Cancer accounts for nearly 10 million deaths in 2020 and is a leading cause of death worldwide. Radiation therapy is an effective modality to cure cancer. The ultimate goal of successful radiation therapy is to accurately deliver a safe and therapeutic dose of radiation to cancerous target cells while limiting radiation to the healthy tissue in the beam pathway and the surrounding normal tissue. With advancing radiation treatment technology, better imaging techniques are imperative for safe, high-dose delivery. Artificial intelligence developments on image-guided radiation therapy technologies, which range from Kilovoltage and Megavoltage modalities to two-dimensional and three-dimensional techniques, are discussed in depth.
Section snippetsIntroduction to X-Ray Guidance in Radiation TherapyArtificial intelligence (AI), which is also referred to as machine intelligence, usually denotes intelligence demonstrated by machines.1 Generally speaking, AI describes machines that mimic cognitive functions (such as learning) of the human mind. AI, as a concept, was proposed back in the 1950s. However, recent advances in computing capability allow the development of high-level features learning models to represent complex relationships within observational data. Figure 1 shows representative
Review of X-Ray Modalities in Radiation TherapyThe primary goal and the ideal scenario of radiation therapy are to deliver a useful dose of radiation to the target cancerous cells while sparing the surrounding healthy tissues and tissues along the radiation beam path2. Although it is impossible to achieve complete sparing of the surrounding healthy tissues, the objective of safe delivery of radiation therapy (RT) is to keep the entrance, exit, and scatter doses as low as possible by employing various treatment techniques. As RT technologies
Cone-Beam CT ReconstructionX-ray cone-beam CT (CBCT) with 2D detectors is capable of obtaining high-resolution projection images with a relatively simple scanner geometry. It is often used for interventional radiology, dental CT, besides modern radiotherapy. For the cone-beam geometry, Feldkamp Davis and Kress (FDK) algorithm6 has been extensively used as the standard reconstruction method.7, 8, 9 Unfortunately, the FDK algorithm for CBCT usually suffers from cone-beam artifacts as the cone-angle increases xxx. Some
Remaining Challenges and Future WorkSimilar to most AI applications, massive amounts of imaging data are required to successfully train the AI model to ensure that the applications are ready to be accurately deployed in routine care. Various co-factors can heavily influence the performance of clinical AI systems (eg, patient demographics, disease stages or subtypes, genotypes, and more). Given the large number of combinations of the co-factors, data from one institution are often insufficient to train a robust AI model.
ConclusionRT imaging techniques have made strides to deliver more conformal therapeutic radiation to target tissues while limiting radiation to healthy tissues. X-ray is still the most available and important imaging modality for patient and tumor localization in image-guided radiotherapy. As discussed, the formation of the 2D X-ray and 3D CT images, image processing, and registration can be markedly improved for tumor and normal organ localization using artificial intelligence techniques. This is
Conflicts of InterestAll authors declare that they have no conflicts of interest.
AcknowledgmentsThe authors would like to thank many researchers who were involved in the related work at our institute.
References (59)KL Moore et al.Experience-based quality control of clinical intensity-modulated radiotherapy planningInt J Radiat Oncol Biol Phys
(2011)
K Kuriyama et al.A new irradiation unit constructed of self-moving gantry-CT and linacInt J Radiat Oncol Biol Phys
(2003)
S Siddique et al.Artificial intelligence in radiotherapyRep Practical Oncol Radiotherapy
(2020)
L Xing et al.Artificial Intelligence in Medicine(2020)
S Gianfaldoni et al.An overview on radiotherapy: from its history to its current applications in dermatologyOpen Access Maced J Med Sci
(2017)
T MackieHistory of tomotherapyPhys Med Biol
(2006)
R Timmerman et al.Image Guided and Adaptive Radiation Therapy(2009)
X Tang et al.A three-dimensional weighted cone beam filtered backprojection (CB-FBP) algorithm for image reconstruction in volumetric CT under a circular source trajectoryPhys Med Biol
(2005)
Y Wang et al.Modified FDK algorithm for cone-beam reconstruction with efficient weighting schemeIEEE
(2006)
X Tang et al.A three-dimensional-weighted cone beam filtered backprojection (CB-FBP) algorithm for image reconstruction in volumetric CT-helical scanningPhys Med Biol
(2006)
HK TuyAn inversion formula for cone-beam reconstructionSIAM J Appl Math
(1983)
BD SmithImage reconstruction from cone-beam projections: necessary and sufficient conditions and reconstruction methodsIEEE Trans Med Imaging
(1985)
IJ Kalet et al.Knowledge-based computer systems for radiotherapy planningAm J Clin Oncol
(1990)
M Mardani et al.Deep-Learning based prediction of achievable dose for personalizing inverse treatment planningInt J Radiat Oncol Biol Phys
(2016)
X Chen et al.A feasibility study on an automated method to generate patient-specific dose distributions for radiotherapy using deep learningMed Phys
(2019)
V Kearney et al.DoseNet: a volumetric dose prediction algorithm using 3D fully-convolutional neural networksPhys Med Biol
(2018)
B Ibragimov et al.Segmentation of organs-at-risks in head and neck CT images using convolutional neural networksMed Phys
(2017)
M Ma et al.Incorporating dosimetric features into the prediction of 3D VMAT dose distributions using deep convolutional neural networkPhys Med Biol
(2019)
W Zhao et al.A model-based scatter artifacts correction for cone beam CTMed Phys
(2016)
N Mail et al.The influence of bowtie filtration on cone-beam CT image qualityMed Phys
(2009)
J Boone et al.An analytical model of the scattered radiation distribution in diagnostic radiologyMed Phys
(1988)
RS Thing et al.Optimizing cone beam CT scatter estimation in egs_cbct for a clinical and virtual chest phantomMed Phys
(2014)
L Zhu et al.Scatter correction method for X-ray CT using primary modulation: theory and preliminary resultsIEEE
(2006)
J Wang et al.Scatter correction for cone-beam computed tomography using moving blocker strips: a preliminary studyMed Phys
(2010)
J Maier et al.Deep Scatter Estimation (DSE): accurate real-time scatter estimationfor X-Ray CT using a deep convolutional neural networkJ Nondestr Eval
(2017)
DC Hansen et al.ScatterNet: a convolutional neural network for cone-beam CT intensity correctionMed Phys
(2018)
Y Jiang et al.Scatter correction of cone-beam CT using a deep residual convolution neural network (DRCNN)Phys Med Biol
(2019)
T Niu et al.Shading correction for on-board cone-beam CT in radiation therapy using planning MDCT imagesMed Phys
(2010)
EY Sidky et al.Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimizationPhys Med Biol
(2008)
View full text© 2022 Elsevier Inc. All rights reserved.
留言 (0)