Front Oncol. 2025 Mar 19;15:1468232. doi: 10.3389/fonc.2025.1468232. eCollection 2025.

ABSTRACT

OBJECTIVES: Radiotherapy is a fundamental cancer treatment method, and pre-treatment patient-specific quality assurance (prePSQA) plays a crucial role in ensuring dose accuracy and patient safety. Artificial intelligence model for measurement-free prePSQA have been investigated over the last few years. While these models stack successive pooling layers to carry out sequential learning, directly splice together different modalities along channel dimensions and feed them into shared encoder-decoder network, which greatly reduces the anatomical features specific to different modalities. Furthermore, the existing models simply take advantage of low-dimensional dosimetry information, meaning that the spatial features about the complex dose distribution may be lost and limiting the predictive power of the models. The purpose of this study is to develop a novel deep learning model for measurement-guided therapeutic-dose (MDose) prediction from head and neck cancer radiotherapy data.

METHODS: The enrolled 310 patients underwent volumetric-modulated arc radiotherapy (VMAT) were randomly divided into the training set (186 cases, 60%), validation set (62 cases, 20%), and test set (62 cases, 20%). The effective prediction model explicitly integrates the multi-scale features that are specific to CT and dose images, takes into account the useful spatial dose information and fully exploits the mutual promotion within the different modalities. It enables medical physicists to analyze the detailed locations of spatial dose differences and to simultaneously generate clinically applicable dose-volume histograms (DVHs) metrics and gamma passing rate (GPR) outcomes.

RESULTS: The proposed model achieved better performance of MDose prediction, and dosimetric congruence of DVHs, GPR with the ground truth compared with several state-of-the-art models. Quantitative experimental predictions show that the proposed model achieved the lowest values for the mean absolute error (37.99) and root mean square error (4.916), and the highest values for the peak signal-to-noise ratio (52.622), structural similarity (0.986) and universal quality index (0.932). The predicted dose values of all voxels were within 6 Gy in the dose difference maps, except for the areas near the skin or thermoplastic mask indentation boundaries.

CONCLUSIONS: We have developed a feasible MDose prediction model that could potentially improve the efficiency and accuracy of prePSQA for head and neck cancer radiotherapy, providing a boost for clinical adaptive radiotherapy.

PMID:40177241 | PMC:PMC11961879 | DOI:10.3389/fonc.2025.1468232

Front Robot AI. 2025 Mar 19;12:1520374. doi: 10.3389/frobt.2025.1520374. eCollection 2025.

ABSTRACT

A significant number of individuals have been affected by pandemic diseases, such as COVID-19 and seasonal influenza. Nucleic acid testing is a common method for identifying infected patients. However, manual sampling methods require the involvement of numerous healthcare professionals. To address this challenge, we propose a novel transoral swab sampling robot designed to autonomously perform nucleic acid sampling using a visual-tactile fusion approach. The robot comprises a series-parallel hybrid flexible mechanism for precise distal posture adjustment and a visual-tactile perception module for navigation within the subject's oral cavity. The series-parallel hybrid mechanism, driven by flexible shafts, enables omnidirectional bending through coordinated movement of the two segments of the bendable joint. The visual-tactile perception module incorporates a camera to capture oral images of the subject and recognize the nucleic acid sampling point using a deep learning method. Additionally, a force sensor positioned at the distal end of the robot provides feedback on contact force as the swab is inserted into the subject's oral cavity. The sampling robot is capable of autonomously performing transoral swab sampling while navigating using the visual-tactile perception algorithm. Preliminary experimental trials indicate that the designed robot system is feasible, safe, and accurate for sample collection from subjects.

PMID:40177224 | PMC:PMC11961991 | DOI:10.3389/frobt.2025.1520374

Exp Biol Med (Maywood). 2025 Mar 19;250:10359. doi: 10.3389/ebm.2025.10359. eCollection 2025.

