Todd Hollon

Associate Professor
University of Michigan
tocho (at) umich.edu


Publications

The complete list of MLiNS Lab publications.

2026

  1. Todd Hollon
    NEJM AI · 2026

    An editorial on why specialized models remain essential for medical AI, using neurovascular imaging as a case study for the limits of general-purpose systems and the need for domain-specific benchmarking.


  2. Figure from: Learning from routine health system data builds better neuroimaging AI models
    Akhil Kondepudi and Todd Hollon
    NATURE MEDICINE · 2026

    A Nature Medicine Research Briefing on NeuroVFM. Trained with Vol-JEPA on 5.24M CT and MRI series from 566,915 routine clinical studies - without diagnostic labels or paired reports - the model reached state-of-the-art accuracy across 82 CT and 74 MRI diagnostic tasks, and in a silent prospective study of 1,155 consecutive studies achieved 92.6% balanced triage accuracy against 71.2% for GPT-5.


  3. Figure from: Health system learning enables generalist neuroimaging models
    Akhil Kondepudi, Akshay Rao, Chenhui Zhao, Yiwei Lyu, Samir Harake, Soumyanil Banerjee, Jacob Ogle, Rushikesh S. Joshi, Anna-Katharina Meissner, Xinhai Hou, Cheng Jiang, Asadur Chowdury, Ashok Srinivasan, Brian Athey, Vikas Gulani, Aditya Pandey, Honglak Lee, and Todd Hollon
    NATURE MEDICINE · 2026

    NeuroVFM is a visual foundation model trained on 5.24M clinical MRI and CT volumes via health system learning, a paradigm that learns directly from uncurated data generated during routine clinical care. Using a scalable volumetric joint-embedding predictive architecture, it delivers state-of-the-art radiologic diagnosis and report generation with interpretable visual grounding, surpassing frontier models in accuracy, triage, and expert preference while reducing hallucinations.


  4. Figure from: Learning neuroimaging models with health system-scale data
    Yiwei Lyu, Samir Harake, Asadur Chowdury, Soumyanil Banerjee, Rachel Gologorsky, Shixuan Liu, Anna-Katharina Meissner, Akshay Rao, Chenhui Zhao, Akhil Kondepudi, Cheng Jiang, Xinhai Hou, Rushikesh S. Joshi, Volker Neuschmelting, Ashok Srinivasan, Dawn Kleindorfer, Brian Athey, Vikas Gulani, Aditya Pandey, Honglak Lee, and Todd Hollon
    NATURE BIOMEDICAL ENGINEERING · 2026

    Introduces Prima, a visual foundation model for brain MRI trained at health-system scale for diagnosis, triage, and clinically grounded decision support.


  5. Figure from: Learning complete and explainable visual representations from itemized text supervision
    Yiwei Lyu, Chenhui Zhao, Soumyanil Banerjee, Shixuan Liu, Akshay T. Rao, Akhil Kondepudi, Honglak Lee, and Todd C. Hollon
    COMPUTER VISION AND PATTERN RECOGNITION · 2026

    Standard contrastive language-image pre-training can neglect objects in visual scenes. ItemizedCLIP forces models to learn and attend to all described items, resulting in better visual representations.


  6. Figure from: CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization
    Xinhai Hou, Shaoyuan Xu, Manan Biyani, Moyan Li, Jia Liu, Todd C. Hollon, and Bryan Wang
    COMPUTER VISION AND PATTERN RECOGNITION · 2026

    Recent visual agents can score well while using image tools unfaithfully-e.g., cropping irrelevant regions or ignoring tool outputs. CodeV represents tools as executable Python code and trains with Tool-Aware Policy Optimization (TAPO), using process-level rewards on visual tool inputs and outputs to improve both accuracy and faithful tool use on search and broader multimodal benchmarks.


  7. Figure from: Towards Scalable Language-Image Pre-training for 3D Medical Imaging
    Chenhui Zhao, Yiwei Lyu, Asadur Zaman Chowdury, Edward S. Harake, Akhil Kondepudi, Akshay T. Rao, Xinhai Hou, Honglak Lee, and Todd C. Hollon
    TRANSACTIONS ON MACHINE LEARNING RESEARCH · 2026

    Vision-language pre-training for volumetric MRI and CT is usually limited by radiologist-curated datasets. HLIP instead uses hierarchical attention over slice, scan, and study to pre-train on uncurated clinical data at scale, boosting performance on public brain MRI and head CT benchmarks.


  8. Figure from: Anatomic Predilection of Isocitrate Dehydrogenase-Mutant Gliomas: A Multi-Institutional Spatial Analysis
    Park M, Weiss H, Harake ES, Fang C, Springer A, Goff NK, Markert JE, Reinecke D, Maarouf N, Heiland DH, Miller AM, Todd C. Hollon, John G. Golfinos, and Daniel A. Orringer
    NEUROSURGERY · 2026

    A multi-institutional spatial analysis characterizing where IDH-mutant gliomas arise in the brain, informing surgical planning, sampling, and interpretation of tumor biology across centers.


  9. Maarouf NI, Reinecke D, Smith A, Markert JE, Cogan TG, Han X, Alyakin A, Alber DA, Park M, Goff NK, Weiss H, Harake ES, Eddy K, Todd C. Hollon, Eric K. Oermann, and Daniel A. Orringer
    NEUROSURGERY · 2026

    This study applies natural language processing to automatically extract key glioma molecular markers from pathology reports, enabling scalable clinical data curation for research and decision support.


  10. Figure from: CNS-Obsidian: A Neurosurgical Vision-Language Model Built From Scientific Publications
    Alyakin A, Stryker J, Alber DA, Lee JV, Sangwon KL, Duderstadt B, Save A, Kurland D, Frome S, Singh S, Zhang J, Yang E, Park KY, Orillac C, Valliani AA, Neifert S, Liu A, Patel A, Livia C, Lau D, Laufer I, Rozman PA, Hidalgo ET, Riina H, Feng R, Todd C. Hollon, Aphinyanaphongs Y, Golfinos JG, Snyder L, Leuthardt EC, Kondziolka D, and Eric K. Oermann
    NEUROSURGERY · 2026

    CNS-Obsidian is a neurosurgical vision-language model trained on multimodal data from CNS Publications journals, progressing from general and medical VLMs to a specialty-specific expert for differential diagnosis, education, and clinical dialogue. A blinded randomized trial evaluates CNS-Obsidian as a multimodal co-pilot for neurosurgical diagnosis against GPT-4o with provider feedback.


