About me

Welcome! This is Jianghao, currently working toward my Master degree in Robotics Engineering with the School of Mechanical and Electrical Engineeringe, University of Electronic Science and Technology of China, advised by Prof. Guotai Wang and Prof. Shaoting Zhang . My research focuses on developing novel methods to reduce the annotation efforts for computer-aided detection and diagnosis. This includes, but is not limited to, techniques such as Domain Adaptation, Test Time Adaptation, and Self-supervised learning.

News

  • [Apr, 2024] Our paper “FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation” has been accepted by IEEE TMI.
  • [Mar, 2024] I became a reviewer for MICCAI 2024, as a master’s student!
  • [Feb, 2024] Our paper “RPL-SFDA: Reliable Pseudo Label-guided Source-free Cross-modality Adaptation for NPC GTV Segmentation” has been accepted by ISBI 2024
  • [Oct, 2023] I have been awarded the China National Scholarship! (Link)
  • [Sep, 2023] Our paper “UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation” has been accepted by IEEE TMI. (Link)
  • [Jun, 2023] Our paper “A novel one-to-multiple unsupervised domain adaptation framework for abdominal organ segmentation” has been accepted by MedIA. (Link)
  • [Apr, 2023] Our paper “TISS-net: Brain tumor image synthesis and segmentation using cascaded dual-task networks and error-prediction consistency” has been accepted by Neurocomputing. (Link)
  • [Feb, 2023] Our paper “UPL-TTA: Uncertainty-Aware Pseudo Label Guided Fully Test Time Adaptation for Fetal Brain Segmentation” has been accepted by IPMI 2023. (Link)
  • [Dec, 2022] I have joined Shanghai AI Lab(Link) as a research intern.
  • [Sep, 2022] 1 joint paper “CrossMoDA 2021 challenge: Benchmark of cross-modality domain adaptation techniques for vestibular schwannoma and cochlea segmentation” has been accepted by MedIA. (Link)
  • [Jan, 2022] My first paper “FPL-UDA: Filtered Pseudo Label-Based Unsupervised Cross-Modality Adaptation for Vestibular Schwannoma Segmentation” has been accepted by ISBI 2022 (Oral Presentation). (Link)(code)