Predicting successful clinical candidates for fiducial-free lung tumor tracking with a deep learning binary classification model

TL;DR

This study develops a deep learning model that accurately predicts which lung cancer patients are suitable for fiducial-free tumor tracking, potentially streamlining treatment planning by replacing the traditional simulation process.

Contribution

The paper introduces a novel deep learning classification approach that predicts lung tumor trackability directly from DRR images, eliminating the need for the Lung Optimized Treatment simulation.

Findings

Achieved 100% accuracy in classifying trackable vs. untrackable lesions.

Successfully tested five different neural network architectures.

Demonstrated potential to replace the LOT simulation process.

Abstract

The CyberKnife system is a robotic radiosurgery platform that allows the delivery of lung SBRT treatments using fiducial-free soft-tissue tracking. However, not all lung cancer patients are eligible for lung tumor tracking. Tumor size, density and location impact the ability to successfully detect and track a lung lesion in 2D orthogonal X-ray images. The standard workflow to identify successful candidates for lung tumor tracking is called Lung Optimized Treatment (LOT) simulation, and involves multiple steps from CT acquisition to the execution of the simulation plan on CyberKnife. The aim of the study is to develop a deep learning classification model to predict which patients can be successfully treated with lung tumor tracking, thus circumventing the LOT simulation process. Target tracking is achieved by matching orthogonal x-ray images with a library of digital radiographs reconstructed from the simulation CT scan (DRRs). We developed a deep learning model to create a binary classification of lung lesions as being trackable or untrackable based on tumor template DRR extracted from the CyberKnife system, and tested five different network architectures. The study included a total of 271 images (230 trackable, 41 untrackable) from 129 patients with one or multiple lung lesions. 80% of the images were used for training, 10% for validation, and the remaining 10% for testing. For all 5 convolutional neural networks, the binary classification accuracy reached 100% after training, both in the validation and the test set, without any false classifications. A deep learning model can distinguish features of trackable and untrackable lesions in DRR images, and can predict successful candidates for fiducial-free lung tumor tracking.