1
|
Liang B, Tan J, Lozenski L, Hormuth DA, Yankeelov TE, Villa U, Faghihi D. Bayesian Inference of Tissue Heterogeneity for Individualized Prediction of Glioma Growth. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:2865-2875. [PMID: 37058375 PMCID: PMC10599765 DOI: 10.1109/tmi.2023.3267349] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
Reliably predicting the future spread of brain tumors using imaging data and on a subject-specific basis requires quantifying uncertainties in data, biophysical models of tumor growth, and spatial heterogeneity of tumor and host tissue. This work introduces a Bayesian framework to calibrate the two-/three-dimensional spatial distribution of the parameters within a tumor growth model to quantitative magnetic resonance imaging (MRI) data and demonstrates its implementation in a pre-clinical model of glioma. The framework leverages an atlas-based brain segmentation of grey and white matter to establish subject-specific priors and tunable spatial dependencies of the model parameters in each region. Using this framework, the tumor-specific parameters are calibrated from quantitative MRI measurements early in the course of tumor development in four rats and used to predict the spatial development of the tumor at later times. The results suggest that the tumor model, calibrated by animal-specific imaging data at one time point, can accurately predict tumor shapes with a Dice coefficient 0.89. However, the reliability of the predicted volume and shape of tumors strongly relies on the number of earlier imaging time points used for calibrating the model. This study demonstrates, for the first time, the ability to determine the uncertainty in the inferred tissue heterogeneity and the model-predicted tumor shape.
Collapse
|
2
|
Static-Dynamic coordinated Transformer for Tumor Longitudinal Growth Prediction. Comput Biol Med 2022; 148:105922. [DOI: 10.1016/j.compbiomed.2022.105922] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2022] [Revised: 07/18/2022] [Accepted: 07/30/2022] [Indexed: 11/20/2022]
|
3
|
Wu C, Lorenzo G, Hormuth DA, Lima EABF, Slavkova KP, DiCarlo JC, Virostko J, Phillips CM, Patt D, Chung C, Yankeelov TE. Integrating mechanism-based modeling with biomedical imaging to build practical digital twins for clinical oncology. BIOPHYSICS REVIEWS 2022; 3:021304. [PMID: 35602761 PMCID: PMC9119003 DOI: 10.1063/5.0086789] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Accepted: 04/29/2022] [Indexed: 12/11/2022]
Abstract
Digital twins employ mathematical and computational models to virtually represent a physical object (e.g., planes and human organs), predict the behavior of the object, and enable decision-making to optimize the future behavior of the object. While digital twins have been widely used in engineering for decades, their applications to oncology are only just emerging. Due to advances in experimental techniques quantitatively characterizing cancer, as well as advances in the mathematical and computational sciences, the notion of building and applying digital twins to understand tumor dynamics and personalize the care of cancer patients has been increasingly appreciated. In this review, we present the opportunities and challenges of applying digital twins in clinical oncology, with a particular focus on integrating medical imaging with mechanism-based, tissue-scale mathematical modeling. Specifically, we first introduce the general digital twin framework and then illustrate existing applications of image-guided digital twins in healthcare. Next, we detail both the imaging and modeling techniques that provide practical opportunities to build patient-specific digital twins for oncology. We then describe the current challenges and limitations in developing image-guided, mechanism-based digital twins for oncology along with potential solutions. We conclude by outlining five fundamental questions that can serve as a roadmap when designing and building a practical digital twin for oncology and attempt to provide answers for a specific application to brain cancer. We hope that this contribution provides motivation for the imaging science, oncology, and computational communities to develop practical digital twin technologies to improve the care of patients battling cancer.
