Deep learning enables MV-based real-time image guided radiation therapy for prostate cancer patients

Abstract

Using MV images for real-time image guided radiation therapy (IGRT) is ideal as it does not require additional imaging equipment, adds no additional imaging dose and provides motion data in the treatment beam frame of reference. However, accurate tracking using MV images is challenging due to low contrast and modulated fields. Here, a novel real-time marker tracking system based on a convolutional neural network (CNN) classifier was developed and evaluated on retrospectively acquired patient data for MV-based IGRT for prostate cancer patients. 

MV images, acquired from 29 VMAT prostate cancer patients treated in a multi-institutional clinical trial, were used to train and evaluate a CNN-based marker tracking system. The CNN was trained using labelled MV images from 9 prostate cancer patients (35 fractions) with implanted markers. CNN performance was evaluated on an independent cohort of unseen MV images from 20 patients (78 fractions), using a Precision‐Recall curve (PRC), area under the PRC plot (AUC) and sensitivity and specificity. The accuracy of the tracking system was evaluated on the same unseen dataset and quantified by calculating mean absolute (± 1 SD) and [1st, 99th] percentiles of the geometric tracking error in treatment beam co-ordinates using manual identification as the ground truth. 

The CNN had an AUC of 0.99, sensitivity of 98.31% and specificity of 99.87%. The mean absolute geometric tracking error was 0.30 ± 0.27 and 0.35 ± 0.31 mm in the lateral and superior-inferior directions of the MV images, respectively. The [1st, 99th] percentiles of the error were [-1.03, 0.90] and [-1.12, 1.12] mm in the lateral and SI directions, respectively.

The high classification performance on unseen MV images demonstrates the CNN can successfully identify implanted prostate markers. Furthermore, the sub-millimetre accuracy and precision of the marker tracking system demonstrates potential for adaptation to real-time applications.

Artificial Intelligence in Urooncology: What We Have and What We Expect

“…It additionally provides motion data with treatment beam alignment. For this purpose, Chrystall et al [39] developed a novel realtime marker tracking system using a convolutional neural network (CNN) classifier. The CNN demonstrated high accuracy in identifying implanted prostate markers with an AUC of 0.99, a sensitivity of 98.31%, and a specificity of 99.87%.…”

Surveying the clinical practice of treatment adaptation and motion management in particle therapy

“…While rescanning and abdominal compression do not require a highly sophisticated optimised workflow, active RRMM strategies do. Automation and artificial intelligence were identified as a requirement for an efficient APT workflow, but it was not part of the survey for RRMM, even though it gains large impact for real-time motion monitoring and adaptive treatment concepts [36] , [37] , [38] .…”