Personalising population-based respiratory motion models of the heart using neighbourhood approximation based on learnt anatomical features

Peressutti, Devis; Penney, Graeme P.; Kolbitsch, Christoph; King, Andrew P.

doi:10.1016/j.media.2014.05.013

Cited by 5 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This could be, in parts, due to the common approach of establishing the motion representation based on the entire population; potential existence of patient subpopulations that optimally resemble a patient's true motion patterns is ignored. Hypothesizing existence of such subpopulations, we complement and extend recent works on selecting and determining appropriate population subsets (Samei et al 2012, Peressutti et al 2013, Tanner et al 2015 and investigate the benefit of enriching patient-specific pre-treatment-built motion modelling by subpopulation-based motion information.…”

Section: Introductionmentioning

confidence: 87%

“…Thus, S consists of all patients belonging to the same cluster as patient p = 0. In related work by Peressutti et al (2013), motion clustering was applied to personalize population models for affine cardiac respiratory motion compensation. In their work, inter-patient motion similarity is quantified by calculating pairwise Euclidean distances between patient-specific motion models to perform standard spectral clustering.…”

Section: Subpopulation-based Correspondence Modellingmentioning

confidence: 99%

See 1 more Smart Citation

Subpopulation-based correspondence modelling for improved respiratory motion estimation in the presence of inter-fraction motion variations

et al. 2017

View full text Add to dashboard Cite

Correspondence modelling between low-dimensional breathing signals and internal organ motion is a prerequisite for application of advanced techniques in radiotherapy of moving targets. Patient-specific correspondence models can, for example, be built prior to treatment based on a planning 4D CT and simultaneously acquired breathing signals. Reliability of pre-treatment-built models depends, however, on the degree of patient-specific inter-fraction motion variations. This study investigates whether motion estimation accuracy in the presence of inter-fraction motion variations can be improved using correspondence models that incorporate motion information from different patients. The underlying assumption is that inter-patient motion variations resemble patient-specific inter-fraction motion variations for subpopulations of patients with similar breathing characteristics. The hypothesis is tested by integrating a sparse manifold clustering approach into a regression-based correspondence modelling framework that allows for automated identification of patient subpopulations. The evaluation is based on a total of 73 lung 4D CT data sets, including two cohorts of patients with repeat 4D CT scans (cohort 1: 14 patients; cohort 2: ten patients). The results are consistent for both cohorts: The subpopulation-based modelling approach outperforms general population modelling (models built on all data sets available) as well as pre-treatment-built models trained on only the patient-specific motion information. The results thereby support the hypothesis and illustrate the potential of subpopulation-based correspondence modelling.

show abstract

Section: Introductionmentioning

confidence: 87%

Section: Subpopulation-based Correspondence Modellingmentioning

confidence: 99%

Subpopulation-based correspondence modelling for improved respiratory motion estimation in the presence of inter-fraction motion variations

et al. 2017

View full text Add to dashboard Cite

show abstract

“…However, a well-performed NuTracker model trained for one patient usually performs incorrectly for another, because the model's inputs (coordinates and surrogate states) can vary dramatically between patients, and patient identities are not fed into the model. Most cross-population models (Klinder and Lorenz 2012, Peressutti et al 2014, Romaguera et al 2021b address this problem by aligning the input spaces of different patients using inter-patient registrations. This approach is quite challenging due to anatomical variations and missing correspondences in the presence of pathology.…”

Section: Cross-population Learning Via Meta-learningmentioning

confidence: 99%

NuTracker: a coordinate-based neural network representation of lung motion for intrafraction tumor tracking with various surrogates in radiotherapy

