Reconstruction of 3D lung models from 2D planning data sets for Hodgkin's lymphoma patients using combined deformable image registration and navigator channels

Ng, Angela; Nguyen, Thanh Thi; Moseley, Joanne; Hodgson, David C.; Sharpe, Michael B.; Brock, Kristy K.

doi:10.1118/1.3284368

Cited by 10 publications

(9 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, since the availability of different OAR segmentations is currently limited to what is available in the database, and since delineating new OARs requires specialization, experience, and time, ways to use ML to deform an existing OAR template into a patientspecific segmentation could be worth investigating. 19 Furthermore, it will be interesting to investigate whether the single CT selection approach (sCT) can be improved, by understanding how to best combine more metrics than organ positions. With more data available, the use of deep convolutional neural networks could be explored 56 to replace the use of features extracted from the radiographs with the use of the radiographs themselves, potentially by proposing 2-D OAR segmentations that can be used to reconstruct 3-D versions.…”

Section: Discussionmentioning

confidence: 99%

“…4 We remark that, for the purpose of dose reconstruction, anatomy resemblance (configuration and properties of internal organs) does not necessarily imply anatomy realism. 8 To improve phantom individualization for patients with no 3-D imaging, adaptation techniques have been studied such as morphing organ shapes 19,20 and organ repositioning. 21 In this work, we attempt to improve upon the use of simple hand-crafted criteria, and upon adaptation techniques, by proposing an end-to-end approach based on nontrivial criteria (models) discovered by machine learning (ML).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning for the prediction of pseudorealistic pediatric abdominal phantoms for radiation dose reconstruction

et al. 2020

View full text Add to dashboard Cite

Purpose: Current phantoms used for the dose reconstruction of long-term childhood cancer survivors lack individualization. We design a method to predict highly individualized abdominal three-dimensional (3-D) phantoms automatically. Approach: We train machine learning (ML) models to map (2-D) patient features to 3-D organat-risk (OAR) metrics upon a database of 60 pediatric abdominal computed tomographies with liver and spleen segmentations. Next, we use the models in an automatic pipeline that outputs a personalized phantom given the patient's features, by assembling 3-D imaging from the database. A step to improve phantom realism (i.e., avoid OAR overlap) is included. We compare five ML algorithms, in terms of predicting OAR left-right (LR), anterior-posterior (AP), inferior-superior (IS) positions, and surface Dice-Sørensen coefficient (sDSC). Furthermore, two existing human-designed phantom construction criteria and two additional control methods are investigated for comparison. Results: Different ML algorithms result in similar test mean absolute errors: ∼8 mm for liver LR, IS, and spleen AP, IS; ∼5 mm for liver AP and spleen LR; ∼80% for abdomen sDSC; and ∼60% to 65% for liver and spleen sDSC. One ML algorithm (GP-GOMEA) significantly performs the best for 6/9 metrics. The control methods and the human-designed criteria in particular perform generally worse, sometimes substantially (þ5-mm error for spleen IS, −10% sDSC for liver). The automatic step to improve realism generally results in limited metric accuracy loss, but fails in one case (out of 60). Conclusion: Our ML-based pipeline leads to phantoms that are significantly and substantially more individualized than currently used human-designed criteria.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning for the prediction of pseudorealistic pediatric abdominal phantoms for radiation dose reconstruction

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Another study [48] developed a ‘navigator channel’-based approach to reconstruct 3D lung models from 2D planning projections. Compared with the ‘navigator channel’ based technique, Bio-CBCT-est does not require a library of patients to build a pool of lung models.…”

Section: Discussionmentioning

confidence: 99%

A Biomechanical Modeling Guided CBCT Estimation Technique

You

Tehrani

Wang

2017

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Two-dimensional-to-three-dimensional (2D-3D) deformation has emerged as a new technique to estimate cone-beam computed tomography (CBCT) images. The technique is based on deforming a prior high-quality 3D CT/CBCT image to form a new CBCT image, guided by limited-view 2D projections. The accuracy of this intensity-based technique, however, is often limited in low-contrast image regions with subtle intensity differences. The solved deformation vector fields (DVFs) can also be biomechanically unrealistic. To address these problems, we have developed a biomechanical modeling guided CBCT estimation technique (Bio-CBCT-est) by combining 2D-3D deformation with finite element analysis (FEA)-based biomechanical modeling of anatomical structures. Specifically, Bio-CBCT-est first extracts the 2D-3D deformation-generated displacement vectors at the high-contrast anatomical structure boundaries. The extracted surface deformation fields are subsequently used as the boundary conditions to drive structure-based FEA to correct and fine-tune the overall deformation fields, especially those at low-contrast regions within the structure. The resulting FEA-corrected deformation fields are then fed back into 2D-3D deformation to form an iterative loop, combining the benefits of intensity-based deformation and biomechanical modeling for CBCT estimation. Using eleven lung cancer patient cases, the accuracy of the Bio-CBCT-est technique has been compared to that of the 2D-3D deformation technique and the traditional CBCT reconstruction techniques. The accuracy was evaluated in the image domain, and also in the DVF domain through clinician-tracked lung landmarks.

show abstract

“…As functional imaging continues to improve, the concept of automated target volume delineation in IGRT treatment planning using FDG-PET/CT may help improve objectivity in a better-defined BTV [ 67 ]. Deformable registration is also emerging and being utilized in IGRT to improve target acquisition and localization [ 68 69 ]. As technologic advances continue to evolve and gain momentum in lymphoma management, successful adoption of these technologies requires clear understanding of the complexity of IGRT, current knowledge, quality assurance, necessary training and skills associated with such implementation in order to exploit the benefits of IGRT.…”

Section: Discussionmentioning

confidence: 99%

Image-guided radiation therapy in lymphoma management

Eng

2015

Radiat Oncol J

View full text Add to dashboard Cite

Image-guided radiation therapy (IGRT) is a process of incorporating imaging techniques such as computed tomography (CT), magnetic resonance imaging (MRI), Positron emission tomography (PET), and ultrasound (US) during radiation therapy (RT) to improve treatment accuracy. It allows real-time or near real-time visualization of anatomical information to ensure that the target is in its position as planned. In addition, changes in tumor volume and location due to organ motion during treatment can be also compensated. IGRT has been gaining popularity and acceptance rapidly in RT over the past 10 years, and many published data have been reported on prostate, bladder, head and neck, and gastrointestinal cancers. However, the role of IGRT in lymphoma management is not well defined as there are only very limited published data currently available. The scope of this paper is to review the current use of IGRT in the management of lymphoma. The technical and clinical aspects of IGRT, lymphoma imaging studies, the current role of IGRT in lymphoma management and future directions will be discussed.

show abstract

Reconstruction of 3D lung models from 2D planning data sets for Hodgkin's lymphoma patients using combined deformable image registration and navigator channels

Cited by 10 publications

References 45 publications

Machine learning for the prediction of pseudorealistic pediatric abdominal phantoms for radiation dose reconstruction

Machine learning for the prediction of pseudorealistic pediatric abdominal phantoms for radiation dose reconstruction

A Biomechanical Modeling Guided CBCT Estimation Technique

Image-guided radiation therapy in lymphoma management

Contact Info

Product

Resources

About