Bio


Mateus A. Esmeraldo is a Postdoctoral Research Fellow in the Department of Radiology at Stanford University, currently working under the mentorship of Dr. Bruno P. Soares. His current research focuses on pediatric neuroradiology and the integration of artificial intelligence (AI) tools to enhance diagnostic and healthcare delivery in neuropediatric populations, with a particular emphasis on magnetic resonance imaging.

Originally from Brazil, Mateus earned his medical degree Magna cum Laude from the University of Ceará - Sobral. He completed his residency in Radiology at the University of São Paulo, where he was awarded the Guerbet-InRad Best Resident Award and received the CBR/ESOR Europe Scholarship for complementary training in Neuroradiology at Addenbrooke’s Hospital, University of Cambridge, during his final year.

Following his residency, Mateus served as a Radiologist in the Ultrasound Section of the Institute of Radiology (InRad) at the University of São Paulo. In this role, he was engaged in clinical and research activities involving Doppler ultrasound and transcranial ultrasound in adult patients. His work was closely aligned with innovation-driven projects in neuroimaging and artificial intelligence, and he also participated in academic and teaching initiatives for medical students and residents.

Clinical Focus


  • Fellow

Honors & Awards


  • Bayer - CBR Award (2024), Bayer, Brazilian College of Radiology (CBR) and European School of Radiology (2024)
  • Best Resident InRad - Guerbet Award, InRad (University of São Paulo) and Guerbet (2024)
  • Magna Cum Laude, University of Ceará - School of Medicine (2021)

All Publications


  • A Comprehensive 2.5-Minute Brain MRI Protocol in the Pediatric Emergency Department: Diagnostic Evaluation of the Multicontrast NeuroMix Sequence. AJNR. American journal of neuroradiology Esmeraldo, M. A., Soares, B. P., Reis, E. P., Dahmoush, H., Bhandari, A., Campion, A. W., Sprenger, T., Skare, S., Zaharchuk, G., Decker, J. H. 2026

    Abstract

    Prolonged acquisition times and motion artifacts limit the use of MRI in the pediatric emergency department, frequently necessitating sedation and reducing workflow efficiency, or prompting the use of CT with associated ionizing radiation. Recent MRI advances enable fast, comprehensive neuroimaging without radiation exposure. This study evaluates the diagnostic interchangeability of a fast 2.5-minute MRI multicontrast sequence (NeuroMix) with a standard MRI protocol for detecting clinically relevant intracranial findings in the pediatric emergency department.We retrospectively identified sequential pediatric patients who underwent both a standard pediatric emergency department MRI protocol and NeuroMix over a one-year period. A finding-enriched cohort of 100 studies was constructed (44 positives and 56 controls). Three radiologists independently reviewed NeuroMix and standard protocol imaging sets in randomized batches. Diagnostic interchangeability was assessed using an agreement-based mixed-effects modeling approach using a noninferiority threshold of 10%. Acquisition times, examination completeness, artifact prevalence, interreader agreement, and diagnostic performance metrics were compared between protocols, in accordance with STARD.NeuroMix demonstrated diagnostic interchangeability with the standard pediatric emergency MRI protocol for detection of clinically relevant findings, with an interchangeability estimate of -3.1% (95% CI, -6.6% to +0.3%), remaining within the noninferiority margin. Overall diagnostic accuracy was identical for NeuroMix and standard imaging (87.7%). Interreader agreement for detection of clinically relevant findings was substantial for both NeuroMix (κ = 0.65) and the standard protocol (κ = 0.73). Mean acquisition time was markedly shorter for NeuroMix when compared with the standard protocol (median 2.67 minutes vs 15.26 minutes, p < 0.001). Moderate to severe artifacts and repeat sequence acquisitions occurred less frequently with NeuroMix.A 2.5-minute NeuroMix-based MRI protocol demonstrated diagnostic interchangeability with a standard pediatric emergency MRI protocol for clinically relevant intracranial findings with substantially reduced acquisition time and imaging artifacts. These results support NeuroMix as a fast, radiation-free approach that may serve, depending on the clinical scenario, as a supplementary or alternative neuroimaging protocol in pediatric emergency care.

