{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T22:11:35Z","timestamp":1791929495002,"version":"4.3.4"},"reference-count":72,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017170","name":"Thailand Science Research and Innovation","doi-asserted-by":"publisher","award":["4775447"],"award-info":[{"award-number":["4775447"]}],"id":[{"id":"10.13039\/501100017170","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Radiographic imaging remains a cornerstone of diagnostic practice. However, accurate interpretation faces challenges from subtle visual signatures, anatomical variability, and inter-observer inconsistency. Conventional deep learning approaches, such as convolutional neural networks and vision transformers, deliver strong predictive performance but often lack anatomical grounding and interpretability, limiting their trustworthiness in imaging applications. To address these challenges, we present SpineNeuroSym, a neuro-geometric imaging framework that unifies geometry-aware learning and symbolic reasoning for explainable medical image analysis. The framework integrates weakly supervised keypoint and region-of-interest discovery, a dual-stream graph\u2013transformer backbone, and a Differentiable Radiographic Geometry Module (dRGM) that computes clinically relevant indices (e.g., slip ratio, disc asymmetry, sacroiliac spacing, and curvature measures). A Neuro-Symbolic Constraint Layer (NSCL) enforces monotonic logic in image-derived predictions, while a Counterfactual Geometry Diffusion (CGD) module generates rare imaging phenotypes and provides diagnostic auditing through counterfactual validation. Evaluated on a comprehensive dataset of 1613 spinal radiographs from Sunpasitthiprasong Hospital encompassing six diagnostic categories\u2014spondylolisthesis (n = 496), infection (n = 322), spondyloarthropathy (n = 275), normal cervical (n = 192), normal thoracic (n = 70), and normal lumbar spine (n = 258)\u2014SpineNeuroSym achieved 89.4% classification accuracy, a macro-F1 of 0.872, and an AUROC of 0.941, outperforming eight state-of-the-art imaging baselines. These results highlight how integrating neuro-geometric modeling, symbolic constraints, and counterfactual validation advances explainable, trustworthy, and reproducible medical imaging AI, establishing a pathway toward transparent image analysis systems.<\/jats:p>","DOI":"10.3390\/jimaging12020059","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T17:40:22Z","timestamp":1769622022000},"page":"59","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Neuro-Geometric Graph Transformers with Differentiable Radiographic Geometry for Spinal X-Ray Image Analysis"],"prefix":"10.3390","volume":"12","author":[{"given":"Vuth","family":"Kaveevorayan","sequence":"first","affiliation":[{"name":"Orthopedic Department, Sunpasittiprasong Hospital, Ubon Ratchathani 34000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5896-4895","authenticated-orcid":false,"given":"Rapeepan","family":"Pitakaso","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Optimization SMART Laboratory, Industrial Engineering Department, Faculty of Engineering, Ubon Ratchathani University, Ubon Ratchathani 34190, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7720-7630","authenticated-orcid":false,"given":"Thanatkij","family":"Srichok","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Optimization SMART Laboratory, Industrial Engineering Department, Faculty of Engineering, Ubon Ratchathani University, Ubon Ratchathani 34190, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7747-1922","authenticated-orcid":false,"given":"Natthapong","family":"Nanthasamroeng","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Optimization SMART Laboratory, Engineering Technology Department, Faculty of Industrial Technology, Ubon Ratchathani Rajabhat University, Ubon Ratchathani 34000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5972-317X","authenticated-orcid":false,"given":"Chutchai","family":"Kaewta","sequence":"additional","affiliation":[{"name":"Digital Innovation, Faculty of Computer Science, Ubon Ratchathani Rajabhat University, Ubon Ratchathani 34000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peerawat","family":"Luesak","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Faculty of Engineering, Rajamangala University of Technology Lanna, Chiang Rai 57120, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"108118","DOI":"10.1016\/j.bspc.2025.108118","article-title":"A Hybrid Deep Learning Approach Using XceptionNet and Vision Transformer for Accurate Chest Disease Detection from X-Ray Images","volume":"110","author":"Bhuvanya","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"104623","DOI":"10.1016\/j.compbiomed.2021.104623","article-title":"Deep Learning Segmentation of Transverse Musculoskeletal Ultrasound Images for Neuromuscular Disease