Xing Laboratory

Medical Physics

Our vision is to be a premier laboratory of artificial intelligence (AI), biomedical physics, and bioengineering in the world. We are embarking systematic research on various important issues in these fields by combining our strengths in medical physics, engineering, biology, and medicine. The following are a few highlights of our current research focuses:

Development of novel AI strategies for disease diagnosis, treatment planning, therapeutic guidance, prognosis and outcome assessment

 

Deep learning-driven image reconstruction and analysis, as well the clinical implementation of the novel quantitative image processing techniques

 

Nanotechnology and molecular/biological imaging for precision medicine





 

 

Lei Xing, Ph.D. Jacob Haimson Professor

The Director of Medical Physics Division, Core Faculty at MIPS with over 250 refereed publications.

Profile | Research | Publications

 

 

Lab Updates

10/1/20: Our work on using AI to guide colorectal cancer care decision has been featured in Stanford Medicine and Bio-X news!

9/17/20: A new book edited by Lei Xing, Maryellen L. Giger, and James K. Min titled Artificial Intelligence in Medicine: Technical Basis and Clinical Applications has been published and is now available for purchase on Amazon.

9/14/20: Our manuscript titled "A data-driven dimensionality-reduction algorithm for the exploration of patterns in biomedical data," written by Md Tauhidul Islam and Lei Xing, has been accepted for publication in Nature Biomedical Engineering. Stay tuned!

9/3/20: Our research on using a machine learning strategy to predict survival in colorectal cancer has been published in Gut, a premier journal of gastroenterology. The model not only accurately predicts survival 10 years after a diagnosis of colorectal cancer, but also affords the reasons that explain the prediction. The model has been deployed online at https://colorectalcancersurvival.stanford.edu/.

7/12/20: Two of our abstracts were accepted to the AAPM Science Council Session at the 2020 AAPM Annual Meeting:

  1.  

    SU-CD-TRACK 2-6: Deep-Learning Assisted Automatic Segmentation of Interstitial Needles in 3D Ultrasound Based High Dose-Rate Brachytherapy of Prostate Cancer. Contributors: B Han, F Wang, L Xing, H Bagshaw, M Buyyounouski.
  2.  

    SU-CD-TRACK 2-10: Deriving Ventilation Imaging From Free Breathing Proton MRI Via Deep Convolutional Neural Network. Contributors: D Capaldi, F Guo, L Xing, G Parraga.

An AI paper by Ma M, Kavolchuk N, Buyyounoski M, Xing L, Yang Y entitled “Dosimetric Features-Driven Machine Learning Model for DVHs Prediction in VMAT Treatment Planning” (Med Phys 46, 857-867, 2019. PMID: 30536442) is listed as the Top Download of the Year in Medical Physics! Congrats the team!


The collaborative work on using AI for real-time bladder tumor detection (E. Shkolyar, X. Jia, T.C. Chang, D. Trivedi, K. E. Mach, M. Meng, L. Xing, J. Liao, European Urology 76, 714-718, 2019) won the best video at the 2020 Annual Meeting of American Urological Association (AUA).


Our recent work on using deep learning for CT image reconstruction with only a single projection is published in Nature Biomedical Engineering (Shen L, Zhao W, Xing L, Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning, Nature Biomedical Engineering 3, 880-888, 2019).