Adaptive Weighted Log Subtraction Based on Neural Networks for Markerless Tumor Tracking Using Dual-energy Fluoroscopy

Overview

Journal Med Phys

Specialty Biophysics

Date 2019 Dec 5

PMID 31797397

Citations 1

Authors

Maksat Haytmyradov

Hassan Mostafavi

Roberto Cassetta

Rakesh Patel

Murat Surucu

Liangjia Zhu

John C Roeske

Affiliations

Soon will be listed here.

Abstract

Purpose: To present a novel method, based on convolutional neural networks (CNN), to automate weighted log subtraction (WLS) for dual-energy (DE) fluoroscopy to be used in conjunction with markerless tumor tracking (MTT).

Methods: A CNN was developed to automate WLS (aWLS) of DE fluoroscopy to enhance soft tissue visibility. Briefly, this algorithm consists of two phases: training a CNN architecture to predict pixel-wise weighting factors followed by application of WLS subtraction to reduce anatomical noise. To train the CNN, a custom phantom was built consisting of aluminum (Al) and acrylic (PMMA) step wedges. Per-pixel ground truth (GT) weighting factors were calculated by minimizing the contrast of Al in the step wedge phantom to train the CNN. The pretrained model was then utilized to predict pixel-wise weighting factors for use in WLS. For comparison, the weighting factor was manually determined in each projection (mWLS). A thorax phantom with five simulated spherical targets (5-25 mm) embedded in a lung cavity, was utilized to assess aWLS performance. The phantom was imaged with fast-kV dual-energy (120 and 60 kVp) fluoroscopy using the on-board imager of a commercial linear accelerator. DE images were processed offline to produce soft tissue images using both WLS methods. MTT was compared using soft tissue images produced with both mWLS and aWLS techniques.

Results: Qualitative evaluation demonstrated that both methods achieved soft tissue images with similar quality. The use of aWLS increased the number of tracked frames by 1-5% compared to mWLS, with the largest increase observed for the smallest simulated tumors. The tracking errors for both methods produced agreement to within 0.1 mm.

Conclusions: A novel method to perform automated WLS for DE fluoroscopy was developed. Having similar soft tissue quality as well as bone suppression capability as mWLS, this method allows for real-time processing of DE images for MTT.

Citing Articles

Explainability and controllability of patient-specific deep learning with attention-based augmentation for markerless image-guided radiotherapy.

Terunuma T, Sakae T, Hu Y, Takei H, Moriya S, Okumura T Med Phys. 2022; 50(1):480-494.

PMID: 36354286 PMC: 10100026. DOI: 10.1002/mp.16095.

References

Szucs-Farkas Z, Patak M, Yuksel-Hatz S, Ruder T, Vock P . Single-exposure dual-energy subtraction chest radiography: detection of pulmonary nodules and masses in clinical practice. Eur Radiol. 2007; 18(1):24-31. DOI: 10.1007/s00330-007-0758-z. View

Dhont J, Verellen D, Poels K, Tournel K, Burghelea M, Gevaert T . Feasibility of markerless tumor tracking by sequential dual-energy fluoroscopy on a clinical tumor tracking system. Radiother Oncol. 2015; 117(3):487-90. DOI: 10.1016/j.radonc.2015.08.021. View

Block A, Patel R, Surucu M, Harkenrider M, Roeske J . Evaluation of a template-based algorithm for markerless lung tumour localization on single- and dual-energy kilovoltage images. Br J Radiol. 2016; 89(1068):20160648. PMC: 5604930. DOI: 10.1259/bjr.20160648. View

Haytmyradov M, Mostafavi H, Wang A, Zhu L, Surucu M, Patel R . Markerless tumor tracking using fast-kV switching dual-energy fluoroscopy on a benchtop system. Med Phys. 2019; 46(7):3235-3244. PMC: 6625841. DOI: 10.1002/mp.13573. View

Brody W, Butt G, Hall A, Macovski A . A method for selective tissue and bone visualization using dual energy scanned projection radiography. Med Phys. 1981; 8(3):353-7. DOI: 10.1118/1.594957. View

Patel R, Panfil J, Campana M, Block A, Harkenrider M, Surucu M . Markerless motion tracking of lung tumors using dual-energy fluoroscopy. Med Phys. 2015; 42(1):254-62. DOI: 10.1118/1.4903892. View

Menten M, Fast M, Nill S, Oelfke U . Using dual-energy x-ray imaging to enhance automated lung tumor tracking during real-time adaptive radiotherapy. Med Phys. 2015; 42(12):6987-98. DOI: 10.1118/1.4935431. View

Hoggarth M, Luce J, Syeda F, Bray T, Block A, Nagda S . Dual energy imaging using a clinical on-board imaging system. Phys Med Biol. 2013; 58(12):4331-40. DOI: 10.1088/0031-9155/58/12/4331. View

Shkumat N, Siewerdsen J, Richard S, Paul N, Yorkston J, Van Metter R . Dual-energy imaging of the chest: optimization of image acquisition techniques for the 'bone-only' image. Med Phys. 2008; 35(2):629-32. DOI: 10.1118/1.2828186. View

10.

Yang Y, Zhong Z, Guo X, Wang J, Anderson J, Solberg T . A novel markerless technique to evaluate daily lung tumor motion based on conventional cone-beam CT projection data. Int J Radiat Oncol Biol Phys. 2012; 82(5):e749-56. DOI: 10.1016/j.ijrobp.2011.11.035. View

11.

Sherertz T, Hoggarth M, Luce J, Block A, Nagda S, Harkenrider M . Prospective evaluation of dual-energy imaging in patients undergoing image guided radiation therapy for lung cancer: initial clinical results. Int J Radiat Oncol Biol Phys. 2014; 89(3):525-31. DOI: 10.1016/j.ijrobp.2014.03.004. View

12.

Haytmyradov M, Patel R, Mostafavi H, Surucu M, Wang A, Harkenrider M . A novel phantom for characterization of dual energy imaging using an on-board imaging system. Phys Med Biol. 2018; 64(3):03NT01. PMC: 6602048. DOI: 10.1088/1361-6560/aaf9dd. View

13.

Mostafavi H, Sloutsky A, Jeung A . Detection and localization of radiotherapy targets by template matching. Annu Int Conf IEEE Eng Med Biol Soc. 2013; 2012:6023-7. DOI: 10.1109/EMBC.2012.6347367. View

14.

Fischbach F, Freund T, Rottgen R, Engert U, Felix R, Ricke J . Dual-energy chest radiography with a flat-panel digital detector: revealing calcified chest abnormalities. AJR Am J Roentgenol. 2003; 181(6):1519-24. DOI: 10.2214/ajr.181.6.1811519. View

15.

Darvish-Molla S, Reno M, Sattarivand M . Patient-specific pixel-based weighting factor dual-energy x-ray imaging system using a priori CT data. Med Phys. 2018; 46(2):528-543. DOI: 10.1002/mp.13354. View