  11. Figure from: AI-Powered Pipeline Transforms Neurosurgical Articles Into High-Quality Graphical Abstracts
    Alyakin A, Stryker J, Lee JV, Feng R, Todd C. Hollon, Kondziolka D, and Eric K. Oermann
    NEUROSURGERY PRACTICE · 2026

    An automated pipeline extracts structured text, figures, and captions from neurosurgical manuscripts and procedurally generates journal-style graphical abstracts, scaling visual summaries for research dissemination.


  12. Figure from: Minimizing the risks of stereotactic brain biopsy in suspected central nervous system lymphoma: a retrospective database study
    Li A, Saleh S, Sharba N, Guivatchian E, Sagher O, Sullivan SE, Heth JA, Todd C. Hollon, Thompson BG, Pandey AS, Umemura Y, and Wajd N. Al-Holou
    JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY · 2026

    A retrospective database analysis identifies factors associated with complications after stereotactic biopsy for suspected CNS lymphoma, informing safer biopsy planning and perioperative management.


  13. Tripathy A, Harake ES, Ahmad A, Sharba N, Li A, Saleh S, Sagher O, Heth JA, Altshuler D, Todd C. Hollon, Thompson BG, Pandey AS, Umemura Y, and Wajd N. Al-Holou
    JOURNAL OF NEUROSURGERY · 2026

    A retrospective study of 616 stereotactic brain biopsies develops and validates pre- and postoperative risk scores for early hospice enrollment, identifying patients least likely to benefit from the procedure. Age, basal ganglia target, mental status deficits, KPS score, prolonged ICU stay, and grade 4 glioma were independent predictors.


  14. Figure from: AI-driven label-free Raman spectromics for intraoperative spinal tumor assessment
    Reinecke D, Müller N, Meissner AK, Fürtjes G, Leyer L, Wang C, Ion-Margineanu A, Maarouf N, Smith A, Todd C. Hollon, Cheng Jiang, Xinhai Hou, Al-Shughri A, Körner LI, Widhalm G, Roetzer-Pejrimovsky T, Snuderl M, Camelo-Piragua S, Golfinos JG, Goldbrunner R, Orringer DA, von Spreckelsen N, and Neuschmelting V
    NPJ DIGITAL MEDICINE · 2026

    This work uses AI-enabled label-free Raman spectromics for rapid intraoperative spinal tumor assessment, supporting real-time tissue characterization during surgery.


  15. Figure from: Intelligent histology for tumor neurosurgery
    Xinhai Hou *, Akhil V. Kondepudi *, Cheng Jiang *, Yiwei Lyu, Edward Samir Harake, Asadur Chowdury, Anna-Katharina Meißner, Volker Neuschmelting, David Reinecke, Gina Fürtjes, Georg Widhalm, Lisa Irina Körner, Jakob Straehle, Nicolas Neidert, Pierre Scheffler, Jürgen Beck, Michael E. Ivan, Ashish H. Shah, Aditya S. Pandey, Sandra Camelo-Piragua, Dieter Henrik Heiland, Oliver Schnell, Chris Freudiger, Jacob Young, Melike Pekmezci, Katie Scotford, Shawn Hervey-Jumper, Daniel Orringer, Mitchel Berger, and Todd Hollon
    NEURO-ONCOLOGY ADVANCES · 2026

    This review synthesizes advances in intelligent histology for neurosurgery, highlighting how stimulated Raman histology and modern machine learning are converging to support faster, more precise intraoperative decision-making.


2025

  1. Figure from: Extending SEEDS to a Supervoxel Algorithm for Medical Image Analysis
    Chenhui Zhao, Yan Jiang, and Todd C. Hollon
    ARXIV · 2025

    This work extends the SEEDS superpixel algorithm from 2D to 3D volumes as 3D SEEDS, reporting substantially faster supervoxel generation and improved segmentation quality across diverse medical imaging tasks.


  2. Figure from: A Phase 2 Study of Multiparametric Magnetic Resonance Imaging-Guided High-Dose Response-Adaptive Radiation Therapy With Concurrent Temozolomide in Patients With Newly Diagnosed Glioblastoma: Results From an Interim Analysis
    Kim MM, Aryal MP, Suresh K, Rosen BS, Parmar H, You D, Leung D, Clarke N, Fortunato J, Al-Holou W, Heth J, Altshuler D, Todd Hollon, Edwards DM, Wahl DR, Lawrence TS, and Cao Y
    INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY, BIOLOGY, PHYSICS · 2025

    An interim phase 2 analysis of mpMRI-guided, response-adaptive chemoradiation for newly diagnosed glioblastoma, evaluating feasibility and early outcomes of individualized dose adaptation.


  3. Figure from: Fast intraoperative detection of primary central nervous system lymphoma and differentiation from common central nervous system tumors using stimulated Raman histology and deep learning
    Reinecke D, Maarouf N, Smith A, Alber D, Markert J, Goff NK, Todd C. Hollon, Asadur Chowdury, Cheng Jiang, Xinhai Hou, Meissner AK, Fürtjes G, Ruge MI, Ruess D, Stehle T, Al-Shughri A, Körner LI, Widhalm G, Roetzer-Pejrimovsky T, Golfinos JG, Snuderl M, Neuschmelting V, and Daniel A. Orringer
    NEURO-ONCOLOGY · 2025

    This study combines stimulated Raman histology and deep learning for fast intraoperative detection of primary CNS lymphoma and differentiation from other common CNS tumors.


  4. Figure from: Predicting therapeutic clinical trial enrollment for adult patients with low- and high-grade glioma using supervised machine learning
    Mehari M, Warrier G, Dada A, Kabir A, Haskell-Mendoza AP, Tripathy A, Jha R, Nieblas-Bedolla E, Jackson JD, Gonzalez AT, Reason EH, Flusche AM, Reihl S, Dalton T, Negussie M, Gonzales CN, Ambati VS, Desjardins A, Daniel AGS, Krishna S, Chang S, Porter A, Fecci PE, Todd Hollon, Chukwueke UN, Badal K, Molinaro AM, and Hervey-Jumper SL
    SCIENCE ADVANCES · 2025

    Supervised machine learning models predict clinical trial enrollment for adults with low- and high-grade glioma from routine data, with the goal of improving accrual and matching patients to studies.


