PREVIS: Predictive visual analytics of anatomical variability for radiotherapy decision support

Abstract Radiotherapy (RT) requires meticulous planning prior to treatment, where the RT plan is optimized with organ delineations on a pre-treatment Computed Tomography (CT) scan of the patient. The conventionally fractionated treatment usually lasts several weeks. Random changes (e.g., rectal and bladder filling in prostate cancer patients) and systematic changes (e.g., weight loss) occur while the patient is being treated. Therefore, the delivered dose distribution may deviate from the planned. Modern technology, in particular image guidance, allows to minimize these deviations, but risks for the patient remain. We present PREVIS: a visual analytics tool for (i) the exploration and prediction of changes in patient anatomy during the upcoming treatment, and (ii) the assessment of treatment strategies, with respect to the anticipated changes. Records of during-treatment changes from a retrospective imaging cohort with complete data are employed in PREVIS, to infer expected anatomical changes of new incoming patients with incomplete data, using a generative model. Abstracted representations of the retrospective cohort partitioning provide insight into an underlying automated clustering, showing main modes of variation for past patients. Interactive similarity representations support an informed selection of matching between new incoming patients and past patients. A Principal Component Analysis (PCA)-based generative model describes the predicted spatial probability distributions of the incoming patient’s organs in the upcoming weeks of treatment, based on observations of past patients. The generative model is interactively linked to treatment plan evaluation, supporting the selection of the optimal treatment strategy. We present a usage scenario, demonstrating the applicability of PREVIS in a clinical research setting, and we evaluate our visual analytics tool with eight clinical researchers.

[1]  Jürgen Bernard,et al.  A Visual-Interactive System for Prostate Cancer Cohort Analysis , 2015, IEEE Computer Graphics and Applications.

[2]  Joseph O. Deasy,et al.  Nonlinear Kernel-Based Approaches for Predicting Normal Tissue Toxicities , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[3]  Bernhard Preim,et al.  Subpopulation Discovery and Validation in Epidemiological Data , 2017, EuroVA@EuroVis.

[4]  Tatiana von Landesberger,et al.  Comparative Local Quality Assessment of 3D Medical Image Segmentations with Focus on Statistical Shape Model-Based Algorithms , 2016, IEEE Transactions on Visualization and Computer Graphics.

[5]  J. Lyman Complication Probability as Assessed from Dose-Volume Histograms , 1985 .

[6]  Eduard Gröller,et al.  Lessons Learnt from Developing Visual Analytics Applications for Adaptive Prostate Cancer Radiotherapy , 2020, VisGap@Eurographics/EuroVis.

[7]  Ross T. Whitaker,et al.  Contour Boxplots: A Method for Characterizing Uncertainty in Feature Sets from Simulation Ensembles , 2013, IEEE Transactions on Visualization and Computer Graphics.

[8]  Bülent Sankur,et al.  A framework for histogram-induced 3D descriptors , 2006, 2006 14th European Signal Processing Conference.

[9]  J. Deasy,et al.  Associations between volume changes and spatial dose metrics for the urinary bladder during local versus pelvic irradiation for prostate cancer , 2017, Acta oncologica.

[10]  M. Sheelagh T. Carpendale,et al.  Empirical Studies in Information Visualization: Seven Scenarios , 2012, IEEE Transactions on Visualization and Computer Graphics.

[11]  Eduard Gröller,et al.  VAPOR: Visual Analytics for the Exploration of Pelvic Organ Variability in Radiotherapy , 2020, Comput. Graph..

[12]  Eduard Gröller,et al.  Pelvis Runner: Visualizing Pelvic Organ Variability in a Cohort of Radiotherapy Patients , 2019, VCBM.

[13]  Bernhard Preim,et al.  Visual Analytics of Image-Centric Cohort Studies in Epidemiology , 2015, Visualization in Medicine and Life Sciences III.

[14]  Bülent Sankur,et al.  3D Model Retrieval Using Probability Density-Based Shape Descriptors , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Renata G. Raidou Uncertainty Visualization: Recent Developments and Future Challenges in Prostate Cancer Radiotherapy Planning , 2018, EuroRV³@EuroVis.

[16]  Ludvig P Muren,et al.  Adaptive radiotherapy in locally advanced prostate cancer using a statistical deformable motion model , 2013, Acta oncologica.

[17]  A. Wentzel,et al.  Cohort-based T-SSIM Visual Computing for Radiation Therapy Prediction and Exploration , 2019, IEEE Transactions on Visualization and Computer Graphics.

[18]  L. Muren,et al.  Organ motion, set-up variation and treatment margins in radical radiotherapy of urinary bladder cancer. , 2003, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[19]  Ludvig P Muren,et al.  Treatment simulations with a statistical deformable motion model to evaluate margins for multiple targets in radiotherapy for high-risk prostate cancer. , 2013, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[20]  J. Reiber,et al.  Integrated Visual Analysis for Heterogeneous Datasets in Cohort Studies , 2010 .

