PIONEERING BIG DATA IN RADIATION ONCOLOGY

Similar documents
Automated Treatment Planning Using a Database of Prior Patient Treatment Plans

Evolution of Head and Neck Treatment Using Protons. Mayank Amin, M.Sc,CMD

THE DOSIMETRIC EFFECTS OF

Proton Therapy Center Czech

Our Facility. Advanced clinical center with the newest and highly exact technology for treatment of patients with cancer pencil beam

Corporate Medical Policy

Evaluation of an automated knowledge based treatment planning system for head and neck

Learning about Mouth Cancer

Head and Neck Treatment Planning: A Comparative Review of Static Field IMRT Rapid Arc Tomotherapy HD

Clinical Education A comprehensive and specific training program. carry out effective treatments from day one

Medical Marijuana Use in Patients with History of SCCHN Treated with Radiotherapy

C a nc e r C e nter. Annual Registry Report

PATIENT INFORMATION ABOUT ADJUVANT THERAPY AFTER THE WHIPPLE OPERATION FOR ADENOCARCINOMA ( CANCER ) OF THE PANCREAS AND RELATED SITES.

Radiation Therapy for Prostate Cancer: Treatment options and future directions

Dosimetric impact of the 160 MLC on head and neck IMRT treatments

How To Know If You Have Cancer At Mercy Regional Medical Center

Diagnosis and Treatment of Common Oral Lesions Causing Pain

Veterinary Oncology: The Lumps We Hate To Treat

Concurrent Chemotherapy and Radiotherapy for Head and Neck Cancer

Particle Therapy for Lung Cancer. Bradford Hoppe MD, MPH Assistant Professor University of Florida

Advanced Radiation Therapy of Cancer by Proton Beam

Goals and Objectives: Breast Cancer Service Department of Radiation Oncology

Principles of Radiation Therapy A Bapsi Chakravarthy, MD Associate e P rofessor Professor Radiation Oncology

Radiation Protection in Radiotherapy

Management of Postmenopausal Women with T1 ER+ Tumors: Options and Tradeoffs. Case Study. Surgery. Lumpectomy and Radiation

Radiotherapy in locally advanced & metastatic NSC lung cancer

Current Status and Perspectives of Radiation Therapy for Breast Cancer

The Science behind Proton Beam Therapy

Esophageal Cancer Treatment

Prostatectomy, pelvic lymphadenect. Med age 63 years Mean followup 53 months No other cancer related therapy before recurrence. Negative.

Current Status and Future Direction of Proton Beam Therapy

Non-Small Cell Lung Cancer Treatment Comparison to NCCN Guidelines

Department of Radiation Oncology

Evaluation of complexity and deliverability of IMRT- treatment plans. Author: Elin Svensson Supervisors: Anna Bäck and Anna Karlsson Hauer

Stomach (Gastric) Cancer. Prof. M K Mahajan ACDT & RC Bathinda

The Canadian National System for Incident Reporting in Radiation Treatment (NSIR-RT) Taxonomy March 2, 2015 V2

Basic Radiation Therapy Terms

Pediatric Oncology for Otolaryngologists

Brain Tumor Treatment

Andre Konski, MD, MBA, MA, FACR Professor & Chair Department of Radiation Oncology Wayne State University School of Medicine Barbara Ann Karmanos

SCD Case Study. Most malignant lesions of the tonsil are either lymphosarcoma or carcinoma.

Radiation therapy involves using many terms you may have never heard before. Below is a list of words you could hear during your treatment.

Dental health following cancer treatment

M D Anderson Cancer Center Orlando TomoTherapy s Implementation of Image-guided Adaptive Radiation Therapy

Principal Investigator: Valerie W. Rusch, MD, FACS, Chief, Thoracic Surgery Memorial Sloan-Kettering Cancer Center

Clinical Trials and Radiation Treatment. Gerard Morton Odette Cancer Centre Sunnybrook Research Institute University of Toronto

New strategies in anticancer therapy

Prostate Cancer Guide. A resource to help answer your questions about prostate cancer

Oropharyngeal carcinoma State of the Art

Protons vs. CyberKnife. Protons vs. CyberKnife. Page 1 UC SF. What are. Alexander R. Gottschalk, M.D., Ph.D.

Radioterapia panencefalica. Umberto Ricardi

KINGS COUNTY HOSPITAL CENTER EXECUTIVE SUMMARY. Always Here When You Need Us

Transition from 2D to 3D Brachytherapy in Cervical Cancers: The Vienna Experience. Richard Pötter MD. BrachyNext, Miami, 2014.