  5. Figure from: Validation of a novel artificial intelligence model (SpinePose) to automatically and accurately predict spinopelvic parameters using scoliosis radiographs in an external cohort
    Rushikesh S. Joshi, Edward S. Harake, Cheng Jiang, Haselhuhn JJ, Linzey JR, Jones JC, Zaki MM, Odland K, Wilseck Z, Joseph JR, Polly DW, Todd C. Hollon, and P. Park
    NEUROSURGERY FOCUS · 2025

    This external-cohort study validates SpinePose for automated spinopelvic parameter prediction from scoliosis radiographs, demonstrating generalizability across institutions.


  6. Figure from: HDL Nanodiscs Loaded with Liver X Receptor Agonist Decreases Tumor Burden and Mediates Long-term Survival in Mouse Glioma Model
    Halseth TA, Mujeeb AA, Liu L, Banerjee K, Lang N, Todd Hollon, Yu M, Vander Roest M, Mei L, He H, Sheth M, Maria G. Castro, and Schwendeman A
    SMALL · 2025

    This preclinical study shows that HDL nanodiscs carrying a liver X receptor agonist reduce glioma burden and improve long-term survival in mouse models.


  7. Figure from: Foundation models for fast, label-free detection of glioma infiltration
    Akhil Kondepudi, Melike Pekmezci, Xinhai Hou, Katie Scotford, Cheng Jiang, Akshay Rao, Edward S. Harake, Asadur Chowdury, Wajd Al-Holou, Lin Wang, Aditya Pandey, Pedro R. Lowenstein, Maria G. Castro, Lisa Irina Koerner, Thomas Roetzer-Pejrimovsky, Georg Widhalm, Sandra Camelo-Piragua, Misha Movahed-Ezazi, Daniel A. Orringer, Honglak Lee, Christian Freudiger, Mitchel Berger, Shawn Hervey-Jumper, and Todd Hollon
    NATURE · 2025

    FastGlioma is a computational pathology model for real-time detection of glioma infiltration at the surgical margin, outperforming the current standard of care.


  8. Figure from: Protocol to annotate and automate single-cell instance segmentation on stimulated Raman histology using deep learning
    Abhishek Bhattacharya, Eric Landgraf, Cheng Jiang, Asadur Chowdury, Akhil Kondepudi, Lin Wang, Edward S. Harake, Xinhai Hou, Lisa Walsh, and Todd C. Hollon
    STAR PROTOCOLS · 2025

    This protocol provides a reproducible workflow for single-cell annotation and segmentation in stimulated Raman histology, enabling scalable dataset curation and model training for computational pathology studies.


  9. Chen JS, Oh JY, Hollon TC, Hervey-Jumper SL, Young JS, and Berger MS
    CANCERS (BASEL) · 2025

    This review summarizes the intraoperative role of Raman spectroscopy in neurosurgical oncology, covering technical principles, current applications, and translational opportunities.


  10. Figure from: An Empirical Study on Unifying JEPA and Language Supervision for Visual Representation Learning
    Shixuan Liu*, Daniel A. Li*, Yiwei Lyu, Akhil Kondepudi, Honglak Lee, and Todd C. Hollon
    NEURIPS UNIREPS WORKSHOP · 2025

    CLIPred is a framework that jointly optimizes the I-JEPA self-supervision and CLIP language supervision objectives for visual representation learning, outperforming either alone and achieving better zero-shot transfer than DINOv2+CLIP at lower training cost.


  11. Figure from: Step-Calibrated Diffusion for Biomedical Optical Image Restoration
    Yiwei Lyu, Sung Jik Cha, Cheng Jiang, Asadur Chowdury, Xinhai Hou, Edward Harake, Akhil Kondepudi, Christian Freudiger, Honglak Lee, and Todd C. Hollon
    AAAI · 2025

    This paper introduces Restorative Step-Calibrated Diffusion (RSCD) for biomedical optical image restoration, improving reconstruction fidelity by adapting denoising dynamics to the characteristics of microscopy data.


2024

  1. Figure from: Localization of protoporphyrin IX during glioma-resection surgery via paired stimulated Raman histology and fluorescence microscopy
    Mustafa Nasir-Moin, Lisa Irina Wadiura, Vlad Sacalean, Devin Juros, Misha Movahed-Ezazi, Emily K. Lock, Andrew Smith, Matthew Lee, Hannah Weiss, Michael Müther, Daniel Alber, Sujay Ratna, Camila Fang, Eric Suero-Molina, Sönke Hellwig, Walter Stummer, Karl Rössler, Johannes A. Hainfellner, Georg Widhalm, Barbara Kiesel, David Reichert, Mario Mischkulnig, Rajan Jain, Jakob Straehle, Nicolas Neidert, Oliver Schnell, Jürgen Beck, Jay Trautman, Steve Pastore, Donato Pacione, Dimitris Placantonakis, Eric Karl Oermann, John G. Golfinos, Todd C. Hollon, Matija Snuderl, Christian W. Freudiger, Dieter Henrik Heiland, and Daniel A. Orringer
    NATURE BIOMEDICAL ENGINEERING · 2024

    Paired stimulated Raman histology and fluorescence microscopy map protoporphyrin IX (PpIX) during glioma resection, linking 5-ALA fluorescence to tissue context for more interpretable intraoperative guidance.


  2. Figure from: A self-supervised framework for learning whole slide representations
    Xinhai Hou *, Cheng Jiang*, Akhil Kondepudi, Yiwei Lyu, Asadur Zaman Chowdury, Honglak Lee, and Todd C. Hollon
    NEURIPS AIM-FM WORKSHOP · 2024

    This study introduces Slide Pre-trained Transformers (SPT), a self-supervised framework for whole-slide representation learning that captures multiscale histologic structure to support downstream pathology tasks with limited manual annotation.


