<?xml version="1.0" encoding="utf-8"?>
    <rss version="2.0">
      <channel xmlns:content="http://purl.org/rss/1.0/modules/content/">
        <title>Frontiers in Imaging | New and Recent Articles</title>
        <link>https://www.frontiersin.org/journals/imaging</link>
        <description>RSS Feed for Frontiers in Imaging | New and Recent Articles</description>
        <language>en-us</language>
        <generator>Frontiers Feed Generator,version:1</generator>
        <pubDate>2026-09-17T17:20:19.321+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1882713</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1882713</link>
        <title><![CDATA[A dynamic quantum clustering approach to brain tumor segmentation]]></title>
        <pubdate>2026-09-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Jacksson Sánchez</author><author>Miguel Martín-Landrove</author>
        <description><![CDATA[IntroductionData clustering is a key tool in medical image analysis and classification. Traditional methods such as k-means often require prior knowledge of the number of clusters and may perform poorly in complex, high-dimensional medical datasets. This study develops and evaluates a novel segmentation method based on Dynamic Quantum Clustering (DQC) for brain tumor MRI analysis.MethodsThe method is first applied to contrast-enhanced T1-weighted MRI and compared with conventional algorithms such as k-means. DQC is then extended to multi-modality MRI datasets using two approaches: independent analysis of each modality and joint analysis of fused multi-modality data. Algorithm parameters are optimized to achieve rapid convergence of the clustering dynamics.Results and discussionResults show that, in single-modality MRI, DQC performs comparably or better than k-means while eliminating the need to predefine the number of clusters. In multi-modality applications, DQC provides effective segmentation for both independent and fused datasets. These findings demonstrate that Dynamic Quantum Clustering is a flexible and efficient approach for medical image segmentation, with strong potential for broader applications in medical image analysis.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1966936</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1966936</link>
        <title><![CDATA[Differentially private federated learning for image analysis in smart-city surveillance]]></title>
        <pubdate>2026-09-10T00:00:00Z</pubdate>
        <category>Mini Review</category>
        <author>Namrata Pandya</author><author>Dhrupa Mistry</author>
        <description><![CDATA[Federated learning combined with differential privacy offers a practical way to train image-analysis models on distributed camera and sensor networks. This combination is most often implemented through DP-SGD, and it avoids centralizing raw visual data. This mini review examines differentially private federated learning (DPFL) in smart-city surveillance, tracing the method from the original DP-SGD formulation to newer, high-accuracy variants, and examining the gradient-leakage threat DPFL is intended to mitigate. We draw on more than 60 sources. These span federated-learning architectures, differential-privacy mechanisms, gradient-inversion attacks, and image-centric applications in surveillance, remote sensing, and IoT-enabled smart cities. Together, they show that DPFL is a credible, rapidly maturing framework rather than a finished solution. Across published CIFAR-10 results at a fixed privacy budget, the gap between private and non-private image classification has narrowed substantially. It fell from about 22 percentage points in 2016 to roughly 13–14 points by 2022. Applied smart-city systems now combine DP with secure aggregation, homomorphic encryption, or adaptive noise. These systems report accuracies above 90%, with reduced communication overhead. The review concludes by identifying the main barriers to moving DPFL from curated benchmarks and hybrid pilot systems to heterogeneous, real-world camera networks.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1885292</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1885292</link>
        <title><![CDATA[GRALIS-Report: auditable region-level attribution and structured clinical report generation for breast cancer histology]]></title>
        <pubdate>2026-09-09T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Raimondo Fanale</author>
        <description><![CDATA[BackgroundDeep learning classifiers for breast cancer histology achieve expert-level accuracy but do not explain which tissue regions drove the diagnosis. We present GRALIS-Report, an attribution pipeline with two defining architectural properties: raw images never enter the report generation stage, and no information is fused across modalities in a latent space. Attribution signals—not pixels—are the sole input to pathology-oriented language; every modality transition is explicit, symbolic, and traceable to the stored structured attribution record, making every visual-totext inference auditable and independently verifiable.MethodsThe system: (i) trains a DenseNet-121 classifier on BreaKHis via knowledge distillation (high internal accuracy on a patient-level split); (ii) applies GRALIS—which transforms the image into a semantic attribution signal: a per-superpixel importance score ϕi computed via coalition-conditioned path integration—and (iii) converts that structured signal into a research SOAP-style report. Formal theoretical properties—canonical form, a priori convergence