Zhou, Yuxiang

Automated diagnostic report generation lies at the core of clinical diagnosis and can alleviate clinician shortages. Existing diagnostic report generation methods have two major limitations: they rely on unimodal inputs (e.g., images), ignoring textual biomarkers like medical history, and lack proactive dialogue capabilities to elicit personalized clinical information. To address those issues, we propose a ProActive Multimodal Agentic (PAMA) system, which performs comprehensive disease analysis by examining biomarkers in diverse sources, including multi-view medical images, medical histories, and diagnostic conversations. Built upon a knowledge graph and recommendation-based dialogue architecture, PAMA actively initiates adaptive, multi-turn conversations with patients, which is integrated with visual data for robust and reliable report generation. Specifically, PAMA actively generates adaptive multi-turn questions to collect clinically relevant background information, and then fuses the resulting dialogue context with visual representations for robust diagnostic report generation. We validate our approach on two real-world benchmark datasets, MIMIC-CXR and IU-Xray, through extensive quantitative evaluations and comparisons with state-of-the-art baselines. Furthermore, we conduct user studies to assess the realism and clinical quality of the generated reports. Finally, we present real-world case studies to examine the performance of our system across diverse scenarios, demonstrating its robustness on scalability, complexity, and data variability.

Background/Objectives: White matter (WM) tract detection is critical in the presurgical planning of tumor resection. However, standard-of-care imaging techniques including T1-weighted, T2-weighted, and Diffusion Tensor Imaging (DTI) often fail to identify WM tracts within edematous regions. In T1/T2-weighted imaging, edema increases extracellular water and reduces tissue contrast, and in diffusion-weighted imaging, edema elevates isotropic diffusion, reducing sensitivity to anisotropic diffusion along WM tracts. Advanced biophysical diffusion modeling techniques such as Neurite Orientation Dispersion and Density Imaging (NODDI) and the Standard Model (SM) address this limitation by compartmentalizing the diffusion signal into free-water, intra-neurite, and extra-neurite contributions. Here, we test if biophysical multi-compartment models can robustly identify WM tracts and recover tractography streamlines within edematous regions. Methods: In this study, we use multi-shell diffusion-weighted MRI data obtained from patients with meningiomas—a pathology allowing for isolation of the effects of edema without the confounding effects of tumor cell invasion. We compared FA from standard and free-water-corrected DTI, the orientation dispersion index (ODI) from NODDI, and P2 (a scalar descriptor of fiber orientation coherence) from the SM fODF in edematous and unaffected contralateral WM regions. As a proof of concept, we visually evaluated the tractography performance across models. Results: Our results show that (1 − ODI) and P2 values in edema remained close to within-subject contralateral measurements, contrasting with substantial reductions in FA and FW-FA. (1 − ODI) showed a small but statistically significant increase in edema (~8%, p = 0.02), while P2 was unchanged. Conclusions: These results highlight the potential of biophysical diffusion models for preoperative mapping in edema.

Background: The potential long-term effects of Severe Acute Respiratory Syndrome Coronavirus (SARS-CoV-2) infection on the brain structure have not yet been fully elucidated. Even though existing studies have reported structural changes in the post-COVID-19 period, the results remain highly inconsistent and controversial. As such, identifying an imaging biomarker for post-COVID brains is still under investigation. This review aims to comprehensively summarize the structural MRI (sMRI) studies that focus on volumetric brain changes at least two weeks following COVID-19 infection. Methods: A systematic literature search was conducted on PubMed, SCOPUS, Web of Science, EMBASE, and Google Scholar up to 9 September 2025. Studies that utilized sMRI to assess volumetric brain changes post-COVID at greater than two weeks following infection were included. Exclusion criteria encompassed research involving pediatric or adolescent populations and imaging modalities other than sMRI. Preprints, reviews, case reports, case series and post-mortem studies were also excluded. Results: Forty-one studies satisfied the inclusion criteria and consisted of 2895 patients and 1729 healthy controls. Despite the wide variability in image acquisition protocols, data processing methods, and comorbidities between studies, multiple studies reported statistically significant volumetric reductions in the hippocampus, amygdala, thalamus, basal ganglia, nucleus accumbens and the cerebellum months to years after infection, especially in older hospitalized patients with severe COVID-19. Conclusions: The emerging literature reports long-term volume changes across various brain regions in individuals previously infected with COVID-19; however, the evidence is inconsistent. Specific imaging biomarkers following exposure to SARS-CoV-2 infection and the underlying mechanisms of these changes are yet to be identified. Future studies with harmonized imaging protocols, longitudinal designs, and integrated biomarker and clinical data are needed to define robust biomarkers and elucidate the pathophysiology of these findings.

Abstract BACKGROUND Glioblastoma (GBM) is a molecularly and phenotypically heterogeneous tumor, with regional invasion patterns driving treatment resistance and universal recurrence. In infiltrative regions, GBM cells adopt at least two predominant invasive phenotypes: Neuronal-enriched (NEU), with synaptic and neurodevelopment programs, and Glycolytic/Plurimetabolic (GPM), with heightened immune and metabolic activity. These subtypes differ in therapeutic vulnerability and microenvironmental interactions; features not captured by conventional contrast-enhanced (T1+C) MRI due to minimal blood-brain barrier (BBB) disruption. Our group sought to develop predictive models to distinguish variability of NEU/GPM subtypes within infiltrative GBM, utilizing graph convolutional networks (GCN), advanced multiparametric MRI (mpMRI), and spatially-matched image-localized biopsies with transcriptomic profiling. METHODS We analyzed 18 mpMRI features —including conventional, diffusion-weighted, and Dynamic Susceptibility Contrast (DSC) perfusion MRI— of 101 image-localized biopsies from MRI non-enhancing infiltrative margins of 64 GBM patient tumors. Features were hierarchically clustered per modality; each cluster was represented as a node in a Neo4j graph. Edges connected nodes sharing overlapping samples. Nodes were annotated with NEU or GPM subtype proportion. GCNs were trained to classify subtype-enriched nodes using graph topology and node features. RESULTS GCNs achieved high predictive performance on held-out test data (AUC = 0.95 for NEU, 0.88 for GPM; 70:30 train-test split) with similar 5-fold cross-validation performance and generalized well to an independent cohort (AUC > 0.85, n = 45). Importantly, performance was robust without relying on T1+C imaging, enabling prediction beyond BBB-disrupted regions. GCNs outperformed traditional classifiers (logistic regression, random forest). CONCLUSION Our results demonstrate that GCN-modeling of mpMRI features enables non-invasive prediction of invasive GBM subtypes at the tumor margin. Unlike convolutional neural networks (CNN), which rely on spatial continuity, GCNs leverage relational structure between heterogeneous imaging features, making them ideal for modeling sparse, non-grid data. This may support non-invasive regional vulnerability detection, surgical targeting, and improved response assessment.