Spring 2024

CIG is looking for motivated WashU students for the following projects. We have a history of mentoring undergraduate and graduate students interested in research, with many of our alumni becoming PhD students in top programs (including WashU) and many projects leading to publications in top venues (see below). If you are interested in a given project, please apply by emailing your resume and a short description of your interests to the project supervisor.

Self-supervised Learning for Ptychographic Image Reconstruction

Status: available
Description: Ptychography is an imaging technique that captures multiple overlapping snapshots of a sample, illuminated coherently by a moving localized probe. Deep learning has gained popularity in ptychographic image reconstruction due to its excellent performance. However, deep learning methods usually require high quality ground truths as training targets, limiting its applicability in practice. This project aims to develop a novel self-supervised learning method for ptychographic image reconstruction.
Supervision: Weijie Gan (weijie.gan@wustl.edu), Ulugbek Kamilov
Areas: Scientific Imaging, Deep Learning

Deep Learning-Based Registration for Mammography

Status: available
Description: Mammography is a crucial tool in breast cancer screening, but its effectiveness depends heavily on the accurate comparison of current and previous scans. Image registration, the process of aligning several images, is essential in this context. The primary goal of this project is to develop a deep learning-based model for the registration of mammography images. This system aims to improve the accuracy and efficiency of breast cancer screening by enhancing the comparison of multiple mammograms.
Supervision: Shirin Shoushtari (s.shirin@wustl.edu), Aimilia Gastounioti , Ulugbek Kamilov
Areas: Medical Imaging, Deep Learning

Optimized Restoration Priors for Computational Imaging

Status: available
Description: Recent research has shown the potential of using restoration networks, such as image deblurring networks, as implicit priors for imaging inverse problems. Despite the powerful performance in a range of imaging problems, the selection of the restoration networks is heuristic. The goal of this project is to explore the optimal restoration priors for specific imaging problems.
Supervision: Weijie Gan (weijie.gan@wustl.edu), Ulugbek Kamilov
Areas: Computational Imaging, Image Restoration

Training Priors for Plug-and-Play Methods

Status: available
Description: Plug-and-play methods are a popular approach in computational imaging that use a learned prior in order to solve imaging inverse problems. The standard approach trains a neural network as a Gaussian denoiser to be the prior. This project will explore a new approach when training such denoisers. The student will need to train and test multiple models across several imaging inverse problems to determine its viability.
Supervision: Edward Chandler (e.p.chandler@wustl.edu), Ulugbek Kamilov
Areas: Computational Imaging, Deep Learning

Deep Learning for Quantitative MRI

Status: available
Description: Quantitative MRI refers to a set of techniques to determine quantitatively tissue parameters from MRI data. The goal of this project is to develop a practical deep learning approaches for high-quality quantitative MRI parameter estimation.
Supervision: Weijie Gan (weijie.gan@wustl.edu), Ulugbek Kamilov
Areas: Medical Imaging, Deep Learning

Deep Learning for MRI Denoising

Status: reserved (Kellan Duan)
Description: Noise is one of the fundamental limiting factors in magnetic resonance imaging (MRI). The ability to reduce noise in MRI can significantly expand its applicability and comfort to patients. The goal of this project is to design novel deep learning methods for MRI denoising. This project will be conducted in collaboration with Prof. Dmitriy Yablonskiy in the school of medicine.
Supervision: Yuanhao Wang (yuanhao@wustl.edu), Ulugbek Kamilov
Areas: Medical Imaging, Deep Learning

Accelerated Data Acquisition for Quantitative MRI

Status: reserved (Johnny Wu and Rosie Tang)
Description: Quantitative MRI (qMRI) refers to a set of techniques to determine quantitatively tissue parameters from MRI data. However, qMRI is often time consuming, limiting its applicability. The goal of this project is to explore deep learning approaches for accelerating data acquisition in qMRI, while maintaining the desired quality. This project will be conducted in collaboration with Prof. Dmitriy Yablonskiy in the school of medicine.
Supervision: Yuanhao Wang (yuanhao@wustl.edu), Ulugbek Kamilov
Areas: Medical Imaging, Deep Learning