Assessment","volume":"135","author":"Marzola","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"110505","DOI":"10.1016\/j.mri.2025.110505","article-title":"RCLM-Net: A Rich-Club Properties Based Lightweight Deep Neural Network for Multimodal Sequence Spine MR Images Segmentation","volume":"123","author":"He","year":"2025","journal-title":"Magn. Reson. Imaging"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2642","DOI":"10.1016\/j.acra.2024.11.045","article-title":"Development and Validation of Multiparametric MRI-Based Interpretable Deep Learning Radiomics Fusion Model for Predicting Lymph Node Metastasis and Prognosis in Rectal Cancer: A Two-Center Study","volume":"32","author":"Yang","year":"2025","journal-title":"Acad. Radiol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1016\/j.acra.2024.11.037","article-title":"Non-Invasive Prediction of Lymph Node Metastasis in NSCLC Using Clinical, Radiomics, and Deep Learning Features from 18F-FDG PET\/CT Based on Interpretable Machine Learning","volume":"32","author":"Duan","year":"2025","journal-title":"Acad. Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"108221","DOI":"10.1016\/j.engappai.2024.108221","article-title":"Diffusion-Based Wasserstein Generative Adversarial Network for Blood Cell Image Augmentation","volume":"133","author":"Ngasa","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107360","DOI":"10.1016\/j.bspc.2024.107360","article-title":"FedGraphMRI-Net: A Federated Graph Neural Network Framework for Robust MRI Reconstruction Across Non-IID Data","volume":"102","author":"Ahmed","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"108249","DOI":"10.1016\/j.bspc.2025.108249","article-title":"Multimodal Medical Image Fusion Based on Edge Detection and Salient Feature Extraction","volume":"110","author":"Zheng","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"103154","DOI":"10.1016\/j.artmed.2025.103154","article-title":"Symbolic and Hybrid AI for Brain Tissue Segmentation Using Spatial Model Checking","volume":"167","author":"Belmonte","year":"2025","journal-title":"Artif. Intell. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.diii.2022.09.005","article-title":"Generative Adversarial Networks (GAN)-Based Data Augmentation of Rare Liver Cancers: The SFR 2021 Artificial Intelligence Data Challenge","volume":"104","author":"Lawrance","year":"2023","journal-title":"Diagn. Interv. Imaging"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103668","DOI":"10.1016\/j.media.2025.103668","article-title":"Robust Image Representations with Counterfactual Contrastive Learning","volume":"105","author":"Roschewitz","year":"2025","journal-title":"Med. Image Anal."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"112745","DOI":"10.1016\/j.knosys.2024.112745","article-title":"Data Augmentation Based on Large Language Models for Radiological Report Classification","volume":"308","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"128129","DOI":"10.1016\/j.eswa.2025.128129","article-title":"Weakly Supervised Lesion Localization and Attribution for OCT Images with a Guided Counterfactual Explainer Model","volume":"287","author":"Jiang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"102975","DOI":"10.1016\/j.jcot.2025.102975","article-title":"Correlation Between MRI and DTI Parameters in Acute Thoracic Spinal Cord Injury and Clinical Outcomes: A Prospective Observational Study","volume":"66","author":"Verma","year":"2025","journal-title":"J. Clin. Orthop. Trauma"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"105583","DOI":"10.1016\/j.cmpb.2020.105583","article-title":"Using Deep Learning to Generate Synthetic B-Mode Musculoskeletal Ultrasound Images","volume":"196","author":"Cronin","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"102290","DOI":"10.1016\/j.compmedimag.2023.102290","article-title":"Incremental Learning for an Evolving Stream of Medical Ultrasound Images Via Counterfactual Thinking","volume":"109","author":"Gao","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1186\/s41747-024-00529-y","article-title":"Image Biomarkers and Explainable AI: Handcrafted Features Versus Deep Learned Features","volume":"8","author":"Rundo","year":"2024","journal-title":"Eur. Radiol. Exp."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"108042","DOI":"10.1016\/j.compbiomed.2024.108042","article-title":"Evidence-Based XAI: An Empirical Approach to Design More Effective and Explainable Decision Support Systems","volume":"170","author":"Famiglini","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2086","DOI":"10.1016\/j.spinee.2024.06.009","article-title":"Deep Learning-Based Detection of Lumbar Spinal Canal Stenosis Using Convolutional Neural Networks","volume":"24","author":"Suzuki","year":"2024","journal-title":"Spine J."