Search Results (33)

Background: Radiology underpins diagnosis and treatment across pediatrics, yet most artificial intelligence (AI) tools are developed for adults and validated on adult datasets only. Of more than 200 AI systems cleared by the United States (U.S.) Food and Drug Administration (FDA), only about 3% include pediatric validation. Because children differ from adults in anatomy, physiology, pathology, epidemiology, and imaging protocols, adult-trained models often perform sub-optimally in pediatric settings. Methods: A narrative review of peer-reviewed literature from 2000 to 2025 was conducted using PubMed, MEDLINE, Google Scholar, and Scopus. Studies involving AI applications in pediatric X-ray, ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), echocardiography, and point-of-care ultrasound with quantitative performance metrics were included. Findings were synthesized by imaging modality, clinical task, and differences between high-income countries (HICs) and low- and middle-income countries (LMICs). Results: AI demonstrated strong performance across multiple pediatric imaging tasks. In X-ray interpretation, AI detected fractures with area under the curve (AUC) values up to 0.96 (sensitivity, 90.8%; specificity, 88.7%). Pneumonia classification achieved 76.5% accuracy, and foreign body aspiration detection showed 95.3% specificity in HICs. In ultrasound, AI improved junior sonographers’ detection of intussusception (AUC 0.857 to 0.966) and reduced scan time by more than 50%. AI-assisted bone age estimation achieved a mean error of 0.39 years. In echocardiography, AI-derived ejection fraction showed excellent agreement with experts’ interclass correlation coefficient (ICC 0.983), and AI support improved atrioventricular septal defect detection (84.4% to 86.5%). In MRI, the use of AI enhanced lesion detection and supported quantitative analysis. Deep-learning models trained on routine T1- and T2-weighted sequences predicted liver stiffness across multi-site datasets, while advanced neuroimaging pipelines improved the identification of subtle epileptogenic lesions that are often missed on conventional pediatric MRI. However, adult-trained models showed limited generalizability to children. Still, excluding children under the age of two years improved the reading accuracy of pediatric chest X-rays (CXRs) by adult-trained models from 88% to 97%. AI faces challenges beyond the development of age-specific models. Substantial heterogeneity, limited pediatric-specific datasets, and unresolved medicolegal responsibility further restrict adoption worldwide. Challenges are amplified in LMICs, where unstable electricity, limited radiology resources, weak digital infrastructure, and scarce pediatric providers limit implementation. Additionally, many large language models underperform and lack inclusive algorithms suitable for pediatric radiology in many LMICs. Conclusions: AI can enhance diagnostic accuracy, efficiency, and access to pediatric imaging, particularly in resource-limited settings, through task-shifting and decision support. However, it cannot replace pediatric radiologists as of today. Safe adoption requires pediatric-specific model development, standardized validation metrics, diverse datasets that include LMIC populations, stronger digital infrastructure, robust radiologist training in AI capabilities, and the establishment of clear guidelines and medicolegal policies. Full article

Antiretroviral drugs (ARVDs) remain the cornerstone of HIV/AIDS management, but their therapeutic efficacy and safety are highly influenced by bioconversion processes such as hepatic metabolism and enzymatic transformation. Variability in metabolic pathways, mediated by cytochrome P450 enzymes and other liver-based systems, contributes to interindividual differences in drug response, toxicity, and resistance. Recent advances in artificial intelligence, particularly artificial neural networks (ANNs), offer promising tools for modeling and optimizing these complex bioconversion processes. ANNs are capable of learning nonlinear relationships from high-dimensional datasets, making them ideal for predicting the pharmacokinetic parameters, enzyme–substrate interactions, and metabolic stability of ARVDs. This review explores the emerging role of ANNs in understanding and optimizing the metabolic transformation of antiretroviral agents. Key applications are discussed, including prediction of drug–enzyme interactions, in silico modeling of hepatic clearance, and simulation of enzyme kinetics. The integration of molecular descriptors, omics data, and clinical parameters into ANN models allows for improved prediction accuracy and personalized therapy. Furthermore, ANN-based tools can aid in early-stage drug development by identifying metabolic liabilities and guiding structural modifications to enhance metabolic stability. Despite their potential, challenges such as data scarcity, model interpretability, and standardization remain. Future research should focus on hybrid models combining ANN with mechanistic pharmacokinetics, the incorporation of real-world patient data, and validation against experimental outcomes. Overall, ANNs represent a powerful approach to optimizing ARVDs bioconversion, with the potential to improve efficacy, reduce toxicity, and support the development of next-generation antiretroviral therapies Full article

