaluations; combining AI-processed Doppler data with other imaging modalities, such as computed tomography or MRI, for comprehensive assessments; AI usage in order to predict disease progression and tailor treatment strategies based on individual patient profiles; and constructing large-scale, multicenter datasets to improve the robustness and generalizability of AI algorithms.

The research paper aims to study The Rise of Artificial Intelligence: A Boon or a Bane under Legal Regime. It will examine how the Artificial Intelligence (AI) in the real world refers in various domains and across various fields to boost innovation with transformative technology. The jurisprudential aspect highlights the philosophy of law concerning Artificial Intelligence along with its fundamental principles and moral values. It will analyse AI as a catalyst for progressing in today’s current era which symbolises the capacity of human intellect with AI through development in the modern day. AI as a positive footprint in the society understands the interaction of humans and AI. It will also examine the AI as a loss of human touch and its values where there is a gap between emotional connection between AI and human. The growing privacy challenges with regard to breach of personal data is a threat to human world. It will analyse the ethical and legal concerns of AI systems with lack of privacy and data protection. The growing dependence of AI poses challenges in security concerns. It will understand the AI in legal profession while providing legal services. It contrasts AI with major countries like The United States, The United Kingdom and The European Union as a comparative analysis. It will examine that how AI is truly a boon or a bane.

Simple SummaryDistinguishing between benign vs. malignant bone lesions is often difficult on imaging. Many bone lesions are infrequent or rarely seen, and often only specialist radiologists have sufficient expertise to provide an accurate diagnosis. In addition, some benign bone tumours may exhibit potentially aggressive features that mimic malignant bone tumours, making the diagnosis even more difficult. The rapid development of artificial intelligence (AI) techniques has led to remarkable progress in image-recognition tasks, including the classification and characterization of various tumours. This study will review the most recent evidence for AI techniques in differentiating bone lesions on various imaging modalities using a systematic approach. Potential clinical applications of AI techniques for clinical diagnosis and management of bone lesions will also be discussed.An accurate diagnosis of bone tumours on imaging is crucial for appropriate and successful treatment. The advent of Artificial intelligence (AI) and machine learning methods to characterize and assess bone tumours on various imaging modalities may assist in the diagnostic workflow. The purpose of this review article is to summarise the most recent evidence for AI techniques using imaging for differentiating benign from malignant lesions, the characterization of various malignant bone lesions, and their potential clinical application. A systematic search through electronic databases (PubMed, MEDLINE, Web of Science, and clinicaltrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 34 articles were retrieved from the databases and the key findings were compiled and summarised. A total of 34 articles reported the use of AI techniques to distinguish between benign vs. malignant bone lesions, of which 12 (35.3%) focused on radiographs, 12 (35.3%) on MRI, 5 (14.7%) on CT and 5 (14.7%) on PET/CT. The overall reported accuracy, sensitivity, and specificity of AI in distinguishing between benign vs. malignant bone lesions ranges from 0.44–0.99, 0.63–1.00, and 0.73–0.96, respectively, with AUCs of 0.73–0.96. In conclusion, the use of AI to discriminate bone lesions on imaging has achieved a relatively good performance in various imaging modalities, with high sensitivity, specificity, and accuracy for distinguishing between benign vs. malignant lesions in several cohort studies. However, further research is necessary to test the clinical performance of these algorithms before they can be facilitated and integrated into routine clinical practice.

Artificial Intelligence (AI) systems increasingly shape many aspects of daily life, influencing our jobs, finances, healthcare, and online content. This expansion has led to the rise of human–AI systems, where humans communicate, collaborate, or otherwise interact with AI, such as using AI outputs to make decisions. While these systems have shown potential to enhance human capabilities and improve performance on benchmarks, evidence suggests that they often underperform compared to AI‐only or human‐only approaches in experiments and real‐world applications. Here, we argue that human–AI systems should be developed with a greater emphasis on human‐centered factors—such as usability, fairness, trust, and user autonomy—within the algorithmic design and evaluation process. We advocate for integrating human‐centered principles into AI development through human‐centered algorithmic design and contextual evaluation with real users. Drawing on interdisciplinary research and our tutorial at two major AI conferences, we highlight examples and strategies for AI researchers and practitioners to embed these principles effectively. This work offers a systematic synthesis that integrates technical, practical, and ethical insights into a unified framework. Additionally, we highlight critical ethical considerations, including fairness, labor, privacy, and human agency to ensure that systems meet performance goals while serving broader societal interests. Through this work, we aim to inspire the field to embrace a truly human‐centered approach to algorithmic design and deployment.

