Dr. Ying Xiao: Radiation Therapy Oncology Group Bioinformatics


Published on

On July 25. Dr. Ying Xiao delivered a presentation titled "RTOG - Radiation Therapy Oncology Group Bioinformatics."

Published in: Health & Medicine, Business
  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Dr. Ying Xiao: Radiation Therapy Oncology Group Bioinformatics

  1. 1. RTOG Bioinformatics Y. Xiao, Ph.D. RTOG, ACRRadiation Oncology, Jefferson Medical College 1
  2. 2. Evidence Based Radiation OncologyRadiation Therapy Oncology Group (RTOG)  Improve The Survival Outcome And Quality Of Life  Evaluate New Forms Of Radiotherapy Delivery  Test New Systemic Therapies In Conjunction With Radiotherapy  Employ Translational Research Strategies 2
  3. 3. RTOG Bioinformatics MissionTo facilitate the development and todevelop personalized predictive modelsfor radiation therapy guidance fromspecific characteristics of patients andtreatments with integrated clinical trialdatabases, bridging clinical science,physics, biology, information technologyand mathematics 3
  4. 4. BIOINFORMATICS ELEMENTS AND PROCEDURES Available to BioWGDatabase RT Dose/Images/Clinical Data Genomic/Proteomic BiomarkerData Analysis Protocol development/Protocol operation support/Trial Outcome-Secondary Analysis Validation/Development/Research 4
  5. 5. DATA/DATA Integration 5
  6. 6. RTOG DATA for BioWG InvestigationProtocol N Endpoints0022 oropharyngeal cancer 60 Salivary function0117 lung 73 Pneumonitis and esophagitis0126 prostate ~1500 Erectile dysfunction; rectal bleeding Fecal incontinence vs dose0225 nasopharyngeal 60 Salivary function0232 prostate brachytherapy0234 head and neck 230 TCP? Ongoing, not recruiting0236 lung SBRT 52 Ongoing: TCP, toxicity0321 prostate HDR brachy 110 Late/Acute GU/GI0522 head and neck Local control0529 IMRT anal canal cancer 59 GI/GU acute9311 lung ~150 NIH R01 (Deasy). Toxicity: esophagitis; pneumonitis9406 EBRT prostate 800 NIH R01 (Tucker) toxicity9803 3D CRT GBM 40 Brain toxicity 6
  7. 7. Rapid Learning CAT(Computer Assisted Theragnostics) MAASTRO/RTOG CollaborationAndre Dekker, PhDMAASTRO Knowledge Engineering 7
  8. 8. Why Rapid Learning/CAT?Personalized medicine improves survival and quality of life. Personalized medicine • Explosion of data • Explosion of decisions • Decision support • Evidence base [..] rapid learning [..] where we can learn from each patient to guide practice, is [..] crucial to guide rational health policy and to contain costs [..]. Lancet Oncol 2011;12:933 8
  9. 9. Prediction by MDs? • Non Small Cell Lung Cancer • 2 year survival • 30 patients • 8 MDs • AUC: 0.57 • Retrospective 9
  10. 10. How to getdata for rapid learning 10
  11. 11. Challenges to share data[..] the problem is not really technical […]. Rather, the problems areethical, political, and administrative. Lancet Oncol 2011;12:9331.Administrative (time)2.Political (value, authorship)3.Ethical (privacy)4.Technical 11
  12. 12. CAT approachCAT is a research project in whichwe develop an IT infrastructure -> technicalto make radiotherapy centerssemantic interoperable (SIOp*) -> administrativewhile the data stays inside your hospital -> ethicalunder your full control -> political* SIOp level 3 = Machine Readable ->Data in common syntax and with common meaning 12
  13. 13. Components CTMS PACS ETL ExportDistributed Deident. Learning & FilterApplication Ontology Sharing XML Query DICOM 13
  14. 14. Key features• No sharing of data, truly federated• Machine learning (retro.) & clinical trials (prosp.)• NCI Thesaurus with formal additions• 5 languages, 5 countries & 5 legal systems• Focus on radiotherapy• Inclusion of non-academic centers• Industry involvement 14
  15. 15. Network 11/2011 5 2 Active or funded CAT partners (10) Prospective centers (4)Map from cgadvertising.com 15
  16. 16. Laryngeal carcinoma model• 994 MAASTRO patients• 1990-2005• www.predictcancer.org• Input parameters – Age – Hemoglobin – T-stage – EDQ2T (Gy) – Gender – N+ – Tumor location• Output parameters – Overall survival www.predictcancer.org, Egelmeer et al., Radiother Oncol. 2011 Jul;100(1):108 16
  17. 17. Larynx Query 17
  18. 18. Validation - Result 18
  19. 19. Final Model Created Central ServerDistributed Update Learning ModelArchitecture Send Average Send Average Send Average Consensus Model Consensus Model Consensus Model Send Model Parameters Send Model Model Server Parameters RTOG Send Model Parameters Model Server Learn Model Model Server Roma MAASTRO from Local Data Learn Model Learn Model from Local Data from Local Data Only aggregate data is exchanged between the Central Server and the local Servers 19
  20. 20. Distributed Learning Results 20