Generative Models for Imaging Inverse Problems

Status: reserved (Harry Gao)
Description: In recent years, the field of computational imaging has witnessed a surge in the adoption of deep generative models. Among these, the denoising diffusion model stands out as a promising approach for solving imaging inverse problems. The objective of this project is not only to develop an innovative diffusion model specifically designed for these inverse problems but also to understand their robustness. Our aim is to provide both empirical evidence and theoretical foundations that underscore its robustness and applicability in real-world scenarios.
Supervision: Weijie Gan (weijie.gan@wustl.edu), Ulugbek Kamilov
Areas: Medical Imaging, Deep Learning

Deformation Compensated Learning

Status: reserved (Chicago Park)
Description: The goal of this project is to explore self-supervised deep learning under object motion. Recently, CIG has developed Deformation Compensated Learning (DeCoLearn) as a novel technique for such scenarios. The goal of this project is to extend DeCoLearn to be more applicable in medical imaging.
Supervision: Weijie Gan (weijie.gan@wustl.edu), Ulugbek Kamilov
Areas: Computational Imaging, Deep Learning

Deep Learning for Blind Inverse Problems

Status: reserved (Haoyu Zhang)
Description: Blind imaging inverse problem is an important topic in medical imaging, where both image and forward operator are unknown and needs to be estimated. The goal of this project is to investigate a new deep learning method for blind imaging inverse problem.
Supervision: Weijie Gan (weijie.gan@wustl.edu), Ulugbek Kamilov
Areas: Computational Imaging, Deep Learning

Vidio restoration for two-photon microscopy

Status: reserved (David Wang)
Description: The project seeks to improve the efficiency of existing non-deep-learning methods in Two-Photon Microscopy analysis. A primary challenge in Two-Photon Microscopy is the prevalence of motion artifacts that compromise data integrity while capturing moving subjects. The goal is to develop a deep learning-based solution to improve video quality by effectively correcting these motion artifacts.
Supervision: Weijie Gan (weijie.gan@wustl.edu), Ulugbek Kamilov
Areas: Computational Microscopy, Deep Learning

Deep learning for diagnosis of post-traumatic elbow disease

Status: reserved (Vincent Siu)
Description: Deep learning may revolutionize the study of musculoskeletal conditions by automating the evaluation pipeline. This project seeks to develop tissue and modality-specific DL algorithms for automatic evaluation of disease stage and explore multi-modal in post-traumatic elbow conditions using histology, computed tomography, and magnetic resonance imaging. This project is in collaboration with the Musculoskeletal Soft Tissue Laboratory.
Supervision: Weijie Gan (weijie.gan@wustl.edu), Ulugbek Kamilov
Areas: Biomedical Imaging, Deep Learning

Learning for Small Angle Neutron Scattering (SANS)

Status: reserved (Naveen Asokan)
Description: SANS is a widely used technique to investigate material’s structure at the atomic scales. Long exposure to the neutron beam is often necessary to capture detailed structural information in SANS. The prolonged measurement time required for the acquisition poses a challenge in various applications such as real-time reaction monitoring. The goal of this project is to develop deep learning techniques to accelerate SANS experiments.
Supervision: Shirin Shoushtari (s.shirin@wustl.edu), Marcus Foston, Ulugbek Kamilov
Areas: Scientific Imaging, Deep Learning

Learning the Development Patterns of Cancer

Status: reserved (Harry Mellow)
Description: Modern medical imaging techniques such as PET/CT offer us an informative visual insight of lesions in vivo. With several following-up scans for the same patient suffering from cancer over time, we want to know what the average trend of cancer development is, where the cancer cells will attack next and further, and whether the current treatment slows down cancer development. The goal of this project is to develop a practical deep learning approach to capture development patterns for cancer.
Supervision: Flora Sun (zhixin.sun@wustl.edu), Ulugbek Kamilov
Areas: Medical Imaging, Deep Learning