    View details for DOI 10.3174/ajnr.A9454

    View details for PubMedID 42242728

  • Pipeline evaluation of a state-of-the-art AI algorithm for detection of focal cortical dysplasia: insights into potential failure sources. Brain informatics Esmeraldo, M. A., Chambers, S., Kravutske, Y., Reis, E. P., Kasprian, G., Geraldo, A. F., Gatidis, S., Soares, B. P. 2026

    Abstract

    PURPOSE: MELD Graph is a state-of-the-art artificial intelligence (AI) model for automated detection of focal cortical dysplasia (FCD), but its performance remains limited, highlighting the need to investigate which aspects of the pipeline affect its accuracy.METHODS: A retrospective failure-mode analysis of the MELD Graph pipeline was performed in 242 subjects, with model predictions and FreeSurfer segmentations reviewed to classify errors as segmentation-associated or algorithm-related. FCD imaging features salient to humans were quantified, with statistical associations examined for both MELD Graph detection and focal FreeSurfer segmentation failure.RESULTS: MELD Graph demonstrated overall performance similar to previously published non-harmonized results, achieving a sensitivity of 69%, specificity of 44%, and positive predictive value (PPV) of 75%. Focal FreeSurfer segmentation failures were associated with 21% of false negative patients, 25% of false positive clusters in patients, and 16% of false positive clusters in controls. Following manual cortical segmentation correction and rerunning of MELD Graph, 67% of the segmentation-associated missed lesions were detected, and segmentation-associated false positive clusters were reduced or eliminated in 75% of controls with such clusters. Higher conspicuity on T1-weighted images was associated with MELD Graph detection, whereas greater conspicuity on T2-FLAIR images relative to T1 was associated with detection failure. Non-bottom-of-sulcus lesion location, higher human conspicuity measures, and low T1 image quality were positively associated with focal FreeSurfer segmentation failures.CONCLUSION: FreeSurfer segmentation failures are a significant potential source of error in the MELD Graph pipeline. FCD imaging features salient to humans and image quality were also associated with variability in algorithm performance. Robust cortical segmentation and stronger integration of T2-FLAIR imaging features may be beneficial for automated FCD detection tools.CLINICAL TRIAL REGISTRATION: Not applicable. This study is a retrospective analysis of previously acquired open-source imaging datasets and does not constitute a clinical trial.

    View details for DOI 10.1186/s40708-026-00299-w

    View details for PubMedID 41931246

  • Updates on Adult Transcranial Doppler, Gray-Scale, and Contrast-enhanced US Techniques. Radiographics : a review publication of the Radiological Society of North America, Inc A Esmeraldo, M., de Melo, E. R., Fritzen, M., Braga, K., Brunetto, M. F., Ferreira, P. S., Chiovatto, E. D., Chiovatto, R. D., Freeman, C. W., Cavalanti Gomes, A., Chammas, M. C. 2026; 46 (4): e250182

    Abstract

    Transcranial US is a noninvasive, portable, real-time imaging technique that enables targeted evaluation of the intracranial circulation and select brain parenchymal structures through cranial bone windows. Traditionally, transcranial Doppler (TCD) has been used in well-established clinical scenarios, including vasospasm monitoring, stroke risk assessment, and ancillary testing for brain death. TCD encompasses two main techniques: nonimaging TCD (niTCD) and TCD imaging (TCDi). niTCD is a "blind" US technique that relies on standardized depths for vessel localization, guided by characteristic flow waveforms. In contrast, TCDi is a triplex approach that integrates gray-scale (B-mode) US, color Doppler US, and spectral Doppler US into an image-guided examination, enabling direct visualization of the intracranial anatomy and improving diagnostic confidence and reproducibility. In parallel, transcranial B-mode sonography (TCS), incorporated into modern TCDi, has demonstrated promising applications in adult patients, both in the neurointensive care unit and in outpatient practice. In addition, contrast-enhanced US (CEUS) has emerged as a powerful adjunct, markedly enhancing the Doppler signal in patients with poor bone windows, and has expanded the scope of transcranial US toward new exploratory vascular and cerebral perfusion applications. This article provides a comprehensive update on transcranial US in adults, including gray-scale imaging, Doppler techniques, and CEUS applications. With a focus on evidence-based indications and practical techniques, this article aims to support broader awareness and clinical adoption of transcranial US in contemporary adult neuroimaging, with a particular emphasis on TCDi, which remains underrecognized and underused despite its demonstrated clinical value in select indications. © The Author(s) 2026. Published by the Radiological Society of North America under a CC BY 4.0 license.

    View details for DOI 10.1148/rg.250182

    View details for PubMedID 41818128

  • Microcephaly with Simplified Gyral Pattern in Children: Quantitative Morphometric Assessment on Brain MRI and Correlation with Clinical Outcome. AJNR. American journal of neuroradiology Chambers, S., Esmeraldo, M. A., Kravutske, Y., Haider, L., Kasprian, G., Geraldo, A. F., Soares, B. P. 2026