bound, and structural incompatibility of locality with exact completeness—are proved in a companion preprint (arXiv:2605.05480); the present paper is entirely experimental.ResultOn the BreaKHis test set (1,187 images), independent faithfulness benchmarks place GRALIS at rank 2 of 6 on pixel-level deletion AUC and rank 2 of 3 on ROAD MoRF AUC (the three methods for which ROAD was computed), with the largest MoRF-LeRF discrimination gap among the three evaluated methods. This ranking reflects a deliberate design trade-off: by operating at superpixel rather than pixel resolution, GRALIS sacrifices marginal pixel-level faithfulness relative to Integrated Gradients in exchange for region level spatial coherence, a pre-run Monte Carlo sample-size bound (not numerically instantiated in this paper), and a fully auditable attribution-to-report pipeline—properties that pixel-precise methods do not jointly provide. Cross-dataset evaluation on two held-out external subsets further characterises this trade-off: on IDC Breast Cancer (50 × 50 px patches, frozen backbone), GRALIS ranks first on both Deletion AUC and ROAD MoRF; on PatchCamelyon (96 × 96 px), GRALIS ranks sixth—a result plausibly associated with a mismatch between the fixed superpixel granularity (nseg = 30) and the finer discriminative feature scale of lymph-node patches, although a dedicated nseg ablation would be required to test this explanation. A supplementary ExpiScores profile is reported alongside these independent metrics; we caution that this metric shares authorship with the present work and should be weighted accordingly. The deterministic engine generated 1,187/1,187 syntactically complete reports with no execution failures; 1,175 (98.99%) corresponded to correct classifier predictions, with the 12 discordant cases identified retrospectively using test labels, operating fully offline. An expert perception discordance study (N = 4 anatomopathologists, 60 cases) reveals marked inter-rater variability in perceived clinical utility, suggesting that perceived explanation utility may not constitute a stable ground truth in histopathology.RESULTSThis is reported as a methodological finding for the XAI evaluation community, not as evidence of clinical utility. No clinical efficacy claims are made.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1910013</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1910013</link>
        <title><![CDATA[Artificial intelligence in breast cancer imaging: a systematic review of detection, segmentation, explainability, and clinical translation]]></title>
        <pubdate>2026-09-03T00:00:00Z</pubdate>
        <category>Systematic Review</category>
        <author>Iqra Iqbal Khan</author><author>Syed Adil Hussain Shah</author><author>Alexandra Tsipourakis</author><author>Marta Malavolta</author><author>Aleesha Aleesha</author><author>Syed Baqir Hussain Shah</author><author>Mozhdeh Hajiani</author><author>Andrea Buccoliero</author><author>Konstantinos Panagiotopoulos</author><author>Syed Taimoor Hussain Shah</author><author>Marco Agostino Deriu</author>
        <description><![CDATA[IntroductionBreast cancer remains the most commonly diagnosed malignancy in women worldwide, with approximately 2.3 million new cases and 670,000 deaths in 2022. Artificial intelligence (AI) is increasingly being applied across breast imaging for detection, characterization, segmentation, risk stratification, explainability, and clinical translation.MethodsThis systematic review synthesized 284 eligible peer-reviewed publications published between 2015 and 2025, identified through a PRISMA 2020-compliant search of four indexed databases. A supplementary relevance-ranked Google Scholar screen was reported separately. A targeted May 2026 narrative update of recent prospective and implementation studies was also conducted without adding these records to the PRISMA denominator.ResultsThe reviewed evidence encompassed classical machine learning and radiomics, convolutional neural networks, YOLO-family detectors, vision transformers and hybrid CNN-Transformer architectures, U-Net variants, Mask R-CNN, SAM, and MedSAM across mammography, tomosynthesis, MRI, ultrasound, contrast-enhanced mammography, and emerging photoacoustic imaging. The evidence highlights advances in explainable AI, multimodal and radiogenomic fusion, federated learning, and open-source deployment, while persistent challenges include data heterogeneity, class imbalance, domain shift, bias, incomplete calibration, and limited prospective validation. Retrospective benchmark findings were derived from the 284-study systematic corpus, whereas prospective clinical utility and real-world implementation were informed by the separate 2026 narrative update.DiscussionAI shows substantial potential to enhance breast cancer imaging, but broader clinical translation requires robust external and prospective validation, improved calibration, assessment of generalizability and bias, and integration into clinical workflows. Supplementary Data Sheet S1 should be interpreted as a provenance-tagged evidence map rather than a formal study-level risk-of-bias assessment, with 38 entries verified from full text, 48 based on abstracts, and 198 based on DOI/source pages or other web-accessible records.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1845480</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1845480</link>
        <title><![CDATA[Wavelet-based features to improve cross-forgery generalization in deepfake detection]]></title>