In October 2025, an outbreak occurred among farmed Chinese rice-field eels (Monopterus albus) in Jiangxi, China. A Nocardia seriolae strain designated JXMa251025, which has not been previously documented in Chinese rice-field eels, was isolated from moribund fish exhibiting multiple white nodules of various sizes in visceral tissues. Histopathological examination revealed multi-organ damage, including necrosis of liver cells, granulomatous inflammation with hemorrhage in visceral organs, and necrosis of renal glomeruli and tubules accompanied by vascular congestion. Artificial infection trials confirmed that strain JXMa251025 reproduced clinical signs consistent with those observed in the natural outbreak. Infection experiments resulted in 100% mortality in high-concentration challenge groups, with a median lethal dose (LD₅₀) of 9.76 × 10⁵ CFU/mL, indicating high virulence. Whole-genome sequencing revealed a circular chromosome of 8,295,032 bp with a GC content of 68.10%. The genome contains 66 tRNA genes and four copies each of the 23S, 16S, and 5S rRNA genes. Phylogenomic analysis placed strain JXMa251025 within a clade of Nocardia seriolae strains with approximately 99% bootstrap support, confirming its identification as Nocardia seriolae. Further genomic screening identified 253 potential virulence genes associated with nutrient metabolism, regulatory systems, immune modulation, effector delivery, and exotoxin production. Antibiotic susceptibility testing showed that strain JXMa251025 was sensitive to seven antibiotics: ciprofloxacin, neomycin, enrofloxacin, florfenicol, gentamicin, amikacin, and doxycycline. This study represents the first report of Nocardia seriolae infecting Chinesse rice-field eels, providing useful descriptive information for disease diagnosis and reference. Full article

Background: Stable isotope-based analytical methods have brought about a significant transformation in the study of energy nutrient metabolism, enabling precise in vivo measurement of metabolic fluxes at systemic, tissue, and organ-specific levels in both healthy and diseased states. The regulation of these metabolic fluxes is governed by dynamic interactions between proteins, lipids, carbohydrates, and their precursors—such as glucose, fatty acids, and amino acids—as well as final metabolic products. Discussion: Advanced analytical technologies, including nuclear magnetic resonance (NMR) spectroscopy and mass spectrometry (MS), which can offer enhanced precision, have been developed for investigating nutrient metabolism and fluxes in humans, providing precise information on metabolic pathways. These techniques have primarily utilized stable isotopes, such as ²H, ¹³C, ¹⁵N, and ¹⁸O, which have largely replaced radioactive isotopes and are now central to metabolic research. These isotopes have been used to label glucose, fatty acids, or amino acids—the main biomolecular precursors—enabling detailed investigation at systemic, tissue, and organ-specific levels of carbohydrate, lipid, and protein metabolism, and revealing pathway alterations associated with diseases conditions, such as diabetes, non-alcoholic fatty liver disease, cardiovascular disorders, and cancer. The use of deuterium oxide (D₂O) has allowed for long-term metabolic studies, providing a cost-effective and less invasive means to monitor metabolic changes over days to months. Total daily energy expenditure can be measured in free living conditions by the doubly stable isotopes ²H- and ¹⁸O-labeled water method. Stable isotope tracing, combined with advanced imaging and modeling, has also been instrumental in assessing body composition, energy expenditure, and nutrient bioavailability. Collectively, these methods have expanded our understanding of human physiology and disease, supporting the development of novel diagnostic tools, the identification of new biomarkers, and the tailoring of nutritional and therapeutic interventions. Conclusions: This review aimed to provide an overview of the applications of stable isotopes for the study of energy nutrient metabolic pathways. The ongoing integration of stable isotope approaches with artificial intelligence, omics technologies, and miniaturized detection techniques could promise to further refine our understanding of human metabolism and drive advances in personalized medicine. Full article