    Abstract

    Microcephaly with simplified gyral pattern (MSGP) represents an often subtle subtype of malformation of cortical development that is commonly accompanied by epilepsy and neurodevelopmental delay. However, whether gyral simpflication scales to reduced brain volume, and if MRI features predict clinical outcome still remains unclear. The aims of this study are therefore to apply a quantitative morphometric approach to distinguish simplified gyral pattern from microcephaly-related effects, and to correlate quantitative MRI-derived features with clinical outcome.From a single-center cohort of 34 patients with microcephaly and visually confirmed simplified gyral pattern (SGP) (shallow sulci, normal cortical thickness), 18 subjects (mean age 7.1±6.5 years) that fulfilled the eligibility criteria were retrospectively included for final analysis. 26 age- and sex-matched healthy controls were included. Volumetric gray/white-matter volumes (GMV/WMV) and surface-based measures were derived using FreeSurfer. Scaling corrections based on log-log robust regression and cortical folding analyses were subsequently analyzed. Principal component analyses clustered along morphometric phenotypes. ANCOVA, Kendall τ correlations, and logistic regression were applied to evaluated group differences and clinical outcome predictors.Compared with healthy controls, patients showed significantly reduced WMV, cortical surface area, local gyrification index (LGI) (all q<0.003), and mildly increased cortical thickness. Allometric modeling indicated that while WMV and LGI scaled proportionally to total brain volume, cortical surface area was disproportionately reduced, suggesting deviation beyond microcephalic scaling. Spectral folding analysis showed loss of specifically macro-scale (primary) folding power. Morphometric clustering separated four subtypes differing in cortical thickness and area, of which the cluster with lowest surface area and LGI exhibited universal developmental delay and included both early deaths. Across the cohort, neurodevelopmental delay correlated negatively with surface area. Logistic regression suggested lower surface area, WMV, and LGI as predictors of adverse clinical outcome (q<0.02).The presence of SGP may reflect additional disturbance of primary sulcation and tangential cortical expansion beyond scaling to microcephaly alone. Our results suggest reduced cortical surface area as a key morphometric marker and strong MRI feature predictive of neurodevelopmental delay, underscoring the clinical value of quantitative morphometry for stratifying disease severity in microcephaly with simplified gyral pattern.

    View details for DOI 10.3174/ajnr.A9282

    View details for PubMedID 41807040

  • Explainable DSC Perfusion Radiomics for Post-Treatment Glioblastoma Assessment Using a Soft-Voting Machine-Learning Ensemble. Cancers Christodoulou, R. C., Christofi, G., Vamvouras, G., Esmeraldo, M. A., Papageorgiou, P. S., Vassiliou, E., Solomou, E. E., Papageorgiou, S. G., Georgiou, M. F. 2026; 18 (21)

    Abstract

    After chemoradiation for glioblastoma, residual or recurrent tumor (tumor-positive disease, TP) and treatment-related change (TRC), which includes pseudoprogression and radiation necrosis, look alike on conventional MRI. We tested whether radiomic features from dynamic susceptibility contrast (DSC) perfusion MRI alone can separate them.We analyzed 224 post-treatment MRI examinations from 168 patients in the public UCSD-PTGBM collection. A machine-learning ensemble was trained on 1223 radiomic features from the leakage-corrected relative cerebral blood volume (rCBV) map, with training (109 patients, 143 examinations) and test (59 patients, 81 examinations) data separated at the patient level and the model fixed before testing. The analysis was repeated on the cerebral blood flow (CBF) map from the same scans, and DSC was compared with arterial spin labeling (ASL) in patients who had both.On the independent test set (patient-level analysis), the model distinguished TP from TRC with an area under the receiver operating characteristic curve (AUC) of 0.79 (95% CI 0.67-0.89). It detected 31 of 49 patients with tumor (sensitivity 63%) and correctly identified all 10 patients with TRC (specificity 100%); at a predefined higher-sensitivity cut-off, sensitivity was 69% and specificity 80%. With the CBF map, the AUC did not differ significantly (0.78; p = 0.89), but there was a different balance of sensitivity and specificity. In an exploratory subset of 36 patients, DSC and ASL did not differ significantly (AUC 0.82 vs. 0.71; p = 0.52).DSC perfusion radiomics alone identified tumor with high specificity but missed about one-third of tumors: a positive result may support a diagnosis of tumor, whereas a negative result cannot exclude it. External, multicenter validation is needed before clinical use.

    View details for DOI 10.3390/cancers18213567

    View details for PubMedID 43026886

    View details for PubMedCentralID PMC13761451

  • Explainable MRI radiomics identifies a PTEN-associated imaging phenotype in adult gliomas. Frontiers in oncology Christodoulou, R. C., Vamvouras, G., Esmeraldo, M. A., Papageorgiou, P. S., Vassiliou, E., Solomou, E. E., Papageorgiou, S. G., Georgiou, M. F. 2026; 16: 1900609

