In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks

Respiratory-Correlated cone beam computed tomography (4D-CBCT) is an emerging image-guided radiation therapy (IGRT) technique that is used to account for the uncertainties caused by respiratory-induced motion in the radiotherapy treatment of tumors in thoracic and upper-abdomen regions. In 4D-CBCT,...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Dweek, Samaa (author)
مؤلفون آخرون: Dhou, Salam (author), Shanableh, Tamer (author)
التنسيق: article
منشور في: 2022
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/23580
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513434005012480
author Dweek, Samaa
author2 Dhou, Salam
Shanableh, Tamer
author2_role author
author
author_facet Dweek, Samaa
Dhou, Salam
Shanableh, Tamer
author_role author
dc.creator.none.fl_str_mv Dweek, Samaa
Dhou, Salam
Shanableh, Tamer
dc.date.none.fl_str_mv 2022-04-14T09:10:24Z
2022-04-14T09:10:24Z
2022
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Samaa Dweek, Salam Dhou, and Tamer Shanableh "In-between projection interpolation in cone-beam CT imaging using convolutional neural networks", Proc. SPIE 12031, Medical Imaging 2022: Physics of Medical Imaging, 1203129 (4 April 2022); https://doi.org/10.1117/12.2611474
http://hdl.handle.net/11073/23580
10.1117/12.2611474
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv Society of Photo-Optical Instrumentation Engineers (SPIE)
dc.relation.none.fl_str_mv https://doi.org/10.1117/12.2611474
dc.subject.none.fl_str_mv Image-guided radiation therapy
4D cone-beam CT (CBCT)
Respiratory motion
Image interpolation
Convolutional neural networks (CNNs)
Deep learning
dc.title.none.fl_str_mv In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks
dc.type.none.fl_str_mv Postprint
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description Respiratory-Correlated cone beam computed tomography (4D-CBCT) is an emerging image-guided radiation therapy (IGRT) technique that is used to account for the uncertainties caused by respiratory-induced motion in the radiotherapy treatment of tumors in thoracic and upper-abdomen regions. In 4D-CBCT, projections are sorted into bins based on their respiratory phase and a 3D image is reconstructed from each bin. However, the quality of the resulting 4D-CBCT images is limited by the streaking artifacts that result from having an insufficient number of projections in each bin. In this work, an interpolation method based on Convolutional Neural Networks (CNN) is proposed to generate new in-between projections to increase the overall number of projections used in 4D-CBCT reconstruction. Projections simulated using XCAT phantom were used to assess the proposed method. The interpolated projections using the proposed method were compared to the corresponding original projections by calculating the peak-signal-to-noise ratio (PSNR), root mean square error (RMSE), and structural similarity index measurement (SSIM). Moreover, the results of the proposed method were compared to the results of existing standard interpolation methods, namely, linear, spline, and registration-based methods. The interpolated projections using the proposed method had an average PSNR, RMSE, and SSIM of 35.939, 4.115, and 0.968, respectively. Moreover, the results achieved by the proposed method surpassed the results achieved by the existing interpolation methods tested on the same dataset. In summary, this work demonstrates the feasibility of using CNN-based methods in generating in-between projections and shows a potential advantage to 4D-CBCT reconstruction.
format article
id aus_a96e8d34f9eb93be6651fa2a4c2cfb3a
identifier_str_mv Samaa Dweek, Salam Dhou, and Tamer Shanableh "In-between projection interpolation in cone-beam CT imaging using convolutional neural networks", Proc. SPIE 12031, Medical Imaging 2022: Physics of Medical Imaging, 1203129 (4 April 2022); https://doi.org/10.1117/12.2611474
10.1117/12.2611474
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/23580
publishDate 2022
publisher.none.fl_str_mv Society of Photo-Optical Instrumentation Engineers (SPIE)
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural NetworksDweek, SamaaDhou, SalamShanableh, TamerImage-guided radiation therapy4D cone-beam CT (CBCT)Respiratory motionImage interpolationConvolutional neural networks (CNNs)Deep learningRespiratory-Correlated cone beam computed tomography (4D-CBCT) is an emerging image-guided radiation therapy (IGRT) technique that is used to account for the uncertainties caused by respiratory-induced motion in the radiotherapy treatment of tumors in thoracic and upper-abdomen regions. In 4D-CBCT, projections are sorted into bins based on their respiratory phase and a 3D image is reconstructed from each bin. However, the quality of the resulting 4D-CBCT images is limited by the streaking artifacts that result from having an insufficient number of projections in each bin. In this work, an interpolation method based on Convolutional Neural Networks (CNN) is proposed to generate new in-between projections to increase the overall number of projections used in 4D-CBCT reconstruction. Projections simulated using XCAT phantom were used to assess the proposed method. The interpolated projections using the proposed method were compared to the corresponding original projections by calculating the peak-signal-to-noise ratio (PSNR), root mean square error (RMSE), and structural similarity index measurement (SSIM). Moreover, the results of the proposed method were compared to the results of existing standard interpolation methods, namely, linear, spline, and registration-based methods. The interpolated projections using the proposed method had an average PSNR, RMSE, and SSIM of 35.939, 4.115, and 0.968, respectively. Moreover, the results achieved by the proposed method surpassed the results achieved by the existing interpolation methods tested on the same dataset. In summary, this work demonstrates the feasibility of using CNN-based methods in generating in-between projections and shows a potential advantage to 4D-CBCT reconstruction.Society of Photo-Optical Instrumentation Engineers (SPIE)2022-04-14T09:10:24Z2022-04-14T09:10:24Z2022Postprintinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfSamaa Dweek, Salam Dhou, and Tamer Shanableh "In-between projection interpolation in cone-beam CT imaging using convolutional neural networks", Proc. SPIE 12031, Medical Imaging 2022: Physics of Medical Imaging, 1203129 (4 April 2022); https://doi.org/10.1117/12.2611474http://hdl.handle.net/11073/2358010.1117/12.2611474en_UShttps://doi.org/10.1117/12.2611474oai:repository.aus.edu:11073/235802024-08-22T12:07:38Z
spellingShingle In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks
Dweek, Samaa
Image-guided radiation therapy
4D cone-beam CT (CBCT)
Respiratory motion
Image interpolation
Convolutional neural networks (CNNs)
Deep learning
status_str publishedVersion
title In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks
title_full In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks
title_fullStr In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks
title_full_unstemmed In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks
title_short In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks
title_sort In-Between Projection Interpolation in Cone-Beam CT Imaging using Convolutional Neural Networks
topic Image-guided radiation therapy
4D cone-beam CT (CBCT)
Respiratory motion
Image interpolation
Convolutional neural networks (CNNs)
Deep learning
url http://hdl.handle.net/11073/23580