Spring 2023

  • Noise Adaptive Deep Denoisers for Imaging (E. McMillian, Y. Hu, and U. S. Kamilov)
  • Interactive Digit Recognition for ML Education (J. Ti, F. Sun, and U. S. Kamilov)
  • Detecting Multiple Myeloma using Deep Image Analysis (X. Yang, F. Sun, and U. S. Kamilov)
  • Deep Learning for 3D Quantitative Brain MRI (K. Prinos, Y. Hu, and U. S. Kamilov)
  • Machine Learning Biomarkers for Fetal Growth Restrictions (Z. Xiang, Y. Hu, and U. S. Kamilov)
  • Deep Learning for Digital Mammography (E. Sul, S. Shoushtari, and U. S. Kamilov)
  • Deep Learning for the Next-Gen Scientific Imaging (J. Yao, W. Zhang, S. Shoushtari, and U. S. Kamilov)
  • Deep learning for diagnosis of post-traumatic elbow disease (V. Siu, W. Gan, and U. S. Kamilov)
  • Deformation-Compensated Learning (C. Park, W. Gan, and U. S. Kamilov)
  • Continuous Regualarier for Inverse Problems (N. Huang, W. Gan, and U. S. Kamilov)
  • Breast Cancer Risk Assessment using Machine Learning (C. Jin, S. Shoushtari, and U. S. Kamilov)
  • Robust deep learning for computational imaging (E. Chandler, J. Liu, and U. S. Kamilov)
  • Efficient and effective data-driven image representations (H. Gao, W. Gan, and U. S. Kamilov)
  • Deep learning for the next-generation microscopy (Y. Wang, J. Liu, and U. S. Kamilov)

Fall 2022

  • Deep learning for the next-generation microscopy (Y. Wang, J. Liu, and U. S. Kamilov)
  • Deep learning for diagnosis of post-traumatic elbow disease (H. T. James, W. Gan, and U. S. Kamilov)
  • Memory and computationally efficient deep learning (Z. Zou, J. Liu, and U. S. Kamilov)
  • Efficient and effective data-driven image representations (H. Gao, W. Gan, and U. S. Kamilov)
  • Robust deep learning for computational imaging (E. Chandler, J. Liu, and U. S. Kamilov)
  • Breast Cancer Risk Assessment using Machine Learning (C. Jin, S. Shoushtari, and U. S. Kamilov)
  • Continuous Regualarier for Inverse Problems (N. Huang, W. Gan, and U. S. Kamilov)
  • Deformation-Compensated Learning (C. Park, W. Gan, and U. S. Kamilov)
  • Deep Learning for Digital Mammography (E. Choi, S. Shoushtari, and U. S. Kamilov)
  • Quantitative Brain MRI using Deep Learning (H. Li, Y. Hu, and U. S. Kamilov)
  • Image Restoration using Generative Models (Y. Ma, S. Shoushtari, and U. S. Kamilov)
  • Deep Complex Neural Networks for Imaging (M. Yu, W. Gan, and U. S. Kamilov)

Spring 2022

  • Detecting multiple myeloma using deep image analysis (J. Hu, F. Sun, and U. S. Kamilov)
  • Deep learning for diagnosis of post-traumatic elbow disease (H. T. James, W. Gan, and U. S. Kamilov)
  • Deep learning for the next-generation microscopy (X. Chen, J. Liu, and U. S. Kamilov)
  • Learning strategies for MRI reconstruction (H. Gao, W. Gan, and U. S. Kamilov)
  • Memory and computationally efficient deep learning (Z. Zou, J. Liu, and U. S. Kamilov)
  • Memory-efficient deep image restoration (J. Zeng, X. Xu, and U. S. Kamilov)
  • Inhomogeneity correction in quantitative brain MRI (E. Chandler, X. Xu, and U. S. Kamilov)
  • Deep learning for calf muscle and fat measurement (Y. Luo, X. Xu, and U. S. Kamilov)

Fall 2021

  • Regularization by artifact removal for PET (J. Choi, W. Gan, and U. S. Kamilov)
  • Deep learning for diagnosis of post-traumatic elbow disease (Y. Yuan, W. Gan, M. David, S. Lake, and U. S. Kamilov)
  • Implementing optimization algorithms in Jupyter Notebook (X. Huang and U. S. Kamilov)
  • Deep learning for abdominal visceral and subcutaneous fat measurement (T. Lee, X. Xu, P. Commean, and U. S. Kamilov)
  • Deep learning for calf muscle and fat measurement (Y. Luo, X. Xu, P. Commean, and U. S. Kamilov)
  • Synthesizing high-resolution videos using deep learning (W. Shangguan, Y. Sun, and U. S. Kamilov)
  • Asynchronous plug-and-play priors with theoretical guarantees (H. Qin, Y. Sun, and U. S. Kamilov)
  • Learning Optimal Sampling Strategies for MRI (D. Jin, W. Gan, and U. S. Kamilov)
  • Image Transformers for Computational Imaging (Z. Zhang, J. Liu, and U. S. Kamilov)
  • Detecting multiple myeloma using deep image analysis (F. Sun, W. Gan, M. Shokeen, and U. S. Kamilov)
  • Inhomogeneity correction in quantitative brain MRI (E. Chandler, X. Xu, and U. S. Kamilov)