[21]  Reinhard Klein,et al.  A Visual Analytics Approach to Study Anatomic Covariation , 2014, 2014 IEEE Pacific Visualization Symposium.

[22]  Elmar Eisemann,et al.  Cytosplore: Interactive Immune Cell Phenotyping for Large Single‐Cell Datasets , 2016, Comput. Graph. Forum.

[23]  Marcel Breeuwer,et al.  Visual Analysis of Tumor Control Models for Prediction of Radiotherapy Response , 2016, Comput. Graph. Forum.

[24]  Arjan Bel,et al.  A voxel-based finite element model for the prediction of bladder deformation. , 2011, Medical physics.

[25]  Bernd Hamann,et al.  Modeling and Visualization of Uncertainty-Aware Geometry Using Multi-variate Normal Distributions , 2018, 2018 IEEE Pacific Visualization Symposium (PacificVis).

[26]  Pascal Haigron,et al.  Population model of bladder motion and deformation based on dominant eigenmodes and mixed‐effects models in prostate cancer radiotherapy , 2017, Medical Image Anal..

[27]  Anna Vilanova,et al.  Uncertainty evaluation of image-based tumour control probability models in radiotherapy of prostate cancer using a visual analytic tool , 2018, Physics and imaging in radiation oncology.

[28]  Bernhard Preim,et al.  State‐of‐the‐Art Report: Visual Computing in Radiation Therapy Planning , 2019, Comput. Graph. Forum.

[29]  Brian Everitt,et al.  Cluster analysis , 1974 .

[30]  Stefan Wesarg,et al.  Visual Analytics for model-based medical image segmentation: Opportunities and challenges , 2013, Expert Syst. Appl..

[31]  Reinhard Klein,et al.  Accurate Interactive Visualization of Large Deformations and Variability in Biomedical Image Ensembles , 2016, IEEE Transactions on Visualization and Computer Graphics.

[32]  Kai Lawonn,et al.  Visualization and Analysis of Lumbar Spine Canal Variability in Cohort Study Data , 2013, VMV.

[33]  Hans Hagen,et al.  Intuitive Error Space Exploration of Medical Image Data in Clinical Daily Routine , 2017, EuroVis.

[34]  M. Alber,et al.  Modelling individual geometric variation based on dominant eigenmodes of organ deformation: implementation and evaluation , 2005, Physics in medicine and biology.

[35]  Charl P. Botha,et al.  Eurographics/ Ieee-vgtc Symposium on Visualization 2010 Dynamic Multi-view Exploration of Shape Spaces , 2022 .

[36]  Elmar Eisemann,et al.  VarVis: Visualizing Anatomical Variation in Branching Structures , 2016, EuroVis.

[37]  Charl P. Botha,et al.  Image-based rendering of intersecting surfaces for dynamic comparative visualization , 2011, The Visual Computer.

[38]  Luiza Bondar,et al.  Statistical modeling of CTV motion and deformation for IMRT of early-stage rectal cancer. , 2014, International journal of radiation oncology, biology, physics.

[39]  L Bondar,et al.  A population-based model to describe geometrical uncertainties in radiotherapy: applied to prostate cases , 2011, Physics in medicine and biology.

[40]  Lawrence B Marks,et al.  Radiation dose-volume effects of the urinary bladder. , 2010, International journal of radiation oncology, biology, physics.

[41]  Marcel Breeuwer,et al.  Visual Analytics for the Exploration and Assessment of Segmentation Errors , 2016, VCBM/MedViz.

[42]  Horst K. Hahn,et al.  Uncertainty in medical visualization: Towards a taxonomy , 2014, Comput. Graph..

[43]  Marcel Breeuwer,et al.  Comparative Visual Analysis of Pelvic Organ Segmentations , 2018, EuroVis.

[44]  R. L. Thorndike Who belongs in the family? , 1953 .

[45]  Junpeng Wang,et al.  Visualization and Visual Analysis of Ensemble Data: A Survey , 2019, IEEE Transactions on Visualization and Computer Graphics.

[46]  Cynthia A. Brewer,et al.  ColorBrewer.org: An Online Tool for Selecting Colour Schemes for Maps , 2003 .

[47]  Eduard Gröller,et al.  Bladder Runner: Visual Analytics for the Exploration of RT‐Induced Bladder Toxicity in a Cohort Study , 2018, Comput. Graph. Forum.

[48]  Georges G. Grinstein,et al.  Dimensional anchors: a graphic primitive for multidimensional multivariate information visualizations , 1999, NPIVM '99.

[49]  Kai Lawonn,et al.  Interactive Visual Analysis of Image-Centric Cohort Study Data , 2014, IEEE Transactions on Visualization and Computer Graphics.

[50]  Jake Van Dyk,et al.  Experience-driven dose-volume histogram maps of NTCP risk as an aid for radiation treatment plan selection and optimization. , 2007, Medical physics.