Upcoming Planned Work:

  • AIM 1 (ILD): Ongoing investigation and re-tuning of ILD model.
  • AIM 2 (SGR): Ongoing validation of automated SGR (autoSGR) calculations.
  • AIM 3 (CBCT): Validation of pipeline following fortification.


MIRA Clinical Learning Environment (MIRA-CLE) for Lung

Translation of data science research into clinical practice will require automated pipelines that are tied into the entire treatment pathway in ways that facilitate real-time analysis. MIRACLE will help deliver value-based healthcare via better patient selection (ILD/SGR) and monitoring/adjusting treatment to decrease toxicity (CBCT).

AIM 1: Identifying underlying undiagnosed inflammatory lung disease (ILD) from CT images using deep learning.

AIM 2: Estimating individual patients’ specific tumor growth-rate (SGR) using serial CT imaging.

AIM 3: Estimating individual treatment toxicity risk using radiation treatment planning information & serial cone-beam CT images (CBCT).

Key Milestones:

  • AIM 1 (ILD): Model development phase – classification analysis complete & potential sources of model bias identified; undergoing investigation & re-tuning of model. Limited storage issue resolved.
  • AIM 2 (SGR): autoSGR validation phase – undergoing validation of automated SGR (autoSGR) calculations with dataset of manually calculated SGRs. Web framework built for quality assurance of pipeline.
  • AIM 3 (CBCT): Pipeline development phase for CBCT – fortifying pipeline for image-based marker calculation application based on a more robust framework.

Last modified: July 17, 2020