Tricia Cox on 7/18/2012 at Oncology Center. Sarah Randolf. Female

Enhancing the Child s Voice in Clinical Care and Research

Radiation Oncology Nursing Care. Helen Lusby Radiation Oncology Nurse BAROC 2012

Analysis of Population Cancer Risk Factors in National Information System SVOD

Post Treatment Log File Based QA Varian. Krishni Wijesooriya, PhD University of Virginia. D e p a r t m e n t of R a d i a t i o n O n c o l o g y

The evolution of rectal cancer therapy. Objectives

Proton Therapy for Head & Neck Cancers

ALCHEMIST (Adjuvant Lung Cancer Enrichment Marker Identification and Sequencing Trials)

Prostate cancer is the most common cause of death from cancer in men over age 75. Prostate cancer is rarely found in men younger than 40.

Radiotherapy in Plasmacytoma and Myeloma. David Cutter Multiple Myeloma NSSG Annual Meeting 14 th September 2015

Radiation Fibrosis Fact Sheet

Your Certified Professional Cancer Coach. An Integrative Answer to Cancer Exclusive Professional Program for Patients with Cancer

Radiation Therapy in Prostate Cancer Current Status and New Advances

Contemporary Orthopedic Care: The O.R. Through Rehabilitation

Intensity-Modulated Radiation Therapy (IMRT)

Chapter I Overview Chapter Contents

Centralizing image and data management in radiation oncology with MOSAIQ Data Director

Our Department: structure and organization

Pancreatic Cancer: FDA Approved Treatments and Clinical Trials

Seton Medical Center Hepatocellular Carcinoma Patterns of Care Study Rate of Treatment with Chemoembolization N = 50

Intensity Modulated Radiation Therapy (IMRT) for Thyroid Cancer

Case Number: RT (M) Potential Audiences: Intent Doctor, Oncology Special Nurse, Resident Doctor

Management of low grade glioma s: update on recent trials

Radiation Therapy for Cancer Treatment

The Cancer Center of Chester County Annual Report 2006 With statistical data from 2005

In 1946 Harvard physicist Robert Wilson ( ) suggested:

There must be an appropriate administrative structure for each residency program.

Health Information. Technology and Cancer Information Management. Health Information Technology & Cancer Information Management 363

GUIDELINES FOR THE MANAGEMENT OF LUNG CANCER

Foundations of Oncology Nursing Practice

Thomas A. Kollmorgen, M.D. Oregon Urology Institute

Big Data and Oncology Care Quality Improvement in the United States

IBA Proton Therapy. Biomed days Vincent Bossier. System Architect Protect, Enhance and Save Lives

Clinical Trial Design. Sponsored by Center for Cancer Research National Cancer Institute

Breast Health Program

R E X C A N C E R C E N T E R. Annual Report Rex Cancer Care Committee 2012 On behalf of the Rex Cancer Center & Rex Health Care

Transcription:

TM PIONEERING BIG DATA IN RADIATION ONCOLOGY Todd McNutt PhD Associate Professor Radiation Oncology Johns Hopkins University Presented at the Target Insight Toronto, CAN May 8 th, 2015

Disclosures This work has been partially funded with collaborations from: Philips Radiation Oncology Systems Elekta Oncology Systems Toshiba Medical Systems as well as Commonwealth Foundation Maritz Foundation 2

Problem Ability to advance radiotherapy is limited by our knowledge of which patients are at risk of high grade toxicity or of limited ability to cure. Knowledge from clinical trials is quite coarse and fails to consider all of the aspects of the individual patient. Big Data offers an opportunity to better predict treatment outcome and provide improved clinical decisions for individual patients.

Personalized care using database of prior patients How to best to treat individual patient? Pathology Diagnosis Performance Status Comorbidities Patient History Radiotherapy Surgery Chemotherapy CONSULT TREATMENT Survival FOLLOW-UP Quality of Life Clinical assessments Lab Values Toxicities Disease Status Prediction of complications for early intervention? Predicted response and toxicity?

Precision Radiotherapy Treatment Planning

Mucositis data collected at JHU # patients Toxicity grade 6

Promote Culture of Data Collection Data collected over entire treatment Consult Demographics Diagnosis Staging Baseline Tox Baseline QoL History Weekly On Treatment Toxicity QoL Patient status Symptom Mgmt End of Treatment Acute toxicity QoL Patient status Symptom mgmt Disease response Follow Up Late toxicity QoL Patient status Disease response Simulation Targets OARs OVH Planning Rx Dose DVH Image Guidance Motion Disease Response At what time point do we have enough data to make decision based on future prediction? Auto Plan Risk Based Symptom Mgmt Therapy Mgmt Input Variables => Prediction?