  3. Figure from: An empirical study of CLIP fine-tuning with similarity clusters
    Shixuan Liu, Yiwei Lyu, Honglak Lee, and Todd C. Hollon
    NEURIPS FITML WORKSHOP · 2024

    SimCLIP is a generalized framework for CLIP fine-tuning that constructs minibatches containing clusters of similar image-text pairs to produce harder in-batch negatives, improving downstream performance over standard CLIP fine-tuning without hand-crafted hard negative captions.


  4. Figure from: Super-resolution of biomedical volumes with 2D supervision
    Cheng Jiang, Alexander Gedeon, Yiwei Lyu, Eric Landgraf, Yufeng Zhang, Xinhai Hou, Akhil Kondepudi, Asadur Chowdury, Honglak Lee, and Todd C. Hollon
    CVPR WORKSHOP · 2024

    This work proposes Masked Slice Diffusion for Super-Resolution (MSDSR), a strategy for volumetric biomedical super-resolution trained with only 2D supervision, enabling high-quality 3D reconstruction when fully paired 3D labels are scarce.


  5. Figure from: Development and Validation of an Artificial Intelligence Model to Accurately Predict Spinopelvic Parameters
    Edward S. Harake, Joseph R. Linzey, Cheng Jiang, Rushikesh S. Joshi, Mark M. Zaki, Jaes C. Jones, Siri S. Khalsa, John H. Lee, Zachary Wilseck, Jacob R. Joseph, Todd C. Hollon, and Paul Park
    JOURNAL OF NEUROSURGERY SPINE · 2024

    This work introduces and validates an AI model for automated spinopelvic parameter estimation from imaging, aiming to improve speed and consistency in preoperative spinal alignment assessment.


2023

  1. Figure from: Combined cytotoxic and immune-stimulatory gene therapy for primary adult high-grade glioma: a phase 1, first-in- human trial
    Yoshie Umemura, Daniel Orringer, Larry Junck, Maria L Varela, Molly E J West, Syed M Faisal, Andrea Comba, Jason Heth, Oren Sagher, Denise Leung, Aaron Mammoser, Shawn Hervey-Jumper, Daniel Zamler, Viveka N Yadav, Patrick Dunn, Wajd Al-Holou, Todd Hollon, Michelle M Kim, Daniel R Wahl, Sandra Camelo-Piragua, Andrew P Lieberman, Sriram Venneti, Paul McKeever, Theodore Lawrence, Ryo Kurokawa, Karen Sagher, David Altshuler, Lili Zhao, Karin Muraszko, Maria G Castro, and Pedro R Lowenstein
    LANCET ONCOLOGY · 2023

    A phase 1, first-in-human trial of combined cytotoxic and immune-stimulatory gene therapy delivered to the resection cavity in adults with primary high-grade glioma, reporting safety and early efficacy signals.


  2. Figure from: Hierarchical Discriminative Learning Improves Visual Representations of Biomedical Microscopy
    Cheng Jiang*, Xinhai Hou*, Akhil Kondepudi, Asadur Chowdury, Christian W. Freudiger, Daniel A. Orringer, Honglak Lee, and Todd C. Hollon
    COMPUTER VISION AND PATTERN RECOGNITION · 2023

    HiDisc is a self-supervised learning method that leverages the inherent patient-slide-patch hierarchy of biomedical microscopy to learn stronger visual representations without explicit negative mining.


  3. Figure from: Fine-grained Text Style Transfer with Diffusion-Based Language Models
    Yiwei Lyu, Tiange Luo, Jiacheng Shi, Todd C. Hollon, and Honglak Lee
    ACL Repl4NLP Workshop · 2023

    This paper introduces a diffusion-based approach for fine-grained text style transfer, improving controllability while preserving semantic content.


  4. Figure from: AI-based molecular classification of diffuse gliomas using rapid, label-free optical imaging
    Todd Hollon, Cheng Jiang, Asadur Chowdury, Mustafa Nasir-Moin, Akhil Kondepudi, Alexander Aabedi, Arjun Adapa, Wajd Al-Holou, Jason Heth, Oren Sagher, Pedro Lowenstein, Maria Castro, Lisa Irina Wadiura, Georg Widhalm, Volker Neuschmelting, David Reinecke, Niklas von Spreckelsen, Mitchel Berger, Shawn Hervey-Jumper, John Golfinos, Matija Snuderl, Sandra Camelo-Piragua, Christian Freudiger, Honglak Lee, and Daniel Orringer
    NATURE MEDICINE · 2023

    Diffuse gliomas are classified using the molecular features. DeepGlioma predicts the molecular genetics of brain tumors within minutes of biopsy, in the operating room, to better inform surgical goals.


  5. Daniel A. Orringer and Todd C. Hollon
    MED · 2023

    This perspective discusses how deep learning can accelerate inference of clinically relevant glioma genetics from imaging and tissue data.


  6. Figure from: Subclonal evolution and expansion of spatially distinct THY1-positive cells is associated with recurrence in glioblastoma
    Wajd N. Al-Holou, Hanxiao Wang, Visweswaran Ravikumar, Sunita Shankar, Morgan Oneka, Ziad Fehmi, Roel GW Verhaak, Hoon Kim, Drew Pratt, Sandra Camelo-Piragua, Corey Speers, Daniel R Wahl, Todd Hollon, Oren Sagher, Jason A Heth, Karin M. Muraszko, Theodore S. Lawrence, Ana C de Carvalho, Tom Mikkelsen, Arvind Rao, Alnawaz Rehemtulla
    NEOPLASIA · 2023

    This study links recurrence in glioblastoma to subclonal expansion of spatially distinct THY1-positive populations, highlighting mechanisms of progression and resistance.


  7. Figure from: A comparison of ventricular volume and linear indices in predicting shunt dependence in aneurysmal subarachnoid hemorrhage
    Talbot-Stetsko HK, Pawlowski KD, Aaron BL, Adapa AR, Altshuler DB, Srinivasan S, Pandey AS, Maher CO, Hollon TC, and Khalsa SSS
    WORLD NEUROSURGERY X · 2023

    This analysis compares volumetric and linear imaging metrics for predicting shunt dependence after aneurysmal subarachnoid hemorrhage.


