PROJECT TITLE :

Contextual Atlas Regression Forests: Multiple-Atlas-Based Automated Dose Prediction in Radiation Therapy

ABSTRACT:

Radiation therapy is an integral half of cancer treatment, but up to now it remains highly manual. Plans are created through optimization of dose volume objectives that specify intent to minimize, maximize, or achieve a prescribed dose level to clinical targets and organs. Optimization is NP-laborious, requiring highly iterative and manual initialization procedures. We tend to present an indication-of-concept for a method to automatically infer the radiation dose directly from the patient's treatment planning image based on a database of previous patients with corresponding clinical treatment plans. Our technique uses regression forests augmented with density estimation over the most informative features to be told an automatic atlas-selection metric that is tailored to dose prediction. We tend to validate our approach on 276 patients from 3 clinical treatment arrange sites (whole breast, breast cavity, and prostate), with an overall dose prediction accuracies of 78.sixty eight%, sixty four.76p.c, 86.83% beneath the Gamma metric.