Voxel-accurate MRI-microscopy correlation enables AI-powered prediction of brain disease states

Schroers, J.; Yang, Y.; Reyhan, E.; Sivapalan, N.; Ismail-Zade, E.; Heuer, A.; Scheck, J. G.; Langeroudi, A. P.; Alhalabi, O. T.; Moghiseh, T.; Fischer, M.; Jende, J.; Suchorska, B.; Heiland, D. H.; Karreman, M. A.; Ricklefs, F. L.; Breckwoldt, M. O.; Kurz, F. T.; Venkataramani, V.

doi:10.1101/2025.10.06.680637

bioRxiv · 10.1101/2025.10.06.680637

Voxel-accurate MRI-microscopy correlation enables AI-powered prediction of brain disease states

Schroers, J.·Yang, Y.·Reyhan, E.·Sivapalan, N.·Ismail-Zade, E.·Heuer, A.·Scheck, J. G.·Langeroudi, A. P.·Alhalabi, O. T.·Moghiseh, T.·Fischer, M.·Jende, J.·Suchorska, B.·Heiland, D. H.·Karreman, M. A.·Ricklefs, F. L.·Breckwoldt, M. O.·Kurz, F. T.·Venkataramani, V.

View original source ↗Export metadata ↓

Abstract

Magnetic resonance imaging (MRI) is essential for visualizing the healthy and diseased brain, yet the cellular basis of MRI signal and how it changes over time remain poorly understood. Here, we present BRIDGE (Brain Radiological Imaging with Deep-learning based Ground-Truth Exploration), a platform integrating in vivo MRI with in vivo two-photon (2P) and ex vivo super-resolution microscopy using a multi-step, iterative co-registration pipeline. It enables in vivo, longitudinal, and voxel-precise mapping of MRI signals to their cellular origins for the first time. The registered overlay reveals the cellular and anatomical origins of MRI signals and enables training of convolutional neural networks to enhance the effective resolution of MRI. Using BRIDGE, we identified a microenvironmental vessel biomarker for early metastatic colonization in patient-derived xenograft models of brain metastasis. In particular we found that distinct T2*-weighted hypointense lesions correspond to reduced blood flow and erythrostasis in perimetastatic capillaries. In glioma, longitudinal intravital studies further demonstrated direct correlations between non-vasogenic T2-weighted signal changes and patient-dependent tumor growth dynamics. Taken together, BRIDGE advances radiological interpretation by establishing a microscopic ground truth for MRI signatures over time, enabling deep learning-based predictive histology, and providing cellular-level insights into tumor microenvironment features with direct clinical imaging implications. Graphical abstractBRIDGE enables longitudinal voxel-to-voxel correlation and ground truth based automatic segmentation of MR images O_FIG O_LINKSMALLFIG WIDTH=177 HEIGHT=200 SRC="FIGDIR/small/680637v1_ufig1.gif" ALT="Figure 1"> View larger version (73K): org.highwire.dtl.DTLVardef@f1f64eorg.highwire.dtl.DTLVardef@1619e3eorg.highwire.dtl.DTLVardef@1dc2e7forg.highwire.dtl.DTLVardef@7097e1_HPS_FORMAT_FIGEXP M_FIG C_FIG

Source connections

Published article ↗

Explore related subjects

cancer biology Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Schroers, J., Yang, Y., Reyhan, E., Sivapalan, N., Ismail-Zade, E., Heuer, A., Scheck, J. G., Langeroudi, A. P., Alhalabi, O. T., Moghiseh, T., Fischer, M., Jende, J., Suchorska, B., Heiland, D. H., Karreman, M. A., Ricklefs, F. L., Breckwoldt, M. O., Kurz, F. T., Venkataramani, V.. 2025-10-07. Voxel-accurate MRI-microscopy correlation enables AI-powered prediction of brain disease states. https://doi.org/10.1101/2025.10.06.680637

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

The Phospholipase A2 Activity of Peroxiredoxin 6 Protects Hepatocarcinoma Cells Against Ferroptosis and Mitophagy Impairment