    Abstract

    PTEN mutation is a recurrent molecular alteration in adult gliomas, associated with PI3K/AKT/mTOR pathway activation, aggressive tumor behavior, and resistance to therapy. PTEN status is currently determined through tissue biopsy, which is susceptible to sampling bias and intratumoral heterogeneity. We investigated whether conventional multiparametric MRI radiomics can identify a noninvasive, interpretable PTEN-associated imaging phenotype in adult gliomas.We retrospectively analyzed 195 adult glioma patients with known PTEN mutation status (184 PTEN-negative, 11 PTEN-positive) from the TCIA MU-Glioma-Post database. A total of 3,669 radiomic features were extracted from enhancing tumor core segmentations on T1CE, T2, and FLAIR MRI. A leakage-conscious nested cross-validation pipeline (5 outer/3 inner folds, 30 Optuna trials) was used for redundancy-aware feature selection, imbalance-adjusted model tuning, and performance evaluation across four classifier architectures. Feature-level explainability was assessed using linear SHAP-style additive contributions. Post-hoc Firth-penalized logistic regression was performed to assess whether the radiomic association was explained by age, IDH status, MRI timing, or treatment exposure.The primary elastic-net logistic regression classifier achieved an outer out-of-fold ROC-AUC of 0.874 (95% CI 0.808-0.936), sensitivity of 90.9%, specificity of 71.7%, balanced accuracy of 81.3%, and Brier score of 0.052. PR-AUC was 0.211 (95% CI, 0.112-0.400), reflecting a low PTEN-positive prevalence (5.6%) and indicating limited positive predictive value despite strong discrimination. The most influential features were wavelet- and LoG-filtered GLCM and NGTDM texture descriptors from T1CE, T2, and FLAIR, suggesting a multisequence phenotype characterized by heterogeneous enhancement architecture and disrupted local texture organization. The radiomic score remained independently associated with PTEN positivity after adjustment for age, MRI timing, and documented treatment exposure across multiple Firth-penalized models (OR per SD range: 1.57-1.62, all p ≤ 0.005).Conventional multiparametric MRI radiomics identifies a biologically plausible, explainable PTEN-associated imaging phenotype in adult gliomas that is robust to adjustment for clinical and treatment-related confounders. However, given the small PTEN-positive cohort, severe class imbalance, modest PR-AUC, and absence of external validation, the findings are exploratory and hypothesis-generating. Prospective multi-institutional validation in larger, molecularly balanced cohorts is required before clinical translation.

    View details for DOI 10.3389/fonc.2026.1900609

    View details for PubMedID 42687984

    View details for PubMedCentralID PMC13533706

  • Calibrated and explainable multiparametric MRI radiomics for differentiating tumor positive disease from treatment-related changes in glioblastoma. Frontiers in oncology Christodoulou, R. C., Vamvouras, G., Esmeraldo, M. A., Papageorgiou, P. S., Vassiliou, E., Solomou, E. E., Papageorgiou, S. G., Georgiou, M. F. 2026; 16: 1890956

    Abstract

    Differentiating tumor from treatment-related changes (TRC) remains a key challenge in post-treatment glioblastoma (GBM) monitoring, as both can exhibit overlapping enhancement and FLAIR abnormalities on standard MRI. Our goal was to build and internally validate an explainable, calibrated, multiparametric MRI radiomics model to distinguish between tumor and treatment effects.We retrospectively included patients from the UCSD-PTGBM cohort who had post-treatment GBM MRI examinations with available reference labels for tumor-positive disease (TP) or TRC. Examinations were eligible when contrast-enhanced T1-weighted imaging, FLAIR, ADC, DSC perfusion imaging, and corresponding tumor segmentation masks were available. After applying the eligibility and exclusion criteria, the final study cohort comprised 168 patients with 224 MRI examinations, 173 TP and 51 TRC cases. Radiomic features were extracted from all four MRI sequences. Feature selection and hyperparameter tuning were performed exclusively on the training data before evaluating the model on the test set. Performance metrics, calibration, decision curve analysis, and SHAP-based interpretability were assessed.The extra trees classifier trained on the top 50 radiomic features demonstrated strong performance on the held-out test set, with an AUC of 0.887, PR-AUC of 0.952, balanced accuracy of 83.7%, sensitivity of 75.0%, and specificity of 92.3%. Platt calibration improved the Brier score from 0.229 to 0.132 and the expected calibration error from 0.275 to 0.084. Decision curve analysis indicated a net benefit across relevant clinical thresholds. SHAP analysis revealed balanced contributions from ADC, DSC, T1CE, and FLAIR modalities.A calibrated and explainable multiparametric MRI radiomics model showed robust internal performance in differentiating tumor from treatment effects in post-treatment GBM. As these findings are hypothesis-generating from an internally validated study, external validation is needed to confirm clinical usefulness and broader applicability.

