Artificial intelligence (AI) is profoundly transforming the paradigm of solid tumor drug development. By integrating multi-omics data, spatial transcriptomics, and advanced computational models, AI has significantly accelerated the discovery and validation of new targets, compressing the traditional ten-year research and development cycle to two to three years. Generative AI platforms have optimized small molecule inhibitors, biologics, and messenger RNA vaccines, achieving breakthroughs in overcoming tumor heterogeneity, improving efficacy, and predicting drug resistance. However, clinical translation still faces challenges such as data bias, algorithm transparency, and the validation gap between models and real-world human experience. This review aims to systematically elaborate on the transformative role of AI in solid tumor drug development and to promote interdisciplinary cooperation as well as the construction of ethical frameworks to enable the full realization of precision oncology.

Cardiovascular diseases (CVDs) remain the leading cause of global morbidity and mortality, highlighting the urgent need for innovative diagnostic and prognostic approaches to address their complex pathophysiology. Recent advances in molecular cardiology have unveiled immune-derived microRNAs (miRNAs), or immuno-miRs, as pivotal regulators in the interplay between immune responses and cardiovascular pathology. Secreted by immune cells such as T lymphocytes, macrophages, and neutrophils, these small non-coding RNAs modulate critical signaling pathways by regulating gene expression. Immuno-miRs influence essential processes, including inflammation, endothelial dysfunction, and fibrotic remodeling—core mechanisms underlying conditions such as atherosclerosis, myocardial infarction, and heart failure. Moreover, their presence in systemic circulation within extracellular vesicles underscores their role in intercellular communication, impacting both immune and non-immune cardiovascular cells, such as cardiomyocytes and endothelial cells. This dual functionality renders immuno-miRs promising candidates as diagnostic biomarkers for early disease detection and as prognostic tools for assessing disease progression and therapeutic efficacy. Furthermore, emerging miRNA-based interventions—such as miRNA mimics and inhibitors—show considerable promise in modulating immune dysregulation in CVDs, although clinical translation remains a significant challenge. In this review, we comprehensively examine the regulatory roles of immuno-miRs in both innate and adaptive immune responses and explore recent advancements in miRNA-based therapies. By consolidating current knowledge and identifying existing gaps, we provide a comprehensive overview of the transformative potential of immuno-miRs in CVD management. Integrating these molecules into personalized medicine may pave the way for more effective, targeted, and minimally invasive strategies to combat one of the world’s most pressing health challenges.

Blood oxygen level-dependent (BOLD) functional magnetic resonance imaging (fMRI) is essential for non-invasively investigating brain function. However, conventional fMRI methods are limited by low spatial and temporal resolution. This narrative review evaluates recent advancements in deep learning techniques for high-resolution BOLD-fMRI reconstruction, focusing on super-resolution, segmentation, and image registration. A comprehensive literature search was conducted across PubMed, IEEE, Scopus, and Web of Science databases for the period 2000–2023. Studies employing deep learning methods, including convolutional neural networks, transformer-based models, and generative adversarial networks for super-resolution, segmentation, and registration of BOLD-fMRI, were included. Deep learning approaches demonstrated significant improvements in spatial resolution, segmentation accuracy, and registration robustness. Convolutional neural network-based models, particularly generative adversarial networks, notably improved image reconstruction quality and detail preservation. Preliminary studies targeting specific brain regions such as the cerebellum and hippocampus showed promise; however, systematic evaluations across broader brain areas and large-scale clinical validations remain limited. While deep learning techniques have led to substantial advancements in high-resolution BOLD-fMRI reconstruction, future research should focus on standardized protocols, multi-center validation, and improving computational efficiency and model generalization to enhance clinical utility.

Cholelithiasis and gallstone-related complications remain one of the most prevalent gastrointestinal diseases globally. Age, gender, body mass index, physical activity, dietary factors, and genetics play a role in the development of gallstones. More than 20% of patients with gallstones will develop symptomatic disease during their lifetime, which can often lead to complications and significant morbidity. Laparoscopic cholecystectomy is considered the standard of care for symptomatic gallstone disease. Still, in select patient populations and in those who are non-surgical candidates, medical management, with bile acid therapy such as ursodeoxycholic acid (UDCA) or mechanical therapy such as extracorporeal shock wave lithotripsy, is preferred. UDCA is a hydrophilic bile acid that lowers biliary cholesterol saturation and aids in dissolving small, cholesterol-rich gallstones. UDCA appears to be well tolerated in the populations studied. While serious adverse events were uncommon in the available literature, UDCA’s efficacy is limited by a high recurrence rate. The aim of this review is to summarize the current evidence and developments regarding the role of UDCA therapy in the management of cholelithiasis and choledocholithiasis.

Glioblastoma (GBM) is the most prevalent and aggressive form of primary brain malignancy in adults. Despite continuous advancements in standard treatment modalities, the prognosis for patients remains extremely poor, with a median survival of less than two years. In recent years, chimeric antigen receptor T-cell (CAR-T) therapy has achieved revolutionary success in hematologic malignancies, marking a significant breakthrough in the field of immunotherapy. However, the successful application of CAR-T therapy to GBM still faces dual challenges: antigen heterogeneity and the immunosuppressive tumor microenvironment. This review systematically summarizes these challenges encountered in CAR-T therapy for GBM and the innovative strategies currently under development to address these challenges, providing insights for the future clinical translation of CAR-T therapy in GBM.

