Hong-Yu Zhou
Postdoctoral fellow
Department of Biomedical Informatics
Harvard Medical School
Harvard University
Email: whuzhouhongyu at gmail.com

Recent News

Paper (Selected / Full)

A Transformer-based Representation-learning Model with Unified Processing of Multimodal Input for Clinical Diagnostics.
Hong-Yu Zhou*, Yizhou Yu*, Chengdi Wang*, Shu Zhang, Yuanxu Gao, Jia Pan, Jun Shao, Guangming Lu, Kang Zhang, Weimin Li.
A multimodal transformer for clinical diagnostics.
Nature Biomedical Engineering 2023 | Paper | Code | ESI - Top 1% highly cited papers
Advancing Radiograph Representation Learning with Masked Record Modeling.
Hong-Yu Zhou*, Chenyu Lian*, Liansheng Wang, Yizhou Yu.
Multimodal modeling for visual representation learning.
ICLR 2023 | Paper | Code
nnFormer: Volumetric Medical Image Segmentation via a 3D Transformer.
Hong-Yu Zhou*, Jiansen Guo*, Yinghao Zhang*, Xiaoguang Han, Lequan Yu, Liansheng Wang, Yizhou Yu.
A widely adopted baseline for 3D medical image segmentation.
TIP 2023 | Paper | Code | ESI - Top 1% highly cited papers
Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs by Comparing Image Representations.
Hong-Yu Zhou*, Shuang Yu*, Kai Ma, Cheng Bian, Chunyan Chu, Hanruo Liu, Yefeng Zheng.
MICCAI 2020 | Paper | Code

Selected Awards

  • First place in AASCE 2019, held in conjunction with MICCAI 2019. We proposed an approach to accurately estimate the spinal curvature in Adolescent Idiopathic Scoliosis (AIS).
  • First place in Segthor 2019 Challenge, held in conjunction with ISBI 2019. We proposed a method to segment organs at risk segmentation in Computed Tomography (CT) images.
  • First place in AI4Health Challenge, held by Thales group which provides solutions for over 50% of worldwide radiology examinations. In this challenge, we proposed a novel methodology to accurately detect key points in X-rays with a mean error smaller than 0.3 pixels.
  • Second place in ODIR 2019, held by Peking University.

Academic Service

I regularly serve as reviewers for following conferences and journals.
  • Conference: for ICLR, ICML, NeurIPS, CVPR, ICCV, ECCV, AAAI, MICCAI, etc.
  • Journal: for Nature, Nature Biomedical Engineering, Nature Machine Intelligence, TPAMI, TMI, MedIA, TKDE, TMM, TIP, Pattern Recognition, iScience (Cell family), etc.