  8. Figure from: Generation of 3D ex vivo mouse- and patient-derived glioma explant slice model for integration of confocal time-lapse imaging and spatial analysis
    Comba A, Varela ML, Faisal SM, Abel CC 2nd, Argento AE, Al-Holou WN, Hollon TC, Perelman JD, Dunn PJ, Motsch S, Castro MG, and Lowenstein PR
    STAR PROTOCOLS · 2023

    This protocol establishes 3D ex vivo glioma explant slice models from mouse and patient tissue for integrated confocal time-lapse imaging and spatial analysis.


2022

  1. Figure from: OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology
    Cheng Jiang*, Asadur Chowdury*, Xinhai Hou*, Akhil Kondepudi, Christian W. Freudiger, Kyle Conway, Sandra Camelo-Piragua, Daniel A. Orringer, Honglak Lee, and Todd C. Hollon
    NEURIPS DATASETS & BENCHMARKS · 2022

    OpenSRH is the first public dataset of clinical stimulated Raman histology images from brain tumor patients, released alongside benchmarks to accelerate machine learning research for intraoperative brain tumor diagnosis.


  2. Figure from: Generating novel pituitary datasets from open-source imaging data and deep volumentric segmentation
    Rachel Gologorsky, Edward Harake, Grace von Oiste, Mustafa Nasir-Moin, William Couldwell, Eric Oermann, and Todd Hollon
    PITUITARY · 2022

    This study builds a new pituitary imaging resource by combining open-source scans with deep volumetric segmentation, enabling larger and more standardized datasets for pituitary AI research.


  3. Figure from: Methods and Impact for Using Federated Learning to Collaborate on Clinical Research
    Alexander T M Cheung, Mustafa Nasir-Moin, Young Joon Fred Kwon, Jiahui Guan, Chris Liu, Lavender Jiang, Christian Raimondo, Silky Chotai, Lola Chambless, Hasan S Ahmad, Daksh Chauhan, Jang W Yoon, Todd Hollon, Vivek Buch, Douglas Kondziolka, Dinah Chen, Lama A Al-Aswad, Yindalon Aphinyanaphongs, and Eric Karl Oermann
    NEUROSURGERY · 2022

    A practical overview of federated learning for multi-site clinical research in neurosurgery: how models can be trained collaboratively without centralizing raw patient data, and what that means for governance and discovery.


  4. Figure from: Perigeniculate giant cell tumor of temporal bone
    Eric E. Babajanian, Todd C. Hollon, Tori A. Seasor, William Couldwell, and Richard K. Gurgel
    CUREUS · 2022

    This case report details diagnosis and surgical management of a rare perigeniculate giant cell tumor of the temporal bone.


  5. Figure from: Single-cell phenotyping using optical imaging and artificial intelligence
    Abhishek Bhattacharya, Daniel Alber, and Todd Hollon
    MLHC · 2022

    This work presents an optical imaging plus AI workflow for single-cell phenotyping, enabling quantitative cellular characterization in complex tissue.


  6. Figure from: Laminectomy at T4 and T5 for Resection of Symptomatic Cavernous Malformation
    Vance L.Fredrickson Todd C.Hollon Robert C.Rennert Marcus D.Mazur Andrew T.Dailey, and William T.Couldwell
    WORLD NEUROSURGERY · 2022

    This operative report describes thoracic laminectomy technique for resection of a symptomatic cavernous malformation, with practical surgical considerations.


  7. Figure from: Spatiotemporal analysis of glioma heterogeneity reveals COL1A1 as an actionable target to disrupt tumor progression
    Andrea Comba, Syed M. Faisal, Patrick J. Dunn, Anna E. Argento, Todd C. Hollon, Wajd N. Al-Holou, Maria Luisa Varela, Daniel B. Zamler, Gunnar L. Quass, Pierre F. Apostolides, Clifford Abel II, Christine E. Brown, Phillip E. Kish, Alon Kahana, Celina G. Kleer, Sebastien Motsch, Maria G. Castro and Pedro R. Lowenstein
    NATURE COMMUNICATIONS · 2022

    Spatiotemporal profiling of glioma heterogeneity implicates COL1A1 in the tumor microenvironment as a tractable target to slow progression, connecting matrix biology to therapeutic opportunity. The MLiNS lab contributed a semantic segmentation model to detect oncostreams in brain tumor microscopy images, supporting quantitative analysis of tumor architecture.


  8. Figure from: Rapid automated analysis of skull base tumor specimens using intraoperative optical imaging and artificial intelligence
    Cheng Jiang, Abhishek Bhattacharya, Joseph Linzey, Rushikesh Joshi, Sung Jik Cha, Sudharsan Srinivasan, Daniel Alber, Akhil Kondepudi, Esteban Urias, Balaji Pandian, Wajd Al-Holou, Steve Sullivan, B. Gregory Thompson, Jason Heth, Chris Freudiger, Siri Khalsa, Donato Pacione, John G. Golfinos, Sandra Camelo-Piragua, Daniel A. Orringer, Honglak Lee, and Todd Hollon
    NEUROSURGERY · 2022

    This study demonstrates rapid AI-assisted analysis of intraoperative optical images from skull base tumor specimens to support real-time surgical decisions.


  9. Figure from: Extent of Resection Research in Skull Base Neurosurgery: Previous Studies and Future Directions
    Todd Hollon, Vance Fredrickson, William Couldwell
    WORLD NEUROSURGERY · 2022

    This review synthesizes evidence on extent-of-resection in skull base neurosurgery and outlines key priorities for future outcome-driven research.


  10. Figure from: Cranio-Orbital Approach for Single-Stage En Bloc Resection of Optic Nerve Glioma: Technical Note
    Vance L Fredrickson, Guilherme J Agnoletto, Todd C Hollon, Bornali Kundu, Vance R Mortimer, William T Couldwell
    OPERATIVE NEUROSURGERY · 2022

    This technical note describes a cranio-orbital approach for single-stage en bloc resection of optic nerve glioma, emphasizing operative strategy and exposure.


  11. Figure from: Microsurgical Excision of Ruptured Lenticulostriate Artery Aneurysm
    Vance L Fredrickson, Serge Makarenko, Todd C Hollon, Robert C Rennert, Ramesh Grandhi, William T Couldwell
    WORLD NEUROSURGERY · 2022

    This case-based report highlights microsurgical management of a ruptured lenticulostriate artery aneurysm, including decision-making for a rare vascular lesion.