Spring 2021

Fall 2020

  • Deep Learning for quantitative brain imaging (E. Chandler, X. Xu, Y. Sun, and U. S. Kamilov)
  • Cycle GAN for quantitative MRI (Y. Li, X. Xu, and U. S. Kamilov)
  • Training robust convolutional neural networks (R. Liu, Y. Sun, and U. S. Kamilov)
  • Implementing CNNs with Tensorflow 2.0 (Z. Wang, Y. Sun, and U. S. Kamilov)
  • Autocalibration for regularization by denoising (M. Xie, Y. Sun, and U. S. Kamilov)

Spring 2020

  • Machine learning for 4D MRI (W. Gan, H. An, U. S. Kamilov)
  • Proximal Optimization for Computerized Tomography (R. Schurz, J. Liu, U. S. Kamilov)
  • End-to-End Training of VAE-GAN Priors (G. Meng, J. Liu, U. S. Kamilov)
  • Design of GAN Prios for Iterative Algorithms (A. Bani, J. Liu, U. S. Kamilov)
  • Recovery Experiments for Deep Learning (J. Liu, Y. Sun, U. S. Kamilov)
  • Autocalibration for Regularization by Denoising (M. Xie, Y. Sun, and U. S. Kamilov)
  • Stochastic Algorithms using Deep Priors (Z. Wu, Y. Sun, U. S. Kamilov)
  • Fast Automatic Focal Plane Selection for Brightfield Microscopy using Machine Learning (Y. Song, X. Xu, N. Laird, Z. Pincus, U. S. Kamilov)
  • Nonlocal Learning for Image Restoration (Y. Li, X. Xu, U. S. Kamilov)
  • Motion-artifact Correction in Quantitative MRI (H. Tang, X. Xu, U. S. Kamilov)

Fall 2019

  • Motion artifact reduction in quantitative brain MRI (N. Woythaler, X. Xu, U. S. Kamilov)
  • Large-Scale Optimization for Computational Imaging (Y. Jia, U. S. Kamilov)
  • Generative Adversarial Networks for Image Restoration (R. Suzuki, X. Xu, U. S. Kamilov)
  • Adversarially robust classifiers for image reconstruction (E. Tang, X. Xu, U. S. Kamilov)
  • Stochastic Algorithms using Deep Priors (Z. Wu, Y. Sun, U. S. Kamilov)
  • Asynchronous large-scale optimization for imaging (Y. Sun, Y. Sun, U. S. Kamilov)
  • Next generation Cryo-EM imaging (M. Xie, Y. Sun, U. S. Kamilov)
  • Computational methods for quantitative brain MR imaging (M. Torop, Y. Sun, U. S. Kamilov)

Spring 2019

  • Deep Single-Molecule Super-Resolution Imaging (S. Xu, Y. Sun, H. Mazidi, M. Lew, U. S. Kamilov)
  • Learning for material imaging with light (Z. Wu, Y. Sun, U. S. Kamilov)
  • Regularization with ConvNets (J. Liu, Y. Sun, U. S. Kamilov)

Fall 2018

  • Regularization with ConvNets (J. Liu, Y. Sun, U. S. Kamilov)
  • Learning for 3D computational imaging (W. Gan, X. Xu, U. S. Kamilov)
  • Convolutional dictionary learning for image reconstruction (F. Long, X. Xu, U. S. Kamilov)
  • Unsupervised deep image learning (H. Zou, Y. Sun, U. S. Kamilov)
  • Distributed algorithms for nonconvex stochastic optimization (M. Abijaoude, U. S. Kamilov)
  • Image restoration with GANs (F. Zhai, Y. Sun, U. S. Kamilov)
  • Learning for MRI (J. Xing, X. Xu, U. S. Kamilov)
  • Learning for material imaging with light (Z. Wu, Y. Sun, U. S. Kamilov)
  • Dictionary Learning for Fourier Ptychographic Microscopy (S. Xu, X. Xu, U. S. Kamilov)