Xiaoling Hu

Postdoctoral Research Fellow

Laboratories for Computational Neuroimaging (LCN)

Athinoula A. Martinos Center for Biomedical Imaging

MGH/Harvard Medical School

Research Statement / CV / Linkedin / Twitter / Scholar / Github

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, advised by Prof. Chao Chen, and worked closely with Prof. Dimitris Samaras and Prof. Prateek Prasanna. During my PhD, I have also been fortunate to spend time at United Imaging Intelligence (UII) and Allen Institute for Cell Science to explore various biomedical scenarios/applications.

Before that, I obtained my master and bachelor degrees from Tsinghua University and Huazhong University of Science and Technology, respectively.

Research Interests: My research interest is Biomedical AI, and I am focusing on developing core AI/ML algorithms applied to medical imaging problems. In particular, I am interested in:

Topology-Driven Deep Image Analysis [NeurIPS'19, ISBI'21, ICLR'21, MICCAI'21, ICLR'22, ECCV'22, arXiv'22, NeurIPS'22, ICLR'23b, NeurIPS'23, Dissertation, arXiv'23b]

Uncertainty Estimation and Its Applications [ICLR'23a, ICLR'23b, ICCV'23b, NeurIPS'23]

Learning with Imperfect Data [ICLR'23a, ICCV'23a, ICCV'23b, arXiv'23b]

Email Address: xihu3 at mgh dot harvard dot edu

Contact Address: 62 13th St, Charlestown, MA 02129

Tutorials

Topology-Driven Image Analysis
Chao Chen, Bjoern Menze, Xiaoling Hu, Johannes C. Paetzold, Saumya Gupta
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023
Website

Selected Publications (Full Publications)

(* denotes equal contributions, ^† denotes students working closely with me)

	TopoSemiSeg: Enforcing Topological Consistency for Semi-Supervised Segmentation of Histopathology Images Meilong Xu^†, Xiaoling Hu, Saumya Gupta, Shahira Abousamra, Chao Chen Tech report arXiv Code
	Brain-ID: Learning Robust Feature Representations for Brain Imaging Peirong Liu, Oula Puonti, Xiaoling Hu, Daniel C. Alexander, Juan Eugenio Iglesias Tech report arXiv Code
	Topology-Aware Uncertainty for Image Segmentation Saumya Gupta^†, Yikai Zhang, Xiaoling Hu, Prateek Prasanna, Chao Chen Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023 Short version is also presented at NeurReps Workshop Paper Code
	Learning Topological Representations for Deep Image Understanding Xiaoling Hu PhD Dissertation pdf ProQuest Slide
	Calibrating Uncertainty for Semi-Supervised Crowd Counting Chen Li^†, Xiaoling Hu, Shahira Abousamra, Chao Chen International Conference on Computer Vision (ICCV), 2023 Paper Code Slide Poster Video
	Enhancing Modality-Agnostic Representations via Meta-Learning for Brain Tumor Segmentation Aishik Konwer^†, Xiaoling Hu, Xuan Xu, Joseph Bae, Chao Chen, Prateek Prasanna International Conference on Computer Vision (ICCV), 2023 Paper Slide
	Learning Probabilistic Topological Representations Using Discrete Morse Theory Xiaoling Hu, Dimitris Samaras, Chao Chen International Conference on Learning Representations (ICLR), 2023 (Spotlight, notable-top-25%) Short version is selected as Oral presentation* at Medical Imaging meets NeurIPS Workshop* Paper OpenReview Code Slide Poster
	Confidence Estimation Using Unlabeled Data Chen Li^†, Xiaoling Hu, Chao Chen International Conference on Learning Representations (ICLR), 2023 Paper OpenReview Code Poster
	Structure-Aware Image Segmentation with Homotopy Warping Xiaoling Hu Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022 Paper OpenReview Code Slide Poster
	Deep Statistic Shape Model for Myocardium Segmentation Xiaoling Hu, Xiao Chen, Yikang Liu, Eric Z. Chen, Terrence Chen, Shanhui Sun Tech report arXiv
	Learning Topological Interactions for Multi-Class Medical Image Segmentation Saumya Gupta^†, Xiaoling Hu, ..., Prateek Prasanna, Chao Chen European Conference on Computer Vision (ECCV), 2022 (Oral, acceptance rate 2.7%) Paper Code Slide Poster Video
	Trigger Hunting with a Topological Prior for Trojan Detection Xiaoling Hu, Xiao Lin, Michael Cogswell, Yi Yao, Susmit Jha, Chao Chen International Conference on Learning Representations (ICLR), 2022 Paper OpenReview Code Slide Poster
	A Manifold View of Adversarial Risk Wenjia Zhang, Yikai Zhang, Xiaoling Hu, Mayank Goswami, Chao Chen, Dimitris Metaxas International Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Paper Code
	A Topology-Attention ConvLSTM Network and Its Application to EM Images Jiaqi Yang^†, Xiaoling Hu, Chao Chen, Chia-Ling Tsai International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021 Paper OpenReview Code Slide Poster
	Topology-aware Segmentation Using Discrete Morse Theory Xiaoling Hu, Yusu Wang, Li Fuxin, Dimitris Samaras, Chao Chen International Conference on Learning Representations (ICLR), 2021 (Spotlight, acceptance rate 5.6%) Paper OpenReview Code Slide Poster
	3D Topology-Preserving Segmentation with Compound Multi-Slice Representation Jiaqi Yang^†, Xiaoling Hu, Chao Chen, Chia-Ling Tsai IEEE International Symposium on Biomedical Imaging (ISBI), 2021 Paper Poster
	Topology-Preserving Deep Image Segmentation Xiaoling Hu, Li Fuxin, Dimitris Samaras, Chao Chen Thirty-third Conference on Neural Information Processing Systems (NeurIPS), 2019 Paper Code1 Code2 Slide Poster
	Saliency detection based on integration of central bias, reweighting and multi-scale for superpixels Xiaoling Hu, Wenming Yang, Fei Zhou, Qingmin Liao IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016 Paper

Awards

Catacosinos Fellowship, 2023

Industry Experience

	Allen Institute (May 2022-Aug. 2022) Topology-Aware Image Segmentation
	United Imaging Intelligence (UII) (May 2021-Aug. 2021) Deep Shape Model Based Network
	Tencent Youtu Lab (June 2017-Jan. 2018) Object Detection and Clothes Search

Services

Reviewer for ICML, ICLR, NeurIPS, CVPR, ICCV, ECCV, AISTATS, MICCAI, AAAI etc.

Reading Group

Topology Data Analysis Reading Group