ABSTRACT

Opioids exert their analgesic effect by binding to the µ opioid receptor (MOR), which initiates a downstream signaling pathway, eventually inhibiting pain transmission in the spinal cord. However, current opioids are addictive, often leading to overdose contributing to the opioid crisis in the United States. Therefore, understanding the structure-activity relationship between MOR and its ligands is essential for predicting MOR binding of chemicals, which could assist in the development of non-addictive or less-addictive opioid analgesics. This study aimed to develop machine learning and deep learning models for predicting MOR binding activity of chemicals. Chemicals with MOR binding activity data were first curated from public databases and the literature. Molecular descriptors of the curated chemicals were calculated using software Mold2. The chemicals were then split into training and external validation datasets. Random forest, k-nearest neighbors, support vector machine, multi-layer perceptron, and long short-term memory models were developed and evaluated using 5-fold cross-validations and external validations, resulting in Matthews correlation coefficients of 0.528-0.654 and 0.408, respectively. Furthermore, prediction confidence and applicability domain analyses highlighted their importance to the models' applicability. Our results suggest that the developed models could be useful for identifying MOR binders, potentially aiding in the development of non-addictive or less-addictive drugs targeting MOR.

PMID:40177220 | PMC:PMC11961360 | DOI:10.3389/ebm.2025.10359

World J Hepatol. 2025 Mar 27;17(3):101721. doi: 10.4254/wjh.v17.i3.101721.

ABSTRACT

BACKGROUND: In recent years, the utilization of artificial intelligence (AI) technology has gained prominence in the field of liver disease.

AIM: To analyzes AI research in the field of liver disease, summarizes the current research status and identifies hot spots.

METHODS: We searched the Web of Science Core Collection database for all articles and reviews on hepatopathy and AI. The time spans from January 2007 to August 2023. We included 4051 studies for further collection of information, including authors, countries, institutions, publication years, keywords and references. VOS viewer, CiteSpace, R 4.3.1 and Scimago Graphica were used to visualize the results.

RESULTS: A total of 4051 articles were analyzed. China was the leading contributor, with 1568 publications, while the United States had the most international collaborations. The most productive institutions and journals were the Chinese Academy of Sciences and Frontiers in Oncology. Keywords co-occurrence analysis can be roughly summarized into four clusters: Risk prediction, diagnosis, treatment and prognosis of liver diseases. "Machine learning", "deep learning", "convolutional neural network", "CT", and "microvascular infiltration" have been popular research topics in recent years.

CONCLUSION: AI is widely applied in the risk assessment, diagnosis, treatment, and prognosis of liver diseases, with a shift from invasive to noninvasive treatment approaches.

PMID:40177211 | PMC:PMC11959664 | DOI:10.4254/wjh.v17.i3.101721

J Med Imaging (Bellingham). 2025 Mar;12(2):024004. doi: 10.1117/1.JMI.12.2.024004. Epub 2025 Apr 1.

ABSTRACT

PURPOSE: The issue of delivered doses during computed tomography (CT) scans encouraged sparser sets of X-ray projection, severely degrading reconstructions from conventional methods. Although most deep learning approaches benefit from large supervised datasets, they cannot generalize to new acquisition protocols (geometry, source/detector specifications). To address this issue, we developed a method working without training data and independently of experimental setups. In addition, our model may be initialized on small unsupervised datasets to enhance reconstructions.

APPROACH: We propose a conditioned generative latent optimization (cGLO) in which a decoder reconstructs multiple slices simultaneously with a shared objective. It is tested on full-dose sparse-view CT for varying projection sets: (a) without training data against Deep Image Prior (DIP) and (b) with training datasets of multiple sizes against state-of-the-art score-based generative models (SGMs). Peak signal-to-noise ratio (PSNR) and structural SIMilarity (SSIM) metrics are used to quantify reconstruction quality.

RESULTS: cGLO demonstrates better SSIM than SGMs (between + 0.034 and + 0.139 ) and has an increasing advantage for smaller datasets reaching a + 6.06 dB PSNR gain. Our strategy also outperforms DIP with at least a + 1.52 dB PSNR advantage and peaks at + 3.15 dB with fewer angles. Moreover, cGLO does not create artifacts or structural deformations contrary to DIP and SGMs.

CONCLUSIONS: We propose a parsimonious and robust reconstruction technique offering similar to better performances when compared with state-of-the-art methods regarding full-dose sparse-view CT. Our strategy could be readily applied to any imaging reconstruction task without any assumption about the acquisition protocol or the quantity of available data.

PMID:40177097 | PMC:PMC11961077 | DOI:10.1117/1.JMI.12.2.024004

Front Artif Intell. 2025 Mar 18;8:1565287. doi: 10.3389/frai.2025.1565287. eCollection 2025.

