Xianjing Liu

Machine Learning; Computer Vision; Population studies; Genetics; Epidemiology;

prof_pic.png

I am currently doing my PhD at the Biomedical Imaging Group Rotterdam (BIGR) at Erasmus MC under the supervision of Prof. Wiro J. Niessen, Prof. Eppo B. Wolvius, and Dr. Gennady V. Roshchupkin. Earlier, I’ve completed my Bachelors and Masters from Shenzhen University, and gained industrial experience as a R&D engineer at Shenzhen Wisonic Co., Ltd. and a computer vision researcher at Hong Kong Polytechnic University in collaboration with Esquel Group.

I mainly work on the interpretability and confounding problems in deep learning, with applications in population-based genetic and epidemiological studies, by using multimodal data sets (e.g., 2D/3D facial images, brain MRI, genotic data) from the Generation R Study and the Rotterdam Study. I significantly contributed to the craniofacial shape analysis

I have extensive collaborations. For internal collaborations within Erasmus MC, I work closely with Manfred Kayser from department of genetic identification, and Marlies Wakkee from department of dermatology. For external collaborations, I work closely with the school of public health of Harvard University, the school of public health and primary care of Chinese University of Hong Kong, and the school of design of Hong Kong Polytechnic University. Please find my publication list for the research output from these collaborations.

I am also active in educational activities. I have supervised 6 master students from Technical University of Delft (TUD) for 9-month thesis or 10-week internship. Feel free to contact me to explore opportunities!

Github
LinkedIn
Google scholar.

news

Mar 4, 2024 My paper Predicting skin cancer risk from facial images with an explainable artificial intelligence (XAI) based approach: a proof-of-concept study is accepted by Lancet’s eClinicalMedicine!
Nov 24, 2023 My co-first author paper Automated three-dimensional analysis of facial asymmetry in patients with syndromic coronal synostosis: a retrospective study is accepted by Journal of Cranio-Maxillofacial Surgery.
Nov 1, 2023 Since November 1st 2023, I work as a postdoc at Erasmus MC. I work on medical image analysis and population gonomics, with Joyce, Christopher and Gennady!
Feb 16, 2023 My paper ‘Association between prenatal alcohol exposure and children’s facial shape’ is accepted by Human Reproduction, and has been reposted by over 400 news stories shortly after its press release.
Oct 1, 2022 My coauthor paper Worldwide distribution, risk factors, and temporal trends of testicular cancer incidence and mortality: A global analysis is accepted by European Urology Oncology.

selected publications

2024

  1. eclinm
    Predicting skin cancer risk from facial images with an explainable artificial intelligence (XAI) based approach. A proof-of-concept study
    eClinicalMedicine, Mar 2024

2023

  1. humrep
    Association between prenatal alcohol exposure and children’s facial shape. A prospective population-based cohort study
    Human Reproduction, Feb 2023
  2. arXiv
    AI-based association analysis for medical imaging using latent-space geometric confounder correction
    arXiv, Nov 2023
  3. jcms
    Automated three-dimensional analysis of facial asymmetry in patients with syndromic coronal craniosynostosis, a retrospective study
    Journal of Cranio-Maxillofacial Surgery, Nov 2023

2021

  1. miccai 2021
    Projection-Wise Disentangling for Fair and Interpretable Representation Learning. Application to 3D Facial Shape Analysis
    Lecture Notes in Computer Science, Sep 2021