        <pubdate>2026-08-05T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Niccolò Marini</author><author>Stefano Berretti</author><author>Roberto Caldelli</author>
        <description><![CDATA[Deepfake detection remains a challenging problem due to the ever-evolving techniques used to synthesize realistic fake images and videos. Traditional detection methods primarily operate in the pixel domain, often struggling to generalize across different forgery types. In this work, we explore an approach that integrates wavelet-based frequency analysis with deep learning to enhance deepfake detection. By decomposing input images using the Discrete Wavelet Transform (DWT), we extract multi-resolution features that capture both global structures and fine-grained manipulation artifacts; such features are then input to a neural network. Our results show that level-1 DWT features mainly induce a sensitivity-specificity tradeoff: they improve fake-class sensitivity and F1 in cross-forgery settings, while RGB models retain stronger specificity and in-forgery performance. This suggests that wavelet sub-bands expose manipulation cues that are useful for detecting unseen fake classes, but they should not be interpreted as a uniform robustness improvement.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1836077</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1836077</link>
        <title><![CDATA[A deep learning-based decision fusion framework for image forgery localization]]></title>
        <pubdate>2026-07-16T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Pengpeng Yang</author><author>Daniele Baracchi</author><author>Dasara Shullani</author><author>Marco Fontani</author><author>Rongrong Ni</author><author>Yao Zhao</author><author>Alessandro Piva</author>
        <description><![CDATA[As an answer to the need to prove the authenticity of digital images, several forensic tools for image forgery localization have been proposed in the past. However, authenticity analysis remained a challenging task, which requires an expert's knowledge to correctly interpret each forensic algorithm's output. Moreover, since different tools look for different manipulation traces, a thorough analysis requires the joint interpretation of the maps produced by several tools, which is nontrivial since each tool's reliability is possibly affected by different elements. Recently, deep learning-based forgery localization schemes were proposed, allowing for more automated reasoning; however, their accuracy significantly decreases when they are tested on forgeries that deviate from those used for the training phase. This work proposes a deep learning-based framework that merges the forgery localization maps provided by model-based image forensics tools based on the U-Net architecture. The experiments show that the proposed approach improves the quality of forgery localization maps compared to those produced by single tools and by state-of-the-art fusion frameworks while simultaneously achieving a desirable generalization capability.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1844310</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1844310</link>
        <title><![CDATA[Comprehensive guideline for X-ray microtomography-guided bone analysis and histology applied to the assessment of defect repair in long and flat bones]]></title>
        <pubdate>2026-07-10T00:00:00Z</pubdate>
        <category>Methods</category>
        <author>Bruno Henrique Costa</author><author>Isabela Louise Pereira Lopes</author><author>Michelle de Oliveira</author><author>Tamires Aparecida Jaques de Resende</author><author>Murilo Leone Miranda Fajardo</author><author>Anna Beatriz Modesto Pires</author><author>Anderson Camargo Moreira</author><author>Iara Frangiotti Mantovani</author><author>Rodrigo Nagata</author><author>Talita Martins</author><author>Eduardo Henrique Martins Nunes</author><author>Taíse Matte Manhabosco</author><author>Erika Costa de Alvarenga</author>
        <description><![CDATA[Bone regeneration studies require reliable analytical tools capable of assessing both microstructural and cellular aspects of tissue repair. This article presents a comprehensive methodological guide that integrates microcomputed tomography (micro-CT) and histological analyses for standardized evaluation of bone defect repair in rodent models, focusing on the tibia (long bone) and calvaria (flat bone). We describe detailed surgical protocols for defect creation, imaging workflows for micro-CT acquisition, reconstruction, and morphometric quantification, alongside histological processing and semi-quantitative scoring of tissue parameters. Illustrative results demonstrate how micro-CT enables three-dimensional, non-destructive quantification of mineralized tissue, while histology provides complementary insights into non-mineralized structures, vascularization, and cellular organization. The combined use of these techniques enhances reproducibility, ensures methodological consistency, and allows for robust comparisons across studies. By establishing a standardized workflow, this protocol supports translational research in bone repair and offers a valuable resource for evaluating regenerative strategies and biomaterials.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1854187</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1854187</link>
        <title><![CDATA[Deep learning for secure imaging and video surveillance in smart cities: from bibliometric mapping to real-world implementations]]></title>