MOSAIQ Browser Departmental Analytics Framework Multi-Disciplinary Clinics RadOnc Users Security Certificate Johns Hopkins Enterprise Login SiteMinder Access Management Mobile Solutions Mosaiq Browser -IIS -ASP.NET -C# -SQL Data Access Layer SQL SQL Query Log Clinical Analytics IDE - Visual Studio - SVN repository MOSAIQ Security Rights MOSAIQ DB

Data Collection in Clinic Clinical Assessment Quality of life Disease Status 5/27/2015 9

Head and Neck Oncospace Landscape Home-based Assessment (FitNinja) Head and Neck Tissue Bank (Chung) SNP Genotyping Pre-Treatment Imaging (Kiess/Hobbs/Shen) On-Treatment Imaging (Lee/Shekhar) (Toshiba) Oncospace - On-Treatment Evaluation - RT dosimetry Swallow Function (Starmer et al) Toxicity PROs Oncologic Outcome Neck Function (Sweet) Ocular Function (Subramanian) Post-Treatment Oncologic and Toxicity (Ding/Fakhry/Murano/Prince/ Wasserman Ecological Momentary Assessments (EMAs)

Extract, Transform, Load DICO M MOSAIQ - SQL Query - Lab, Toxicity, Assessments Oncospace Pinnacle TPS - Scripts, Python, DICOM - DVH, OVH, Shapes

Oncospace tables and schema Patient Private Health Info (access restricted) Family History Social History Medical History Medications (chemo) Surgical Procedures Test Results (Labs) Assessments (Toxicities) Clinical Events Tumors Radiation Summary Patient Representations (CT based geometries) (m:n) Image Transform Image Feature Pathology Feature Organ DVH Data Organ Dose Summaries 1 : N multiple instances 1 : 1 single instance m : n relates m to n Organ DVH Feature ROI DVH Data Radiotherapy Sessions ROI Dose Summary ROI DVH Features Shape Descriptor Regions of Interest Data (m:n) Shape Relationship Features

Data inventory 500 450 400 350 Toxicities (24var/pt) Quality of Life (64var/pt) Measured data (6 var/pt) Disease response(8var/pt) 300 250 200 150 100 50 0 0-2w 2-4w 4-6w 6w-3m 3m-6m 6m-1y 1-2y 2-3y 3-4y 4-5y 5-6y >6y 5/27/2015 13

Organs at risk with full dose 5/27/2015 14

Learning health system can t exist without data Decision Point Facts Controls Outcomes time Knowledge Database Facts Decisions Controls Presentation of Predictions Predictive Modeling Predicted Outcomes Data Feedback (Facts, Outcomes) 15

Oncospace Consortium Repository (It s all about the data) Johns Hopkins U. Washington U. Toronto Sunnybrook U. Virginia Institution X Knowledge Base Registry $/pt Quality Reporting Decision Support Research N

Toxicity trends during and after treatment detect outliers During Treatment Follow up Dysphagia Swallowing Worsens after Tx for many patients then improves long term Mucositis Inflammation Heals after Tx for most patients Xerostomia Dry Mouth Tends to be permanent #pts Toxicity grade (0-5)

Toxicity trends during and after treatment detect outliers During Treatment Follow up Dysgeusia Taste disturbance Worsens through Tx then improves long term Voice Change Worsens through Tx #pts Toxicity grade (0-5)

DVH, Toxicities and Grade distributions Voice Change Larynx 50% Volume Dysphagia Larynx_edema 30% Volume Toxicity Grade 0,1,2,3,4,5 Mean and stddev of DX% at grade Number of patients by grade at D50%

OVH: serial vs parallel Target OAR1 OAR2 r 70,1 r 70,2 For parallel organs, OAR2 is more easily spared. For serial organs, OAR1 is more easily spared.

Shape-dose relationship for radiation plan quality Shape relationship DB of prior patients Dose prediction parotids 0 PTV 0 5 10 15 20 25 30 35 40 45 50 55 60 65 70 normalized volume 1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 Dose (Gy) Right parotid Left parotid For a selected Organ at Risk and %V, find the lowest dose achieved from all patients whose %V is closer to the selected target volume? Decisions: Plan quality assessment Automated planning IMRT objective selection Dosimetric trade-offs