  21. 21. Web-based Documentation System with Exchange of DICOM RT forMulticenter Clinical Studies in Particle Therapy Priv.-Doz. Dr. med. Stephanie E. Combs, DEGRO 2012 21
  22. 22. PARTICLE THERAPY• particle therapy is a new and promising technique in radiation oncology for cancer treatment• compared to standard radiation therapy (RT) with photons, it is with either – ions (e.g. Carbon C12, Helium He2, Oxygen O16) or – protons (H1)• advantages: − more precise dose delivery sparing of normal tissue and  to the target organs at risk − enhanced radiobiological  increase in local tumor control effectiveness (carbon ions) 22
  23. 23. What we need to do.....• First results of clinical phase I and II trials performed at NIRS support the assumption that carbon ions provide an enhanced biological effectiveness in adenoid cystic carcinomas, H/N melanomas, lung and liver tumors, large soft tissue sarcomas, chordomas / chondrosarcomas and prostate cancer• Randomized trials proving the superiority of heavy charged particles in comparison to photon IMRT and protons required – Randomized trial of proton vs. Carbon ion RT for chordomas and chondrosarcomas of the skull base• Radiobiologic research will enable better exploitation of the advantages of carbon ion RT in future trials• Physics Research: e.g.High Precision Treatment of Moving Targets 23
  24. 24. HIT HEIDELBERG ION-BEAM THERAPY CENTER• began patient treatment in Nov. 2009• main focus: – clinical studies to evaluate the benefits of ion therapy for several indications• ULICE project (Union of Light Ions Centers in Europe) – development of a database with transnational access – platform for international clinical multicenter studies – accessible by external/internal oncologists, physicists, researchers 24
  25. 25. Establish a common database for hadrontherapy.- few centers have treated patients with particle therapy- heterogeneous concepts of dose prescription, delivery- hetereogeneous studies and treatment protocols ULICE DATABASE Harmonized ULICE DATABASE Exchange of study and clinical treatment experience concept Standards and Transfer of basic (biologic) know-how data 25
  26. 26. METHODS• Approach: – central, web-based system – interfaces to the mandatory existing information systems of the hospital – avoidance of redundant entry of any patient/clinical data – study-specific modules, which can easily be adapted – implementation of security and data protection measures to fulfill legal requirements 26 Kessel K., ..., Combs SE, Radiat Oncol, 7, 115 (2012).
  27. 27. GENERAL PRINCIPLES AND ARCHITECTURE• database with standard interfaces of the PACS world – storage of all data in an SQL database (DICOM data model) – possibility to dynamically extend with additional data structures – interfaces to process and import information from • DICOM data • HL7 messages – Java applet for • manual import of data by web-upload • receiving and sending data with DICOM C-Store – the underlying components are compliant with the IHE Framework• telemedicine record – combines the functionality of • a medical record with • a professional DICOM RT viewer (Class IIb) – allows us to exchange, store, process and visualize text data, all types of DICOM images, and any other multimedia data – with extensions for study documentation 27 Kessel K., ..., Combs SE, Radiat Oncol, 7, 115 (2012).
  28. 28. INTEGRATION OF OTHER INFORMATION SYSTEMS 28 Kessel K., ..., Combs SE, Radiat Oncol
  29. 29. SECURITY CONCEPT• the system uses the encrypted https protocol to exchange data between the central server and other systems• users need an account and password to access the system• a roles-and-rights concept enables a very detailed configuration for each study or client• (basic patient) data can be pseudonymized – the original patient information is kept in a separate database – when a user has the right to view all data of a patient, the data is de- pseudonymized “on the fly”• external users – communication via application gateway in the demilitarized zone (DMZ) – client certificates to verify authorized browsers 29 Kessel K., ..., Combs SE, Radiat Oncol, 7, 115 (2012).
  30. 30. RESULTS• documentation began May 2011 and we documented 900 patients• all access to the system takes place over the Internet – no software needs to be installed (except a JRE)• exchange and storage of various DICOM RT data• visualization with the DICOM RT ion viewer – examination and review of radiation plans from every computer in the hospital without having to go to a PACS or a radiation therapy planning station• with our web-based approach, we have succeeded in developing a database for multicenter studies within the ULICE project• future prospects: extend automatic and electronic study analyses 30 Kessel K., ..., Combs SE, Radiat Oncol, 7, 115 (2012).