    View details for DOI 10.3389/fonc.2026.1890956

    View details for PubMedID 42682614

    View details for PubMedCentralID PMC13529537

  • Calibrated and explainable multiparametric MRI radiomics for differentiating tumor positive disease from treatment-related changes in glioblastoma FRONTIERS IN ONCOLOGY Christodoulou, R. C., Vamvouras, G., Esmeraldo, M. A., Papageorgiou, P. S., Vassiliou, E., Solomou, E. E., Papageorgiou, S. G., Georgiou, M. F. 2026; 16
  • Image quality evaluation of neonatal brain magnetic resonance imaging using a deep learning reconstruction algorithm: A quantitative and multireader study using variable denoising levels at 3 tesla. Journal of clinical imaging science Alvi, Z., Reis, E. P., Esmeraldo, M. A., Shin, D., Banerjee, S., Dahmoush, H. M., Campion, A., Chambers, S., Kravutske, Y., Gatidis, S., Soares, B. P. 2026; 16: 29

    Abstract

    Neonatal imaging is particularly challenging because newborns are prone to head motion, which can degrade image quality and complicate interpretation. Improving brain magnetic resonance imaging (MRI) image quality may help reduce diagnostic uncertainty and facilitate the nuanced assessment of early myelinating structures in the neonatal brain. Although deep learning reconstruction algorithms designed to improve MRI image quality have been evaluated in pediatric imaging, they have not been specifically studied in exclusively neonatal populations. This pilot study sought to evaluate image quality improvement through the employment of a deep learning reconstruction algorithm in neonatal brain imaging.3D T1-weighted brain MRIs were obtained in a small cohort of 15 neonates. A deep learning reconstruction algorithm was applied to the image sets using low, medium, and high levels of denoising. Three radiologists qualitatively rated image quality (signal-to-noise ratio [SNR], presence of artifacts, and overall clarity) on a 4-point scale of eight early myelinating structures. Objective apparent SNR (aSNR) and apparent contrast-to-noise ratio (aCNR), based on signal intensities of white and gray matter, were measured across all three denoising levels.Evaluation by radiologists indicated an overall increase in all image quality categories and increased conspicuity of the early myelinating structures as the level of denoising increased. Objective aSNR and aCNR values also increased progressively with denoising, with significant differences observed for nearly all pairwise comparisons.Our findings suggest improvement in image quality with the use of the deep learning reconstruction algorithm in 3D T1-weighted neonatal brain MRI, though the small sample size and pilot design limit generalizability. Diagnostic accuracy and clinical outcomes were not evaluated and warrant future investigation.

    View details for DOI 10.25259/JCIS_32_2026

    View details for PubMedID 42559199

    View details for PubMedCentralID PMC13440578

  • Longitudinal Neuroimaging in Pediatric Coccidioidomycosis: Full Spectrum of Brain, Spine and Head and Neck Findings. AJNR. American journal of neuroradiology Chambers, S., Esmeraldo, M. A., Moeremans, M., Halverson, M., Soares, B. P., Dahmoush, H., Geraldo, A. F. 2026

    Abstract

    Coccidioidomycosis is an endemic mycosis in some regions of the Americas including the southwestern United States with recognized potential for extra-pulmonary dissemination. Nevertheless, its neuroradiologic spectrum in children, particularly with respect to longitudinal evolution and head and neck involvement, remains incompletely characterized. We retrospectively reviewed n=16 pediatric patients with definitive or probable infection evaluated at a single quaternary care center in an endemic region, analyzing clinical/laboratory data and serial neuroimaging findings. Most children were previously healthy. Neuroimaging abnormalities represented the initial manifestation in more than one-third of cases and were frequently multifocal and temporally dynamic, including both clinically silent and delayed lesions. Craniospinal meningitis and related complications such as hydrocephalus, stroke, intracranial vasculopathy and chronic arachnoiditis were the most common and severe findings of central nervous system involvement. Parenchymal granulomas were more common than previously described, while cerebrovenous thrombosis and diffuse white matter signal abnormalities could also occur. Head and neck involvement was identified in 56% of patients, most commonly craniofacial osteomyelitis, but also temporomandibular joint septic arthritis, necrotic cervical lymphadenopathy/lymphadenitis, cutaneous lesions, and chorioretinitis, suggesting these features may be more prevalent in children than previously recognized. These findings expand the known imaging spectrum of pediatric coccidioidomycosis and underscore the importance of neuroradiologist familiarity with these patterns to facilitate early disease recognition within the appropriate clinical and epidemiologic context followed by timely initiation of antifungal therapy. A low threshold for neuroimaging, coupled with comprehensive, multi-compartment evaluation over time, is essential for accurate delineation of disease extent and for monitoring therapeutic response.