Hepatocellular carcinoma (HCC) remains a major cause of cancer-related mortality worldwide, and its management is limited by heterogeneous risk profiles, suboptimal surveillance performance, diagnostic uncertainty in chronically diseased livers, and difficulty individualizing prognosis after treatment. The aim of this narrative review was to critically evaluate artificial intelligence (AI) applications across the HCC care continuum, with emphasis on their intended clinical role, reported performance, evidence maturity, and barriers to implementation. A major strength of this review is that it moves beyond a descriptive catalog of models by structuring the literature around clinically relevant decision points and by explicitly distinguishing emerging proof-of-concept tools from applications with stronger translational potential. Across risk stratification, surveillance, imaging-based diagnosis, pathology, treatment-response prediction, and prognostication, we found that AI consistently demonstrates promise, particularly for identifying patients at higher future HCC risk, improving lesion detection and characterization on ultrasound, CT, MRI, and contrast-enhanced ultrasound, assisting histopathologic classification, and predicting outcomes such as microvascular invasion, recurrence, survival, and response to locoregional therapies. However, we also found that the evidence base remains highly uneven: many diagnostic studies are retrospective and lesion-enriched rather than embedded in true surveillance populations, many prognostic models lack robust external validation and calibration assessment, and reference standards, imaging protocols, and dataset composition vary substantially across studies. These findings are clinically relevant because they highlight both where AI may offer near-term value and why most published systems are not yet ready for routine use. Overall, AI in HCC should be viewed as a rapidly evolving but still transitional field. Its future impact will depend not only on higher-performing algorithms but on clearly defined clinical use cases, multicenter and prospective validation, transparent reporting, workflow-aware evaluation, and implementation strategies that support safe, equitable, and scalable adoption. Full article

Background: The heterogeneous nature of cancer with varying degrees of fat, necrosis, fibrosis, and varying degrees of tissue repair severely impacts the success of acquiring adequate tissue samples during percutaneous image-guided biopsy. Although ultrasound or CT fluoroscopy are used to identify tumor location and thus to guide biopsy needle insertion, these technologies do not provide the necessary resolution to determine tissue composition and enable the selection of the most appropriate location for biopsy specimen extraction. As a result, biopsy must be repeated, leading to significant cost to the health care system. Methods: In this study, we introduce a combined optical imaging/artificial intelligence (OI/AI) methodology for the real-time assessment of tissue morphology at the tip of the biopsy needle, prior to the collection of a biopsy specimen. Addressing a significant clinical challenge, this approach aims to reduce the proportion of biopsy cores—currently as high as 40%—that yield low diagnostic value due to elevated adipose or low tumor content. Our methodology employs micron-scale optical coherence tomography (OCT) imaging to obtain detailed structural tissue information using a minimally invasive needle probe. The OCT images are automatically analyzed using a convolutional neural network (CNN)-driven AI software developed by our team. A U-net style architecture was used to segment regions of tumor from the OCT scans. U-Net is a specialized convolutional neural network (CNN) architecture designed for fast, precise image segmentation, which involves classifying each pixel in an image to outline objects. This streamlined approach shows promise to provide clinicians with real-time results, supporting more accurate and informed decisions regarding biopsy site selection. To evaluate this technology, we conducted a clinical study using a custom-made OCT imager and recorded OCT images from patients diagnosed with liver cancers. Expert OCT interpreters supplied annotated reference images that were used to train a custom AI algorithm. Results: OCT imaging with ~10 mm axial and 20 mm lateral resolution enabled the collection of high-quality images of the tissue. The AI analysis was performed offline. UNet achieved an AUC of ~0.877 on the validation dataset, indicating promising performance for the relatively small data set used to train the model. The AI model matched human interpretations approximately 90% of the time, highlighting its promise for making biopsy procedures both more accurate and more efficient. Conclusions: A novel OCT instrument and AI software were evaluated for assessing tissue composition at the tip of biopsy needle. The OCT instrument produced micron-scale resolution images of the tissue, enabling AI analysis and accurate real-time discrimination of tissue type. This preliminary study demonstrated the clinical potential of this technology for improving biopsy success. Full article

