A biomechanical finite element model to generate a library of cervix CTVs

Carpe Diem: Making the Most of Plan-of-the-Day for Cervical Cancer Radiation Therapy

PURPOSE

Radiation therapy is the key treatment for locally advanced cervical cancer. Organ motion presents a challenge to accurate targeting of external beam radiation therapy. The plan-of-the-day (PotD) adaptive approach is therefore an attractive option. We present our experience and the procedural steps required to implement PotD for cervix cancer.

METHODS AND MATERIALS

We reviewed relevant studies on organ motion and adaptive radiation therapy identified through a literature search and cross referencing. These included 10 dosimetric and 3 quality of life studies directly assessing the PotD approach to radiation therapy in cervix cancer.

RESULTS

Studies show improvements in target coverage and reduction of dose received by normal tissues and suggest improved toxicity. Clinical implementation of PotD has been slow because of a number of difficulties and uncertainties, which we discuss with the aim of helping teams to implement PotD at their center.

CONCLUSIONS

The PotD approach improves dosimetry and may improve toxicity. We describe a framework to assist with practical implementation.

Dosimetric benefit of a library of plans versus single-plan strategy for pre-operative gastric cancer radiotherapy

BACKGROUND AND PURPOSE

The stomach experiences large volume and shape changes during pre-operative gastric radiotherapy. This study evaluates the dosimetric benefit for organs-at-risk (OARs) of a library of plans (LoP) compared to the traditional single-plan (SP) strategy.

MATERIALS AND METHODS

Twelve patients who received SP CBCT-guided pre-operative gastric radiotherapy (45 Gy; 25 fractions) were included. Clinical target volume (CTV) consisted of CTV_stomach (i.e., stomach + 10 mm uniform margin minus OARs) and CTV_LN (i.e., regional lymph node stations). For LoP, five stomach volumes (approximately equidistant with fixed volumes) were created using a previously developed stomach deformation model (volume = 150-750 mL). Appropriate planning target volume (PTV) margins were calculated for CTV_stomach (SP and LoP, separately) and CTV_LN. Treatment plans were automatically generated/optimized and the best-fitting library plan was manually selected for each daily CBCT. OARs (i.e., liver, kidneys, heart, spleen, spinal canal) doses were accumulated and dose-volume histogram (DVH) parameters were evaluated.

RESULTS

The non-isotropic PTV_stomach margins were significantly (p < 0.05) smaller for LoP than SP (median = 13.1 vs 19.8 mm). For each patient, the average PTV was smaller using a LoP (difference range 134-1151 mL). For all OARs except the kidneys, DVH parameters were significantly reduced using a LoP. Differences in mean dose (Dmean) for liver, heart and spleen ranged between -1.8 to 5.7 Gy. For LoP, a benefit of heart Dmean > 4 Gy and spleen Dmean > 2 Gy was found in 4 and 5 patients, respectively.

CONCLUSION

A LoP strategy for pre-operative gastric cancer reduced average PTV and reduced OAR dose compared to a SP strategy, thereby potentially reducing risks for radiation-induced toxicities.

Improving predictive CTV segmentation on CT and CBCT for cervical cancer by diffeomorphic registration of a prior

PURPOSE

Automatic cervix-uterus segmentation of the clinical target volume (CTV) on CT and cone beam CT (CBCT) scans is challenged by the limited visibility and the non-anatomical definition of certain border regions. We study potential performance gain of convolutional neural networks by regulating the segmentation predictions as diffeomorphic deformations of a segmentation prior.

METHODS

We introduce a 3D convolutional neural network (CNN) which segments the target scan by joint voxel-wise classification and the registration of a given prior. We compare this network to two other 3D baseline models: one treating segmentation as a classification problem (segmentation-only), the other as a registration problem (deformation-only). For reference and to highlight benefits of a 3D model, these models are also benchmarked against a 2D segmentation model. Network performances are reported for CT and CBCT segmentation of the cervix-uterus CTV. We train the networks on data of 84 patients. The prior is provided by the CTV segmentation of a planning CT. Repeat CT or CBCT scans constitute the target scans to be segmented.

RESULTS

All 3D models outperformed the 2D segmentation model. For CT segmentation, combining classification and registration in the proposed joint model proved beneficial, achieving a Dice score of 0.87 and a mean squared error (MSE) of the surface distance below 1.7 mm. No such synergy was observed for CBCT segmentation, for which the joint and the deformation-only model performed similarly, achieving a Dice score of about 0.80 and a MSE surface distance of 2.5 mm. However, the segmentation-only model performed notably worse in this low contrast regime. Visual inspection revealed that this performance drop translated into geometric inconsistencies between the prior and target segmentation. Such inconsistencies where not observed for the deformation-based models.