    View details for DOI 10.3174/ajnr.A9556

    View details for PubMedID 42532677

  • Knobloch Syndrome in Childhood: Neuroradiologic Findings and Clinical Correlation. Journal of child neurology Kravutske, Y., Esmeraldo, M. A., Chambers, S., Dahmoush, H. M., Halverson, M. R., Geraldo, A. F., Soares, B. P. 2026: 8830738261444228

    View details for DOI 10.1177/08830738261444228

    View details for PubMedID 42093600

  • Fetal Dural Sinus Malformation: Prenatal Diagnosis and Follow-up With Thrombus Resolution and Associated Developmental Venous Anomalies. Journal of child neurology Esmeraldo, M. A., Chambers, S., Geraldo, A. F., Dahmoush, H. M., Soares, B. P. 2026: 8830738261433220

    View details for DOI 10.1177/08830738261433220

    View details for PubMedID 41930572

  • Comprehensive segmentation of focal cortical dysplasia by combining surface-based and whole-brain MRI deep learning algorithms: a proof-of-concept study. Biomedical physics & engineering express Kravutske, Y., A Esmeraldo, M., Chambers, S., Reis, E. P., Haider, L., Kasprian, G., Soares, B. P. 2026

    Abstract

    Focal cortical dysplasia type II (FCD II) is a significant cause of drug-resistant epilepsy, and the full surgical resection of the lesion is linked with excellent disease-free outcomes. Its imaging hallmark is the white matter hyperintense funnel-shaped transmantle sign on T2-FLAIR magnetic resonance imaging (MRI). Manual delineation of this abnormality is challenging and inconsistent. Most current artificial intelligence (AI) segmentation tools focus on cortical features and do not fully evaluate the white matter component. We tested whether integrating an algorithm trained on white matter lesions may improve FCD II segmentation. Methods: We evaluated the combination of two AI algorithms, MELD Graph (surface-based FCD segmentation) and MindGlide (whole-brain/white-matter lesion segmentation tool) in 49 FCD cases with a radiologically confirmed transmantle sign. Segmentation accuracy was assessed against expert manual annotations using the Dice similarity coefficient and segmentation volumes. Results: MELD Graph detected the lesion in 31 cases, 22 of which had the transmantle sign included in the expert lesion mask. Among these, MindGlide detected the transmantle sign in eight cases (36%). The mean added Dice score was 0.033 (95% CI, 0.013-0.056). Overall Dice values of MELD Graph were 0.321 and increased to 0.354 with the addition of MindGlide. It also contributed additional lesion volume in these eight cases, ranging from 0.028 to 4.18 cm³, with a mean added volume of 0.77 cm³. Discussion: Despite not being trained on FCD data, MindGlide, when combined with MELD Graph, provided a modest improvement in FCD II segmentation, including the deep white matter component of the lesion that is not captured by MELD Graph.These findings provide preliminary evidence supporting the consideration of a sequential cortical and white matter segmentation approach in FCD II, which may guide further epilepsy-specific AI model development.

    View details for DOI 10.1088/2057-1976/ae3d3e

    View details for PubMedID 41587495

  • External Validation of an Artificial Intelligence Triaging System for Chest X-Rays: A Retrospective Independent Clinical Study DIAGNOSTICS Castilla, A., D'Amorim, I., Wanderley, M., Esmeraldo, M., Yoshida, A., Eigier, A., Sawamura, M. 2025; 15 (22)

    Abstract

    Background: Chest radiography (CXR) is the most frequently performed radiological exam worldwide, but reporting backlogs, caused by a shortage of radiologists, remain a critical challenge in emergency care. Artificial intelligence (AI) triage systems can help alleviate this challenge by differentiating normal from abnormal studies and prioritizing urgent cases for review. This study aimed to externally validate TRIA, a commercial AI-powered CXR triage algorithm (NeuralMed, São Paulo, Brazil). Methods: TRIA employs a two-stage deep learning approach, comprising an image segmentation module that isolates the thoracic region, followed by a classification model trained to recognize common cardiopulmonary pathologies. We trained the system on 275,399 CXRs from multiple public and private datasets. We performed external validation retrospectively on 1045 CXRs (568 normal and 477 abnormal) from a teaching university hospital that was not used for training. We established ground truth using a large language model (LLM) to extract findings from original radiologist reports. An independent radiologist review of a 300-report subset confirmed the reliability of this method, achieving an accuracy of 0.98 (95% CI 0.978-0.988). We compared four ensemble decision strategies for abnormality detection. Performance metrics included sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC) with 95% CI. Results: The general abnormality classifier achieved strong performance (AUROC 0.911). Individual pathology models for cardiomegaly, pneumothorax, and effusion showed excellent results (AUROC of 0.968, 0.955, and 0.935, respectively). The weighted ensemble demonstrated the best balance, with an accuracy of 0.854 (95% CI, 0.831-0.874), a sensitivity of 0.845 (0.810-0.875), a specificity of 0.861 (0.830-0.887), and an AUROC of 0.927 (0.911-0.940). Sensitivity-prioritized methods achieving sensitivity >0.92 produced lower specificity (<0.69). False negatives were mainly subtle or equivocal cases, although many were still flagged as abnormal by the general classifier. Conclusions: TRIA achieved robust and balanced accuracy in distinguishing normal from abnormal CXRs. Integrating this system into clinical workflows has the potential to reduce reporting delays, prioritize urgent cases, and improve patient safety. These findings support its clinical utility and warrant prospective multicenter validation.