2021

  1. Figure from: Uncovering Spatiotemporal Heterogeneity of High-Grade Gliomas: From Disease Biology to Therapeutic Implications
    Andrea Comba, Syed M Faisal, Maria Luisa Varela, Todd Hollon, Wajd N Al-Holou, Yoshie Umemura, Felipe J Nunez, Sebastien Motsch, Maria G Castro, and Pedro R Lowenstein
    FRONTIERS IN ONCOLOGY · 2021

    This review examines spatiotemporal heterogeneity in high-grade glioma and its implications for tumor biology, progression, and treatment design.


  2. Figure from: Lateral Suboccipital Craniotomy With C1-C2 Hemilaminectomies and C1-C3 Fusion for the Treatment of a C1-C2 Synovial Cyst Causing Spinal Cord Compression: 2-Dimensional Operative Video
    Davide Marco Croci, Vance L. Fredrickson, Todd C. Hollon, Andrew T. Dailey, and William T. Couldwell
    OPERATIVE NEUROSURGERY · 2021

    This operative video article details a lateral suboccipital approach with staged decompression and fusion for a C1-C2 synovial cyst causing cord compression.


  3. Figure from: Label-free brain tumor imaging using Raman-based methods
    Todd Hollon and Daniel A. Orringer
    JOURNAL OF NEURO-ONCOLOGY · 2021

    This review outlines Raman-based, label-free brain tumor imaging methods and their potential to improve intraoperative diagnosis and margin assessment.


  4. Figure from: Rapid, label-free detection of diffuse glioma recurrence using intraoperative stimulated Raman histology and deep neural networks
    Todd C Hollon, Balaji Pandian, Esteban Urias, Akshay V Save, Arjun R Adapa, Sudharsan Srinivasan, Neil K Jairath, Zia Farooq, Tamara Marie, Wajd N Al-Holou, Karen Eddy, Jason A Heth, Siri Sahib S Khalsa, Kyle Conway, Oren Sagher, Jeffrey N Bruce, Peter Canoll, Christian W Freudiger, Sandra Camelo-Piragua, Honglak Lee, Daniel A Orringer
    NEURO-ONCOLOGY · 2021

    This study demonstrates that stimulated Raman histology with deep neural networks can identify diffuse glioma recurrence intraoperatively, supporting rapid distinction between recurrent tumor and treatment-related changes.


  5. Figure from: Clinical Translation of Stimulated Raman Histology
    Cordelia Orillac, Todd Hollon, Daniel A Orringer
    METHODS IN MOLECULAR BIOLOGY · 2021

    This methods chapter reviews practical considerations for clinical deployment of stimulated Raman histology, from instrumentation to intraoperative workflow.


  6. Figure from: Ventricular Volume Change as a Predictor of Shunt-Dependent Hydrocephalus in Aneurysmal Subarachnoid Hemorrhage
    Haley K Talbot-Stetsko, Kristen D Raue, Bryan L Aaron, Arjun R Adapa, David B Altshuler, Sudharsan Srinivasan, Aditya S Pandey, Cormac O Maher, Todd C Hollon, Siri Sahib S Khalsa
    WORLD NEUROSURGERY · 2021

    This study evaluates ventricular volume dynamics as predictors of shunt-dependent hydrocephalus after aneurysmal subarachnoid hemorrhage.


  7. Figure from: Far Lateral Craniotomy for Obliteration of High-Risk Craniocervical Junction Arteriovenous Fistula
    Guilherme J Agnoletto, Vance L Fredrickson, Todd C Hollon, William T Couldwell
    NEUROLOGY INDIA · 2021

    This report describes a far lateral craniotomy technique for safe obliteration of a high-risk craniocervical junction arteriovenous fistula.


  8. Figure from: Idiopathic chronic temporal lobe herniation with associated epilepsy
    Austin Gamblin, Vance L Fredrickson, Todd C Hollon, Karen L Salzman, William T Couldwell
    ACTA NEUROCHIRURGICA · 2021

    This case series characterizes idiopathic chronic temporal lobe herniation associated with epilepsy and discusses diagnostic and surgical management considerations.


2020

  1. Figure from: Normal cerebral ventricular volume growth in childhood
    Noah S Cutler , Sudharsan Srinivasan , Bryan L Aaron, Sharath Kumar Anand , Michael S Kang, David B Altshuler, Thomas C Schermerhorn, Todd C Hollon , Cormac O Maher , and Siri Sahib S Khalsa
    JOURNAL OF NEUROSURGERY PEDIATRICS · 2020

    This study defines normative trajectories of cerebral ventricular volume growth in childhood to support pediatric neuroimaging interpretation.


  2. Figure from: Automated histologic diagnosis of CNS tumors with machine learning
    Siri Sahib S Khalsa, Todd C Hollon, Arjun Adapa, Esteban Urias, Sudharsan Srinivasan, Neil Jairath, Julianne Szczepanski, Peter Ouillette, Sandra Camelo-Piragua, Daniel A Orringer
    CNS ONCOLOGY · 2020

    This work presents an early machine learning framework for automated CNS tumor histologic diagnosis, showing how computational analysis can augment intraoperative pathology interpretation.


  3. Figure from: Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks
    Todd C Hollon, Balaji Pandian, Arjun R Adapa, Esteban Urias, Akshay V Save, Siri Sahib S Khalsa, Daniel G Eichberg, Randy S D'Amico, Zia U Farooq, Spencer Lewis, Petros D Petridis, Tamara Marie, Ashish H Shah, Hugh J L Garton, Cormac O Maher, Jason A Heth, Erin L McKean, Stephen E Sullivan, Shawn L Hervey-Jumper, Parag G Patil, B Gregory Thompson, Oren Sagher, Guy M McKhann 2nd, Ricardo J Komotar, Michael E Ivan, Matija Snuderl, Marc L Otten, Timothy D Johnson, Michael B Sisti, Jeffrey N Bruce, Karin M Muraszko, Jay Trautman, Christian W Freudiger, Peter Canoll, Honglak Lee, Sandra Camelo-Piragua, Daniel A Orringer
    NATURE MEDICINE · 2020

    A deep learning workflow combining stimulated Raman histology with convolutional neural networks delivers near real-time intraoperative brain tumor diagnosis, matching pathologist accuracy while compressing turnaround from ~30 minutes to under 150 seconds.