Assessment of MRI technologists in acceptance and willingness to integrate artificial intelligence into practice

Artificial intelligence (AI) stands as a monumental breakthrough in the technological landscape of the past decade. The fusion of artificial intelligence (AI) with teaching strategies has emerged as a crucial driving force in contemporary education. Recently, AI has risen to prominence as a formidable ally in the realm of learning. Within the educational arena,artificial intelligence(AI) has become a revolutionary force, presenting innovative and exceptional solutions to age-old challenges while simultaneously forging new pathways for individualized and adaptable learning journeys. Amidst the digital upheaval, artificial intelligence (AI) has been intricately integrated into various educational frameworks, ranging from virtual learning experiences and data-driven forecasts to sophisticated tutoring systems and automated grading mechanisms. Its capacity to fundamentally reshape multiple sectors, affecting every facet of society, is especially apparent within the educational domain.AI holds the promise of transforming the educational landscape in its entirety by accommodating diverse learning preferences and enhancing the learning atmosphere. AI breathes freshness into pedagogy, thereby radically altering conventional teaching and learning techniques. This metamorphosis is driven by AI’s remarkable ability to juggle multiple tasks, such as intelligent tutoring, automated evaluations, and bespoke content delivery (Ray & Sikdar, 2023).This chapter elucidates the foundational role of AI in educational revolutions,outlining various methods of AI implementation in educational progress,current trends,and future research trajectories (Dey, 2024). Leveraging different AI technologies and algorithms for business and management education is the priority of this chapter.

With the increasing dominance of artificial intelligence (AI) techniques, the important prospects for their application have extended to various medical fields, including domains such as in vitro diagnosis, intelligent rehabilitation, medical imaging, and prognosis. Breast cancer is a common malignancy that critically affects women's physical and mental health. Early breast cancer screening-through mammography, ultrasound, or magnetic resonance imaging (MRI)-can substantially improve the prognosis for breast cancer patients. AI applications have shown excellent performance in various image recognition tasks, and their use in breast cancer screening has been explored in numerous studies. This paper introduces relevant AI techniques and their applications in the field of medical imaging of the breast (mammography and ultrasound), specifically in terms of identifying, segmenting, and classifying lesions; assessing breast cancer risk; and improving image quality. Focusing on medical imaging for breast cancer, this paper also reviews related challenges and prospects for AI.

Purpose This study has proposed a socially responsible approach towards artificial intelligence (AI) deployment and tested a revised AI device use acceptance (RAIDUA)-based conceptual model involving the potential indirect moderating role of consumers’ privacy concerns (PRCO) regarding AI-enabled devices. Design/methodology/approach The newly introduced RAIDUA model was verified with empirical data gathered from 280 respondents. A partial least square-driven methodology was used in the present study. Further, a simple slope analysis was also performed to assess the PRCO for their plausible moderating role. Findings Results confirmed a negative moderation impact of consumers’ PRCO in the interaction between perceived usefulness expectancy and consumers’ perceived emotions. Further moderation analysis confirmed that PRCO weakens the positive interaction between emotions and consumers’ expected willingness and/or desire to practically accept the use of AI-enabled devices, whereas there is a positive moderation effect of consumers’ PRCO in the negative interaction between perceived emotions and objection to the practical use of AI-enabled devices. Social implications This study has proposed AI usefulness expectancy as a socially responsible approach towards ethical AI deployment and tested the RAIDUA model for acceptance and integration of AI-enabled devices. Originality/value This study uniquely integrates AI usefulness expectancy along with perceived AI PRCO as a moderating factor in the RAIDUA model for AI adoption. Both aspects had been overlooked by frequently used Farooq et al.’s (2017) UTAUT-3, Gursoy et al.’s (2019) AIDUA and Salam et al.’s (2025) unified MOOC utilization model frameworks in AI literature. Therefore, we submit that the RAIDUA model offers a novel and original theoretical contribution in technology integration literature and AI adoption-related body of knowledge.

Artificial intelligence(AI)is transforming cancer medicine across three key domains. First, AI enables the conversion of unstructured visual data-such as pathology slides and radiological images-into structured, quantifiable formats. This improves diagnostic reproducibility and allows for automated tumor detection, classification, and prognostication with accuracy comparable to or exceeding that of specialists. Second, AI facilitates high‒dimensional analysis of omics data, including RNA sequencing and DNA methylation profiles. Machine learning models can uncover latent molecular patterns, predict splicing abnormalities, and identify dependency genes, enabling more refined molecular classification and novel therapeutic target identification. Third, multimodal AI integrates heterogeneous data types-images, genomics, and clinical text-into unified analytical frameworks. This allows for non‒invasive prediction of molecular alterations, treatment responsiveness assessment, and outcome prediction. Integration with large language models(LLMs)further enhances interpretability and enables cross‒modal reasoning in clinical decision‒making contexts. Together, these 3 layers of AI application-image structuring, omics analysis, and multimodal integration-form the foundation for a next‒generation approach to cancer care. AI does not merely automate existing tasks but offers new pathways to understanding cancer's origins, molecular essence, and progression trajectories‒bringing the vision of true precision oncology closer to clinical reality.