About

Ali Nabavizadeh, MD, is an Associate Professor of Radiology at the Hospital of the University of Pennsylvania. He is primarily an adult neuroradiologist with additional training in pediatric neuroradiology and nuclear radiology. His clinical expertise focuses on using neuroimaging to diagnose various diseases of the central nervous system. Dr. Nabavizadeh holds a research appointment at the Children’s Hospital of Philadelphia and is the imaging lead of two consortia, including the Children’s Brain Tumor Network (CBTN), which is dedicated to biospecimen-driven data generation. His research concentrates on multimodality imaging using structural and physiologic MRI imaging, along with PET probes and molecular imaging techniques, to better understand the complex nature of the brain tumor microenvironment. Dr. Nabavizadeh has contributed extensively to the field with over 140 peer-reviewed publications in prestigious journals. He serves as the associate editor for the brain tumor section at the American Journal of Neuroradiology and has led multiple prospective imaging trials, including investigator-initiated and industry-sponsored FDA registry trials.

Research topics

• Medicine
• Computer Science
• Radiology
• Internal medicine
• Pathology
• Artificial Intelligence
• Neuroscience
• Anatomy
• Pharmacology
• Surgery
• Chemistry
• Medical physics
• Oncology
• Biology
• Cognitive science
• Psychiatry
• Psychology
• Bioinformatics
• Cancer research

Selected publications

• Role of Neuroimaging in Cancer-Treatment Neurotoxicity

  American Journal of Roentgenology · 2025-06-25 · 9 citations

  reviewSenior author

  As cancer therapies evolve and become increasingly targeted, the spectrum of treatment-related neurotoxicities presents a growing challenge. This Review highlights important neurotoxic complications associated with commonly used and emerging cancer therapies, emphasizing the critical role of neuroimaging in their detection and differentiation from disease progression and other entities. The specific entities considered include neurologic immune-related adverse events, immune effector cell-associated neurotoxicity syndrome, and tumor inflammation-associated neurotoxicity. Imaging techniques, such as perfusion MRI, vessel wall imaging, and amino acid PET, are complementary in improving performance in diagnosing neurotoxicity syndromes and guiding timely clinical decision-making and intervention. A multidisciplinary approach integrating oncology, neurology, and imaging is crucial for balancing therapeutic benefits with neurotoxicity risk. Early recognition and intervention are essential; although many treatment-induced neurotoxicities are reversible, delayed diagnosis can result in long-term disability or even death. By recognizing characteristic imaging patterns, radiologists play a central role in identifying emerging treatment-related neurotoxicity syndromes, thereby supporting safe, high-quality, patient-centered cancer care.

  PublisherDOI

• Artificial Intelligence for Response Assessment in Pediatric Neuro-Oncology (AI-RAPNO), part 2: challenges, opportunities, and recommendations for clinical translation

  The Lancet Oncology · 2025-10-28 · 4 citations

  reviewSenior author
  PublisherDOI

• Supplementary Table S5 from Corticosteroid-Dependent Association between Prognostic Peripheral Blood Cell-Free DNA Levels and Neutrophil-Mediated NETosis in Patients with Glioblastoma

  2025-04-01

  supplementary-materialsOpen access

  <p>List of all methylGSA results for (Gene Ontology,GO, gene sets) differential methylation comparing cluster 1 vs cluster 2 from unsupervised clustering of the plasma ccfDNA methylation results.</p>

  PublisherDOI

• Supplementary Table S2 from Corticosteroid-Dependent Association between Prognostic Peripheral Blood Cell-Free DNA Levels and Neutrophil-Mediated NETosis in Patients with Glioblastoma

  2025-04-01

  supplementary-materialsOpen access

  <p>Published reference methylomes used in deconvolution</p>

  PublisherDOI

• Training the next generation of physicians for artificial intelligence-assisted clinical neuroradiology: ASNR MICCAI Brain Tumor Segmentation (BraTS) 2025 Lighthouse Challenge education platform

  ArXiv.org · 2025-09-21

  preprintOpen access

  High-quality reference standard image data creation by neuroradiology experts for automated clinical tools can be a powerful tool for neuroradiology & artificial intelligence education. We developed a multimodal educational approach for students and trainees during the MICCAI Brain Tumor Segmentation Lighthouse Challenge 2025, a landmark initiative to develop accurate brain tumor segmentation algorithms. Fifty-six medical students & radiology trainees volunteered to annotate brain tumor MR images for the BraTS challenges of 2023 & 2024, guided by faculty-led didactics on neuropathology MRI. Among the 56 annotators, 14 select volunteers were then paired with neuroradiology faculty for guided one-on-one annotation sessions for BraTS 2025. Lectures on neuroanatomy, pathology & AI, journal clubs & data scientist-led workshops were organized online. Annotators & audience members completed surveys on their perceived knowledge before & after annotations & lectures respectively. Fourteen coordinators, each paired with a neuroradiologist, completed the data annotation process, averaging 1322.9+/-760.7 hours per dataset per pair and 1200 segmentations in total. On a scale of 1-10, annotation coordinators reported significant increase in familiarity with image segmentation software pre- and post-annotation, moving from initial average of 6+/-2.9 to final average of 8.9+/-1.1, and significant increase in familiarity with brain tumor features pre- and post-annotation, moving from initial average of 6.2+/-2.4 to final average of 8.1+/-1.2. We demonstrate an innovative offering for providing neuroradiology & AI education through an image segmentation challenge to enhance understanding of algorithm development, reinforce the concept of data reference standard, and diversify opportunities for AI-driven image analysis among future physicians.

