Analysis of Deformation Fields in Spatio-temporal CBCT images of lungs for radiotherapy patients

TL;DR

This study analyzes deformation fields in spatio-temporal CBCT images of lung tumors during radiotherapy to predict treatment response early, using Jacobian statistics and hypothesis testing.

Contribution

It introduces a method to analyze Jacobian distributions in tumor regions for early prediction of treatment response in lung cancer patients.

Findings

Jacobian means follow a specific order in regions during treatment

Early prediction of partial response achieved with 3 weeks of data

Statistical significance confirmed with Fisher's test (p=0.043)

Abstract

Deformable registration of spatiotemporal Cone-Beam Computed Tomography (CBCT) images taken sequentially during the radiation treatment course yields a deformation field for a pair of images. The Jacobian of this field at any voxel provides a measure of the expansion or contraction of a unit volume. We analyze the Jacobian at different sections of the tumor volumes obtained from delineation done by radiation oncologists for lung cancer patients. The delineations across the temporal sequence are compared post registration to compute tumor areas namely, unchanged (U), newly grown (G), and reduced (R) that have undergone changes. These three regions of the tumor are considered for statistical analysis. In addition, statistics of non-tumor (N) regions are taken into consideration. Sequential CBCT images of 29 patients were used in studying the distribution of Jacobian in these four different regions, along with a test set of 16 patients. Statistical tests performed over the dataset consisting of first three weeks of treatment suggest that, means of the Jacobian in the regions follow a particular order. Although, this observation is apparent when applied to the distribution over the whole population, it is found that the ordering deviates for many individual cases. We propose a hypothesis to classify patients who have had partial response (PR). Early prediction of the response was studied using only three weeks of data. The early prediction of response of treatment was supported by a Fisher's test with odds ratio of 5.13 and a p-value of 0.043.