Collapse
Affiliation(s)
- Chengyue Wu
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas 78712, USA
| | | | | | | | - Kalina P. Slavkova
- Department of Physics, The University of Texas at Austin, Austin, Texas 78712, USA
| | | | | | - Caleb M. Phillips
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas 78712, USA
| | - Debra Patt
- Texas Oncology, Austin, Texas 78731, USA
| | - Caroline Chung
- Department of Radiation Oncology, MD Anderson Cancer Center, University of Texas, Houston, Texas 77030, USA
| | | |
Collapse
|
4
|
Chemotherapy response prediction with diffuser elapser network. Sci Rep 2022; 12:1628. [PMID: 35102179 PMCID: PMC8803972 DOI: 10.1038/s41598-022-05460-z] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2021] [Accepted: 11/10/2021] [Indexed: 12/31/2022] Open
Abstract
AbstractIn solid tumors, elevated fluid pressure and inadequate blood perfusion resulting from unbalanced angiogenesis are the prominent reasons for the ineffective drug delivery inside tumors. To normalize the heterogeneous and tortuous tumor vessel structure, antiangiogenic treatment is an effective approach. Additionally, the combined therapy of antiangiogenic agents and chemotherapy drugs has shown promising effects on enhanced drug delivery. However, the need to find the appropriate scheduling and dosages of the combination therapy is one of the main problems in anticancer therapy. Our study aims to generate a realistic response to the treatment schedule, making it possible for future works to use these patient-specific responses to decide on the optimal starting time and dosages of cytotoxic drug treatment. Our dataset is based on our previous in-silico model with a framework for the tumor microenvironment, consisting of a tumor layer, vasculature network, interstitial fluid pressure, and drug diffusion maps. In this regard, the chemotherapy response prediction problem is discussed in the study, putting forth a proof of concept for deep learning models to capture the tumor growth and drug response behaviors simultaneously. The proposed model utilizes multiple convolutional neural network submodels to predict future tumor microenvironment maps considering the effects of ongoing treatment. Since the model has the task of predicting future tumor microenvironment maps, we use two image quality evaluation metrics, which are structural similarity and peak signal-to-noise ratio, to evaluate model performance. We track tumor cell density values of ground truth and predicted tumor microenvironments. The model predicts tumor microenvironment maps seven days ahead with the average structural similarity score of 0.973 and the average peak signal ratio of 35.41 in the test set. It also predicts tumor cell density at the end day of 7 with the mean absolute percentage error of $$2.292\pm 1.820$$
2.292
±
1.820
.
Collapse
|
5
|
Bridging cell-scale simulations and radiologic images to explain short-time intratumoral oxygen fluctuations. PLoS Comput Biol 2021; 17:e1009206. [PMID: 34310608 PMCID: PMC8341701 DOI: 10.1371/journal.pcbi.1009206] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2021] [Revised: 08/05/2021] [Accepted: 06/22/2021] [Indexed: 11/19/2022] Open
Abstract
Radiologic images provide a way to monitor tumor development and its response to therapies in a longitudinal and minimally invasive fashion. However, they operate on a macroscopic scale (average value per voxel) and are not able to capture microscopic scale (cell-level) phenomena. Nevertheless, to examine the causes of frequent fast fluctuations in tissue oxygenation, models simulating individual cells’ behavior are needed. Here, we provide a link between the average data values recorded for radiologic images and the cellular and vascular architecture of the corresponding tissues. Using hybrid agent-based modeling, we generate a set of tissue morphologies capable of reproducing oxygenation levels observed in radiologic images. We then use these in silico tissues to investigate whether oxygen fluctuations can be explained by changes in vascular oxygen supply or by modulations in cellular oxygen absorption. Our studies show that intravascular changes in oxygen supply reproduce the observed fluctuations in tissue oxygenation in all considered regions of interest. However, larger-magnitude fluctuations cannot be recreated by modifications in cellular absorption of oxygen in a biologically feasible manner. Additionally, we develop a procedure to identify plausible tissue morphologies for a given temporal series of average data from radiology images. In future applications, this approach can be used to generate a set of tissues comparable with radiology images and to simulate tumor responses to various anti-cancer treatments at the tissue-scale level. Low levels of oxygen, called hypoxia, are observable in many solid tumors. They are associated with more aggressive malignant cells that are resistant to chemo-, radio-, and immunotherapies. Recently developed imaging techniques provide a way to measure the magnitude of frequent short-term oxygen fluctuations, but they operate on a macro-scale voxel level. To examine the possible causes of rapid oxygen fluctuations at the cell level, we developed a hybrid agent-based mathematical model. We tested two different mechanisms that may be responsible for these cyclic effects on tissue oxygenation: temporal variations in vascular influx of oxygen and modulations in cellular oxygen absorption. Additionally, we developed a procedure to identify plausible tissue morphologies from data collected from radiological images. This can provide a bridge between the micro-scale simulations with individual cells and the longitudinal medical images containing average values. In future applications, this approach can be used to generate a set of tissues compatible with radiology images and to simulate tumor responses to various anticancer treatments at the cell-scale level.