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1016\/j.spinee.2025.01.020","article-title":"Automated Measurement of Pelvic Parameters Using Convolutional Neural Network in Complex Spinal Deformities: Overcoming Challenges in Coronal Deformity Cases","volume":"25","author":"Kang","year":"2025","journal-title":"Spine J."},{"key":"ref_21","first-page":"1377","article-title":"Spinal Vertebral Fracture Detection and Fracture Level Assessment Based on Deep Learning","volume":"79","author":"Wang","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"106827","DOI":"10.1016\/j.crad.2025.106827","article-title":"A Deep Learning Pipeline for Systematic and Accurate Vertebral Fracture Reporting in Computed Tomography","volume":"83","author":"Glessgen","year":"2025","journal-title":"Clin. Radiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"112244","DOI":"10.1016\/j.ejrad.2025.112244","article-title":"The Value of a Deep Learning Image Reconstruction Algorithm for Assessing Vertebral Compression Fractures Using Dual-Energy Computed Tomography","volume":"190","author":"Tang","year":"2025","journal-title":"Eur. J. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"107813","DOI":"10.1016\/j.neunet.2025.107813","article-title":"DiffCNN: A Collaborative Framework of Diffusion Model and CNN for Semi-Supervised Medical Image Segmentation","volume":"191","author":"Xu","year":"2025","journal-title":"Neural Netw."},{"key":"ref_25","first-page":"100039","article-title":"Electroencephalography Decoding Model Based on Fusion Deep Graph Convolutional Neural Network for Spinal Cord Injury","volume":"1","author":"Lou","year":"2025","journal-title":"Healthc. Rehabil."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"111251","DOI":"10.1016\/j.engappai.2025.111251","article-title":"Multi-Axis Vision Transformer for Medical Image Segmentation","volume":"158","author":"Khan","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"110675","DOI":"10.1016\/j.engappai.2025.110675","article-title":"Advancing Interpretable Cardiac Disease Diagnosis Via a Transformer-Convolutional Hybrid Network on Electrocardiograms","volume":"152","author":"Liu","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"102651","DOI":"10.1016\/j.rineng.2024.102651","article-title":"Towards Ovarian Cancer Diagnostics: A Vision Transformer-Based Computer-Aided Diagnosis Framework with Enhanced Interpretability","volume":"23","author":"Alahmadi","year":"2024","journal-title":"Results Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"110559","DOI":"10.1016\/j.clinimag.2025.110559","article-title":"Global Radiology: Building Equitable and Effective Partnerships with Low and Middle-Income Countries","volume":"125","author":"Kwarteng","year":"2025","journal-title":"Clin. Imaging"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1016\/j.jacr.2024.04.025","article-title":"Building Radiology Equity: Themes from the 2023 RAD-AID Conference on International Radiology and Global Health","volume":"21","author":"Lugossy","year":"2024","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"108302","DOI":"10.1016\/j.bspc.2025.108302","article-title":"Bone Fracture Detection and Classification Using Node-Level Capsule Graph Neural Network with X-Ray Images of Broken and Unbroken Bones","volume":"110","author":"Kanagaraj","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.cogr.2025.05.001","article-title":"A Multi-View Graph Neural Network Approach for Magnetic Resonance Imaging-Based Diagnosis of Knee Injuries","volume":"5","author":"Deng","year":"2025","journal-title":"Cogn. Robot."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.gaitpost.2025.03.007","article-title":"Automated Quantification of the Anatomic Accuracy of Muscle Paths and Its Application in an Image-Based Subject-Specific Modeling Workflow for Adult Spinal Deformity","volume":"119","author":"Peeters","year":"2025","journal-title":"Gait Posture"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"129038","DOI":"10.1016\/j.neucom.2024.129038","article-title":"IncARMAG: A Convolutional Neural Network with Multi-Level Autoregressive Moving Average Graph Convolutional Processing Framework for Medical Image Classification","volume":"617","author":"Remigio","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"129804","DOI":"10.1016\/j.neucom.2025.129804","article-title":"Backpropagation-Based Learning with Local Derivative Approximation and Memory Replay in Biologically Plausible Neural Systems","volume":"634","author":"Boone","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"100522","DOI":"10.1016\/j.patter.2022.100522","article-title":"Backpropagation with Biologically Plausible Spatiotemporal Adjustment for Training Deep Spiking Neural Networks","volume":"3","author":"Shen","year":"2022","journal-title":"Patterns"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"101379","DOI":"10.1016\/j.mtbio.2024.101379","article-title":"Synergistic Enhancement of Spinal Fusion in Preclinical Models Using Low-Dose rhBMP-2 and Stromal Vascular Fraction in an Injectable Hydrogel