ABSTRACT

Vehicle-to-Everything (V2X) communication promises to revolutionize road safety and efficiency. However, challenges in data sharing and network reliability impede its full realization. This paper addresses these challenges by proposing a novel Deep Learning (DL) approach for traffic prediction in V2X environments. We employ Bidirectional Long Short-Term Memory (BiLSTM) networks and compare their performance against other prominent DL architectures, including unidirectional LSTM and Gated Recurrent Unit (GRU). Our findings demonstrate that the BiLSTM model exhibits superior accuracy in predicting traffic patterns. This enhanced prediction capability enables more efficient resource allocation, improved network performance, and enhanced safety for all road users, reducing fuel consumption, decreased emissions, and a more sustainable transportation system.

PMID:40176965 | PMC:PMC11962783 | DOI:10.3389/frai.2025.1565287

J Sleep Res. 2025 Apr 3:e70061. doi: 10.1111/jsr.70061. Online ahead of print.

ABSTRACT

Automated sleep staging on wearable data could improve our understanding and management of epilepsy. This study evaluated sleep scoring by a deep learning model on 223 night-sleep recordings from 50 patients measured in the hospital with an electroencephalogram (EEG) and a wearable device. The model scored the sleep stage of every 30-s epoch on the EEG and wearable data, and we compared the output with a clinical expert on 20 nights, each for a different patient. The Bland-Altman analysis examined differences in the automated staging in both modalities, and using mixed-effect models, we explored sleep differences between patients with and without seizures. Overall, we found moderate accuracy and Cohen's kappa on the model scoring of standard EEG (0.73 and 0.59) and the wearable (0.61 and 0.43) versus the clinical expert. F1 scores also varied between patients and the modalities. The sensitivity varied by sleep stage and was very low for stage N1. Moreover, sleep staging on the wearable data underestimated the duration of most sleep macrostructure parameters except N2. On the other hand, patients with seizures during the hospital admission slept more each night (6.37, 95% confidence interval [CI] 5.86-7.87) compared with patients without seizures (5.68, 95% CI 5.24-6.13), p = 0.001, but also spent more time in stage N2. In conclusion, wearable EEG and accelerometry could monitor sleep in patients with epilepsy, and our approach can help automate the analysis. However, further steps are essential to improve the model performance before clinical implementation. Trial Registration: The SeizeIT2 trial was registered in clinicaltrials.gov, NCT04284072.

PMID:40176726 | DOI:10.1111/jsr.70061

Bioinform Adv. 2025 Mar 20;5(1):vbaf044. doi: 10.1093/bioadv/vbaf044. eCollection 2025.

ABSTRACT

SUMMARY: Modern biological research critically depends on public databases. The introduction and propagation of errors within and across databases can lead to wasted resources as scientists are led astray by bad data or have to conduct expensive validation experiments. The emergence of generative artificial intelligence systems threatens to compound this problem owing to the ease with which massive volumes of synthetic data can be generated. We provide an overview of several key issues that occur within the biological data ecosystem and make several recommendations aimed at reducing data errors and their propagation. We specifically highlight the critical importance of improved educational programs aimed at biologists and life scientists that emphasize best practices in data engineering. We also argue for increased theoretical and empirical research on data provenance, error propagation, and on understanding the impact of errors on analytic pipelines. Furthermore, we recommend enhanced funding for the stewardship and maintenance of public biological databases.

AVAILABILITY AND IMPLEMENTATION: Not applicable.

PMID:40177265 | PMC:PMC11964588 | DOI:10.1093/bioadv/vbaf044

Bioact Mater. 2025 Mar 19;49:437-455. doi: 10.1016/j.bioactmat.2025.02.008. eCollection 2025 Jul.

ABSTRACT

Peptide metabolites are emerging biomolecules with numerous possibilities in biomaterial-based regenerative medicine due to their inherent bioactivities. These small, naturally occurring compounds are intermediates or byproducts of larger proteins and peptides, and they can have profound effects, such as antiviral therapeutics, proangiogenic agents, and regenerative medicinal applications. This study is among the first to focus on using thymosin β4 protein-derived metabolites to pioneer novel applications for peptide metabolites in biomaterials. This study found that the novel peptide metabolite acetyl-thymosin β4 (amino acid 1-17) (Ac-Tβ1-17) exhibited significant protease inhibition activity against SARS-CoV-2, surpassing its precursor protein. Additionally, Ac-Tβ1-17 demonstrated beneficial effects, such as cell proliferation, wound healing, and scavenging of reactive oxygen species (ROS) in human umbilical vein endothelial cells (HUVEC). Integrating Ac-Tβ1-17 into a peptide-based scaffold facilitated cell growth and angiogenesis inside the scaffold and through gradual release into the surrounding environment. The Ac-Tβ1-17 peptide treatment induced significant biochemical responses in HUVEC, increasing Akt, ERK, PI3K, MEK, and Bcl-2 gene expression and proangiogenic proteins. Ac-Tβ1-17 peptide treatment showed similar results in ex vivo by enhancing mouse fetal metatarsal growth and angiogenesis. These findings highlight the potential of natural protein metabolites to generate biologically active peptides, offering a novel strategy for enhancing biomaterial compatibility. This approach holds promise for developing therapeutic biomaterials using peptide metabolites, presenting exciting prospects for future research and applications.