Collapse
|
6
|
Lee D, Alam SR, Jiang J, Zhang P, Nadeem S, Hu YC. Deformation driven Seq2Seq longitudinal tumor and organs-at-risk prediction for radiotherapy. Med Phys 2021; 48:4784-4798. [PMID: 34245602 DOI: 10.1002/mp.15075] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Revised: 05/21/2021] [Accepted: 06/07/2021] [Indexed: 11/06/2022] Open
Abstract
PURPOSE Radiotherapy presents unique challenges and clinical requirements for longitudinal tumor and organ-at-risk (OAR) prediction during treatment. The challenges include tumor inflammation/edema and radiation-induced changes in organ geometry, whereas the clinical requirements demand flexibility in input/output sequence timepoints to update the predictions on rolling basis and the grounding of all predictions in relationship to the pre-treatment imaging information for response and toxicity assessment in adaptive radiotherapy. METHODS To deal with the aforementioned challenges and to comply with the clinical requirements, we present a novel 3D sequence-to-sequence model based on Convolution Long Short-Term Memory (ConvLSTM) that makes use of series of deformation vector fields (DVFs) between individual timepoints and reference pre-treatment/planning CTs to predict future anatomical deformations and changes in gross tumor volume as well as critical OARs. High-quality DVF training data are created by employing hyper-parameter optimization on the subset of the training data with DICE coefficient and mutual information metric. We validated our model on two radiotherapy datasets: a publicly available head-and-neck dataset (28 patients with manually contoured pre-, mid-, and post-treatment CTs), and an internal non-small cell lung cancer dataset (63 patients with manually contoured planning CT and 6 weekly CBCTs). RESULTS The use of DVF representation and skip connections overcomes the blurring issue of ConvLSTM prediction with the traditional image representation. The mean and standard deviation of DICE for predictions of lung GTV at weeks 4, 5, and 6 were 0.83 ± 0.09, 0.82 ± 0.08, and 0.81 ± 0.10, respectively, and for post-treatment ipsilateral and contralateral parotids, were 0.81 ± 0.06 and 0.85 ± 0.02. CONCLUSION We presented a novel DVF-based Seq2Seq model for medical images, leveraging the complete 3D imaging information of a relatively large longitudinal clinical dataset, to carry out longitudinal GTV/OAR predictions for anatomical changes in HN and lung radiotherapy patients, which has potential to improve RT outcomes.
Collapse
Affiliation(s)
- Donghoon Lee
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Sadegh R Alam
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Jue Jiang
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Pengpeng Zhang
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Saad Nadeem
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Yu-Chi Hu
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| |
Collapse
|
7
|
A simple, open and extensible gating Control unit for cardiac and respiratory synchronisation control in small animal MRI and demonstration of its robust performance in steady-state maintained CINE-MRI. Magn Reson Imaging 2021; 81:1-9. [PMID: 33905831 PMCID: PMC8274699 DOI: 10.1016/j.mri.2021.04.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2020] [Accepted: 04/22/2021] [Indexed: 11/22/2022]
Abstract
Prospective cardiac gating during MRI is hampered by electromagnetic induction from the rapidly switched imaging gradients into the ECG detection circuit. This is particularly challenging in small animal MRI, as higher heart rates combined with a smaller myocardial mass render routine ECG detection challenging. We have developed an open-hardware system that enables continuously running MRI scans to be performed in conjunction with cardio-respiratory gating such that the relaxation-weighted steady state magnetisation is maintained throughout the scan. This requires that the R-wave must be detected reliably even in the presence of rapidly switching gradients, and that data previously acquired that were corrupted by respiratory motion re-acquired. The accurately maintained steady-state magnetisation leads to an improvement in image quality and removes alterations in intensity that may otherwise occur throughout the cardiac cycle and impact upon automated image analysis. We describe the hardware required to enable this and demonstrate its application and robust performance using prospectively cardio-respiratory gated CINE imaging that is operated at a single, constant TR. Schematics, technical drawings, component listing and assembly instructions are made publicly available.
