 |
Xiaoling HuPostdoctoral Research FellowAthinoula A. Martinos Center for Biomedical ImagingMGH/Harvard Medical SchoolCV / Scholar / Github / arXiv / OpenReview / Linkedin / Twitter |
I am maintaining a GitHub repo: Topology-Driven (Deep) Image Analysis. Please feel free to contribute!
I am currently a Postdoctoral Research Fellow at MGH/Harvard Medical School, hosted by Prof. Juan Eugenio Iglesias and Prof. Bruce Fischl.
I obtained my PhD degree from the Department of Computer Science at Stony Brook University.
Before that, I obtained my master and bachelor degrees from Tsinghua University and Huazhong University of Science and Technology, respectively.
Research Interests:
My research focuses on Machine Learning for Healthcare, with an emphasis on developing core AI/ML algorithms for healthcare applications.
In particular, I am interested in:
-
- Topology-Driven Deep Image Analysis: TopoLoss (NeurIPS'19), DMT (ICLR'21), TopoTrigger (ICLR'22), TopoInteraction (ECCV'22), Warping (NeurIPS'22), TopoSemiSeg (ECCV'24)
- Learning with Reliability, Interpretability, and Robustness: Consistency Ranking (ICLR'23), Structural Uncertainty (ICLR'23, NeurIPS'23), , Calibrating Count (ICCV'23), Hierarchical Uncertainty Estimation (ICLR'25)
- Multimodal AI and Generative AI (GenAI) for Healthcare: Brain-ID (ECCV'24), RankByGene (arXiv'24), TopoCellGen (CVPR'25), Learn2Synth (ICCV'25)
- Healthcare Applications: Modality-Agnostic Tumor Segmentation (ICCV'23), Anomaly-Guided Lesion Segmentation (MedIA'24), Scalable MRI Segmentation (arXiv'25)
Contact Address: 149 13th St, Charlestown, MA 02129
Mentoring
Recent Services
Organizer
Selected Publications (Full Publications)
 |
NEW! Scalable Segmentation for Ultra-High-Resolution Brain MR Images |
 |
NEW! RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistency |
 |
Deep Statistic Shape Model for Myocardium Segmentation |
Papers
 |
NEW! Learn2Synth: Learning Optimal Data Synthesis using Hypergradients for Brain Image Segmentation |
 |
NEW! TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model |
 |
NEW! Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging |
 |
Semi-supervised Segmentation of Histopathology Images with Noise-Aware Topological Consistency |
 |
Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imaging |
 |
Registration by Regression (RbR): a framework for interpretable and flexible atlas registration |
 |
Spatial Diffusion for Cell Layout Generation |
 |
Hard Negative Sample Mining for Whole Slide Image Classification |
 |
Semi-Supervised Contrastive VAE for Disentanglement of Digital Pathology Images |
 |
Anomaly-guided weakly supervised lesion segmentation on retinal OCT images |
 |
Topology-Aware Uncertainty for Image Segmentation |
 |
Calibrating Uncertainty for Semi-Supervised Crowd Counting |
 |
Enhancing Modality-Agnostic Representations via Meta-Learning for Brain Tumor Segmentation |
 |
Learning Probabilistic Topological Representations Using Discrete Morse Theory |
 |
Confidence Estimation Using Unlabeled Data |
 |
Structure-Aware Image Segmentation with Homotopy Warping |
 |
Learning Topological Interactions for Multi-Class Medical Image Segmentation |
 |
Trigger Hunting with a Topological Prior for Trojan Detection |
 |
A Manifold View of Adversarial Risk |
 |
A Topology-Attention ConvLSTM Network and Its Application to EM Images |
 |
Topology-aware Segmentation Using Discrete Morse Theory |
 |
3D Topology-Preserving Segmentation with Compound Multi-Slice Representation |
 |
Topology-Preserving Deep Image Segmentation |
Thesis
 |
Learning Topological Representations for Deep Image Understanding |
Awards
Industry Experience
 |
Topology-Aware Image Segmentation |
 |
Deep Shape Model Based Network |
 |
Object Detection and Clothes Search |