CONCLUSION

Constraining the solution space of admissible segmentation predictions to those reachable by a diffeomorphic deformation of the prior proved beneficial as it improved geometric consistency. Especially for CBCT, with its poor soft tissue contrast, this type of regularization becomes important as shown by quantitative and qualitative evaluation. This article is protected by copyright. All rights reserved.

Gastric deformation models for adaptive radiotherapy: Personalized vs population-based strategy

BACKGROUND AND PURPOSE

To create a library of plans (LoP) for gastric cancer adaptive radiotherapy, accurate predictions of shape changes due to filling variations are essential. The ability of two strategies (personalized and population-based) to predict stomach shape based on filling was evaluated for volunteer and patient data to explore the potential for use in a LoP.

MATERIALS AND METHODS

For 19 healthy volunteers, stomachs were delineated on MRIs with empty (ES), half-full (HFS) and full stomach (FS). For the personalized strategy, a deformation vector field from HFS to corresponding ES was acquired and extrapolated to predict FS. For the population-based strategy, the average deformation vectors from HFS to FS of 18 volunteers were applied to the HFS of the remaining volunteer to predict FS (leave-one-out principle); thus, predictions were made for each volunteer. Reversed processes were performed to predict ES. To validate, for seven gastric cancer patients, the volunteer population-based model was applied to their pre-treatment CT to predict stomach shape on 2-3 repeat CTs. For all predictions, volume was made equal to true stomach volume.

RESULTS

FS predictions were satisfactory, with median Dice similarity coefficient (mDSC) of 0.91 (population-based) and 0.89 (personalized). ES predictions were poorer: mDSC = 0.82 for population-based; personalized strategy yielded unachievable volumes. Population-based shape predictions (both ES and FS) were comparable between patients (mDSC = 0.87) and volunteers (0.88).

CONCLUSION

The population-based model outperformed the personalized model and demonstrated its ability in predicting filling-dependent stomach shape changes and, therefore, its potential for use in a gastric cancer LoP.

Deformation trajectory prediction using a neural network trained on finite element data-application to library of CTVs creation for cervical cancer

Purpose. We propose a neural network for fast prediction of realistic, time-parametrized deformations between pairs of input segmentations. The proposed method was used to generate a library of planning CTVs for cervical cancer radiotherapy.Methods.A 3D convolutional neural network (CNN) was introduced to predict a stationary velocity field given the distance maps of the cervix CTV in empty and full bladder anatomy. Diffeomorphic deformation trajectories between the two states were obtained by time integration. Intermediate deformation states were used to populate a library of cervix CTVs. The network was trained on cervix CTV deformations of 20 patients generated by finite element modeling (FEM). Validation was performed on FEM data of 9 healthy volunteers. Additionally, for these subjects, CTV deformations were observed in a series of repeat MR scans as the bladder filled from empty to full. Predicted and FEM libraries were compared, and benchmarked against the observed deformations. Finally, for an independent test set of 20 patients the predicted libraries were evaluated clinically, and compared to the current method.Results.The median Dice score over the validation subjects between the predicted and FEM libraries was >0.95 throughout the deformation, with a median 90 percentile surface distance of <3 mm. The ability to cover observed CTVs was similar for both the FEM-based and the proposed method, with residual offsets being about twice as large as the difference between the two methods. Clinical evaluation showed improved library properties over the method currently used in clinic.Conclusions.We proposed a CNN trained on FEM deformations, which predicts the deformation trajectory between two input states of the cervix CTV in one forward pass. We applied this to CTV library prediction for cervical cancer. The network is able to mimic FEM deformations well, while being much faster and simpler in use.

Image-Based Polygonal Lattices for Mechanical Modeling of Biological Materials: 2D Demonstrations

Understanding the structure-property relationship of biological materials, such as bones, teeth, cells, and biofilms, is critical for diagnosing diseases and developing bioinspired materials and structures. The intrinsic multiphase heterogeneity with interfaces places great challenges for mechanical modeling. Here, we develop an image-based polygonal lattice model for simulating the mechanical deformation of biological materials with complicated shapes and interfaces. The proposed lattice model maintains the uniform meshes inside the homogeneous phases and restricts the irregular polygonal meshes near the boundaries or interfaces. This approach significantly simplifies the mesh generation from images of biological structures with complicated geometries. The conventional finite element simulations validate this polygonal lattice model. We further demonstrate that the image-based polygonal lattices generate meshes from images of composite structures with multiple inclusions and capture the nonlinear mechanical deformation. We conclude the paper by highlighting a few future research directions that will benefit from the functionalities of polygonal lattice modeling.