    View details for DOI 10.3390/diagnostics15222899

    View details for Web of Science ID 001625925700001

    View details for PubMedID 41300923

    View details for PubMedCentralID PMC12651339

  • Prenatal Diagnosis of VLDLR-associated Cerebellar Hypoplasia via Fetal MRI. Neuropediatrics Povlow, M. R., Esmeraldo, M. A., Dahmoush, H. M., Halverson, M. R., Barsh, G. R., Soares, B. P. 2025

    View details for DOI 10.1055/a-2736-4758

    View details for PubMedID 41213595

  • Intersection of Brain Complexity, Functional Connectivity, and Neuropsychology: A Systematic Review. Cureus de Moura Targino, R., Esmeraldo, M. A., Cajazeiras Falcão, I., Macêdo Melo, K. 2025; 17 (3): e80719

    Abstract

    The definition of brain complexity is based on the principal property of the coexistence of a high degree of integration and differentiation within a single neural system. Despite the fruitful scope of emerging studies involving the applicability of brain complexity metrics, there is a notable scarcity of research focusing on the qualitative characteristics of conscious systems, which are recognized for their high complexity. These qualitative characteristics are expressed in complex cognitive processes, reflecting the interaction between distinct neuropsychological domains, such as attention, memory, language, and executive functions (EFs). Cognitive flexibility and inhibitory control, for instance, emerge from the dynamic integration of distributed neural networks, underscoring the interdependence between brain complexity and cognitive functioning. In light of this, the present study aimed to evaluate how studies addressing measures of functional connectivity and brain complexity, obtained through resting-state functional magnetic resonance imaging (rs-fMRI), relate to neuropsychological aspects. To achieve this, a systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and based on the PICO (Patient, Intervention, Comparison, Outcome) strategy. Studies were searched in PubMed, CAPES Periodicals, and Virtual Health Library databases to identify relevant studies published between 2019 and March 2024. Articles were included based on study type, sample characteristics, methodological aspects, and specific listed variables. Exclusion criteria encompassed theoretical studies, animal research, and studies involving children/adolescents, as well as those addressing psychiatric conditions, psychoactive substance use, intervention evaluations (e.g., transcranial magnetic stimulation), and disorders of consciousness, due to limitations in applying neuropsychological measures. Possible limitations include the exclusion of studies with specific populations and clinical conditions, which may limit the generalizability of findings to broader, more diverse groups. After applying the selection criteria, 30 articles were chosen and fully analyzed. The results allowed for the establishment of characteristics of the research landscape in this area, initially highlighting a greater number of studies focused on functional connectivity compared to those directed at brain complexity. Additionally, EFs were identified as the most frequently addressed neuropsychological domain in the studies, consistent with the most commonly used evaluative measures in the research: Trail Making Test (TMT), Symbol Digit Modalities Test (SDMT), and verbal fluency tasks. The findings suggest that this is an area of study still in its early stages of development, with notable gaps in the in-depth understanding of the relationships between neural network complexity metrics and neuropsychological functioning.

    View details for DOI 10.7759/cureus.80719

    View details for PubMedID 40242669

    View details for PubMedCentralID PMC12002407

  • Mevalonic Aciduria in a Pediatric Patient: A Case Report and Literature Review of Neuroimaging Findings. Cureus Esmeraldo, M. A., Prates, I. R., Lucato, L. T., Barbosa Junior, A. A. 2024; 16 (7): e65209

    Abstract

    Mevalonic aciduria is a rare autosomal recessive disorder resulting from mevalonate kinase deficiency. Neuroimaging findings associated with the disease have been documented in only a few case reports. We present a case of mevalonic aciduria with both already reported and novel neuroimaging findings and conduct a literature review regarding the role of neuroimaging in the understanding and diagnosis of mevalonate kinase deficiency disorders. The brain magnetic resonance imaging of the reported case revealed several notable findings, including polymicrogyric cortical thickening, an interhypothalamic adhesion or small hypothalamic hamartoma (findings not classically associated with mevalonic aciduria), and mild cerebellar atrophy. This case underscores the significance of recognizing the diverse spectrum of neuroimaging findings associated with the disease, encompassing both well-documented features and those that have not been traditionally reported.