Autoimmune hepatitis (AIH) is a chronic, progressive inflammatory liver disease characterized by autoimmune-mediated hepatic injury. Currently, glucocorticoid drugs, primarily prednisone, with or without azathioprine, are commonly recommended as first-line therapeutic agents in treatment guidelines by many scientific associations. However, the primary objective of treatment is to achieve a complete biochemical response, which is defined as the normalization of both transaminases and immunoglobulin G levels within six to twelve months. Ideally, this should also be accompanied by histological remission. Nevertheless, corticosteroid therapy is associated with significant adverse effects, potentially resulting in treatment discontinuation. In this context, it has become evident that standard treatment is inadequate for a proportion of patients, leading to the emergence of other treatment options and lines. Novel immunomodulatory agents, a class of drugs that regulate the body’s immune functions, have been confirmed to possess properties that modulate immune balance and induce immune tolerance. In recent years, these agents have played an increasingly significant role in the clinical management of AIH. This article provided an in-depth review of recent advancements in the development of novel immunomodulators, including immune cell nucleic acid inhibitors, calmodulin phosphate inhibitors, mammalian target of rapamycin inhibitors, tumor necrosis factor-α inhibitors, interleukin-2, anti-CD20 monoclonal antibodies, and B cell-activating factor inhibitors, for the treatment of AIH.

Lung cancer remains the leading cause of cancer-related mortality worldwide. Early detection of pulmonary nodules is crucial for timely diagnosis and effective treatment. Conventional computer-aided detection systems have shown limitations, including high false-positive rates and low sensitivity. Recent advances in deep learning, particularly convolutional neural networks (CNNs), have shown great potential in improving the accuracy and reliability of nodule detection and classification. This study aimed to develop and evaluate an automatic method for lung nodule detection and classification using a CNN-based architecture applied to computed tomography images from the publicly available LIDC-IDRI database.

This retrospective study was conducted on 82 patients (10,496 computed tomography slices) selected from the LIDC-IDRI database. The proposed method consists of five main steps: image preprocessing, lung parenchyma segmentation using Otsu’s thresholding and morphological operations, detection of nodule candidates, feature extraction, and classification using a CNN model. The CNN architecture includes two convolutional layers (20 and 30 filters, 3×3 kernel), ReLU activation, max-pooling layers, and a Softmax output layer. The network was trained with a mini-batch size of 32 for 50 epochs using the Stochastic Gradient Descent with Momentum optimizer (learning rate = 0.001, momentum = 0.9). Model performance was evaluated in terms of sensitivity, specificity, precision, and accuracy.

The proposed CNN model successfully detected pulmonary nodules and achieved accurate classification between benign and malignant nodules. On the LIDC-IDRI dataset, the model achieved a sensitivity of 98.7%, specificity of 97.5%, precision of 97.9%, and accuracy of 98.4%. Comparative analysis with recent studies, including hybrid CNN-long short-term memory and ResNet-based models, demonstrated that the proposed method provides competitive performance while maintaining lower computational complexity. The classification of nodule subtypes (solid, partially frosted, totally frosted) showed satisfactory discrimination results.

The proposed CNN-based system demonstrates the feasibility and robustness of deep learning for automatic lung nodule detection and classification. Despite strong results, the study acknowledges limitations such as single-database validation and a relatively small training size. Future work will focus on validating the model across other datasets (e.g., ELCAP, NELSON) and optimizing multi-class classification performance to enhance generalizability and clinical applicability.

The global integration of traditional medicine (TM) and modern medicine reflects a fundamental shift in healthcare aimed at delivering more holistic, culturally sensitive, and patient-centered care. With over 80% of the global population relying on some form of TM, especially in Asia, Africa, and Latin America, there is growing momentum to institutionalize TM alongside evidence-based biomedicine. Countries like India, China, and Korea have led integration through formal education, government-supported research, and clinical frameworks, while high-income countries are increasingly adopting complementary and integrative medicine models. However, this convergence faces substantial challenges, including differences in epistemology, regulatory standards, evidence hierarchies, and practitioner training. Limited clinical trials, quality assurance concerns, and issues related to intellectual property rights and biopiracy further complicate harmonization. Despite these barriers, the World Health Organization’s Traditional Medicine Strategy (2014–2023) and its newly established Global Centre for Traditional Medicine (India) underscore a growing international commitment to evidence-based integration. Opportunities lie in promoting collaborative research, strengthening regulatory frameworks, enhancing digital health platforms for TM documentation, and fostering intercultural dialogue between health systems. If guided ethically and scientifically, integration can improve access to care, reduce treatment costs, and offer personalized health solutions for chronic and lifestyle-related diseases. This review explored global integration models, evaluated emerging challenges, and identified strategies to support an inclusive, pluralistic, and sustainable healthcare future that respects both traditional wisdom and modern science.

Soft tissue cytopathology plays a vital role in the diagnosis and management of soft tissue neoplasms, necessitating a standardized classification system to improve diagnostic accuracy and guide clinical decision-making. This article provides a concise review of the World Health Organization (WHO) Reporting System for Soft Tissue Cytopathology and presents a practical diagnostic approach to soft tissue cytopathology.

The WHO Reporting System is reviewed in conjunction with relevant literature. The reporting system employs a six-category framework: non-diagnostic, benign, atypical, soft tissue neoplasm of uncertain malignant potential, suspicious for malignancy, and malignant.

Each category is associated with a corresponding risk of malignancy and recommended clinical management guidelines. This classification aligns with the WHO Classification of Soft Tissue and Bone Tumours (5th edition) and incorporates cytomorphologic features, ancillary studies, and clinical correlation to enhance diagnostic reproducibility and communication among pathologists and clinicians. The system supports a probabilistic approach to risk stratification, enabling more consistent diagnostic and therapeutic strategies.

This framework provides a robust foundation for the interpretation of soft tissue fine-needle aspiration biopsies and optimized patient care.