PMID:40177110 | PMC:PMC11964602 | DOI:10.1016/j.bioactmat.2025.02.008

Front Pharmacol. 2025 Mar 19;16:1580686. doi: 10.3389/fphar.2025.1580686. eCollection 2025.

NO ABSTRACT

PMID:40176899 | PMC:PMC11961961 | DOI:10.3389/fphar.2025.1580686

Front Genet. 2025 Mar 19;16:1579848. doi: 10.3389/fgene.2025.1579848. eCollection 2025.

ABSTRACT

Periodontitis, a prevalent global oral health issue, is primarily characterized by chronic inflammation resulting from bacterial infection. Periodontitis primarily affects the tissues surrounding and supporting the teeth, encompassing the gingival tissue, periodontal attachment apparatus, and the bony socket. The disease mechanism results from intricate interactions between hereditary factors, the body's defense mechanisms, and shifts in the composition of oral microbiota, with each element playing a crucial role in the initiation and advancement of the pathological process. The early symptoms of periodontitis are often not obvious, resulting in patients often not seeking medical attention until they are seriously ill, so finding biomarkers for periodontitis is essential for timely diagnosis and treatment. In this study, we selected two datasets (GSE10334 and GSE16134) by in-depth analysis of publicly available sequencing data of affected and unaffected gum tissue in periodontitis patients in the GEO database. To identify key genes associated with periodontitis pathogenesis and explore potential therapeutic biomarkers, we employed two complementary computational approaches: Random Forest, a robust machine learning algorithm for feature selection, and Weighted Gene Co-expression Network Analysis (WGCNA), a systems biology method for identifying co-expressed gene modules. Through comprehensive analysis of these combined datasets, our objective is to elucidate the underlying molecular pathways governing periodontal disease progression, thereby identifying novel therapeutic targets that may facilitate the design of improved clinical interventions for this condition. This study establishes a substantial scientific foundation that contributes to both clinical applications and fundamental research in periodontitis. The findings not only offer valuable insights for developing early diagnostic strategies and therapeutic interventions but also provide a robust theoretical framework to guide future investigations into the molecular mechanisms underlying this complex disease.

PMID:40176796 | PMC:PMC11961894 | DOI:10.3389/fgene.2025.1579848

Philos Trans R Soc Lond B Biol Sci. 2025 Apr 3;380(1923):20240021. doi: 10.1098/rstb.2024.0021. Epub 2025 Apr 3.

ABSTRACT

Animal vocalizations contain a varying degree of nonlinear phenomena (NLP) caused by irregular or chaotic vocal organ dynamics. Several hypotheses have been proposed to explain NLP presence, from unintentional by-products of poor vocal technique to having a functional communicative role. We aimed to disentangle the role of sex, age and physiological constraints in the occurrence of NLP in the songs of the lemur Indri indri, which are complex harmonic vocal displays organized in phrases. Age and sex affected the presence and type of NLP in songs. In particular, the proportion of the phenomena considered decreased with age, except for subharmonics. Subharmonics potentially mediate the perception of lower pitch, making signallers appear larger. Subharmonics and frequency jumps occurred in lower-pitched notes than regular units, while chaos and sidebands occurred in higher-pitched units. This suggests that different types of NLP can be associated with different vocal constraints. Finally, indris might present short-term vocal fatigue, with units occurring in the last position of a phrase having the highest probability of containing NLP. The presence of NLP in indris might result from proximate causes, such as physiological constraints, and ultimate causes, such as evolutionary pressures, which shaped the communicative role of NLP.This article is part of the theme issue 'Nonlinear phenomena in vertebrate vocalizations: mechanisms and communicative functions'.

