About

Polina Golland is a professor at MIT CSAIL, affiliated with the Department of Electrical Engineering and Computer Science. Her research areas include AI for Healthcare and Life Sciences, Artificial Intelligence and Machine Learning, and Biological and Medical Devices and Systems. She focuses on developing techniques for analysis and synthesis of systems that interact with the external world through perception, communication, and action, while also learning, making decisions, and adapting to changing environments. Her work leverages computational, theoretical, and experimental tools to advance sensors, energy transducers, physical substrates for computation, and systems addressing shared human challenges.

Research topics

• Medicine
• Radiology
• Biology
• Internal medicine
• Cardiology

Selected publications

• Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It

  ArXiv.org · 2026-04-02

  articleOpen access

  We present MaskGen, a theoretically grounded and deliberately simple approach for domain generalization in 3D biomedical image segmentation. Modern segmentation models degrade sharply under shifts in modality, disease severity, clinical sites, and more, limiting their reliable adoption. Existing generalization methods address this using extreme augmentations, hand-engineered domain statistics mixing, or architectural redesigns that add significant implementation overhead while yielding inconsistent performance across biomedical settings. MaskGen instead presents a principled learning strategy with marginal overhead that utilizes both source-domain image intensities and domain-stable foundation model representations to train robust segmentation models. As a result, MaskGen achieves strong gains in both fully supervised and few-shot segmentation across broad clinical shifts in biomedical studies. Unlike prior approaches, MaskGen is architecture- and loss-agnostic, compatible with standard augmentation pipelines, easy to implement, and tackles arbitrary anatomical regions. Its implementation is freely available at https://github.com/sebodiaz/MaskGen.

  PublisherOA PDF

• Multi-stage CNN for Fast Registration of 3D Preoperative CTs to 2D Intraoperative X-Rays

  Lecture notes in computer science · 2026-01-01

  book-chapterOpen access
  PublisherOA PDFDOI

• Fast Multi-Stack Slice-to-Volume Reconstruction via Multi-Scale Unrolled Optimization

  arXiv (Cornell University) · 2026-01-12

  preprintOpen accessSenior author

  Fully convolutional networks have become the backbone of modern medical imaging due to their ability to learn multi-scale representations and perform end-to-end inference. Yet their potential for slice-to-volume reconstruction (SVR), the task of jointly estimating 3D anatomy and slice poses from misaligned 2D acquisitions, remains underexplored. We introduce a fast convolutional framework that fuses multiple orthogonal 2D slice stacks to recover coherent 3D structure and refines slice alignment through lightweight model-based optimization. Applied to fetal brain MRI, our approach reconstructs high-quality 3D volumes in under 10s, with 1s slice registration and accuracy on par with state-of-the-art iterative SVR pipelines, offering more than speedup. The framework uses non-rigid displacement fields to represent transformations, generalizing to other SVR problems like fetal body and placental MRI. Additionally, the fast inference time paves the way for real-time, scanner-side volumetric feedback during MRI acquisition.

  PublisherDOI

• Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It

  arXiv (Cornell University) · 2026-04-02

  preprintOpen access

  We present MaskGen, a theoretically grounded and deliberately simple approach for domain generalization in 3D biomedical image segmentation. Modern segmentation models degrade sharply under shifts in modality, disease severity, clinical sites, and more, limiting their reliable adoption. Existing generalization methods address this using extreme augmentations, hand-engineered domain statistics mixing, or architectural redesigns that add significant implementation overhead while yielding inconsistent performance across biomedical settings. MaskGen instead presents a principled learning strategy with marginal overhead that utilizes both source-domain image intensities and domain-stable foundation model representations to train robust segmentation models. As a result, MaskGen achieves strong gains in both fully supervised and few-shot segmentation across broad clinical shifts in biomedical studies. Unlike prior approaches, MaskGen is architecture- and loss-agnostic, compatible with standard augmentation pipelines, easy to implement, and tackles arbitrary anatomical regions. Its implementation is freely available at https://github.com/sebodiaz/MaskGen.

  PublisherDOI

• Towards real-time alignment of 3D CT and 2D X-Ray with multi-stage CNNs

  HAL (Le Centre pour la Communication Scientifique Directe) · 2026-01-01

  article

  International audience

  Publisher

• Aligning Fetal Anatomy with Kinematic Tree Log-Euclidean PolyRigid Transforms

  ArXiv.org · 2026-03-02

  articleOpen accessSenior author

  Automated analysis of articulated bodies is crucial in medical imaging. Existing surface-based models often ignore internal volumetric structures and rely on deformation methods that lack anatomical consistency guarantees. To address this problem, we introduce a differentiable volumetric body model based on the Skinned Multi-Person Linear (SMPL) formulation, driven by a new Kinematic Tree-based Log-Euclidean PolyRigid (KTPolyRigid) transform. KTPolyRigid resolves Lie algebra ambiguities associated with large, non-local articulated motions, and encourages smooth, bijective volumetric mappings. Evaluated on 53 fetal MRI volumes, KTPolyRigid yields deformation fields with significantly fewer folding artifacts. Furthermore, our framework enables robust groupwise image registration and a label-efficient, template-based segmentation of fetal organs. It provides a robust foundation for standardized volumetric analysis of articulated bodies in medical imaging.

