Machine Learning for Medical Imaging

A multi-disciplinary initiative at UW-Madison

The overall purpose of the ML4MI initiative is to foster interdisciplinary collaboration between machine learning (ML) experts and medical imaging researchers at the University of Wisconsin, in order to develop and apply state-of-the-art ML solutions to challenging problems in medical imaging. This initiative responds to rapidly growing interest in ML techniques within medical imaging research, due to the unprecedented potential to solve challenging problems in areas such as image reconstruction, image processing, and computer-aided diagnosis. ML4MI is generously supported by the UW Departments of Radiology and Medical Physics, and the Grainger Institute for Engineering.

SIGN UP FOR UPDATES

Monthly seminars

A regular seminar series began in February 2018, and includes 1) seminars describing technical developments in ML with potential biomedical applications, 2) seminars by local or external Radiology researchers, describing problems that may benefit from ML approaches and ongoing projects involving ML techniques, and 3) seminars by biomedical researchers (not in Radiology), describing pioneering experiences applying ML in their fields of study. The seminar location will alternate between ECB/WID and SMPH/WIMR. These seminars will also provide an opportunity for UW researchers to become familiar with researchers “on the other side of campus.”

This is an accordion element with a series of buttons that open and close related content panels.

2018 Seminars

Month Speaker Date/Time Location Title
Feb 2018 Rob Nowak, PhD (UW ECE) 2/15, 4 pm SMPH/HSLC Rm 1325 Machine Learning for Medical Imaging
Mar Fang Liu, PhD (UW) 3/23, 4 pm ME1106 Deep Learning: Recent Applications in Medical Imaging
Apr Tom Grist, MD (UW) 4/27, 4 pm ME1106 Artificial Intelligence in Medical Imaging: Perspective from the International Society for Strategic Studies in Radiology
May Joseph Cheng, PhD (Stanford) 5/24, 4 pm SMPH/HSLC Rm 1325 (Re)learning MRI Reconstruction
June Amod Jog, PhD (Martinos Center for Biomedical Imaging) 6/8, 4 pm SMPH/HSLC Rm 1325 Pulse Sequence Resilient Fast Brain Segmentation
Aug Vikas Singh (UW) 8/03, 4 pm SMPH/HSLC Rm 1325 Visual Relations, Relative Attributes and Graph Neural Networks
Aug Curtis Langlotz (Stanford – Radiology) 8/10, 9-10:30 am SMPH/HSLC Rm 1325 Developing a Center of Excellence for Machine Learning Research in Medical Imaging
Sept Jayashree Kalpathy-Cramer (Martinos Center for Biomedical Imaging) 9/27, 4-5pm SMPH/HSLC Rm 1345

Deep Learning in Medical Imaging-Opportunities and Challenges
Oct Polina Golland (MIT Electrical Engineering and Computer Science) 10/25, 4 pm CS 1240 Medical Image Imputation  
Nov Jerry Prince, PhD (Johns Hopkins University, Electrical and Computer Engineering) 11/15, 4 pm SMPH/HSLC Rm 1345 Single Image Super-Resolution for 2D and 3D MRI
Dec Juan Santos from HeartVista 12/14, 4 pm SMPH/HSLC Rm 1345

Autonomous MRI

 

2019 Seminars

 

Month Speaker Date/Time Location Title
Jan 2019 No Seminar Scheduled – – –
Feb James Gee, PhD (U. Penn Radiology) 2/28, 4pm SMPH/HSLC Rm 1345

Subspecialty-Level Differential Diagnoses by Machine on Clinical Brain MRI
Mar Michael Lustig, PhD (Berkeley Electrical Engineering and Computer Science) 3/28, 1pm Computer Science (CS) 1240 Low-Dimensional Models in High-Dimensional MRI
Apr Guillermo Sapiro, PhD, MSc (Duke Electrical and Computer Engineering) 4/24, 4pm

F2/401 Juhl Conference Room, UW Clinical Science Center

 Computer Vision and Data Science Transforming (Develop)Mental Health and Deep Brain Stimulation
Oct Sebastian Raschka, PhD (UW Statistics) 10/18, 4pm

1345 HSLC 

 Convolutional Neural Networks for Predicting and Hiding Personal Traits from Face Images
Nov Maciej Mazurowski, PhD (Duke Radiology) 11/15, 4pm

1345 HSLC 

 Machine Learning in Radiology

2020 Seminars

 

Month Speaker Date/Time Location Title
Jan

Jong Chul Ye, PhD (KAIST Bio and Brain Engineering)

 1/13, 4pm HSLC 1345

Understanding Geometry of Deep Learning for Medical Image Reconstruction
TBD Raúl San José Estépar, PhD (Harvard Radiology) TBD (will be rescheduled) TBD

Artificial Intelligence in Quantitative Imaging of Chronic Lung Injury: Enabling Clinical and Genetic Discovery

 

Pilot grant proposals – 2019 pilot grants awarded

The purpose of this pilot grant program is to foster interdisciplinary collaboration between ML experts and medical imaging clinicians and researchers at the University of Wisconsin’s Departments of Radiology and Medical Physics, and College of Engineering. Specific topics of interest include the development and characterization of novel ML methods with significant medical imaging applications, and the development and validation of new imaging applications for state-of-the-art ML methods. In 2018, pilot grants were awarded to the following collaborative teams: – Kevin Johnson,  Alejandro Roldan, and Shiva Rudraraju, “Patient specific hemodynamics using machine learning based fusion of MRI measurements and computational fluid dynamics” – Varun Jog and Alan McMillan, “DeepRad: An accessible, open-source tool for deep learning in medical imaging” In 2019, pilot grants were awarded to the following collaborative teams: – Sean Fain and Victor Zavala, “Blending Expert and Machine Learning Using Quantitative Chest CT and Clinical Biomarkers to Predict Asthma Severity and Outcomes” – Meghan Lubner, Varun Jog, and Dane Morgan, “Application of Machine Learning to CT characterization of Renal Cell Carcinoma“

This is an accordion element with a series of buttons that open and close related content panels.

RFA Information

This RFA seeks to fund proposals that are likely to spark enduring collaborations and lead to external funding for further research. Pilot awards are $50,000 maximum in direct costs for 12 months of support. Potential applicants are encouraged to contact Diego Hernando (dhernando@wisc.edu) or Varun Jog (vjog@wisc.edu) with questions about programmatic relevance.

DOWNLOAD THE 2019 RFA (now closed)

For any administrative questions, please contact:

ML4MI Summer Bootcamps

ML4MI  hosts bootcamps with the goal of giving participants a rapid, hands-on introduction into the principles and application of machine learning for medical imaging. This bootcamp is supported by the Grainger Institute of Engineering and the Departments of Radiology and Medical Physics. These bootcamps cover the basics of machine learning and applications for image segmentation, classification, and reconstruction. Please sign up for updates for information on future bootcamps! The source material is also available for self study. 

Bootcamp Source Materials:

ML4MI Bootcamp Github

Bootcamp Organizer Contacts:

PREVIOUS WORKSHOP: OCTOBER 5, 2018 

This workshop was held on October 5, 2018 at the UW Fluno Center. The one-day workshop featured keynote talks by leaders in the fields of ML and Radiology, a seminar on bioethics, a panel of radiologists, and poster presentations by junior researchers.

Workshop Agenda  

Contact: