Statistical Deformation Reconstruction Using Multi-organ Shape Features for Pancreatic Cancer Localization

TL;DR

This paper develops a statistical multi-organ deformation model using shape features from CT images to improve pancreatic cancer localization during respiratory motion, enhancing deformation prediction accuracy for radiotherapy.

Contribution

It introduces a multi-organ deformation library and a per-region deformation learning method that outperforms traditional models in estimating organ movements.

Findings

Achieved a mean deformation estimation error of 1.2 mm.

Demonstrated improved prediction accuracy over general models.

Validated the approach on 250 volumes from 25 patients.

Abstract

Respiratory motion and the associated deformations of abdominal organs and tumors are essential information in clinical applications. However, inter- and intra-patient multi-organ deformations are complex and have not been statistically formulated, whereas single organ deformations have been widely studied. In this paper, we introduce a multi-organ deformation library and its application to deformation reconstruction based on the shape features of multiple abdominal organs. Statistical multi-organ motion/deformation models of the stomach, liver, left and right kidneys, and duodenum were generated by shape matching their region labels defined on four-dimensional computed tomography images. A total of 250 volumes were measured from 25 pancreatic cancer patients. This paper also proposes a per-region-based deformation learning using the reproducing kernel to predict the displacement of pancreatic cancer for adaptive radiotherapy. The experimental results show that the proposed concept estimates deformations better than general per-patient-based learning models and achieves a clinically acceptable estimation error with a mean distance of 1.2 $\pm$ 0.7 mm and a Hausdorff distance of 4.2 $\pm$ 2.3 mm throughout the respiratory motion.