        <pubdate>2026-07-08T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Samad Olalekan Olansile</author><author>Oluwatosin Ahmed Amodu</author><author>Mohamed Sani Adam</author><author>Isaac Oluwafemi Elesemoyo</author><author>Raja Azlina Raja Mahmood</author>
        <description><![CDATA[The integration of imaging sensors, unmanned aerial vehicles (UAVs), and satellite platforms has expanded capabilities in surveillance, smart-city systems, and remote sensing. Advances in deep learning and computer vision enable automated detection, tracking, and scene understanding across diverse environments, including safety-critical settings; however, these systems impose requirements for security, privacy, and adversarial robustness. This paper presents a dual-database bibliometric and science-mapping analysis of deep learning research for secure imaging and video surveillance. Two independently constructed corpora, derived from Scopus (𝒟S) and Web of Science (𝒟W) for the period 2010–early 2026, are analyzed using VOSviewer-based keyword co-occurrence clustering to identify dominant research themes and methodological trends across surveillance, smart cities, remote sensing, and computer vision; annual publication trend interpretation is restricted to complete calendar years from 2010–2025. Quantitative bibliometric analyses (e.g., publication trends, geographic distribution, institutional productivity, and keyword co-occurrence structure) are conducted on both 𝒟S and 𝒟W, with cross-database comparison used for validation. Complementarily, detailed analysis of prominent keywords and inter-cluster connectivity, as well as the review of real-world deployment systems and field-dataset studies, are conducted based on data from the Scopus dataset (𝒟S), which provides detailed author-keyword information for cluster-level interpretation and broader topical coverage. The deployment-oriented review distinguishes physical or edge implementations from studies using real-world datasets. The findings indicate deployment-oriented secure visual intelligence within the mapped literature, with the Scopus cluster structure separating spatio-temporal surveillance understanding, real-time object detection, remote sensing, biometric recognition, edge/cloud smart-city security, re-identification, adversarial robustness, UAV/drone sensing, crowd analytics, event summarization, and low-cost edge implementation. Increased emphasis on UAV-based imaging and adversarial robustness is also observed. This study provides a structured mapping of the research landscape and identifies gaps relevant to the development of reliable imaging systems in connected environments.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1846377</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1846377</link>
        <title><![CDATA[Facial attribute-aware DeepFake detection through semi-supervised facial attribute labeling]]></title>
        <pubdate>2026-06-24T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Vittorio Stile</author><author>Roberto Caldelli</author><author>Sara Balderas-Díaz</author><author>Gabriel Guerrero-Contreras</author><author>Inmaculada Medina-Bulo</author>
        <description><![CDATA[This study investigates the correlation between misclassifications in DeepFake detection and high-level facial attributes. A pre-trained frame-level classifier is used to distinguish manipulated from authentic video content, and its wrong predictions are analyzed in detail. To enrich the dataset, we automatically annotate each video with additional labels, including gender, hair color, hair length, ear visibility, and ethnicity, using a semi-supervised facial-attribute recognition pipeline. We extend this analysis with controlled training-time exclusions on FaceForensics++, keeping a unified test set to isolate generalization bias. Compared to the no-exclusion baseline (Accuracy = 0.806, AUC = 0.823), excluding samples with ears visible yields the largest degradation (Accuracy = 0.741, AUC = 0.763), while excluding non-visible ears has a milder effect (Accuracy = 0.813, AUC = 0.832). Hair length shows a moderate but consistent impact that interacts with ear visibility. We also explain the observed confusion-matrix asymmetry as a consequence of fixed score thresholds and video-level k-of-n aggregation. The results demonstrate that ear visibility is a critical factor for robust FAKE vs. REAL discrimination and motivate attribute-aware training, including targeted data curation, attribute-specific augmentation, and threshold calibration. The proposed framework provides actionable guidance for bias-aware training strategies and supports the development of more interpretable and operationally reliable DeepFake detection systems.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1754419</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1754419</link>
        <title><![CDATA[AI-enabled multi-disease diagnosis using low-cost CBC reports]]></title>
        <pubdate>2026-06-17T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Maria Bibi</author><author>Waqar Khalid Saeed</author><author>Saima Jabeen</author><author>Sajid Shah</author><author>Gauhar Ali</author><author>Mohammed ELAffendi</author><author>Maqbool Khan</author>