Liu¹,

Wang²,

Wen³

et al. 2022

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Tracking tumors and surrounding tissues in real-time is critical for reducing errors and uncertainties during radiotherapy. Existing methods are either limited by the linear representation or scale poorly with the volume resolution. To address both issues, we propose a novel coordinate-based neural network representation of lung motion to predict the instantaneous 3D volume at arbitrary spatial resolution from various surrogates: patient surface, fiducial marker, and single kV projection. Approach: The proposed model, namely NuTracker, decomposes the 4DCT into a template volume and dense displacement fields (DDFs), and uses two coordinate neural networks to predict them from spatial coordinates and surrogate states. The predicted template is spatially warped with the predicted DDF to produce the deformed volume for a given surrogate state. The nonlinear coordinate networks enable representing complex motion at infinite resolution. The decomposition allows imposing different regularizations on the spatial and temporal domains. The meta-learning and multi-task learning are used to train NuTracker across patients and tasks, so that commonalities and differences can be exploited. NuTracker was evaluated on seven patients implanted with markers using a leave-one-phase-out procedure. Main results: The 3D marker localization error is 0.66 mm on average and <1 mm at 95th-percentile, which is about 26% and 32% improvement over the predominant linear methods. The tumor coverage and image quality are improved by 5.7% and 11% in terms of dice and PSNR. The difference in the localization error for different surrogates is small and is not statistically significant. Cross-population learning and multi-task learning contribute to performance. The model tolerates surrogate drift to a certain extent. Significance: NuTracker can provide accurate estimation for entire tumor volume based on various surrogates at infinite resolution. It is of great potential to apply the coordinate network to other imaging modalities, e.g., 4DCBCT and other tasks, e.g.,4D dose calculation.

show abstract

“…[13][14][15][16][17][18] However, the cine-MRI could only provide twodimensional (2D) information of the tumour movement and does not contain the information of out-of -plane motion, which would reduce the accuracy of tumourtracking therapy. [19][20][21] Although it is possible to estimate the tumour motion in 3D space by alternately acquiring cine-MRI on orthogonal imaging planes, it will reduce the frequency and accuracy of motion estimation. Moreover, the tumour and tissue that have large volumes would deform due to respiration.…”

Section: Introductionmentioning

confidence: 99%

Real‐time 3D MRI reconstruction from cine‐MRI using unsupervised network in MRI‐guided radiotherapy for liver cancer

et al. 2022

View full text Add to dashboard Cite

Respiration has a major impact on the accuracy of radiation treatment for thorax and abdominal tumours. Instantaneous volumetric imaging could provide precise knowledge of tumour and normal organs' three-dimensional (3D) movement, which is the key to reducing the negative effect of breathing motion. Therefore, this study proposed a real-time 3D MRI reconstruction method from cine-MRI using an unsupervised network. Methods and materials: Cine-MRI and setup 3D-MRI from eight patients with liver cancer were utilized to establish and validate the deep learning network for 3D-MRI reconstruction. Unlike previous methods that required 4D-MRI for network training, the proposed method utilized a reference 3D-MRI and cine-MRI to generate the training data. Then, a network was trained in an unsupervised manner to estimate the relationship between the cine-MRI acquired on coronal plane and deformation vector field (DVF) that describes the patient's breathing motion. After the training process, the coronal cine-MRI were inputted into the network, and the corresponding DVF was obtained. By wrapping the reference 3D-MRI with the generated DVF, the 3D-MRI could be reconstructed. Results:The reconstructed 3D-MRI slices were compared with the corresponding phase-sorted cine-MRI using dice similarity coefficients (DSCs) of liver contours and blood vessel localization error. In all patients, the liver DSC had mean value >96.1% and standard deviation < 1.3%; the blood vessel localization error had mean value <2.6 mm, and standard deviation was <2.0 mm. Moreover, the time for 3D-MRI reconstruction was approximately 100 ms. These results indicated that the proposed method could accurately reconstruct the 3D-MRI in real time. Conclusions:The proposed method could accurately reconstruct the 3D-MRI from cine-MRI in real time. This method has great potential in improving the accuracy of radiotherapy for moving tumours.

show abstract

Personalising population-based respiratory motion models of the heart using neighbourhood approximation based on learnt anatomical features

Cited by 5 publications

References 33 publications

Subpopulation-based correspondence modelling for improved respiratory motion estimation in the presence of inter-fraction motion variations

Subpopulation-based correspondence modelling for improved respiratory motion estimation in the presence of inter-fraction motion variations

NuTracker: a coordinate-based neural network representation of lung motion for intrafraction tumor tracking with various surrogates in radiotherapy

Real‐time 3D MRI reconstruction from cine‐MRI using unsupervised network in MRI‐guided radiotherapy for liver cancer

Contact Info

Product

Resources

About