Peroxiredoxin 6 (PRDX6) is a moonlighting protein that plays a key role in regulating redox homeostasis and lipid metabolism through its unique dual peroxidase and calcium-independent phospholipase A2 (iPLA2) activities. Here, we generated a stable HepG2 cell line harboring a D140A mutation to selectively ablate iPLA2 activity, and we compared its phenotype with that of wild-type (WT) and PRDX6-knockout (KO) cells. D140A exhibited low ROS leves, similar to WT cells, confirming that oxidative stress is due to peroxidase deficiency. In contrast, D140A cells displayed higher lipid peroxidation than WT cells, though significantly lower than that of KO cells. Furthermore, the D140A mutant mirrored the KO phenotype regarding intracellular ferrous iron accumulation, impaired lipid droplet biogenesis, and the downregulation of the key ferroptosis regulator GPX4. Mechanistically, integrated proteomic, lipidomic, and enzymatic analyses revealed that a deficiency in iPLA2 activity of PRDX6 disrupted the release of key lipid species necessary for cell structure and signaling. Consequently, organelles involved in lipid synthesis and trafficking, such as peroxisomes, endoplasmic reticulum, mitochondria and lipid droplet, were affected. Specifically, we found that mitochondria exhibited a reduction in cristae and a diminished capacity for mitophagy and autophagy, which ultimately makes cells much more susceptible to erastin-induced ferroptotic cell death. Taken together, our findings demonstrate that PRDX6 iPLA2 activity uniquely coordinates organelle lipid homeostasis and mitophagy to protect cancer cells from ferroptotic cell death. Consequently, the use of iPLA2 inhibitors such as MJ33, which decreased PRDX6 iPLA2 activity to a level comparable to the mutant D140A, could represent a promising therapeutic strategy for inducing ferroptotic cell death in hepatocellular carcinoma.

cancer biology↗

bioRxiv2026

Serum extracellular vesicle proteomics reveals treatment-associated biomarkers in pancreatic ductal adenocarcinoma

Background Longitudinal biomarkers of treatment response in pancreatic ductal adenocarcinoma (PDAC) are needed. Extracellular vesicle (EV)-enriched serum proteomics may provide a minimally invasive approach for monitoring systemic and tumor-associated responses to therapy. Methods Paired pre-treatment and post-treatment serum samples were analyzed from 51 patients with pancreatic cancer, including 25 treated with FOLFIRINOX and 20 treated with gemcitabine-based therapy. EVs were enriched using the Mag-Net method and profiled by data independent acquisition mass spectrometry. After batch correction and filtering, 941 proteins were retained for differential and pathway analyses. Paired linear models and gene set enrichment analyses were used to assess treatment-associated changes. Baseline protein abundance and longitudinal changes were evaluated in relation to overall survival (OS) using Cox models. Results A total of 2,089 EV-associated proteins were identified, with an average of 1,186 proteins quantified per sample. Across the cohort, 26 proteins differed between post- and pretreatment samples. Proteins that increased after treatment were primarily related to extracellular matrix organization and cell adhesion, whereas proteins that decreased after treatment were associated with actin cytoskeletal organization, coagulation, and hemostasis. Treatment-associated changes were more pronounced in the FOLFIRINOX group, in which 32 proteins were differentially expressed. FOLFIRINOX was characterized by coordinated reductions in platelet- and coagulation-associated proteins, including PF4, PF4V1, PPBP, GP5, ITGA2B, and ITGB3, accompanied by enrichment of platelet activation, coagulation, and hemostasis pathways among down-regulated processes. No individual proteins met the same significance threshold in the gemcitabine group. A composite seven-protein platelet score decreased significantly after FOLFIRINOX but not for gemcitabine, and the between-regimen difference in score change was significant. Higher pretreatment ITGB1 abundance was associated with longer OS after multiple-testing correction (HR, 0.112; BH-FDR = 0.0063). In multivariable analysis, greater treatment-associated platelet-score depletion was independently associated with shorter OS (HR per unit increase in {Delta}score, 0.56; P = 0.030). Conclusions Longitudinal serum EV-enriched proteomics identified treatment-associated biological changes in PDAC, including a coordinated platelet-related response predominantly observed after FOLFIRINOX. Baseline ITGB1 abundance and longitudinal platelet-score changes represent potentially complementary prognostic and pharmacodynamic markers. These findings are exploratory and require validation in larger, independent cohorts incorporating platelet counts, coagulation measurements, and targeted proteomic assays.

cancer biology↗

bioRxiv2026

BAF complexes cooperate with lineage-restricted transcription factors to establish cell-state-specific regulatory programs

BRG1/BRM-associated factor (BAF) complexes are essential regulators of chromatin organization and cell identity. Genes encoding BAF subunits are among the most frequently mutated in human cancer. Yet, how disruption of a single subunit gives rise to distinct tumor states remains poorly understood. Atypical teratoid rhabdoid tumors (ATRTs) provide a compelling model, as they are uniformly driven by bi-allelic loss of the BAF subunit SMARCB1, yet segregate into distinct molecular subtypes. Using integrated multi-omics profiling of patient-derived ATRT organoids and primary tumor tissues, we show that transcriptional and chromatin accessibility changes upon SMARCB1 reconstitution are directed by subtype- and lineage-specific transcription factor (TF) repertoires. Genome-wide binding and transcriptomic analyses reveal that SMARCB1 reconstitution enables the lineage-specific TF RFX4 to engage regulatory elements and activate neuronal differentiation programs, partially reprogramming ATRT-MYC toward an ATRT-SHH-like identity. Together, these findings demonstrate that SMARCB1 loss disrupts TF-dependent chromatin priming, revealing that the lineage-specific regulatory output of BAF complexes is constrained by the underlying TF repertoire.

cancer biology↗