Sample automated radiation planning result Original plan Automated plan 30% reduction in dose to parotids 1 0.9 0.8 0.7 0.6 Auto plan Original Plan Dot: right No-dot: left 0.5 0.4 0.3 0.2 0.1 0 0 10 20 30 40 50 60 70 80 Dose(Gy) brain (Gy) (max) Brainstem (Gy) (max) Cord4mm (Gy) (max) L inner ear (Gy)(mean) original 61.25 54.58 41.75 57.18 re-plan 56.33 46.48 37.89 43.72 R inner ear (Gy) (mean) mandible (Gy) (max) larynx for edema (V50) esophagus (Gy)(max) original 40.57 66.58 61% 63.74 re-plan 38.38 63.78 59% 61

Toxicity and Dose Volume Histogram Scott Robertson PhD 23

Prevalence and prediction of treatment-related complications RISK STRUCTURES TOXICITIES / OUTCOMES 10%/Gy 5%/Gy MODELLED RISK May 27, 2015 24

Voice Change

Bad DVH! DVH assumes that every sub-region of an OAR has the same radiosensitivity and functional importance to the related toxicity DVH assumes that each OAR is uniquely responsible for the overall human function related to the toxicity

Spatial dose analysis Method Voice dysfunction n=99, n + =8, n - =91 Xerostomia n=364, n + =275, n - =89 Bagged Naïve Bayes (1000 iterations) 0.915 0.743 Bagged Linear Regression (1000 iterations) 0.905 0.737 Naïve Bayes 0.900 0.734 Linear Regression 0.896 0.731 Random Forest (1000 trees) 0.724 0.683 2015 Hopkins NTCP inhealth LKB 0.596 0.700

Classification with correlated features: unreliability of feature ranking and solutions Simulation of 1, 10 and 20 variables with a correlation of 0.9 with variable 3 http://www.cedars-sinai.edu/ Genuer et al.

Weight loss prediction Endpoint: > 5kg loss at 3 months post RT Larynx salivary glands thyroid hypopharynx yes FALSE FALSE At planning Larynx D55 < 27.5Gy no Diagnostic ICD-9 Combo Parotid D50< 13.5Gy Distance: HD-PTV to Superior Constrictor Muscle >= 1.1cm Combo Masticatory Muscle D41 < 38.4Gy FALSE FALSE FALSE FALSE oropharynx tongue nasopharynx nasal cavities Larynx D80 < 23.0Gy TRUE Larynx salivary glands thyroid hypopharynx Nausea < 1 (CACAE) FALSE Skin Acute < 3 (CACAE) N stage < 2 Diagnostic ICD-9 At end of RT yes Combo Parotid D61< 7.5Gy Pain Intensity - Current < 5 Able to eat foods I like >= 3 (FACT) larynx D59 < 27.4Gy Distance: LD-PTV to Larynx >= -1.3cm Cricopharyngeal Muscle D100 < 38.1Gy oropharynx tongue nasopharynx nasal cavities Diagnostic ICD-9 tongue Esophagitis/ Pharyngitis < 3 (CACAE) Combo Parotid D96< 6.5Gy Larynx D10 < 42.3Gy FALSE TRUE TRUE FALSE FALSE TRUE FALSE TRUE FALSE TRUE FALSE TRUE FALSE TRUE no 5/27/2015 29

What can we do with the data? Shape based auto-planning Clinical (prostate, pancreas) Efficient high quality plan Weight loss prediction Improved symptom management Toxicity Risk DVH based Spatial dose based Disease response prediction Pancreas resectability Head and neck HPV dose de-escalation Shape relationship parotids PTV DB of prior patients normalized volume 1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 Dose prediction 0 0 5 10 15 20 25 30 35 40 45 50 55 60 65 70 Right parotid Left parotid Dose (Gy) 30

Summary The Oncospace model can house RT data effectively and provides a model for sharing Data collection in the clinical environment has been demonstrated All patient on trial Data exploration and analysis across multiple institutions is possible Exploring models to stratify patients to improve the predictive power of the data Decision support to improve quality and safety has been demonstrated Personalized medicine has not been fully demonstrated, but remains a tenable goal

Acknowledgments JHU-RO Sierra Cheng MD Kim Evans MS Michael Bowers BS Joseph Moore PhD Scott Robertson PhD Wuyang Yang MS, MD John Wong PhD Theodore DeWeese MD GI Team Joseph Herman MD Amy Hacker-Prietz PA H&N Team Harry Quon MD Giuseppe Sanguineti MD Heather Starmer MD Ana Keiss MD Mysha Allen RN Sara Afonso RN JHU - CS Russ Taylor PhD Misha Kazhdan PhD Fumbeya Murango BS Philips PROS Karl Bzdusek BS Toshiba Minoru Nakatsugawa PhD Bobby Davey PhD Rachel-Louise Koktava John Haller Elekta