        <description><![CDATA[Complete blood count (CBC) reports are widely used in clinical settings to determine hematological disorders at early stages, offering a cost-effective and rapid alternative to expensive, time-consuming disease-specific tests. This study presents an AI-based method for multi-disease classification using CBC report data. We collected real-world paper-based CBC reports from a local hospital in scanned form for digital processing. State-of-the-art OCR models were used to extract only table data by removing patients' demographics. After cleaning and pre-processing, a custom digital dataset comprising 6,500 patients with 12 clinically relevant parameters was constructed. A rule-based algorithm is designed for disease labeling. We tested machine learning models for binary and multi-disease prediction. The experimental results showed that all machine learning models yielded the highest accuracy after hyperparameter tuning. Gradient Boosting and Random Forest outperform on binary and multi-disease prediction. The multi-label classification technique identified multiple probable pathologies from extracted CBC records, providing an efficient and cost-effective substitute for disease prediction. This approach offers significant benefits in healthcare for early disease diagnosis while minimizing delays associated with traditional testing methods.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1846414</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1846414</link>
        <title><![CDATA[A quantitative framework for explainability assessment in medical imaging]]></title>
        <pubdate>2026-06-15T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Raimondo Fanale</author><author>Roberto Caldelli</author><author>Barbara Martini</author><author>Filippo Sciarrone</author>
        <description><![CDATA[IntroductionDeep learning has achieved strong results in histopathological diagnosis, but the lack of transparency in deep neural network models limits their clinical acceptance. Explainable Artificial Intelligence (XAI) offers a principled route to address this gap by quantifying the reliability and morphological coherence of model predictions in support of clinical decision-making.MethodsWe present an integrated, explainability-augmented deep learning framework for binary histopathological classification on the BreaKHis dataset. The pipeline combines knowledge-distilled InceptionV3 → DenseNet-121 training with three complementary local explanation methods—Gradient-weighted Class Activation Mapping (Grad-CAM), SHapley Additive exPlanations (SHAP), and Local Interpretable Model-agnostic Explanations (LIME). Per-image outputs are aggregated at the dataset level into the ExpiScore composite interpretability index, which captures salience reliability, cross-method coherence, and morphological alignment. Additional regression and decision-tree modules build a trust meta-model that estimates the probability of prediction errors and supports automated triage of clinical cases. Two operational modes are evaluated and kept strictly separate throughout: a fully-automatic mode (CNN classification with no human intervention) and a human-in-the-loop mode (meta-model routing of high-risk cases to expert review).ResultsIn fully-automatic mode, the distilled DenseNet-121 student achieves accuracy 0.9916, F1-score 0.9939, Area Under the receiver-operating-characteristic Curve (AUC) 0.9989, sensitivity 0.9939, and specificity 0.9866 on the 1,187-image held-out test set, with five-fold cross-validation (BreaKHis official folds) further indicating generalization stability (mean accuracy 0.8962 ± 0.0177; mean AUC 0.9598 ± 0.0094). In human-in-the-loop mode, a meta-model trained on XAI-derived features and independently evaluated on the held-out test set routes the 20% of cases with the highest predicted error probability to expert review, raising post-routing accuracy from 0.9898 to 0.9983 (+0.85 pp) and reducing false negatives by 83.3% under the assumption of correct expert resolution of all routed cases.DiscussionThe two regimes are not directly comparable and are reported separately throughout the paper. The fully-automatic figures characterize purely algorithmic performance; the human-inthe-loop figures characterize a clinical-decision-support workflow in which the framework prioritizes cases for expert review. Together they suggest that ExpiScore-driven routing carries discriminative predictive signal for error detection and supports a principled trade-off between predictive accuracy and interpretative transparency, providing held-out test evidence for the potential clinical utility of the proposed routing mechanism within this evaluation setting. External multi-cohort validation and formal calibration of the triage thresholds are required before clinical deployment.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1870528</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1870528</link>
        <title><![CDATA[Integration of imaging with liquid biopsy using artificial intelligence for ultra-early detection of breast cancer]]></title>
        <pubdate>2026-06-11T00:00:00Z</pubdate>
        <category>Mini Review</category>
        <author>Shalaka Ramgir-Naidu</author><author>Asmita Govekar</author><author>Abhishek Ojha</author><author>Meghavi Soni</author>
