Medical imaging and image restoration for clinical applications

In this research topic, we are working on developing state-of-the-art machine learning-based imaging and image restoration techniques for clinical applications in Radiation Therapy (RT) and diagnosis. Notably, RT heavily relies on multi-modality imaging for optimal cancer patient treatment. Medical imaging plays a critical role in every step of the RT workflow, including from patient staging, tumor target and organ-at-risk delineation, radiation treatment planning, treatment plan delivery, and treatment response assessment. We have developed novel image restoration and processing algorithms to improve clinical practice in RT and disease diagnosis, which include organ-at-risk contouring error detection, tumor delineation, internal organ motion tracking, and metal artifact reduction in CT images, 3D blood vessel segmentation, and brain tissue segmentation. In addition, we have conducted novel medical imaging and image processing methods to solve the problems outside the clinical imaging field, such as automatic cell counting in microscope images.

1. DBM-based heart motion tracking

2. Head neck upper-airway motion tracking

3. Active learning for medical image annotation

4. OCT image segmentation by use of CNN

5. OAR contouring error detection in radiation therapy

6. Automatic cell counting in microscopy images by use of density regression

7. Multi-loss based COVID-19 classification with chest X-ray images

 

Related publications

  1. Zong Fan, Shenghua He, Su Ruan, Xiaowei Wang, and Hua Li “Deep learning-based multi-class COVID-19 classification with x-ray images“, Proc. SPIE 11598, Medical Imaging 2021: Image-Guided Procedures, Robotic Interventions, and Modeling, 1159813 (15 February 2021).
  2. Shenghua He, Kyaw Thu Minn, Lilianna Solnica-Krezel, Mark A. Anastasio, Hua Li*, “ Deeply-Supervised Density Regression for Automatic Cell Counting in Microscopy Images”, Medical Image Analysis, 2020.
  3. Shenghua He, Jian Wu, Chunfeng Lian, H. Michael Gach, Sasa Mutic, Walter Bosch, Jeff Michalski, Hua Li*, “ An Adaptive Low-Rank Modeling-based Active Learning Method for Medical Image Annotation”, Innovation and Research in BioMedical Engineering (IRBM), 2020.
  4. Chunfeng Lian, Su Ruan, Thierry Denoeux, Hua Li, and Pierre Vera, “Joint Tumor Segmentation in PET-CT Images using Co-Clustering and Fusion based on Belief Functions”, IEEE Trans. on Image Processing, 2018, 28(2):755-766.
  5. Jian Wu, Thomas Mazur, Su Ruan, Chunfeng Lian, Nalini Daniel, Hilary Lashmett, Laura Ochoa, Imran Zoberi, Mark Anastasio, Michael Gach, Sasa Mutic, Maria Thomas, Hua Li*, “A Deep Boltzmann Machine-Driven Level Set Method for Heart Motion Tracking Using Cine MRI Images“, Medical Image Analysis, 2018, 47:68-80.doi: 10.1016/j.media.2018.03.015.
  6. Chunfeng Lian, Su Ruan, Thierry Denoeux, Hua Li, Pierre Vera, “Spatial Evidential Clustering with Adaptive Distance Metric for Tumor Segmentation in FDG-PET Images“, IEEE Trans. on Biomedical Engineering, 2018, Jan; 65(1):21-30.
  7. Hua Li*, Hsin-Chen Chen, Steven Dolly, Harold Li, Benjamin Fischer-Valuck, James Victoria, James Dempsey, Su Ruan, Mark A. Anastasio, Rojano Kashani, Olga Green, Vivian Rodriguez, Hiram Gay, Wade Thorstad, Sasa Mutic, “An Integrated-Model Driven Method for In-treatment Upper Airway Motion Tracking using Cine MRI in Head & Neck Radiation Therapy“, Medical Physics, 2016, Vol.43, No. 8, pp: 4700-4710.
  8. Hua Li*, Steven Dolly, Hsin-Chen Chen, Mark A. Anastasio, Daniel A. Low, Harold H. Li, Jeff M. Michalski, Wade L. Thorstad, Hiram Gay, Sasa Mutic, “A Comparative Study Based on Image Quality and Clinical Task Performance for CT Reconstruction Algorithms in Radiotherapy“, Journal of Applied Clinical Medical Physics, 2016, Vol.17, No.4, pp: 377-390.
  9. Hsin-Chen Chen, Jun Tan, Steven Dolly, James Kavanaugh, Mark A. Anastasio, Daniel A. Low, H. Harold Li, Michael Altman, Hiram Gay, Wade Thorstad, Sasa Mutic, Hua Li*, “Automated Contouring Error Detection Based on Supervised Geometric Attribute Distribution Models for Radiation Therapy: A General Strategy“, Medical Physics, 2015, Vol. 42, No. 2, pp:1048-59.
  10. Hua Li*, Wade L. Thorstad, Kenneth J. Biehl, Richard Laforest, Yi Su, Kooresh I. Shoghi, Eric D. Donnelly, Daniel A. Low, Wei Lu, “A Novel PET Head and Neck Tumor Delineation Approach based on Adaptive Region-Growing and Dual-front Active Contours: Simulation and Phantom Studies“, Medical Physics, 2008, Vol. 35, No. 8, pp:3711-3721.
  11. Deshan Yang, Hua Li, Daniel Low, Joseph Deasy, Issam Naqa, “A fast inverse consistent deformable image registration method based on symmetric optical flow computation“, Physics in Medicine and Biology, 2008, Vol.53, No.21, pp:6143-6165.
  12. Hua Li, Anthony Yezzi, “Vessels as 4D Curves: Global Minimal 4D Paths to 3D Tubular Structure Extraction“, IEEE Transactions on Medical Imaging, 2007, Vol.26, No.9, pp:1213-1223.
  13. Hua Li, Anthony Yezzi, “Local or Global Minima: Flexible Dual-Front Active Contours“, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, Vol.29, No.1, pp:1-14.
  14. Hua Li, Anthony Yezzi, Laurent Cohen, “A Novel 3D Brain Tissue Segmentation Approach Using Dual-Front Active Contours with Optional User-Interaction“, Special Issue: Recent Advances in Mathematical Methods for the Analysis of Biomedical Images, International Journal of Biomedical Imaging, Volume 2006 (2006), Article ID 53186. (Invited Paper)