  4. Figure from: An automated tissue-to-diagnosis pipeline using intraoperative stimulated Raman histology and deep learning
    Todd C. Hollon and Daniel A. Orringer
    MOLECULAR & CELLULAR ONCOLOGY · 2020

    This article presents an end-to-end tissue-to-diagnosis pipeline that integrates intraoperative stimulated Raman histology with deep learning classification.


  5. Figure from: Denoising stimulated Raman histology using weak supervision to improve label-free optical microscopy of human brain tumors
    Esteban Urias, Christopher Freudiger, Daniel Orringer, Honglak Lee, and Todd Hollon
    MLHC · 2020

    This paper develops weakly supervised denoising for stimulated Raman histology to improve image quality in label-free microscopy of human brain tumors.


2019

  1. Figure from: Synthetic high-density lipoprotein nanoparticles for the treatment of Niemann-Pick diseases
    Mark L Schultz, Maria V Fawaz, Ruth D Azaria, Todd C Hollon, Elaine A Liu, Thaddeus J Kunkel, Troy A Halseth, Kelsey L Krus, Ran Ming, Emily E Morin, Hayley S McLoughlin, David D Bushart, Henry L Paulson, Vikram G Shakkottai, Daniel A Orringer, Anna S Schwendeman, Andrew P Lieberman
    BMC MEDICINE · 2019

    This translational study evaluates synthetic HDL nanoparticles as a therapeutic strategy for Niemann-Pick disease, with evidence of improved disease-relevant outcomes.


  2. Figure from: Surgical Adjuncts to Increase the Extent of Resection: Intraoperative MRI, Fluorescence, and Raman Histology
    Todd Hollon, Walter Stummer, Daniel Orringer, Eric Suero Molina
    NEUROSURGERY CLINICS OF NORTH AMERICA · 2019

    This review compares adjunctive intraoperative technologies that increase extent of resection, including MRI, fluorescence guidance, and Raman histology.


2018

  1. Figure from: A machine learning approach to predict early outcomes after pituitary adenoma surgery
    Todd C Hollon, Adish Parikh, Balaji Pandian, Jamaal Tarpeh, Daniel A Orringer, Ariel L Barkan, Erin L McKean, Stephen E Sullivan
    JOURNAL OF NEUROSURGERY · 2018

    This study develops a machine learning model to forecast early postoperative outcomes after pituitary adenoma surgery, supporting risk stratification and perioperative planning.


  2. Figure from: Clinical Factors Associated With ICU-Specific Care Following Supratentoral Brain Tumor Resection and Validation of a Risk Prediction Score
    Lynze R Franko, Todd Hollon, Joseph Linzey, Christopher Roark, Venkatakrishna Rajajee, Kyle Sheehan, Magnus Teig, Shawn Hervey-Jumper, Jason Heth, Daniel Orringer, Craig A Williamson
    CRITICAL CARE MEDICINE · 2018

    This work identifies predictors of ICU-level needs after supratentorial brain tumor resection and validates a risk score to guide postoperative triage and resource allocation.


  3. Figure from: Shedding Light on IDH1 Mutation in Gliomas
    Todd C Hollon, Daniel A Orringer
    CLINICAL CANCER RESEARCH · 2018

    This commentary discusses emerging biological and clinical implications of IDH1 mutation in gliomas.


  4. Figure from: Surgical Treatment of Olfactory Neuroblastoma: Major Complication Rates, Progression Free and Overall Survival
    Aileen Wertz, Todd Hollon, Lawrence J Marentette, Stephen E Sullivan, Jonathan B McHugh, Erin L McKean
    JOURNAL OF NEUROLOGICAL SURGERY · 2018

    This outcomes study reports complication profiles and survival metrics after surgical treatment of olfactory neuroblastoma.


  5. Figure from: Primary diffuse leptomeningeal melanomatosis: Description and recommendations
    Yamaan S Saadeh, Todd C Hollon, Amanda Fisher-Hubbard, Luis E Savastano, Paul E McKeever, Daniel A Orringer
    JOURNAL OF CLINICAL NEUROSCIENCE · 2018

    This article describes a rare presentation of primary diffuse leptomeningeal melanomatosis and offers practical diagnostic and management recommendations.


  6. Figure from: Microvascular Brainstem Ischemia After Vestibular Schwannoma Surgery: A Clinical and Microanatomic Study
    Todd C Hollon, Luis E Savastano, Davis P Argersinger, Douglas J Quint, B Gregory Thompson
    WORLD NEUROSURGERY · 2018

    This study investigates mechanisms of postoperative microvascular brainstem ischemia after vestibular schwannoma surgery using clinical and microanatomic data.


  7. Figure from: Rapid Intraoperative Diagnosis of Pediatric Brain Tumors Using Stimulated Raman Histology
    Todd C Hollon, Spencer Lewis, Balaji Pandian, Yashar S Niknafs, Mia R Garrard, Hugh Garton, Cormac O Maher, Kathryn McFadden, Matija Snuderl, Andrew P Lieberman, Karin Muraszko, Sandra Camelo-Piragua, Daniel A Orringer
    CANCER RESEARCH · 2018

    This paper extends stimulated Raman histology to pediatric neurosurgery, showing rapid, label-free intraoperative assessment of pediatric brain tumors to help guide operative management.


2017

  1. Figure from: Ventriculoscopic Surgery for Cystic Retrochiasmatic Craniopharyngiomas: Indications, Surgical Technique, and Short-Term Patient Outcomes
    Todd C Hollon, Luis E Savastano, David Altshuler, Ariel L Barkan, Stephen E Sullivan
    OPERATIVE NEUROSURGERY · 2017

    This paper outlines indications and technique for ventriculoscopic treatment of cystic retrochiasmatic craniopharyngiomas and reports short-term clinical outcomes in treated patients.