PMID:40176518 | DOI:10.1098/rstb.2024.0021

Philos Trans R Soc Lond B Biol Sci. 2025 Apr 3;380(1923):20240019. doi: 10.1098/rstb.2024.0019. Epub 2025 Apr 3.

ABSTRACT

African penguins (Spheniscus demersus) extensively use high-frequency food solicitation signals (begging calls) to request food from parents. We studied the occurrence of nonlinear vocal phenomena (NLP) in begging calls in 91 hand-reared penguin chicks at the Southern African Foundation for the Conservation of Coastal Birds. For each chick, we recorded the begging calls daily, from the hatching of wild abandoned eggs to the release of the chicks into the wild approximately three months later. We found that most (70%) of begging calls contain NLP. The most frequently observed are sidebands (54.1%) and deterministic chaos (71.4%), and these phenomena often coexist (26.5%). We suggest that the aperiodic chaotic features of begging calls assist in increasing adults' attention and avoiding habituation. The occurrence of NLP also depends on the penguins' age, with older chicks producing more NLP in their calls. Moreover, we found that NLP significantly increased in chicks after contracting a respiratory disease (for example, bacterial infections or aspergillosis). Such findings might be useful for the timely diagnosis of penguins needing veterinary treatment, contributing to conservation efforts for this endangered species.This article is part of the theme issue 'Nonlinear phenomena in vertebrate vocalizations: mechanisms and communicative functions'.

PMID:40176507 | DOI:10.1098/rstb.2024.0019

Philos Trans R Soc Lond B Biol Sci. 2025 Apr 3;380(1923):20240009. doi: 10.1098/rstb.2024.0009. Epub 2025 Apr 3.

ABSTRACT

Nonlinear acoustic phenomena (NLP) likely facilitate the expression of distress in animal vocalizations, making calls perceptually rough and hard to ignore. Yet, their function in adult human vocal communication remains poorly understood. Here, to examine the production and perception of acoustic correlates of pain in spontaneous human nonverbal vocalizations, we take advantage of childbirth-a natural context in which labouring women typically produce a range of highly evocative loud vocalizations, including moans and screams-as they experience excruciating pain. We combine acoustic analyses of these real-life pain vocalizations with psychoacoustic experiments involving the playback of natural and synthetic calls to both naïve and expert listeners. We show that vocalizations become acoustically rougher, higher in fundamental frequency (pitch), less stable, louder and longer as child labour progresses, paralleling a rise in women's self-assessed pain. In perception experiments, we show that both naïve listeners and obstetric professionals assign the highest pain ratings to vocalizations produced in the final expulsion phase of labour. Experiments with synthetic vocal stimuli confirm that listeners rely largely on nonlinear phenomena to assess pain. Our study confirms that nonlinear phenomena communicate intense, pain-induced distress in humans, consistent with their widespread function to signal distress and arousal in vertebrate vocal signals.This article is part of the theme issue 'Nonlinear phenomena in vertebrate vocalizations: mechanisms and communicative functions'.

PMID:40176506 | DOI:10.1098/rstb.2024.0009

mBio. 2025 Apr 3:e0077825. doi: 10.1128/mbio.00778-25. Online ahead of print.

NO ABSTRACT

PMID:40176258 | DOI:10.1128/mbio.00778-25

BMC Complement Med Ther. 2025 Apr 2;25(1):124. doi: 10.1186/s12906-025-04837-7.

ABSTRACT

INTRODUCTION: Cancer is currently the second most common cause of death worldwide and is often treated with chemotherapy. Music therapy is a widely used adjunct therapy offered in oncology settings to attenuate negative impacts of treatment on patient's physical and mental health; however, music therapy research during chemotherapy is relatively scarce. The aim of this study is to evaluate the impact of group music therapy sessions with patients and caregivers on their perceived anxiety, stress, and wellbeing levels and the perception of chemotherapy-induced side effects for patients.

MATERIALS AND METHODS: This is a retrospective cohort study following the STROBE guidelines. From April to October 2022, 41 group music therapy sessions including 141 patients and 51 caregivers were conducted. Participants filled out pre- and post-intervention Visual Analogue Scales (VAS) assessing their anxiety, stress, and wellbeing levels, and for patients the intensity of chemotherapy-induced side effects.

RESULTS: The results show a statistically significant decrease of anxiety and stress levels (p < .001), an increase in well-being of patients and caregivers (p < .001, p = .009), and a decrease in patients' perceived intensity of chemotherapy-induced side effects (p = .003). Calculated effect sizes were moderate for anxiety, stress, and well-being levels, and small for chemotherapy-induced side effects.