        <description><![CDATA[Breast cancer early detection using liquid biopsy, circulating tumor DNA (ctDNA), artificial intelligence (AI), and multimodal fusion offers a promising but still emerging research strategy to overcome the limitations of conventional imaging. Breast cancer screening and molecular diagnostics remain constrained by the inability of mammography and magnetic resonance imaging to detect pre-invasive disease, alongside the low sensitivity and spatial ambiguity of ctDNA in early-stage settings. This mini-review summarizes the rationale and recent advances in AI-driven multimodal frameworks that integrate imaging phenotypes with blood-derived genotypic signals through feature-, decision-, and intermediate-level fusion strategies. Such approaches improve diagnostic sensitivity and specificity by capturing complementary biological and structural information, enabling earlier detection and longitudinal risk assessment. Despite this progress, clinical translation is hindered by data heterogeneity, the lack of standardized multimodal datasets, and limited prospective validation. This study highlights the emerging biology-first, imaging-informed framework. Despite recent progress, current multimodal approaches remain largely investigational and require robust prospective evidence before clinical deployment. It outlines key future directions, including federated learning, longitudinal modeling, and large-scale validation, to support the future evolution of scalable and equitable early-detection strategies.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1846329</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1846329</link>
        <title><![CDATA[Motion representations for privacy-aware cross-domain action recognition]]></title>
        <pubdate>2026-06-03T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Pascal Benschop</author><author>Jan van Gemert</author><author>Jelte P. Mense</author><author>Justin Dauwels</author>
        <description><![CDATA[Video captured for action recognition often contains sensitive appearance cues such as faces, skin color, and clothing. Models trained on such data may exploit these cues rather than the underlying motion, raising privacy concerns in real-world deployment. In this work, we study action recognition under a motion-focused constraint: the model receives only motion representations that capture pixel displacement over time, while reducing appearance cues that expose identity or scene context. We focus on motion-history images and optical flow as learning-free representations that reduce identifiable appearance information while retaining action recognition accuracy. Our motion I3D model achieves approximately 31% and 52% zero-shot top-1 accuracy on HMDB-51 and UCF-101, respectively, outperforming non-CLIP direct-transfer baselines trained on Kinetics-400 despite operating without any appearance input. In 16-shot adaptation, the same model reaches 52% and 83% top-1 accuracy. In the domain adaptation setting on TP-HMDB↔TP-UCF, our motion-focused models achieve higher action recognition accuracy than prior privacy-preserving methods. Sensitive attribute predictability is reduced relative to RGB by a comparable margin, without requiring a learned privacy filter. On PA-HMDB51, optical flow is the strongest motion representation for privacy preservation, approaching chance level for skin-color prediction and remaining below RGB on most privacy attributes, indicating that motion representations retain useful action information while exposing less personal information.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1817515</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1817515</link>
        <title><![CDATA[Adaptive-LwF: continual training of morphing attack detector without forgetting]]></title>
        <pubdate>2026-05-27T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Lorenzo Pellegrini</author><author>Guido Borghi</author><author>Annalisa Franco</author><author>Davide Maltoni</author>
        <description><![CDATA[In Biometrics, the presence of privacy restrictions on personal data transfer and storage poses significant challenges in creating a sufficiently comprehensive and varied dataset by leveraging various data sources for traditional batch-based training procedures. This is particularly true in the Morphing Attack Detection (MAD) task, in which data involves facial images and a limited number of public datasets of well-controlled images are available. In this context, MAD systems generally suffer from limited generalization capabilities, with low performance on new and unseen data. Therefore, in this paper, we propose Adaptive-LwF, adopting the recent paradigm of Continual Learning (CL) as a viable solution to enable incremental training across multiple sites. Indeed, CL assumes that once a model has been trained, previous data cannot be utilized in subsequent training iterations and can be deleted. In particular, we investigate the performance of different methods in this new scenario, where a model is updated each time a new chunk of data, of variable size, becomes available. We focus our attention on the well-known Learning without Forgetting (LwF) algorithm, proposing a novel adaptive approach able to automatically fine-tune its parameters in relation to the variable size of the specific input chunks. Experimental results confirm that our approach is capable of mitigating the catastrophic forgetting effects, and the superior performance of the Adaptive-LwF algorithm with respect to alternative solutions.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1795278</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1795278</link>
        <title><![CDATA[Deep learning based thermal foot segmentation with probability inversion post-processing for automated epidural block assessment]]></title>
        <pubdate>2026-05-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Sungjoon Hong</author><author>Milan Toma</author>