  2. Figure from: Korsakoff syndrome from retrochiasmatic suprasellar lesions: rapid reversal after relief of cerebral compression in 4 cases
    Luis E Savastano, Todd C Hollon, Ariel L Barkan, Stephen E Sullivan
    JOURNAL OF NEUROSURGERY · 2017

    This case series reports retrochiasmatic suprasellar lesions presenting with Korsakoff syndrome and documents rapid cognitive reversal after decompression.


  3. Figure from: Rapid intraoperative histology of unprocessed surgical specimens via fibre-laser-based stimulated Raman scattering microscopy
    Daniel A Orringer, Balaji Pandian, Yashar S Niknafs, Todd C Hollon, Julianne Boyle, Spencer Lewis, Mia Garrard, Shawn L Hervey-Jumper, Hugh J L Garton, Cormac O Maher, Jason A Heth, Oren Sagher, D Andrew Wilkinson, Matija Snuderl, Sriram Venneti, Shakti H Ramkissoon, Kathryn A McFadden, Amanda Fisher-Hubbard, Andrew P Lieberman, Timothy D Johnson, X Sunney Xie, Jay K Trautman, Christian W Freudiger, Sandra Camelo-Piragua
    NATURE BIOMEDICAL ENGINEERING · 2017

    This study established stimulated Raman histology as a practical intraoperative microscopy method, enabling rapid, label-free visualization of fresh surgical tissue and laying the groundwork for real-time computational neuropathology.


2016

  1. Figure from: Spontaneous subarachnoid hemorrhage due to ruptured cavernous internal carotid artery aneurysm after medical prolactinoma treatment
    Siri Sahib Khalsa, Todd C Hollon, Ravi Shastri, Jonathan D Trobe, Joseph J Gemmete, and Aditya S Pandey
    JOURNAL OF NEUROINTERVENTIONAL SURGERY · 2016

    This case report describes subarachnoid hemorrhage from ruptured cavernous ICA aneurysm after medical prolactinoma therapy, highlighting a rare neurovascular complication.


  2. Figure from: Supratentorial hemispheric ependymomas: an analysis of 109 adults for survival and prognostic factors
    Todd Hollon, Vincent Nguyen, Brandon W Smith, Spencer Lewis, Larry Junck, Daniel A Orringer
    JOURNAL OF NEUROSURGERY · 2016

    This cohort study of 109 adults with supratentorial hemispheric ependymoma characterizes survival outcomes and prognostic factors to inform treatment planning and follow-up.


  3. Figure from: Delayed Sciatic Nerve Injury Resulting From Myositis Ossificans Traumatica
    Zhe Guan, Thomas J Wilson, Jon A Jacobson, Todd C Hollon, Lynda J-S Yang
    PM&R · 2016

    This case report describes delayed sciatic neuropathy caused by myositis ossificans traumatica and discusses diagnosis and treatment timing.


  4. Figure from: Improving the accuracy of brain tumor surgery via Raman-based technology
    Todd Hollon, Spencer Lewis, Christian W Freudiger, X Sunney Xie, Daniel A Orringer
    JOURNAL OF NEUROSURGERY · 2016

    This review discusses Raman-based intraoperative technologies that can improve brain tumor surgery accuracy through real-time tissue characterization.


  5. Figure from: Surgical Management of Skull Base Rosai-Dorfman Disease
    Todd Hollon, Sandra I Camelo-Piragua, Erin L McKean, Stephen E Sullivan, Hugh J L Garton
    WORLD NEUROSURGERY · 2016

    This case-focused report summarizes surgical management considerations for rare skull base Rosai-Dorfman disease.


  6. Figure from: Outcome of Transsphenoidal Surgery for Cushing Disease: A Single-Center Experience Over 32 Years
    William F Chandler, Ariel L Barkan, Todd Hollon, Alla Sakharova, Jayson Sack, Barunashish Brahma, David E Schteingart
    NEUROSURGERY · 2016

    This long-term single-center analysis reports outcomes of transsphenoidal surgery for Cushing disease, identifying patterns in remission and recurrence over three decades of care.


2015

  1. Figure from: Ruptured pediatric cerebellopontine angle epidermoid cyst: a case report detailing radiographic evolution and clinical course
    Zhe Guan, Todd Hollon, J Nicole Bentley, Hugh J L Garton
    JOURNAL OF NEUROSURGERY · 2015

    This pediatric case report documents radiographic evolution and clinical course after rupture of a cerebellopontine angle epidermoid cyst.


  2. Figure from: Advances in the Surgical Management of Low-Grade Glioma
    Todd Hollon, Shawn L Hervey-Jumper, Oren Sagher, Daniel A Orringer
    SEMINARS IN RADIATION ONCOLOGY · 2015

    This review summarizes modern surgical strategies for low-grade glioma, including operative planning, mapping, and extent-of-resection considerations.


  3. Figure from: Skull fracture mimicking eosinophilic granuloma
    Todd Hollon, Paul E McKeever, Hugh J L Garton, Cormac O Maher
    CHILD'S NERVOUS SYSTEM · 2015

    This case report highlights a skull fracture presentation that mimicked eosinophilic granuloma, emphasizing diagnostic pitfalls in pediatric skull lesions.


2013

  1. Figure from: Mutations in glioblastoma oncosuppressive pathways pave the way for oncomodulatory activity of cytomegalovirus
    Todd C Hollon, Richard L Price, Chang-Hyuk Kwon, E Antonio Chiocca
    ONCOIMMUNOLOGY · 2013

    This study links glioblastoma tumor-suppressor pathway mutations with oncomodulatory cytomegalovirus activity, supporting a context-dependent disease model.


  2. Figure from: Cytomegalovirus contributes to glioblastoma in the context of tumor suppressor mutations
    Richard L Price, Jieun Song, Katherine Bingmer, Tae Hyong Kim, Ji-Yeun Yi, Michal O Nowicki, Xiaokui Mo, Todd Hollon, Eric Murnan, Christopher Alvarez-Breckenridge, Soledad Fernandez, Balveen Kaur, Andreana Rivera, Michael Oglesbee, Charles Cook, E Antonio Chiocca, Chang-Hyuk Kwon
    CANCER RESEARCH · 2013

    This paper demonstrates that cytomegalovirus can promote glioblastoma progression in models with specific tumor suppressor mutations.