Composite","volume":"30","author":"Lee","year":"2025","journal-title":"Mater. Today Bio"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"112014","DOI":"10.1016\/j.ejrad.2025.112014","article-title":"The Need for Balancing \u2019Black Box\u2019 Systems and Explainable Artificial Intelligence: A Necessary Implementation in Radiology","volume":"185","author":"Benedetti","year":"2025","journal-title":"Eur. J. Radiol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"107014","DOI":"10.1016\/j.bspc.2024.107014","article-title":"Enhancing Histopathological Medical Image Classification for Early Cancer Diagnosis Using Deep Learning and Explainable AI\u2014LIME & SHAP","volume":"100","author":"Ukwuoma","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"110355","DOI":"10.1016\/j.engappai.2025.110355","article-title":"DC-Net: Decomposing and Coupling Saliency Map for Lesion Segmentation in Ultrasound Images","volume":"148","author":"Ning","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"107085","DOI":"10.1016\/j.bspc.2024.107085","article-title":"Patch-Based Interpretable Deep Learning Framework for Alzheimer\u2019s Disease Diagnosis Using Multimodal Data","volume":"100","author":"Zhang","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"105642","DOI":"10.1016\/j.ebiom.2025.105642","article-title":"AI in Radiological Imaging of Soft-Tissue and Bone Tumours: A Systematic Review Evaluating Against CLAIM and FUTURE-AI Guidelines","volume":"114","author":"Spaanderman","year":"2025","journal-title":"eBioMedicine"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"127238","DOI":"10.1016\/j.eswa.2025.127238","article-title":"WCFormer: An Interpretable Deep Learning Framework for Heart Sound Signal Analysis and Automated Diagnosis of Cardiovascular Diseases","volume":"276","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"100856","DOI":"10.1016\/j.websem.2024.100856","article-title":"Integrating Knowledge Graphs with Symbolic AI: The Path to Interpretable Hybrid AI Systems in Medicine","volume":"84","author":"Vidal","year":"2025","journal-title":"J. Web Semant."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"110368","DOI":"10.1016\/j.compbiomed.2025.110368","article-title":"Enhancing Wisdom Teeth Detection in Panoramic Radiographs Using Multi-Channel Convolutional Neural Network with Clinical Knowledge","volume":"192","author":"Fang","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1278","DOI":"10.1016\/j.procs.2024.04.121","article-title":"NeSyKHG: Neuro-Symbolic Knowledge Hypergraphs","volume":"235","author":"Bhuyan","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"102406","DOI":"10.1016\/j.datak.2025.102406","article-title":"Logic-Infused Knowledge Graph QA: Enhancing Large Language Models for Specialized Domains Through Prolog Integration","volume":"157","author":"Bashir","year":"2025","journal-title":"Data Knowl. Eng."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"113737","DOI":"10.1016\/j.matdes.2025.113737","article-title":"Neuro-Symbolic Artificial Intelligence in Accelerated Design for 4d Printing: Status, Challenges, and Perspectives","volume":"252","author":"Bougzime","year":"2025","journal-title":"Mater. Des."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.compbiomed.2016.11.018","article-title":"Combination of Visual and Symbolic Knowledge: A Survey in Anatomy","volume":"80","author":"Banerjee","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref_50","first-page":"104904","article-title":"Neanderthal Cave Art? A Proposal from Cognitive Archaeology","volume":"61","year":"2025","journal-title":"J. Archaeol. Sci. Rep."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"121366","DOI":"10.1016\/j.neuroimage.2025.121366","article-title":"Rank Labels Scaffold Social Cognitive Maps in the Hippocampal-Entorhinal System","volume":"317","author":"Liu","year":"2025","journal-title":"NeuroImage"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"111416","DOI":"10.1016\/j.patcog.2025.111416","article-title":"Generative Feature Style Augmentation for Domain Generalization in Medical Image Segmentation","volume":"162","author":"Huang","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"107744","DOI":"10.1016\/j.compbiomed.2023.107744","article-title":"Cross-Domain Attention-Guided Generative Data Augmentation for Medical Image Analysis with Limited Data","volume":"168","author":"Xu","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"104130","DOI":"10.1016\/j.ipm.2025.104130","article-title":"Breaking Data Barriers in Medical Diagnosis with MSDGD Framework Based on Gaussian Diffusion Generation","volume":"62","author":"Jia","year":"2025","journal-title":"Inf. Process. Manag."