Surgical resection of liver and lung metastases in breast cancer is increasingly considered a viable option for select patients with oligometastatic disease. Historically regarded as palliative, surgery is now supported by retrospective data suggesting potential survival benefits, particularly in patients with hormone receptor-positive or HER2-positive tumors, long disease-free intervals, and limited metastatic burden. This narrative review summarizes recent evidence on the surgical management of breast cancer metastases to the liver and lung, with a focus on patient selection, perioperative outcomes, and long-term survival. Liver metastasectomy has shown 5-year overall survival rates of up to 60% in well-selected patients, while pulmonary metastasectomy is associated with comparable outcomes when resection is complete and nodal involvement is absent. Minimally invasive techniques and non-surgical approaches, such as microwave ablation and stereotactic radiotherapy, expand treatment options for patients unfit for surgery. The review also explores emerging tools influencing surgical decision-making, including circulating tumor DNA for minimal residual disease detection, transcriptomic profiling to predict organotropism, and artificial intelligence (AI)-driven platforms that assist with surgical planning and multidisciplinary case evaluation. While prospective validation remains limited, these technologies may help redefine surgical candidacy through biologically informed algorithms. Ultimately, the integration of surgery within a multimodal, personalized treatment strategy—guided by systemic control, tumor biology, and evolving digital tools—represents an evolving and biologically informed direction for rigorously selected patients with visceral breast cancer metastases. Full article

Objective: To map and characterize artificial intelligence (AI) applications in post-liver transplantation (LT) care, summarize comparative performance where available, and identify methodological and translational gaps. Methods: We conducted a scoping review in accordance with PRISMA-ScR. A comprehensive search of electronic databases was performed from inception through 1 April 2025. We included primary studies evaluating AI applications in the post-LT period (model development, validation, or implementation). Comparative studies were defined as those reporting head-to-head evaluation of at least two algorithmic models for the same task with quantitative performance metrics. Single-model studies were retained for evidence mapping but analyzed separately. Reviews and the other non-primary literature were included for contextual mapping. Results: The search yielded 3088 records. After deduplication, 2408 were screened, 191 full texts were assessed, and 65 studies were included. Of these, 52 reported primary outcome data. Clinical prediction studies (n = 43) focused on graft survival, rejection, fibrosis, oncologic recurrence, mortality, and composite outcomes. Operational studies (n = 3) evaluated early warning or bedside decision-support systems, and system-level studies (n = 6) examined benchmarking, donor–recipient matching, explainability, fairness, and cross-domain modeling. Most studies were retrospective and single-center, with internal validation commonly reported and external validation uncommon. Conclusions: AI research in post-LT care is expanding, with a predominant focus on clinical prediction. However, limited external validation, heterogeneous methods, and scarce real-world implementation constrain clinical readiness. Standardized evaluation and prospective integration are needed to determine whether AI tools can support decision-making and improve post-transplant outcomes. Full article

Chronic liver disease remains a leading cause of global mortality, yet organ shortages and transplant complications limit the efficacy of orthotopic liver transplantation. While extracorporeal support systems serve as temporary bridges, they fail to restore long-term patient autonomy or replicate complex biosynthetic functions. This systematic review, conducted in accordance with PRISMA 2020 guidelines, evaluates recent advancements in implantable artificial livers (IALs) designed for permanent functional integration. We analyzed 71 eligible studies, assessing cellular sources, fabrication strategies, maturation processes, and functional readiness. Our findings indicate significant progress in stem-cell-derived hepatocytes and bioactive scaffolds, such as decellularized extracellular matrix (dECM). However, a critical technological gap remains in scaling current sub-centimeter prototypes toward clinically relevant volumes (~200 mL). Key engineering challenges include integrating hierarchical vascular networks, requiring primary vessels exceeding 2 mm in diameter for surgical anastomosis, and functional biliary systems to prevent cholestatic injury. Furthermore, while micro-vascularization and protein synthesis are well documented, higher-order functions such as spatial zonation and coordinated metabolic stability remain underreported. Future clinical translation necessitates advancements in multi-cellular patterning, microfluidic-driven maturation, and autologous reprogramming. This review provides a comprehensive roadmap for bridging the gap between biofabricated constructs and organ-scale hepatic replacement, emphasizing the need for standardized functional benchmarks to ensure long-term success. Full article

Background and Objectives: Posthepatectomy liver failure (PHLF) remains a major cause of morbidity and mortality for patients undergoing major liver resections. Recent research highlights the expanding role of machine learning (ML), a crucial subfield of artificial intelligence (AI), in optimizing risk stratification. The aim of the current study was to review, elaborate on and critically analyze the available literature regarding the use of ML-driven risk prediction models for posthepatectomy liver failure. Materials and Methods: A systematic search was conducted in the PubMed/MEDLINE, Scopus and Web of Science databases. Fifteen studies that trained and validated ML models for prediction of PHLF were further included and analyzed. Results: The available literature supports the value of ML-derived models for PHLF prediction. Perioperative clinical, laboratory and imaging features have been combined in a variety of different algorithms to provided interpretable and accurate models for identifying patients at risk of PHLF. The ML-based algorithms have consistently demonstrated high area under the curve and sensitivity values, surpassing traditionally used risk scores in predictive performance. Limitations include the small sample sizes, heterogeneity in populations included, lack of external validation and a reported poor ability to distinguish between true positive and false positive cases in several studies. Conclusions: Despite the constraints, ML-driven tools, in combination with traditional scoring systems and clinical insight, may enable early and accurate PHLF risk detection, personalized surgical planning and optimization of postoperative outcomes in liver surgery. Full article

Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide. Compared with traditional two-dimensional (2D) models, patient-derived CRC organoids more faithfully preserve the genomic, transcriptomic, and architectural features of primary tumors, making them a powerful intermediate platform bridging basic discovery and clinical translation. Over the past several years, organoid systems have rapidly expanded beyond conventional epithelial-only cultures toward increasingly complex architectures, including immune-organoid co-culture models and mini-colon systems that enable long-term, spatially resolved tracking of tumor evolution. These advanced platforms, combined with high-throughput technologies and clustered regularly interspaced short palindromic repeats (CRISPR)-based functional genomics, have substantially enhanced our ability to dissect CRC mechanisms, identify therapeutic vulnerabilities, and evaluate drug responses in a physiologically relevant context. However, current models still face critical limitations, such as the lack of systemic physiology (e.g., gut–liver or gut–brain axes), limited standardization across platforms, and the need for large-scale, prospective clinical validation. These gaps highlight an urgent need for next-generation platforms and computational frameworks. The development of high-throughput multi-omics, CRISPR-based perturbation, drug screening technologies, and artificial intelligence-driven predictive approaches will offer a promising avenue to address these challenges, accelerating mechanistic studies of CRC, enabling personalized therapy, and facilitating clinical translation. In this perspective, we propose a roadmap for CRC organoid research centered on two major technical pillars: advanced organoid platforms, including immune co-culture and mini-colon systems, and mechanistic investigations leveraging multi-omics and CRISPR-based functional genomics. We then discuss translational applications, such as high-throughput drug screening, and highlight emerging computational and translational strategies that may support future clinical validation and precision medicine. Full article

Background/Objectives: The application of predictive and explainable artificial intelligence to bioinformatics data such as single nucleotide polymorphism (SNP) information is attracting rising attention in the diagnosis of various diseases. However, there are few reviews available on the recent progress of genetic artificial intelligence for the early diagnosis of gastrointestinal disease (GID). The purpose of this study is to complete a systematic review on the recent progress of genetic artificial intelligence in GID. Methods: The source of data was ten original studies from PubMed. The ten original studies were eligible according to the following criteria: (participants) the dependent variable of GID or associated disease; (interventions/comparisons) artificial intelligence; (outcomes) accuracy, the area under the curve (AUC), and/or variable importance; a publication year of 2010 or later; and the publication language of English. Results: The performance outcomes reported varied within 79–100 for accuracy (%) and 63–98 for the AUC (%). Random forest was the best approach (AUC 98%) for the classification of inflammatory bowel disease with 13 single nucleotide polymorphisms (SNPs). Similarly, random forest was the best method (R-square 99%) for the regression of the gut microbiome SNP saturation number. The following SNPs were discovered to be major variables for the prediction of GID or associated disease: rs2295778, rs13337626, rs2296188, rs2114039 (esophageal adenocarcinoma); rs28785174, rs60532570, rs13056955, rs7660164 (Crohn’s disease early intestinal resection); rs4945943 (Crohn’s disease); rs316115020, rs316420452 (calcium metabolism); rs738409_G, rs2642438_A, rs58542926_T, rs72613567_TA (steatotic liver disease); rs148710154, rs75146099 (esophageal squamous cell carcinoma). The following demographic and health-related variables were found to be important predictors of GID or associated disease besides SNPs: age, body mass index, disease behavior, immune cell type, intestinal microbiome, MARCKS protein, smoking, and SNP density/number. No deep learning study was found even though deep learning was used as a search term together with machine learning. Conclusions: Genetic artificial intelligence is effective and non-invasive as a decision support system for GID. Full article