        <description><![CDATA[IntroductionEpidural analgesia represents the gold standard for labor pain management, yet clinical failure occurs in approximately 9 to 12 percent of cases, adversely affecting maternal well-being and necessitating additional interventions. Current assessment methods rely on subjective sensory tests that depend on patient feedback, which may be unreliable during active labor. Infrared thermography offers objective monitoring of sympathetic blockade through peripheral temperature changes, but clinical adoption has been limited by the absence of automated analysis tools requiring manual region-of-interest delineation by clinicians.MethodsThis study introduces an automated deep learning pipeline utilizing a U-Net convolutional neural network trained on thermal images from 30 pregnant women to segment foot regions and quantify surface temperatures for epidural analgesia assessment. A principal technical challenge emerged from severe class imbalance, where the foot region occupies substantially less image area than background space. To address this limitation, a probability inversion strategy was implemented during post-processing, optimizing the model to prioritize complete thermal region capture over geometric boundary precision.ResultsThe system achieved a global accuracy of 82.08 percent with foot-class sensitivity of 71.83 percent, successfully segmenting foot regions despite indistinct thermal gradients characteristic of infrared imagery. Automated temperature quantification enabled objective measurement of mean surface temperature within the segmented region.ConclusionsThe proposed automated pipeline offers a non-invasive, objective, and real-time alternative to subjective manual assessment methods, with potential to improve clinical decision-making in obstetric analgesia monitoring and pain management settings. This approach addresses the critical need for standardized, operator-independent evaluation of neuraxial blockade efficacy in high-volume clinical environments.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1758694</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1758694</link>
        <title><![CDATA[Feasibility in the detection of sentinel lymph node-associated blood vessels using intravital microscopy in patients undergoing sentinel lymph node biopsy for melanoma]]></title>
        <pubdate>2026-03-09T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Emmanuel Gabriel</author><author>Daniel T. Fisher</author><author>Minhyung Kim</author><author>Kristopher Attwood</author><author>Xiaoyi Ma</author><author>Valerie Francescutti</author><author>John M. Kane</author><author>Sharon S. Evans</author><author>Joseph J. Skitzki</author>
        <description><![CDATA[While the clinical focus on the sentinel lymph node biopsy (SLNB) is the presence of intra- or extra-nodal metastases, preclinical studies suggest that tumor-draining SLNB-associated vascular architecture and adhesion properties are altered regardless of SLNB positivity. Human intravital microscopy (HIVM) has defined blood vessel abnormalities that may impact lymphocyte adhesion and systemic drug delivery at primary melanoma sites. In this pilot study of HIVM during melanoma SLNB, we sought to determine the feasibility of obtaining HIVM observations of SLNB-associated vessels. We successfully performed HIVM in all 20 SLNB patients, and 7 were found to have nodal micrometastases by standard pathology. HIVM was capable of identifying both functional and non-functional SLNB-associated vessels based on the presence or absence of fluorescent dye uptake, respectively. Comparing vessel characteristics as a secondary exploratory objective, no statistically significant differences were noted in the diameter, flow rate, functionality, or shear stress of SLNB-associated blood vessels between positive and negative SLNBs, which may likely have been a reflection of the minimal disease burden. Nonetheless, these initial observations provide the framework to optimize future trials of HIVM in cancer patients.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1752625</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1752625</link>
        <title><![CDATA[Enhancement of multi-objective Darwinian particle swarm optimization for neural-network-based multimodal medical image fusion]]></title>
        <pubdate>2026-02-26T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Chisom E. Ogbuanya</author>
        <description><![CDATA[The purpose of this research is to develop a multimodal medical image fusion method that will provide high-performance fusion images at a speed high enough for efficient real-time image-guided surgeries. This paper therefore proposes an improved multi-objective Darwinian particle swarm optimization method that incorporates a fractional calculus operator for effective multimodal medical image fusion. This is because multimodal medical image fusion is essential in many clinical diagnoses, and it represents a multi-objective problem due to the important objective indicators for measuring its efficiencies, such as the parameters of the neural network and the speed of the fusion process. The proposed method aims to optimize the Tsallis cross-entropy as a stimulating input to the pulse-coupled neural network (PCNN) for multimodal image fusion. In this work, multi-objective Darwinian particle swarm optimization (MODPSO) is utilized due to its ability to escape local optima more effectively than classical multi-objective particle swarm optimization (MOPSO). The approach uses