DISCUSSION: This is the first study regarding group music therapy sessions for cancer patients and their caregivers during chemotherapy in Colombia. Music therapy has been found to be a valuable strategy to reduce psychological distress in this population and to provide opportunities for fostering self-care and social interaction.

CONCLUSIONS: Music therapy should be considered as a valuable complementary therapy during chemotherapy. However, it is crucial to conduct prospective studies with parallel group designs to confirm these preliminary findings.

PMID:40176020 | DOI:10.1186/s12906-025-04837-7

J Health Popul Nutr. 2025 Apr 2;44(1):103. doi: 10.1186/s41043-025-00845-y.

ABSTRACT

Sturge-Weber Syndrome (SWS), is a rare neuro-oculo-cutaneous disorder that presents unique diagnostic and management challenges, particularly in resource-limited settings. This editorial reflects on a recent case of an undiagnosed SWS in an Ethiopian refugee patient in Sudan, highlighting systemic barriers to healthcare access during a time of war and the importance of clinical vigilance. We advocate for local and global initiatives to further enhance diagnostic capabilities, develop integrated care systems in recognition and management of such a rare and complex condition.

PMID:40176099 | DOI:10.1186/s41043-025-00845-y

Adv Pharmacol. 2025;103:65-80. doi: 10.1016/bs.apha.2025.01.004. Epub 2025 Feb 12.

ABSTRACT

The high rate of medication failures poses a significant challenge for the pharmaceutical sector. Selecting appropriate data from experiments for ADMET (absorption, distribution, metabolism, excretion, and toxicity) prediction and applying it effectively in the context of physiological characteristics is difficult. Currently, ADMET prediction is conducted early in the drug design process to filter out molecules with weak pharmacokinetic properties. Numerous ADMET models for prediction have been designed using computational methods. Verified ADMET datasets have been determined through experiments, utilizing key classifying factors and descriptors to develop in silico approaches. This chapter discusses the relevance of ADMET evaluation in drug design, methodologies for model creation, available ADMET predictive tools, and the limitations of these predicted models.

PMID:40175055 | DOI:10.1016/bs.apha.2025.01.004

Sci Rep. 2025 Apr 2;15(1):11236. doi: 10.1038/s41598-025-89911-3.

ABSTRACT

The early detection of brain tumors is very important for treating them and improving the quality of life for patients. Through advanced imaging techniques, doctors can now make more informed decisions. This paper introduces a framework for a tumor detection system capable of grading gliomas. The system's implementation begins with the acquisition and analysis of brain magnetic resonance images. Key features indicative of tumors and gliomas are extracted and classified as independent components. A deep learning model is then employed to categorize these gliomas. The proposed model classifies gliomas into three primary categories: meningioma, pituitary, and glioma. Performance evaluation demonstrates a high level of accuracy (99.21%), specificity (98.3%), and sensitivity (97.83%). Further research and validation are essential to refine the system and ensure its clinical applicability. The development of accurate and efficient tumor detection systems holds significant promise for enhancing patient care and improving survival rates.

PMID:40175410 | DOI:10.1038/s41598-025-89911-3

Rev Neurol (Paris). 2025 Apr 1:S0035-3787(25)00487-4. doi: 10.1016/j.neurol.2025.03.006. Online ahead of print.

ABSTRACT

In recent years, artificial intelligence (AI) has become an increasingly prominent focus of medical research, significantly impacting epileptology as well. Studies on deep learning (DL) and machine learning (ML) - the core of AI - have explored their applications in epilepsy imaging, primarily focusing on lesion detection, lateralization and localization of epileptogenic areas, postsurgical outcome prediction and automatic differentiation between people with epilepsy and healthy individuals. Various AI-driven approaches are being investigated across different neuroimaging modalities, with the ultimate goal of integrating these tools into clinical practice to enhance the diagnosis and treatment of epilepsy. As computing power continues to advance, the development, research integration, and clinical implementation of AI applications are expected to accelerate, making them even more effective and accessible. However, ensuring the safety of patient data will require strict regulatory measures. Despite these challenges, AI represents a transformative opportunity for medicine, particularly in epilepsy neuroimaging. Since ML and DL models thrive on large datasets, fostering collaborations and expanding open-access databases will become increasingly pivotal in the future.

PMID:40175210 | DOI:10.1016/j.neurol.2025.03.006