  PublisherOA PDFDOI

• Enhancing RAPNO: the need for standardized imaging heuristics and volumetric assessment

  Neuroradiology · 2025-05-15

  articleOpen access1st authorCorresponding

  Finally, while volumetric analysis remains optional in RAPNO, there is a growing consensus on its added value for irregular, infiltrative, or multifocal tumors.For such tumors, tools that offer reliable subregion tracking, change detection, and spatial mapping of new lesions over time are essential for consistent reporting and trial readiness, [4].A natural progression from descriptive frameworks to quantitative, validated tools that are widely accessible grounded in robust imaging standards [5], is urgently needed.We commend the authors for providing a valuable resource and believe that the next phase of RAPNO development should be driven by practical, implementationready strategies.These approaches can enhance consistency across centers, improve reproducibility of imaging assessments, and ultimately support patient-level decision making in both clinical trials and routine care.

  PublisherOA PDFDOI

• Artificial Intelligence for Response Assessment in Pediatric Neuro-Oncology (AI-RAPNO), part 1: review of the current state of the art

  The Lancet Oncology · 2025-10-28 · 6 citations

  review
  PublisherDOI

• Supplementary Table S8 from Corticosteroid-Dependent Association between Prognostic Peripheral Blood Cell-Free DNA Levels and Neutrophil-Mediated NETosis in Patients with Glioblastoma

  2025-04-01

  supplementary-materialsOpen access

  <p>List of all methylGSA results for (Gene Ontology,GO, gene sets) with differential methylation for % neutrophil ccfDNA dichotomized at median.</p>

  PublisherDOI

• AI-Powered Segmentation and Prognosis with Missing MRI in Pediatric Brain Tumors

  medRxiv · 2025-07-16

  preprintOpen access

  ABSTRACT Importance Brain MRI is the main imaging modality for pediatric brain tumors (PBTs); however, incomplete MRI exams are common in pediatric neuro-oncology settings and pose a barrier to the development and application of deep learning (DL) models, such as tumor segmentation and prognostic risk estimation. Objective To evaluate DL-based strategies (image-dropout training and generative image synthesis) and heuristic imputation approaches for handling missing MRI sequences in PBT imaging from clinical acquisition protocols, and to determine their impact on segmentation accuracy and prognostic risk estimation. Design This cohort study included 715 patients from the Children’s Brain Tumor Network (CBTN) and BraTS-PEDs, and 43 patients with longitudinal MRI (157 timepoints) from PNOC003/007 clinical trials. We developed a dropout-trained nnU-Net tumor segmentation model that randomly omitted FLAIR and/or T1w (no contrast) sequences during training to simulate missing inputs. We compared this against three imputation approaches: a generative model for image synthesis, copy-substitution heuristics, and zeroed missing inputs. Model-generated tumor volumes from each segmentation method were compared and evaluated against ground truth (expert manual segmentations) and incorporated into time-varying Cox regression models for survival analysis. Setting Multi-institutional PBT datasets and longitudinal clinical trial cohorts. Participants All patients had multi-parametric MRI and expert manual segmentations. The PNOC cohort had a median of three imaging timepoints and associated clinical data. Main Outcomes and Measures Segmentation accuracy (Dice scores), image quality metrics for synthesized scans (SSIM, PSNR, MSE), and survival discrimination (C-index, hazard ratios). Results The dropout model achieved robust segmentation under missing MRI, with ≤0.04 Dice drop and a stable C-index of 0.65 compared to complete-input performance. DL-based MRI synthesis achieved high image quality (SSIM > 0.90) and removed artifacts, benefiting visual interpretability. Performance was consistent across cohorts and missing data scenarios. Conclusion and Relevance Modality-dropout training yields robust segmentation and risk-stratification on incomplete pediatric MRI without the computational and clinical complexity of synthesis approaches. Image synthesis, though less effective for these tasks, provides complementary benefits for artifact removal and qualitative assessment of missing or corrupted MRI scans. Together, these approaches can facilitate broader deployment of AI tools in real-world pediatric neuro-oncology settings.

  PublisherOA PDFDOI

• Intracerebroventricular bivalent CAR T cells targeting EGFR and IL-13Rα2 in recurrent glioblastoma: a phase 1 trial

  Nature Medicine · 2025-06-01 · 57 citations

  articleOpen access
  PublisherOA PDFDOI

Frequent coauthors

• Anahita Fathi Kazerooni

  121 shared

• Ariana Familiar

  Children's Hospital of Philadelphia

  116 shared

• Benjamin H. Kann

  108 shared

• Arastoo Vossough

  Children's Hospital of Philadelphia

  88 shared

• Daphne A. Haas‐Kogan

  Harvard University

  88 shared

• Hugo J.W.L. Aerts

  85 shared

• Zezhong Ye

  Harvard University

  81 shared

• Anna Zapaishchykova

  Brigham and Women's Hospital

  75 shared

Education

• M.D.

  Shiraz Medical School

  2002