Collapse
|
8
|
Sosa-Marrero C, de Crevoisier R, Hernandez A, Fontaine P, Rioux-Leclercq N, Mathieu R, Fautrel A, Paris F, Acosta O. Towards a Reduced In Silico Model Predicting Biochemical Recurrence After Radiotherapy in Prostate Cancer. IEEE Trans Biomed Eng 2021; 68:2718-2729. [PMID: 33460366 DOI: 10.1109/tbme.2021.3052345] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
OBJECTIVE Purposes of this work were i) to develop an in silico model of tumor response to radiotherapy, ii) to perform an exhaustive sensitivity analysis in order to iii) propose a simplified version and iv) to predict biochemical recurrence with both the comprehensive and the reduced model. METHODS A multiscale computational model of tumor response to radiotherapy was developed. It integrated the following radiobiological mechanisms: oxygenation, including hypoxic death; division of tumor cells; VEGF diffusion driving angiogenesis; division of healthy cells and oxygen-dependent response to irradiation, considering, cycle arrest and mitotic catastrophe. A thorough sensitivity analysis using the Morris screening method was performed on 21 prostate computational tissues. Tumor control probability (TCP) curves of the comprehensive model and 15 reduced versions were compared. Logistic regression was performed to predict biochemical recurrence after radiotherapy on 76 localized prostate cancer patients using an output of the comprehensive and the reduced models. RESULTS No significant difference was found between the TCP curves of the comprehensive and a simplified version which only considered oxygenation, division of tumor cells and their response to irradiation. Biochemical recurrence predictions using the comprehensive and the reduced models improved those made from pre-treatment imaging parameters (AUC = 0.81 ± 0.02 and 0.82 ± 0.02 vs. 0.75 ± 0.03, respectively). CONCLUSION A reduced model of tumor response to radiotherapy able to predict biochemical recurrence in prostate cancer was obtained. SIGNIFICANCE This reduced model may be used in the future to optimize personalized fractionation schedules.
Collapse
|
9
|
Jarrett AM, Hormuth DA, Wu C, Kazerouni AS, Ekrut DA, Virostko J, Sorace AG, DiCarlo JC, Kowalski J, Patt D, Goodgame B, Avery S, Yankeelov TE. Evaluating patient-specific neoadjuvant regimens for breast cancer via a mathematical model constrained by quantitative magnetic resonance imaging data. Neoplasia 2020; 22:820-830. [PMID: 33197744 PMCID: PMC7677708 DOI: 10.1016/j.neo.2020.10.011] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2020] [Revised: 10/19/2020] [Accepted: 10/21/2020] [Indexed: 12/12/2022]
Abstract
The ability to accurately predict response and then rigorously optimize a therapeutic regimen on a patient-specific basis, would transform oncology. Toward this end, we have developed an experimental-mathematical framework that integrates quantitative magnetic resonance imaging (MRI) data into a biophysical model to predict patient-specific treatment response of locally advanced breast cancer to neoadjuvant therapy. Diffusion-weighted and dynamic contrast-enhanced MRI data is collected prior to therapy, after 1 cycle of therapy, and at the completion of the first therapeutic regimen. The model is initialized and calibrated with the first 2 patient-specific MRI data sets to predict response at the third, which is then compared to patient outcomes (N = 18). The model's predictions for total cellularity, total volume, and the longest axis at the completion of the regimen are significant within expected measurement precision (P< 0.05) and strongly correlated with measured response (P < 0.01). Further, we use the model to investigate, in silico, a range of (practical) alternative treatment plans to achieve the greatest possible tumor control for each individual in a subgroup of patients (N = 13). The model identifies alternative dosing strategies predicted to achieve greater tumor control compared to the standard of care for 12 of 13 patients (P < 0.01). In summary, a predictive, mechanism-based mathematical model has demonstrated the ability to identify alternative treatment regimens that are forecasted to outperform the therapeutic regimens the patients clinically. This has important implications for clinical trial design with the opportunity to alter oncology care in the future.
Collapse
Affiliation(s)
- Angela M Jarrett
- Oden Institute for Computational Engineering and Sciences, Austin, TX, USA; Livestrong Cancer Institutes, Austin, TX, USA
| | - David A Hormuth
- Oden Institute for Computational Engineering and Sciences, Austin, TX, USA; Livestrong Cancer Institutes, Austin, TX, USA
| | - Chengyue Wu
- Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX, USA
| | - Anum S Kazerouni
- Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX, USA
| | - David A Ekrut
- Oden Institute for Computational Engineering and Sciences, Austin, TX, USA
| | - John Virostko
- Livestrong Cancer Institutes, Austin, TX, USA; Department of Diagnostic Medicine, The University of Texas at Austin, Austin, TX, USA; Department of Oncology, The University of Texas at Austin, Austin, TX, USA
| | - Anna G Sorace
- Department of Radiology, University of Alabama at Birmingham, Birmingham, AL, USA; Department of Biomedical Engineering, University of Alabama at Birmingham, Birmingham, AL, USA; O'Neal Comprehensive Cancer Center, University of Alabama at Birmingham, Birmingham, AL, USA
| | - Julie C DiCarlo
- Oden Institute for Computational Engineering and Sciences, Austin, TX, USA
| | - Jeanne Kowalski
- Livestrong Cancer Institutes, Austin, TX, USA; Department of Oncology, The University of Texas at Austin, Austin, TX, USA
| | | | - Boone Goodgame
- Department of Oncology, The University of Texas at Austin, Austin, TX, USA; Department of Internal Medicine, The University of Texas at Austin, Austin, TX, USA; Seton Hospital, Austin, TX, USA
| | - Sarah Avery
- Austin Radiological Association, Austin, TX, USA
| | - Thomas E Yankeelov
- Oden Institute for Computational Engineering and Sciences, Austin, TX, USA; Livestrong Cancer Institutes, Austin, TX, USA; Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX, USA; Department of Diagnostic Medicine, The University of Texas at Austin, Austin, TX, USA; Department of Oncology, The University of Texas at Austin, Austin, TX, USA; Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA.