  PublisherOA PDF

• Aligning Fetal Anatomy with Kinematic Tree Log-Euclidean PolyRigid Transforms

  arXiv (Cornell University) · 2026-03-02

  preprintOpen accessSenior author

  Automated analysis of articulated bodies is crucial in medical imaging. Existing surface-based models often ignore internal volumetric structures and rely on deformation methods that lack anatomical consistency guarantees. To address this problem, we introduce a differentiable volumetric body model based on the Skinned Multi-Person Linear (SMPL) formulation, driven by a new Kinematic Tree-based Log-Euclidean PolyRigid (KTPolyRigid) transform. KTPolyRigid resolves Lie algebra ambiguities associated with large, non-local articulated motions, and encourages smooth, bijective volumetric mappings. Evaluated on 53 fetal MRI volumes, KTPolyRigid yields deformation fields with significantly fewer folding artifacts. Furthermore, our framework enables robust groupwise image registration and a label-efficient, template-based segmentation of fetal organs. It provides a robust foundation for standardized volumetric analysis of articulated bodies in medical imaging.

  PublisherDOI

• Volumetrically Consistent Implicit Atlas Learning via Neural Diffeomorphic Flow for Placenta MRI

  arXiv (Cornell University) · 2026-03-17

  preprintOpen accessSenior author

  Establishing dense volumetric correspondences across anatomical shapes is essential for group-level analysis but remains challenging for implicit neural representations. Most existing implicit registration methods rely on supervision near the zero-level set and thus capture only surface correspondences, leaving interior deformations under-constrained. We introduce a volumetrically consistent implicit model that couples reconstruction of signed distance functions (SDFs) with neural diffeomorphic flow to learn a shared canonical template of the placenta. Volumetric regularization, including Jacobian-determinant and biharmonic penalties, suppresses local folding and promotes globally coherent deformations. In the motivating application to placenta MRI, our formulation jointly reconstructs individual placentas, aligns them to a population-derived implicit template, and enables voxel-wise intensity mapping in a unified canonical space. Experiments on in-vivo placenta MRI scans demonstrate improved geometric fidelity and volumetric alignment over surface-based implicit baseline methods, yielding anatomically interpretable and topologically consistent flattening suitable for group analysis.

  PublisherDOI

• Volumetrically Consistent Implicit Atlas Learning via Neural Diffeomorphic Flow for Placenta MRI

  ArXiv.org · 2026-03-17

  articleOpen accessSenior author

  Establishing dense volumetric correspondences across anatomical shapes is essential for group-level analysis but remains challenging for implicit neural representations. Most existing implicit registration methods rely on supervision near the zero-level set and thus capture only surface correspondences, leaving interior deformations under-constrained. We introduce a volumetrically consistent implicit model that couples reconstruction of signed distance functions (SDFs) with neural diffeomorphic flow to learn a shared canonical template of the placenta. Volumetric regularization, including Jacobian-determinant and biharmonic penalties, suppresses local folding and promotes globally coherent deformations. In the motivating application to placenta MRI, our formulation jointly reconstructs individual placentas, aligns them to a population-derived implicit template, and enables voxel-wise intensity mapping in a unified canonical space. Experiments on in-vivo placenta MRI scans demonstrate improved geometric fidelity and volumetric alignment over surface-based implicit baseline methods, yielding anatomically interpretable and topologically consistent flattening suitable for group analysis.

  PublisherOA PDF

• Recent innovations in placental MRI: Integrating visualization and functional imaging

  Placenta · 2026-05-01

  article
  PublisherDOI

Recent grants

• Finding Structure in the Space of Activation Profiles in fMRI

  NSF · $850k · 2009–2013

• CAREER: Computational Modeling of Spatial Activation Patterns in fMRI

  NSF · $500k · 2007–2013

• Neuroimaging Analysis Center (NAC)

  NIH · $27.7M · 1998–2024

• NIH Grant U54EB005149

  NIH · $74.8M · 2015

Frequent coauthors

• Adrian V. Dalca

  207 shared

• Anne‐Katrin Giese

  Massachusetts General Hospital

  195 shared

• Juan Eugenio Iglesias

  Harvard University

  161 shared

• Natalia S. Rost

  Massachusetts General Hospital

  115 shared

• Markus D. Schirmer

  German Center for Neurodegenerative Diseases

  115 shared

• Elfar Adalsteinsson

  110 shared

• Ona Wu

  Athinoula A. Martinos Center for Biomedical Imaging

  107 shared

• Jordi Jiménez-Conde

  Hospital Del Mar

  101 shared

Labs

• MIT EECS Artificial Intelligence + Decision-makingPI