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"103100","DOI":"10.1016\/j.media.2024.103100","article-title":"GAN-Based Generation of Realistic 3D Volumetric Data: A Systematic Review and Taxonomy","volume":"93","author":"Ferreira","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"110625","DOI":"10.1016\/j.compbiomed.2025.110625","article-title":"Radiology Report Generation Using Automatic Keyword Adaptation, Frequency-Based Multi-Label Classification and Text-to-Text Large Language Models","volume":"196","author":"He","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"103264","DOI":"10.1016\/j.media.2024.103264","article-title":"From Vision to Text: A Comprehensive Review of Natural Image Captioning in Medical Diagnosis and Radiology Report Generation","volume":"97","author":"Serrano","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"108810","DOI":"10.1016\/j.cmpb.2025.108810","article-title":"Causal Insights from Clinical Information in Radiology: Enhancing Future Multimodal AI Development","volume":"268","author":"Jantscher","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_59","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"128793","DOI":"10.1016\/j.eswa.2025.128793","article-title":"AgriTL-ViT: A Vision Transformer Model with Attention Techniques for Classification of Plant Leaf Disease","volume":"294","author":"Srivastava","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"107666","DOI":"10.1016\/j.neunet.2025.107666","article-title":"Rect-ViT: Rectified Attention Via Feature Attribution Can Improve the Adversarial Robustness of Vision Transformers","volume":"190","author":"Kang","year":"2025","journal-title":"Neural Netw."},{"key":"ref_62","first-page":"1769","article-title":"AG-GCN: Vehicle Re-Identification Based on Attention-Guided Graph Convolutional Network","volume":"84","author":"Sun","year":"2025","journal-title":"Comput. Mater. Contin."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"113974","DOI":"10.1016\/j.knosys.2025.113974","article-title":"MFLM-GCN: Multi-Relation Fusion and Latent-Relation Mining Graph Convolutional Network for Entity Alignment","volume":"325","author":"Ai","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"113514","DOI":"10.1016\/j.asoc.2025.113514","article-title":"Twin-Layer Attention Graph Convolutional Network (TLA-GCN): Enhancing Abnormality Detection in Chest X-Rays","volume":"181","author":"Rajeshwari","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_65","first-page":"100383","article-title":"Enhanced Water Quality Prediction by LSTM and Graph Attention Network (L-GAT): An Analytical Study of the Pearl River Basin","volume":"28","author":"Liu","year":"2025","journal-title":"Water Res. X"},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"109390","DOI":"10.1016\/j.istruc.2025.109390","article-title":"Rapid Seismic Response Prediction of Steel Frames Based on Graph Attention Network (GAT) with Mamba Blocks","volume":"79","author":"Peng","year":"2025","journal-title":"Structures"},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"137115","DOI":"10.1016\/j.energy.2025.137115","article-title":"Conditional Denoising Diffusion Probabilistic Model Based Ante-Hoc Explainable Scenario Generation for Power Systems Dispatch","volume":"332","author":"Ma","year":"2025","journal-title":"Energy"},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"102115","DOI":"10.1016\/j.media.2021.102115","article-title":"Evaluation and Comparison of Accurate Automated Spinal Curvature Estimation Algorithms with Spinal Anterior-Posterior X-Ray Images: The AASCE2019 Challenge","volume":"72","author":"Wang","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1007\/s00586-009-0913-0","article-title":"A Review of Methods for Quantitative Evaluation of Spinal Curvature","volume":"18","author":"Vrtovec","year":"2009","journal-title":"Eur Spine J"},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1016\/j.jacr.2025.04.007","article-title":"Large Language Models for Global Health Clinics: Opportunities and Challenges","volume":"22","author":"Tripathi","year":"2025","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_71","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1136\/ard.16.4.494","article-title":"Radiological Assessment of Osteo-Arthrosis","volume":"16","author":"Kellgren","year":"1957","journal-title":"Ann. Rheum Dis."},{"key":"ref_72","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1097\/00003086-198007000-00019","article-title":"Methods of Measuring in Legg-Calv\u00e9-Perthes Disease with Special Regard to the Prognosis","volume":"150","author":"Mose","year":"1980","journal-title":"Clin. Orthop. Relat. Res."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/2\/59\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T17:51:59Z","timestamp":1769622719000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/2\/59"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":72,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["jimaging12020059"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12020059","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,28]]}}}