dekker trog - radiomics for oncology - 2017

25
Radiomics for Oncology Andre Dekker Department of Radiation Oncology (MAASTRO) GROW - Maastricht University Medical Centre + Maastricht, The Netherlands SLIDES AVAILABLE ON SLIDESHARE (slideshare.net/AndreDekker)

Upload: andre-dekker

Post on 12-Apr-2017

72 views

Category:

Healthcare


0 download

TRANSCRIPT

Page 1: Dekker   trog  - radiomics for oncology - 2017

Radiomics for Oncology

Andre DekkerDepartment of Radiation Oncology (MAASTRO)GROW - Maastricht University Medical Centre +Maastricht, The Netherlands

SLIDES AVAILABLE ON SLIDESHARE (slideshare.net/AndreDekker)

Page 2: Dekker   trog  - radiomics for oncology - 2017

2

Disclosures• Research collaborations incl. funding and speaker honoraria

– Varian (VATE, SAGE, ROO, chinaCAT, euroCAT), Siemens (euroCAT), Sohard (SeDI, CloudAtlas), Mirada Medical (CloudAtlas), Philips (EURECA, TraIT, SWIFT-RT, BIONIC), Xerox (EURECA), De Praktijkindex (DLRA), ptTheragnostic (DART, Strategy), CZ (My Best Treatment), OncoRadiomics

• Public research funding– Radiomics (USA-NIH/U01CA143062), euroCAT(EU-Interreg), duCAT&Strategy (NL-

STW), EURECA (EU-FP7), SeDI & CloudAtlas & DART (EU-EUROSTARS), TraIT (NL-CTMM), DLRA (NL-NVRO), BIONIC (NWO)

• Spin-offs and commercial ventures– MAASTRO Innovations B.V. (CSO)– Various patents on medical machine learning

Page 3: Dekker   trog  - radiomics for oncology - 2017

3

This talk• Rationale (animation)

• Radiomics workflow & challenges

• New directions

Page 4: Dekker   trog  - radiomics for oncology - 2017

4

Rationale• https://www.youtube.com/watch?v=Vf0F7q8vaS4

Page 5: Dekker   trog  - radiomics for oncology - 2017

Radiomics workflow & (some) challenges

Andre DekkerDepartment of Radiation Oncology (MAASTRO)GROW - Maastricht University Medical Centre +Maastricht, The Netherlands

Page 6: Dekker   trog  - radiomics for oncology - 2017

6

Radiomics WorkflowLambin, Walsh et al., Nat Rev Clin Oncol (in-press)

Larue, et al., Br J Radiol 2017

Page 7: Dekker   trog  - radiomics for oncology - 2017

7

Feature Extraction – Dimensionality reduction

Gillies et al., Radiology 2016;278(2).

219 features in 235 patients

Aerts et al., Nature Communications 5, 4006

Page 8: Dekker   trog  - radiomics for oncology - 2017

8

Feature Extraction – Imaging Protocols

Oliver et al. , Translational Oncology (2015) 8, 524–534

Page 9: Dekker   trog  - radiomics for oncology - 2017

9

Feature Extraction – Robust Segmentation

Parmar et al., PLoS One. 2014; 9(7): e102107.

Approaches1. Perform semi-automatic segmentation2. Remove features which are too sensitive to the exact

segmentation

Larue, et al., Br J Radiol 2017

Page 10: Dekker   trog  - radiomics for oncology - 2017

10

Feature Extraction - Software

Non-texture-based features: Histogram, GeometryTexture-based features: GLCM, GLRLM

Sample capacity: 31 51 33

Correlation Coefficients Distribution

correlation coefficient range

Fudan University Cancer Hospital (unpublished)

Page 11: Dekker   trog  - radiomics for oncology - 2017

11

Feature Extraction – Phantom / Ontology

Page 12: Dekker   trog  - radiomics for oncology - 2017

12

So, Radiomics needs a lot of training data….

Aerts et al., Nature Communications 5, 4006

Page 13: Dekker   trog  - radiomics for oncology - 2017

13

…. and a lot of validation data

Aerts et al., Nature Communications 5, 4006

Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis

Page 14: Dekker   trog  - radiomics for oncology - 2017

14

Radiomics – End result

Page 15: Dekker   trog  - radiomics for oncology - 2017

New directions

Andre DekkerDepartment of Radiation Oncology (MAASTRO)GROW - Maastricht University Medical Centre +Maastricht, The Netherlands

Page 16: Dekker   trog  - radiomics for oncology - 2017

16

Radiomics – Preclinical

Page 17: Dekker   trog  - radiomics for oncology - 2017

17

Radiomics – PET

Page 18: Dekker   trog  - radiomics for oncology - 2017

18

Radiomics - MRI• Rectal cancer - Chemoradiation• Pathological response• Training n=173, Validation n=25• AUC 0.79 (validation)

1) MR GTV delineation

2) GTV ROI extraction

3) LoG filter application according different s

0.3 0.5 1.0 2.0 3.0 4.0

4) Data analysis

|||cT

234

Points

| | |cN

||||||||||||||SKE0485

−0.6−0.4−0.200.20.40.6

| | | | | | | | | |ENT0344

1.6 1.8 2 2.2 2.4

| | | | | | | || | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |Total Points

320 330 340 350 360 370 380 390

0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

TRG1Probability

0 1 2

0 10 20 30 40 50 60 70 80 90 100 110 120 130 140 150 160 170 180 190

Page 19: Dekker   trog  - radiomics for oncology - 2017

19

Radiomics – Delta Radiomicsp = 0.0054 (pCT) and p = 0.00099 (CBCT-FX1)

Page 20: Dekker   trog  - radiomics for oncology - 2017

20

Radiogenomics – Virtual Biopsy

Wu et al., Front Oncol 2016

Page 21: Dekker   trog  - radiomics for oncology - 2017

21

Distributed Radiomics

Page 22: Dekker   trog  - radiomics for oncology - 2017

22

Rapid Learning Health Care

Page 23: Dekker   trog  - radiomics for oncology - 2017

23

Conclusion• We are still in the very early phase• A lot of underpowered, exploratory

papers out there • A lot of dials to control (medical

physics needs to get involved)• Prospective validation as a

decision support system needed• TROG can help by collection of

highly standardized images in their trials

• But the promise is HUGE

1 2 3 4 50

20406080

100120140160

Pubmed RadiomicsRadiomics

Page 24: Dekker   trog  - radiomics for oncology - 2017

24

Acknowledgements• MAASTRO Clinic, Maastricht, The Netherlands

– Philippe Lambin, Ralph Leijenaar,….• Moffitt Cancer Center, Tampa, FL, USA

– Bob Gillies, Bob Gatenby,…• Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical

School, Boston– Hugo Aerts, Emmanuel Rios Velazquez, …

• Radboud University Medical Center, Nijmegen, The Netherlands• VU University Medical Center, Amsterdam, The Netherlands

More info on: www.radiomics.org

Page 25: Dekker   trog  - radiomics for oncology - 2017

Thank you for your attention

Andre DekkerDepartment of Radiation Oncology (MAASTRO)GROW - Maastricht University Medical Centre +Maastricht, The Netherlands