Colorectal liver metastasis (CRLM) poses a significant challenge in oncology due to its high incidence and poor prognosis in unresectable cases. Current treatments, including surgical resection, systemic chemotherapy, and liver-directed therapies, often fail to effectively target hypoxic tumor regions, which are inherently more resistant to these interventions. This review examines the potential of a novel therapeutic strategy combining irreversible electroporation (IRE) ablation and Clostridium novyi-nontoxic (C. novyi-NT) bacterial therapy. IRE is a non-thermal tumor ablation technique that uses high-voltage electric pulses to create permanent nanopores in cell membranes, leading to cell death while preserving surrounding structures, and is often associated with temporary tumor hypoxia due to disrupted perfusion. C. novyi-NT is an attenuated, anaerobic bacterium engineered to selectively germinate and proliferate in hypoxic tumor regions, resulting in localized tumor cell lysis while sparing healthy, oxygenated tissue. The synergy between IRE-induced hypoxia and hypoxia-sensitive C. novyi-NT may enhance tumor destruction and stimulate systemic antitumor immunity. Furthermore, the integration of advanced imaging and artificial intelligence can support precise treatment planning and real-time monitoring. This integrated approach holds promise for improving outcomes in patients with CRLM, though further preclinical and clinical validation is needed. Full article

Liver cirrhosis continues to be a major global health issue, contributing to high morbidity and mortality due to its progressive nature and associated complications. This review explores recent advancements in the diagnosis and treatment of liver cirrhosis and its related syndromes. Non-invasive diagnostic tools, such as elastography and serum biomarkers, have significantly improved early detection, reducing the need for liver biopsies. Advanced imaging techniques, including MRI and CT, further enhance diagnostic accuracy. In parallel, molecular and genomic research is providing new insights into the pathogenesis of the disease, paving the way for precision medicine. On the treatment front, pharmacological innovations, such as antifibrotic agents and targeted therapies, show promise in slowing disease progression. Endoscopic interventions like variceal banding are improving the management of complications, while advancements in liver transplantation and artificial liver support systems offer life-saving alternatives. Regenerative medicine, particularly stem cell therapy and tissue engineering, is emerging as a promising strategy for liver repair. Managing cirrhosis-related syndromes, including portal hypertension, ascites, hepatic encephalopathy, and hepatorenal syndrome, now involves evolving therapeutic approaches such as transjugular intrahepatic portosystemic shunt (TIPS) and novel pharmacotherapies. Prognostic scoring systems like the MELD and Child–Pugh are being refined with new biomarkers for better risk stratification. The future of cirrhosis care will likely involve the integration of artificial intelligence and machine learning for early diagnosis and personalized treatments, alongside emerging therapies currently under investigation. Despite these advancements, challenges such as costs, accessibility, and healthcare disparities remain barriers to widespread adoption. This review highlights the importance of incorporating innovative diagnostic and therapeutic strategies into clinical practice to improve the outcomes for patients with liver cirrhosis and its complications. Full article

Background/Objectives: Liver cirrhosis is a critical chronic condition with increasing global mortality and morbidity rates, emphasizing the necessity for early and accurate diagnosis. This study proposes a comprehensive deep-learning framework for the automatic diagnosis and staging of liver cirrhosis using T2-weighted MRI images. Methods: The methodology integrates stacked ensemble learning, multi-task learning (MTL), and transfer learning within an explainable artificial intelligence (XAI) context to improve diagnostic accuracy, reliability, and transparency. A hybrid model combining multiple pre-trained convolutional neural networks (VGG16, MobileNet, and DenseNet121) with XGBoost as a meta-classifier demonstrated robust performance in binary classification between healthy and cirrhotic cases. Results: The model achieved a mean accuracy of 96.92%, precision of 95.12%, recall of 98.93%, and F1-score of 96.98% across 10-fold cross-validation. For staging (mild, moderate, and severe), the MTL framework reached a main task accuracy of 96.71% and an average AUC of 99.81%, with a powerful performance in identifying severe cases. Grad-CAM visualizations reveal class-specific activation regions, enhancing the transparency and trust in the model’s decision-making. The proposed system was validated using the CirrMRI600+ dataset with a 10-fold cross-validation strategy, achieving high accuracy (AUC: 99.7%) and consistent results across folds. Conclusions: This research not only advances State-of-the-Art diagnostic methods but also addresses the black-box nature of deep learning in clinical applications. The framework offers potential as a decision-support system for radiologists, contributing to early detection, effective staging, personalized treatment planning, and better-informed treatment planning for liver cirrhosis. Full article