Clinical suitability of deep learning based synthetic CTs for adaptive proton therapy of lung cancer

Abstract

Purpose Adaptive proton therapy (APT) of lung cancer patients requires frequent volumetric imaging of diagnostic quality. Cone‐beam CT (CBCT) can provide these daily images, but x‐ray scattering limits CBCT‐image quality and hampers dose calculation accuracy. The purpose of this study was to generate CBCT‐based synthetic CTs using a deep convolutional neural network (DCNN) and investigate image quality and clinical suitability for proton dose calculations in lung cancer patients. Methods A dataset of 33 thoracic cancer patients, containing CBCTs, same‐day repeat CTs (rCT), planning‐CTs (pCTs), and clinical proton treatment plans, was used to train and evaluate a DCNN with and without a pCT‐based correction method. Mean absolute error (MAE), mean error (ME), peak signal‐to‐noise ratio, and structural similarity were used to quantify image quality. The evaluation of clinical suitability was based on recalculation of clinical proton treatment plans. Gamma pass ratios, mean dose to target volumes and organs at risk, and normal tissue complication probabilities (NTCP) were calculated. Furthermore, proton radiography simulations were performed to assess the HU‐accuracy of sCTs in terms of range errors. Results On average, sCTs without correction resulted in a MAE of 34 ± 6 HU and ME of 4 ± 8 HU. The correction reduced the MAE to 31 ± 4HU (ME to 2 ± 4HU). Average 3%/3 mm gamma pass ratios increased from 93.7% to 96.8%, when the correction was applied. The patient specific correction reduced mean proton range errors from 1.5 to 1.1 mm. Relative mean target dose differences between sCTs and rCT were below ± 0.5% for all patients and both synthetic CTs (with/without correction). NTCP values showed high agreement between sCTs and rCT (<2%). Conclusion CBCT‐based sCTs can enable accurate proton dose calculations for APT of lung cancer patients. The patient specific correction method increased the image quality and dosimetric accuracy but had only a limited influence on clinically relevant parameters.

Deep learning methods for enhancing cone‐beam CT image quality toward adaptive radiation therapy: A systematic review

“…Proton 45 and photon 52 abdominal plans were validated once, and a single‐photon lung plan was validated for the stricter 2%/2‐mm criteria 49 . However, no study has investigated sCT accuracy for proton breast plans, whereas the single study that analyzed proton lung plans failed to demonstrate sufficient dosimetric accuracy 59 …”

“…The lung site was well validated for photon plans 40,42,49 for a 3%/3-mm criteria; however, two investigations noted failing 2%/2-mm rates. A single study by Thummerer et al 59 investigated the lung site for proton ART and reported passing rates only for 3%/3-mm criteria.…”

“…Another common technique was to replace voxels outside the patient body contour with air to minimize the impacts from nonanatomical structures. 19,36,37,42,45,46,50,53,56,57,59,60…”

“…49 However, no study has investigated sCT accuracy for proton breast plans, whereas the single study that analyzed proton lung plans failed to demonstrate sufficient dosimetric accuracy. 59 Automatic segmentation is an important intermediary step toward the development of online CBCT-guided ART workflows. Although not the focus of this review, several authors did analyze the performance of sCTs in auto-segmentation tasks.…”

Management of Motion and Anatomical Variations in Charged Particle Therapy: Past, Present, and Into the Future

“…Van der Heyden et al presented a single detector, multi-energy proton radiography system which relied on artificial intelligence to filter out proton scatter (198). In addition, multiple studies have been reported which utilize deep learning as a tool to facilitate accurate proton dose calculation from daily CBCT images (121,(199)(200)(201). Elmahdy et al also reported on a convolutional neural network (CNN)-based model for robust, automatic contour propagation in prostate cancer for online adaptive proton therapy (202).…”