    View details for DOI 10.7759/cureus.65209

    View details for PubMedID 39176373

    View details for PubMedCentralID PMC11340854

  • Intracranial Chondrosarcoma Originating from the Sella Turcica JBNC - Jornal Brasileiro de Neurocirurgia Carlos de Sousa Oliveira, S., Carolina Ferretti Wisenfad, A., Aragão Esmeraldo, M., Medina Guimarães, W., Hiromi Otani, M. 2024
  • Complete C4-C5 Dislocation Secondary to Shallow Water Diving in a Child: A Case-Based Update BRAZILIAN NEUROSURGERY-ARQUIVOS BRASILEIROS DE NEUROCIRURGIA Matos, L., Figueiredo, G., Monteiro, M., Esmeraldo, M., da Ponte, K., Cristino-Filho, G., Leal, P. 2023
  • Eight-and-a-Half Syndrome Secondary to Neurotoxoplasmosis: A Rare Case Report. Neuro-ophthalmology (Aeolus Press) Cavalcante-Neto, J. F., Dos Reis, G. C., Esmeraldo, M. A., Dos Santos, B. R., Leal, P. R., da Ponte, K. F., Cristino-Filho, G., Ribeiro, E. M. 2022; 46 (5): 335-338

    Abstract

    Eight-and-a-half syndrome (EHS) is a neuro-ophthalmological condition characterised by horizontal gaze palsy, internuclear ophthalmoplegia, and ipsilateral facial palsy. Albeit rare, EHS is a well reported condition in the literature, with several reports presenting multiple aetiologies. Infarcts are the cause in more than half the cases. Human immunodeficiency virus (HIV)-related cases are rare, and are probably underreported in low- and middle-income countries. In this report, we describe EHS secondary to neurotoxoplasmosis in a 40-year-old HIV-positive Brazilian man. EHS secondary to neurotoxoplasmosis is a challenging diagnosis, with important differential diagnoses, notably for HIV patients.

    View details for DOI 10.1080/01658107.2022.2043390

    View details for PubMedID 36337230

    View details for PubMedCentralID PMC9635541

  • Late mesenteric ischemia after Sars-Cov-2 infection: case report JORNAL VASCULAR BRASILEIRO Oliveira de Macedo, V., Moreira, G., Fiuza de Albuquerque, A., de Sousa Oliveira, S., Esmeraldo, M., Barroso Barbosa, F. 2021; 20: e20200105

    Abstract

    The purpose of this article is to report the case of a 53-year-old black man, with no previous comorbidities, who presented 48 days after a confirmed diagnosis of COVID-19, complaining of an initially insidious epigastric pain that had progressed to severe pain radiating to the interscapular vertebral region, with hyporexia and episodes of projectile vomiting, with no nausea or fever. Laboratory tests revealed no signs of acute infection or pancreatic injury. Abdominal computed tomography showed dilated, fluid-filled small bowel loops with thickened walls. After clinical treatment, the patient developed persistent abdominal pain. An exploratory laparotomy was performed, finding two sites of small bowel stenosis, with no extrinsic cause, and signs of local ischemia and considerable distension of jejunal and ileal loops. After enterectomy and side-to-side enteroanastomosis, the patient recovered satisfactorily and was discharged with a prescription for oral anticoagulants for outpatient use.

    View details for DOI 10.1590/1677-5449.200105

    View details for Web of Science ID 001003546500017

    View details for PubMedID 34093678

    View details for PubMedCentralID PMC8147701

  • Macroscopic Hematuria as the Initial Presentation of Polycythemia Vera. Cureus Oliveira, S. e., Santos, L. T., Esmeraldo, M. A., Neto, O. s., da Ponte, M. F. 2020; 12 (10): e10800

    Abstract

    Polycythemia vera (PV) is a chronic myeloproliferative neoplasm (CMN) characterized by the accumulation of red blood cells, granulocytes and platelets in the peripheral blood. The main complications of PV are an increased risk of thrombosis, bleeding and transformation to myelodysplasia or acute leukemia. The authors report the case of a 28-year-old man with a complaint of macroscopic hematuria, low back pain and edema of the left arm associated with elevated hemoglobin, hematocrit and lactic dehydrogenase, leukocytosis and increased renal volume. Computed tomography of the chest and abdomen with contrast showed venous ectasia in the left upper limb and thrombosis of the right renal vein with extension to the inferior vena cava. A diagnosis of PV was confirmed by the presence of the JAK2 mutation and a bone marrow biopsy that showed panmyelosis. The patient was anticoagulated and treatment for PV was started with aspirin, phlebotomy and hydroxyurea. Then, the patient was discharged for outpatient follow-up with a hematologist. The case emphasizes the importance of clinical suspicion for atypical presentation of the disease in an unusual age range and of adequate etiological investigation of thrombosis in unusual sites.

    View details for DOI 10.7759/cureus.10800

    View details for PubMedID 33163304

    View details for PubMedCentralID PMC7641481