| |
Collapse
|
10
|
Mang A, Bakas S, Subramanian S, Davatzikos C, Biros G. Integrated Biophysical Modeling and Image Analysis: Application to Neuro-Oncology. Annu Rev Biomed Eng 2020; 22:309-341. [PMID: 32501772 PMCID: PMC7520881 DOI: 10.1146/annurev-bioeng-062117-121105] [Citation(s) in RCA: 28] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/09/2023]
Abstract
Central nervous system (CNS) tumors come with vastly heterogeneous histologic, molecular, and radiographic landscapes, rendering their precise characterization challenging. The rapidly growing fields of biophysical modeling and radiomics have shown promise in better characterizing the molecular, spatial, and temporal heterogeneity of tumors. Integrative analysis of CNS tumors, including clinically acquired multi-parametric magnetic resonance imaging (mpMRI) and the inverse problem of calibrating biophysical models to mpMRI data, assists in identifying macroscopic quantifiable tumor patterns of invasion and proliferation, potentially leading to improved (a) detection/segmentation of tumor subregions and (b) computer-aided diagnostic/prognostic/predictive modeling. This article presents a summary of (a) biophysical growth modeling and simulation,(b) inverse problems for model calibration, (c) these models' integration with imaging workflows, and (d) their application to clinically relevant studies. We anticipate that such quantitative integrative analysis may even be beneficial in a future revision of the World Health Organization (WHO) classification for CNS tumors, ultimately improving patient survival prospects.
Collapse
Affiliation(s)
- Andreas Mang
- Department of Mathematics, University of Houston, Houston, Texas 77204, USA;
| | - Spyridon Bakas
- Department of Mathematics, University of Houston, Houston, Texas 77204, USA;
| | - Shashank Subramanian
- Oden Institute of Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas 78712, USA; ,
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics (CBICA); Department of Radiology; and Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania 19104, USA; ,
| | - George Biros
- Oden Institute of Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas 78712, USA; ,
| |
Collapse
|
11
|
Zhang L, Lu L, Wang X, Zhu RM, Bagheri M, Summers RM, Yao J. Spatio-Temporal Convolutional LSTMs for Tumor Growth Prediction by Learning 4D Longitudinal Patient Data. IEEE TRANSACTIONS ON MEDICAL IMAGING 2020; 39:1114-1126. [PMID: 31562074 PMCID: PMC7213057 DOI: 10.1109/tmi.2019.2943841] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Prognostic tumor growth modeling via volumetric medical imaging observations can potentially lead to better outcomes of tumor treatment management and surgical planning. Recent advances of convolutional networks (ConvNets) have demonstrated higher accuracy than traditional mathematical models can be achieved in predicting future tumor volumes. This indicates that deep learning based data-driven techniques may have great potentials on addressing such problem. However, current 2D image patch based modeling approaches can not make full use of the spatio-temporal imaging context of the tumor's longitudinal 4D (3D + time) patient data. Moreover, they are incapable to predict clinically-relevant tumor properties, other than the tumor volumes. In this paper, we exploit to formulate the tumor growth process through convolutional Long Short-Term Memory (ConvLSTM) that extract tumor's static imaging appearances and simultaneously capture its temporal dynamic changes within a single network. We extend ConvLSTM into the spatio-temporal domain (ST-ConvLSTM) by jointly learning the inter-slice 3D contexts and the longitudinal or temporal dynamics from multiple patient studies. Our approach can incorporate other non-imaging patient information in an end-to-end trainable manner. Experiments are conducted on the largest 4D longitudinal tumor dataset of 33 patients to date. Results validate that the proposed ST-ConvLSTM model produces a Dice score of 83.2%±5.1% and a RVD of 11.2%±10.8%, both statistically significantly outperforming (p < 0.05) other compared methods of traditional linear model, ConvLSTM, and generative adversarial network (GAN) under the metric of predicting future tumor volumes. Additionally, our new method enables the prediction of both cell density and CT intensity numbers. Last, we demonstrate the generalizability of ST-ConvLSTM by employing it in 4D medical image segmentation task, which achieves an averaged Dice score of 86.3%±1.2% for left-ventricle segmentation in 4D ultrasound with 3 seconds per patient case.
Collapse
|
12
|
Abstract
The Quantitative Imaging Network of the National Cancer Institute is in its 10th year of operation, and research teams within the network are developing and validating clinical decision support software tools to measure or predict the response of cancers to various therapies. As projects progress from development activities to validation of quantitative imaging tools and methods, it is important to evaluate the performance and clinical readiness of the tools before committing them to prospective clinical trials. A variety of tests, including special challenges and tool benchmarking, have been instituted within the network to prepare the quantitative imaging tools for service in clinical trials. This article highlights the benchmarking process and provides a current evaluation of several tools in their transition from development to validation.
Collapse
Affiliation(s)
- Keyvan Farahani
- Cancer Imaging Program, National Cancer Institute of NIH, Bethesda, MD
| | - Darrell Tata
- Cancer Imaging Program, National Cancer Institute of NIH, Bethesda, MD
| | | |
Collapse
|
13
|
Hormuth DA, Jarrett AM, Yankeelov TE. Forecasting tumor and vasculature response dynamics to radiation therapy via image based mathematical modeling. Radiat Oncol 2020; 15:4. [PMID: 31898514 PMCID: PMC6941255 DOI: 10.1186/s13014-019-1446-2] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2019] [Accepted: 12/12/2019] [Indexed: 12/11/2022] Open
Abstract
Background Intra-and inter-tumoral heterogeneity in growth dynamics and vascularity influence tumor response to radiation therapy. Quantitative imaging techniques capture these dynamics non-invasively, and these data can initialize and constrain predictive models of response on an individual basis. Methods We have developed a family of 10 biologically-based mathematical models describing the spatiotemporal dynamics of tumor volume fraction, blood volume fraction, and response to radiation therapy. To evaluate this family of models, rats (n = 13) with C6 gliomas were imaged with magnetic resonance imaging (MRI) three times before, and four times following a single fraction of 20 Gy or 40 Gy whole brain irradiation. The first five 3D time series data of tumor volume fraction, estimated from diffusion-weighted (DW-) MRI, and blood volume fraction, estimated from dynamic contrast-enhanced (DCE-) MRI, were used to calibrate tumor-specific model parameters. The most parsimonious and well calibrated of the 10 models, selected using the Akaike information criterion, was then utilized to predict future growth and response at the final two imaging time points. Model predictions were compared at the global level (percent error in tumor volume, and Dice coefficient) as well as at the local or voxel level (concordance correlation coefficient). Result The selected model resulted in < 12% error in tumor volume predictions, strong spatial agreement between predicted and observed tumor volumes (Dice coefficient > 0.74), and high level of agreement at the voxel level between the predicted and observed tumor volume fraction and blood volume fraction (concordance correlation coefficient > 0.77 and > 0.65, respectively). Conclusions This study demonstrates that serial quantitative MRI data collected before and following radiation therapy can be used to accurately predict tumor and vasculature response with a biologically-based mathematical model that is calibrated on an individual basis. To the best of our knowledge, this is the first effort to characterize the tumor and vasculature response to radiation therapy temporally and spatially using imaging-driven mathematical models.
Collapse
Affiliation(s)
- David A Hormuth
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, 201 E. 24th Street, POB 4.102, 1 University Station (C0200), Austin, TX, USA. .,Livestrong Cancer Institutes, The University of Texas at Austin, Austin, TX, USA.