the fact that the convergence rate of MODPSO is improved by introducing a fractional calculus operator, which is incorporated into the updating formulas for the velocity and position of the particles. The PCNN output serves as an optimal parameter for fusing the high-frequency coefficients of decomposed source images, which are initially decomposed into low- and high-frequency subbands. The low-frequency coefficients are fused using an averaging method. Results obtained in this paper show that the proposed method yields the highest average accuracy of 90.7% after a three-fold cross-validation was carried out with a small dataset extracted from a larger available dataset. In conclusion, the experimental results demonstrate the superiority of the proposed method over comparative methods in terms of both visual quality and quantitative evaluation.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2026.1725794</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2026.1725794</link>
        <title><![CDATA[Aluminum impairs cellular ultrastructure and bone microarchitecture in newborn rats]]></title>
        <pubdate>2026-02-19T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Mara Rubia Marques</author><author>Anderson Camargo Moreira</author><author>Iara Frangiotti Mantovani</author><author>Pedro Vale de Azevedo Brito</author><author>Isabela Cristina Gomes de Souza Nascimento</author><author>Celso Peres Fernandes</author><author>Fernanda Cristina Alcantara dos Santos</author>
        <description><![CDATA[Modern lifestyle is strongly marked by the presence of aluminum (Al) in practically all human consumer products. Bone tissue is one of the main sites of Al accumulation, and its toxic effects are well known in individuals subjected to chronic exposure. However, there is still a gap in knowledge regarding the effects of Al on bone formation in the neonatal period. This study evaluated the effect of Al ingestion on rat tibiae during the neonatal period. Wistar rats were divided into control and Al groups. The Al group received AlCl3 (2.02 mg/kg/day) via gavage for fifteen days, then, the right tibiae were used to evaluate osteoblast and osteocyte ultrastructure and bone microarchitecture using transmission electron microscopy and computed X-ray microtomography, respectively. Al promoted swelling and altered mitochondrial crests in osteoblasts. Osteocytes showed accumulation of electron-dense lysosomes and absence of the osmiophilic lamina in the lacunae, showing characteristics similar to osteocytic osteolysis. Cortical Thickness (Ct.Th), Trabecular thickness (Tb.th) and trabecular number (Tb.N) decreased whilst trabecular spacing (Tb.Sp) increased. These results suggest that Al intake during the neonatal period may affect the function of osteoblasts and osteocytes besides compromising bone formation.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2025.1694840</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2025.1694840</link>
        <title><![CDATA[Cardiac adipose tissue, imaging segmentation, and quantification for cardiovascular disease assessment]]></title>
        <pubdate>2026-01-08T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Julian Rene Cuellar Buritica</author><author>Mukul Bhattarai</author><author>Pedro Carrillo</author><author>Manjula Burri</author><author>Jon Klingensmith</author>
        <description><![CDATA[Cardiac adipose tissue (CAT) has emerged as a critical and clinically relevant factor in cardiovascular disease (CVD), yet its full impact remains largely overlooked. The amount of fat surrounding the heart can influence major blood vessels by promoting plaque formation. In conditions such as cardiac steatosis or fatty heart disease, fat infiltration or accumulation within the heart muscle compromises its function may play a role in heart failure (HF) and coronary artery disease (CAD). This review explores the different types of fat deposits surrounding the heart, focusing on the potential contribution of CAT to cardiovascular disease (CVD). Three main imaging modalities for assessing cardiac fat are discussed, including magnetic resonance imaging (MRI), computed tomography (CT), and echocardiography. The segmentation and quantification of the fat for each imaging modality are also presented, correlating these measurements with CVD risk. Each imaging modality offers distinct advantages and limitations in segmenting and quantifying fat. Despite its clinical significance, quantification and characterization of CAT remain challenging, requiring advanced imaging techniques for precise assessment. Future research should focus on unlocking the mechanistic pathways that link CAT to adverse cardiovascular outcomes, ultimately enhancing our ability to predict, prevent, and treat heart disease with greater precision. As imaging technology advances, there is a need for refined segmentation methods and consensus-driven guidelines to establish CAT as a key biomarker in CVD risk stratification.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fimag.2025.1761718</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fimag.2025.1761718</link>
        <title><![CDATA[Editorial: Deep learning for medical imaging applications]]></title>
        <pubdate>2026-01-06T00:00:00Z</pubdate>
        <category>Editorial</category>
        <author>Simone Bonechi</author><author>Monica Bianchini</author><author>Paolo Andreini</author><author>Sandeep Kumar Mishra</author>
        <description></description>
      </item>
      </channel>
    </rss>