Project 14:

Towards Correlation of Clinical Outcomes with Radiation Therapy Dose Distribution

Last updated: 05/5/16 at 1:00PM

Summary

Correlate clinical outcomes with refined dose distributions on critical structures

Goals:

  • To refine the datasets and infrastructure required for predicting clinical outcomes using past patient data.
  • Make the first steps towards accurate toxicity and outcome predictions in a commercial, cloud computing platform.

Students: Alex Mathews, Pranav Lakshminarayanan

Mentor(s): Dr. Todd McNutt, Dr. Russell Taylor

Background and Significance

With cancer treatments, there is a tradeoff between clinical effectiveness and deleterious side effects.

The ability to predict clinical outcomes for a particular patient (taking into account unique anatomy and condition) would allow oncologists to make more informed decisions regarding patient treatment plans.

Deliverables

  • Minimum: (Expected by March 27)
    • Set up a queryable infrastructure with anonymized patient data
    • Implementation and testing of deformable registration algorithm
  • Expected: (Expected by April 24)
    • Implementation and validation of deformable registration algorithm on the dataset
    • Design dose mapping algorithm
  • Maximum: (Expected by May 6)
    • Implementation of dose mapping algorithm

Technical Approach

The steps to achieve our goals are as follows: 1. Set up a development database within the Hopkins network

  • Store anonymized patient data, scans or binary masks, and clinical outcomes
  • Must be queryable and accessible by other devices

2. Deformable registration of critical structures

  • Currently, we are looking at the head and neck region, specifically the parotid glands
  • The deformable registration would bring images into one reference frame

3. Dose distribution mapping

  • Based on how dose is applied, generate a 3D map of received dose over the critical structure
  • Partition the organ in a way to allow for insightful analytics

Dependencies

Access to Oncospace database

  • Complete

Access to space on Hopkins network

  • Complete

Github repositories and access to Oncospace codebase

  • Complete

Milestones and Status

Projected Timeline:

Milestones:

  1. Obtain and set up server
    • Planned Date: March 12
    • Status: In progress
  2. Infrastructure and endpoint documentation
    • Planned Date: March 19
    • Status: In progress
  3. Data transfer from Oncospace database
    • Planned Date: March 27
    • Status: Planned
  4. Implement deformable registration algorithm on test data
    • Planned Date: March 27
    • Status: In progress
  5. Implement deformable registration on full dataset
    • Planned Date: April 17
    • Status: Planned
  6. Implement dose mapping algorithm on full dataset
    • Planned Date: April 30
    • Status: Planned

Reports and presentations

Project Bibliography

Bentzen, S. M., Constine, L. S., Deasy, J. O., Eisbrunch, A., Jackson, A., Marks, L. B., Haken, R. K. T., & Yorke, E. D. (2010). Quantitative analysis of normal tissue effects in the clinic (QUANTEC): An introduction to the scientific issues. International Journal of Radiation Oncology Biology Physics, 76(3), S3–S9.

Bhide SA, Newbold KL, Harrington KJ, Nutting CM. Clinical evaluation of intensity-modulated radiotherapy for head and neck cancers. The British Journal of Radiology. 2012;85(1013):487-494. doi:10.1259/bjr/85942136.

Fumbeya Marungo, Hilary Paisley, John Rhee, Todd McNutt, Scott Robertson, Russell Taylor, “Big Data Meets Medical Physics Dosimetry” (2014)

Kutcher, G., Burman, C., Brewster, L., Goitein, M., & Mohan, R. (1991). Histogram re- duction method for calculating complication probabilities for three-dimensional treatment planning evaluations. International Journal of Radiation Oncology* Biology* Physics, 21(1), 137–146.

Michael Kazhdan, Patricio Simari, Todd McNutt, Binbin Wu, Robert Jacques, Ming Chuang, and Russell Taylor, “A Shape Relationship Descriptor for RadiationTherapy Planning” Medical Image Computing and Computer-Assisted Intervention 5762/2009(12), 100–108 (2009)

Steven F. Petit, Binbin Wu, Michael Kazhdan , André Dekker, Patricio Simari, Rachit Kumar, Russell Taylor, Joseph M. Herman, Todd McNutt,” Increased organ sparing using shape-based treatment plan optimization for intensity modulated radiation therapy of pancreatic adenocarcinoma”, Radiotherapy and Oncology, 102 (2012) 38–44.

Other Resources and Project Files

Coming soon…

courses/446/2016/446-2016-14/project_14_main_page.txt · Last modified: 2016/05/05 12:47 by amathew9@johnshopkins.edu




ERC CISST    LCSR    WSE    JHU