| | - Angela M Jarrett
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, 201 E. 24th Street, POB 4.102, 1 University Station (C0200), Austin, TX, USA.,Livestrong Cancer Institutes, The University of Texas at Austin, Austin, TX, USA
| | - Thomas E Yankeelov
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, 201 E. 24th Street, POB 4.102, 1 University Station (C0200), Austin, TX, USA.,Livestrong Cancer Institutes, The University of Texas at Austin, Austin, TX, USA.,Departments of Biomedical Engineering, The University of Texas at Austin, Austin, TX, USA.,Departments of Diagnostic Medicine, The University of Texas at Austin, Austin, TX, USA.,Departments of Oncology, The University of Texas at Austin, Austin, TX, USA
| |
Collapse
|
14
|
Pally D, Pramanik D, Bhat R. An Interplay Between Reaction-Diffusion and Cell-Matrix Adhesion Regulates Multiscale Invasion in Early Breast Carcinomatosis. Front Physiol 2019; 10:790. [PMID: 31456688 PMCID: PMC6700745 DOI: 10.3389/fphys.2019.00790] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2019] [Accepted: 06/04/2019] [Indexed: 12/12/2022] Open
Abstract
The progression of cancer in the breast involves multiple reciprocal interactions between malignantly transformed epithelia, surrounding untransformed but affected stromal cells, and the extracellular matrix (ECM) that is remodeled during the process. A quantitative understanding of the relative contribution of such interactions to phenotypes associated with cancer cells can be arrived at through the construction of increasingly complex experimental and computational models. Herein, we introduce a multiscale three-dimensional (3D) organo- and pathotypic experimental assay that approximates, to an unprecedented extent, the histopathological complexity of a tumor disseminating into its surrounding stromal milieu via both bulk and solitary motility dynamics. End point and time-lapse microscopic observations of this assay allow us to study the earliest steps of cancer invasion as well as the dynamical interactions between the epithelial and stromal compartments. We then simulate our experimental observations using the modeling environment Compucell3D that is based on the Glazier–Graner–Hogeweg model. The computational model, which comprises adhesion between cancer cells and the matrices, cell proliferation and apoptosis, and matrix remodeling through reaction–diffusion–based morphogen dynamics, is first trained to phenocopy controls run with the experimental model, wherein one or the other matrices have been removed. The trained computational model successfully predicts phenotypes of the experimental counterparts that are subjected to pharmacological treatments (inhibition of N-linked glycosylation and matrix metalloproteinase activity) and scaffold modulation (alteration of collagen density). Further parametric exploration-based simulations suggest that specific permissive regimes of cell–cell and cell–matrix adhesions, operating in the context of a reaction–diffusion–regulated ECM dynamics, promote multiscale invasion of breast cancer cells and determine the extent to which the latter migrate through their surrounding stroma.
Collapse
Affiliation(s)
- Dharma Pally
- Department of Molecular Reproduction, Development and Genetics, Indian Institute of Science, Bangalore, India
| | - Durjay Pramanik
- Department of Molecular Reproduction, Development and Genetics, Indian Institute of Science, Bangalore, India
| | - Ramray Bhat
- Department of Molecular Reproduction, Development and Genetics, Indian Institute of Science, Bangalore, India
| |
Collapse
|
15
|
Hormuth DA, Jarrett AM, Feng X, Yankeelov TE. Calibrating a Predictive Model of Tumor Growth and Angiogenesis with Quantitative MRI. Ann Biomed Eng 2019; 47:1539-1551. [PMID: 30963385 PMCID: PMC6544501 DOI: 10.1007/s10439-019-02262-9] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2019] [Accepted: 03/30/2019] [Indexed: 02/05/2023]
Abstract
The spatiotemporal variations in tumor vasculature inevitably alters cell proliferation and treatment efficacy. Thus, rigorous characterization of tumor dynamics must include a description of this phenomenon. We have developed a family of biophysical models of tumor growth and angiogenesis that are calibrated with diffusion-weighted magnetic resonance imaging (DW-MRI) and dynamic contrast-enhanced (DCE-) MRI data to provide individualized tumor growth forecasts. Tumor and blood volume fractions were evolved using two, coupled partial differential equations consisting of proliferation, diffusion, and death terms. To evaluate these models, rats (n = 8) with C6 gliomas were imaged seven times. The tumor volume fraction was estimated using DW-MRI, while DCE-MRI provided estimates of the blood volume fraction. The first three time points were used to calibrate model parameters, which were then used to predict growth at the remaining four time points and compared directly to the measurements. The best performing model predicted tumor growth with less than 10.3% error in tumor volume and with less than 9.4% error at the voxel-level at all prediction time points. The best performing model resulted in less than 9.3% error in blood volume at the voxel-level. This pre-clinical study demonstrates the potential for image-based, mechanistic modeling of tumor growth and angiogenesis.