  31. 31. More to IntegrateAndre Dekker, PhDMAASTRO Knowledge Engineering 31
  32. 32. How to learn better?• AUC of 0.85 is needed• Survival model AUC 0.75• More patients• More variables• Diversity 32
  33. 33. More variables from a simple CT 33
  34. 34. Biomarkers LOO-AUC 0.76 Selected biomarkers: IL6, IL8, CEA General LOO-AUC = 0.72: Gender, WHO, FEV1, Positive lymph nodes,Radiomics Tumor Volume LOO-AUC 0.75 Selected image features: CT Range, Cluster Shade, Run Percentage (n = 150) 34
  35. 35. Biomarkers General Radiomics AUC 0.87 Biomarker: IL6, IL8, CEA General: Gender, WHO-PS, FEV1, Positive lymph nodes, Tumor Volume n = 131 35 Radiomics: Range, Run Length, Run Percentage
  36. 36. DATA ANALYSIS 36
  37. 37. DATA ANALYSIS- Evidence Based RadiationTherapy Quality Assurance 37
  38. 38. DATA ANALYSIS- Evidence Based Radiation Therapy Quality Assurance (Structure Definition) 38
  39. 39. Critical Impact of Radiotherapy Protocol Compliance and Quality TROG 02.02 L. J. Peters et al, Journal of Clinical Oncology, vol. 28, Number 18, June 2010 39
  40. 40. Failure To Adhere To Protocol Associated With Decreased Survival: RTOG 9704 40 R. Abrams et al, Int. J. Radiation Oncology Biol. Phys., Vol. 82, No. 2, pp. 809–816, 2012
  41. 41. Target Defined from Multiple Institutions S. Kong, Y. Xiao, M. Machtay, et. Al., A “Dry-Run” Study for RTOG1106/ACRIN6697: A Randomized Phase II Trial of Using During-Treatment FDG-PET and Modern Technology to Individualize Adaptive Radiation 41 Therapy in Stage III NSCLC ,IASLC, 2011
  42. 42. Target Inter-Observer Variability Pre-GTV Statistics 42
  43. 43. 43 The maximum volume of brach (brachial plexus) is up to 4-5 fold of the minimum.OAR Variation
  44. 44. Dry Run for Segmentation and Plan Evaluation – 1106 ExampleGTV contours from different institutions. Red thick line represents the consensus contour.(a) Case1, (b) Case2. 44
  45. 45. Oral Presentation AAPM 2012 45
  46. 46. RTOG 0617, NCCTG N0628,CALGB 30609 Conventional vs. High Dose RT R RT: 60 Gy A Paclitaxel N Carboplatin +/- D Cetuximab Paclitaxel O Carboplatin X 2 M +/- Cetuximab RT: 74 Gy I Paclitaxel Z Carboplatin +/- E Cetuximab J. Bradley et al, ASTRO 2011 46
  47. 47. Overall Survival 100 Overall Survival (%) 75 50 Dead Total 25 60 Gy 58 213 74 Gy 70 204 0 HR= 1.45 (1.02, 2.05) p*=0.02 0 3 6 9 12Patients at Risk Months since Randomization60 Gy 213 190 149 124 10474 Gy 204 175 137 116 93*One-sided p-value, left tail 47
  48. 48. DATA ANALYSIS - Evidence Based Radiation Therapy Quality Assurance(Image Guided Radiotherapy) 48
  49. 49. IGRT Data Submission Components 49
  50. 50. Variations Between Systems Y. Cui (Xiao) et al, Int. J. Radiation Oncology Biol. Phys., Vol. 81, No. 1, pp. 305–312, 2011 50
  51. 51. IGRT Credentialing for RTOG Protocols 51
  52. 52. IGRT VariationsY. Cui (Xiao) et al, Implementation of Remote 3D IGRT QA for RTOG Clinical Trials, Int. J. Radiation Oncology Biol. Phys., In Press 52
  53. 53. DATA ANALYSIS- Evidence Based Radiation Therapy Quality Assurance (Intensity Modulated Radiotherapy Planning) 53
  54. 54. Establishing knowledge-based models for IMRT planning quality evaluation Q. Jackie Wu Yaorong Ge Jan 2012DUKE University Radiation Oncology
  55. 55. Case1 Right Parotid Case 2 Left Parotid 100 Case 1 R Parotid 80 Case 2 L Parotid Percent volume (%) 60 40 20 Parotid DVH 0 0 20 40 60 80 100 55 Percent dose (%)
  56. 56. Knowledge Models For IMRT Planning QA• Understand the patient anatomical, physiological factors that influence dose coverage• Quantify their individual influence via mathematical modeling and machine learning• Codify treatment planning experience and guidelines using knowledge engineering• Model Use these factors to model the inter-patient variation and to provide “peer-review” type guidance 56
  57. 57. Example Of Parotid Sparing Modeling Case 1 Case 2 Case 3 Case 4 Case 5 Case 6 Volume (%) 100 50 Actual Plan DVH 0 0 50 100 50 100 50 100 50 100 50 100 50 100 Modeled Lower Dose (%) and Upper Case 7 Case 8 Case 9 Case 10 Case 11 Case 12 Bound of DVH Volume (%) 100 50 0 0 50 100 50 100 50 100 50 100 50 100 50 100 Dose (%) Case 13 Case 14 Case 15 Case 16 Case 17 Case 18 Volume (%) 100 50 0 0 50 100 50 100 50 100 50 100 50 100 50 100 Dose (%) Case 19 Case 20 Case 21 Case 22 Case 23 Case 24 Volume (%) 100 50 0 0 50 100 50 100 50 100 50 100 50 100 50 100 Dose (%) 57