Collapse
Affiliation(s)
- David A Hormuth
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, 201 E. 24th Street, POB 4.102, 1 University Station (C0200), Austin, TX, 78712-1229, USA.
- Livestrong Cancer Institutes, The University of Texas at Austin, Austin, TX, USA.
| | - Angela M Jarrett
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, 201 E. 24th Street, POB 4.102, 1 University Station (C0200), Austin, TX, 78712-1229, USA
- Livestrong Cancer Institutes, The University of Texas at Austin, Austin, TX, USA
| | - Xinzeng Feng
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, 201 E. 24th Street, POB 4.102, 1 University Station (C0200), Austin, TX, 78712-1229, USA
| | - Thomas E Yankeelov
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, 201 E. 24th Street, POB 4.102, 1 University Station (C0200), Austin, TX, 78712-1229, USA
- Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX, USA
- Department of Diagnostic Medicine, The University of Texas at Austin, Austin, TX, USA
- Department of Oncology, The University of Texas at Austin, Austin, TX, USA
- Livestrong Cancer Institutes, The University of Texas at Austin, Austin, TX, USA
| |
Collapse
|
16
|
Jarrett AM, Lima EABF, Hormuth DA, McKenna MT, Feng X, Ekrut DA, Resende ACM, Brock A, Yankeelov TE. Mathematical models of tumor cell proliferation: A review of the literature. Expert Rev Anticancer Ther 2018; 18:1271-1286. [PMID: 30252552 PMCID: PMC6295418 DOI: 10.1080/14737140.2018.1527689] [Citation(s) in RCA: 51] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Abstract
INTRODUCTION A defining hallmark of cancer is aberrant cell proliferation. Efforts to understand the generative properties of cancer cells span all biological scales: from genetic deviations and alterations of metabolic pathways to physical stresses due to overcrowding, as well as the effects of therapeutics and the immune system. While these factors have long been studied in the laboratory, mathematical and computational techniques are being increasingly applied to help understand and forecast tumor growth and treatment response. Advantages of mathematical modeling of proliferation include the ability to simulate and predict the spatiotemporal development of tumors across multiple experimental scales. Central to proliferation modeling is the incorporation of available biological data and validation with experimental data. Areas covered: We present an overview of past and current mathematical strategies directed at understanding tumor cell proliferation. We identify areas for mathematical development as motivated by available experimental and clinical evidence, with a particular emphasis on emerging, non-invasive imaging technologies. Expert commentary: The data required to legitimize mathematical models are often difficult or (currently) impossible to obtain. We suggest areas for further investigation to establish mathematical models that more effectively utilize available data to make informed predictions on tumor cell proliferation.
Collapse
Affiliation(s)
- Angela M Jarrett
- a Institute for Computational Engineering and Sciences , The University of Texas at Austin , Austin , USA
- b Livestrong Cancer Institutes , The University of Texas at Austin , Austin , USA
| | - Ernesto A B F Lima
- a Institute for Computational Engineering and Sciences , The University of Texas at Austin , Austin , USA
| | - David A Hormuth
- a Institute for Computational Engineering and Sciences , The University of Texas at Austin , Austin , USA
- b Livestrong Cancer Institutes , The University of Texas at Austin , Austin , USA
| | - Matthew T McKenna
- c Department of Biomedical Engineering , Vanderbilt University , Nashville , USA
| | - Xinzeng Feng
- a Institute for Computational Engineering and Sciences , The University of Texas at Austin , Austin , USA
| | - David A Ekrut
- a Institute for Computational Engineering and Sciences , The University of Texas at Austin , Austin , USA
| | - Anna Claudia M Resende
- a Institute for Computational Engineering and Sciences , The University of Texas at Austin , Austin , USA
- d Department of Computational Modeling , National Laboratory for Scientific Computing , Petrópolis , Brazil
| | - Amy Brock
- b Livestrong Cancer Institutes , The University of Texas at Austin , Austin , USA
- e Department of Biomedical Engineering , The University of Texas at Austin , Austin , USA
| | - Thomas E Yankeelov
- a Institute for Computational Engineering and Sciences , The University of Texas at Austin , Austin , USA
- b Livestrong Cancer Institutes , The University of Texas at Austin , Austin , USA
- e Department of Biomedical Engineering , The University of Texas at Austin , Austin , USA
- f Department of Diagnostic Medicine , The University of Texas at Austin , Austin , USA
- g Department of Oncology , The University of Texas at Austin , Austin , USA
| |
Collapse
|