  58. 58. Moving Forward• Bigger Database – Knowledge and experience embedded in the IMRT cases – Collaboration with RTOG who has large case pools• Comprehensive Knowledge Base – All types of knowledge sources – Predictive models – Ontological framework• Intuitive and Integrated Decision Support – Minimize cognitive burden 58
  59. 59. Intuitive and Integrative Decision Support Prediction QUANTEC Guidelines Gui 59
  60. 60. Experience-based dose volumehistogram prediction in IMRT: A new QC paradigm Kevin L. Moore, Ph.D., DABR 60
  61. 61. Introduction • Current TPSs cannot guarantee that IMRT plans are fully optimal, and applying quality control methods to the treatment planning process can have a very large impact • The degree to which plan quality variations compromise patient care is unknown • Investigations (WashU, JHU, ROR) have shown that plan quality variations can be quite sizeable, vastly exceeding other uncertainties and putting patients that should have had a low risk of complications into a high-risk category • Quantitative assessment of PTV metrics is easy, normal tissue sparing is not. Anatomical variations confound the plan evaluation process because expected values are (as yet) not available. KL Moore et al, "Experience-based QC of IMRT planning" IJROBP 82, 545 (2011) 61
  62. 62. Predicting DVHs with universal basis function evolution • With universal fitting function and parameter fits pjq(k), which are derived from all N training patients, we have the desired result: • This equation takes as input geometric variables and the derived fitting parameters and outputs a predicted DVH for an organ based only on the input structure set SSij 62
  63. 63. Results: rectum and bladder predictions (training pts) N=20 training patients 63
  64. 64. Results: rectum and bladder predictions (“new” pts) M=20 validation patients 64
  65. 65. Quantifying plan quality variations in RTOG trials • Employ modeling toolkit as secondary study on closed RTOG protocol (e.g. 01-26) to quantify the clinical importance of IMRT plan variability • Plan quality variations in a large-scale, multi- institutional trial will serve as an excellent surrogate for the variability in plan quality across IMRT practitioners• These data represent an unique and nearly ideal test bed to not only quantify plan quality variability but, due to the associated outcomes data with the treatment plans, it can address its clinical importance as well 65
  66. 66. DATA ANALYSIS- Analytical Algorithms 66
  67. 67. Statistical inference Frequentist inference Bayesian inferenceProbability: the proportion of Probability describes degree of belief. Ittimes that an event would reflects one’s strength of belief thatoccur in a large number the proposition is true. Bayesianof similar repeated trials. inference inherently embraces a subjective notion of probability.Model parameters are fixed, Start with a prior belief about the likelyuse the observed data to values of model parameters, then usemake Inference about observed data to modify theseparameters, e.g. Maximum parameters, i.e., deriving posteriorLikelihood Estimation, probability distribution.confidence intervals and P-values The Dempster-Shafer theory is an extension of the Bayesian inference. Wenzhou Chen, Yunfeng Cui, Yanyan He, Yan Yu, James Galvin, Yousuff M. Hussaini, Ying Xiao, “Application of Dempster- 67 Shafer Theory in Dose Response Outcome Analysis”, Physics in Medicine and Biology, In Press
  68. 68. Probability, Belief & Plausibility of RP 68
  69. 69. LKB parameters from Dempster–Shafer theory and other references 69
  71. 71. Introducing A New Organizational Structure NCI Clinical Trials Network
  72. 72. Data and QA Process Flow (receipt, QA, storage) Imaging Institution Studies Patient data Medidata ACR QA IROC Rave Cloud QA QA Study Group Study Groups Patient data (second analysis, outcomes, publications etc.) IROC 72
  73. 73. 73