Presentation is loading. Please wait.

Presentation is loading. Please wait.

Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Mining Medical Images R. Bharat Rao Glenn Fung Balaji Krishnapuram Jinbo Bi Murat.

Similar presentations


Presentation on theme: "Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Mining Medical Images R. Bharat Rao Glenn Fung Balaji Krishnapuram Jinbo Bi Murat."— Presentation transcript:

1 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Mining Medical Images R. Bharat Rao Glenn Fung Balaji Krishnapuram Jinbo Bi Murat Dundar Vikas Raykar Shipeng Yu Sriram Krishnan Xiang Zhou Arun Krishnan Marcos Salganicoff Luca Bogoni Matthias Wolf Anna Jerebko Jonathan Stoeckel

2 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 2 Outline of the talk Mining medical images Computer aided diagnosis (CAD) Key data mining challenges Clinical impact Lessons learnt Several thousand units of the products described in this paper have been commercially deployed in hospitals around the world since 2004

3 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 3 Medical Imaging 1895 X-ray used for broken bones, locating foreign objects 1970 Computed tomography (CT) 3-D imaging As resolution increased in-vivo imaging is widely used to locate medical abnormalities for diagnosis and surgery planning Digital Mammogram CT Scan

4 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 4 Mining medical imaging data Increased resolution has resulted in Data Overload Increased total study time Increase in data does not always translate to improved diagnosis Automatically extract the actionable information from the imaging data in order to ensure improvement in patient care simultaneous reduction in total study time Raw imaging data Clinically relevant information Knowledge based data-mining algorithms Knowledge based data-mining algorithms Computer aided diagnosis/detection CAD

5 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 5 Computer-aided diagnosis/detection (CAD) Used as a second reader Improves the detection performance of a radiologist Reduces mistakes related to misinterpretation The principal value of CAD is determined by carefully measuring the incremental value of CAD in normal clinical practice CAD technologies support the physician by drawing attention to structures in the image that may require further review.

6 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 6 Lung CAD Identify suspicious regions called nodules (which are known to be precursors of cancer) in CT scans of the lung.

7 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 7 Colon PEV Polyp Enhanced Viewer Identify suspicious regions called polyps in CT scans of the colon.

8 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 8 Mammo CAD Identify abnormal masses/calcifications in digital mammograms. PECAD and MammoCAD are only sold outside the US.

9 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 9 PE CAD Pulmonary Embolism (PE) is a sudden blockage in a pulmonary artery caused by an embolus that is formed in one part of the body and travels to the lungs in the bloodstream through the heart. PECAD and MammoCAD are only sold outside the US.

10 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 10 CAD Goal is to detect potentially malignant nodules (lung) polyps (colon) lesions (breast) Pulmonary emboli (lung) in medical images like CT scans, X-ray, MRI, etc. Early detection provides the best prognosis

11 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 11 Typical CAD architecture Candidate Generation Feature Computation Classification Image [ X-ray | CT scan | MRI ] Location of lesions Focus of the current talk Potential candidates Lesion > 90% sensitivity FP/image > 80% sensitivity 2-5 FP/image

12 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 12 Key Data Mining Challenges High accuracy 2-5 FP/image sensitivity > 80% 1.The breakdown of assumptions 2.Highly unbalanced data 3.Feature computation cost 4.Incorporating domain knowledge 5.No objective ground truth

13 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 13 The breakdown of assumptions region on a mammogramlesionnot a lesion Traditional classification algorithms Neural networks Support Vector Machines Logistic Regression …. Often violated in CAD Make two key assumptions (1) Training samples are independent (2) Maximize classification accuracy over all candidates

14 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 14 Violation 1: Training examples are correlated Candidate generation produces a lot of spatially adjacent candidates. Hence there are high level of correlations among candidates. Also correlations exist across different images/detector type/hospitals.

15 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 15 Violation 2: Candidate level accuracy is not important Several candidates from the CG point to the same lesion in the breast. Lesion is detected if at least one of them is detected. It is fine if we miss adjacent overlapping candidates. Hence CAD system accuracy is measured in terms of per lesion/image/patient sensitivity. So why not optimize the performance metric we use to evaluate our system? Most algorithms maximize classification accuracy. Try to classify every candidate correctly.

16 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 16 Solution 1: Multiple Instance Learning Fung, et al. 2006, Bi, et al. 2007, Raykar et al. 2008, Krishnapuram, et al. 2008, How do we acquire labels ? Candidates which overlap with the radiologist mark is a positive. Rest are negative Single Instance Learning Multiple Instance Learning Classify every candidate correctly Positive Bag Classify at-least one candidate correctly We have modified SVM and logistic regression for multiple instance learning

17 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 17 Simple Illustration Single instance learning: Reject as many negative candidates as possible. Detect as many positives as possible. Multiple Instance Learning Single Instance Learning Multiple instance learning: Reject as many negative candidates as possible. Detect at-least one candidate in a positive bag. Accounts for correlation during training

18 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 18 Solution 2: Batch Classification Vural et al., 2009 Accounts for correlation during testing Change the decision boundary during test time.

19 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 19 Skewed data and expensive features 1.Highly unbalanced class distribution (less than 1% are abnormal) 2.Huge number of experimentally engineered features 3.Lot of them are irrelevant and redundant. 4.Feature computation is expensive 5.Stringent run-time requirements 1.Feature selection/Sparse classifiers 2.Cascaded classification architecture 1.Feature selection/Sparse classifiers 2.Cascaded classification architecture

20 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 20 Cascaded classification architecture Bi, et al. 2006

21 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 21 Novel AND-OR training of cascades Dundar and Bi 2007

22 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 22 Incorporating domain knowledge We know that lesions have different shapes/sizes/appearance

23 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 23 Gated Classification architecture

24 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 24 Incorporating domain knowledge Dundar et al Exploit different sub-classes of False Positives

25 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 25 Subjective Ground truth Raykar et al Lesion IDRadiologist 1 Radiologist 2 Radiologist 3 Radiologist 4 Truth Unknown x x x x x x x Each radiologist is asked to annotate whether a lesion is malignant (1) or not (0). In practice there is a substantial amount of disagreement. We have no knowledge of the actual golden ground truth. Getting absolute ground truth (e.g. biopsy) can be expensive. We have proposed an EM algorithm to simultaneously learn the ground truth and the classifier. We have proposed an EM algorithm to simultaneously learn the ground truth and the classifier.

26 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 26 Key Data Mining Challenges ChallengeSolutions 1.Training/testing data is correlatedMultiple instance learning batch classification 2.Evaluation metric is CAD specificMultiple instance learning 3.Highly unbalanced dataCascaded classifiers 4.Feature computation costCascaded classifiers Feature selection methods 5.Incorporating domain knowledgeGated classifiers Polyhedral classifiers 6.No objective ground truthEM algorithm

27 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 27 Clinical Impact 1.How much can a radiologist benefit by using the CAD software ? 2.CAD is mostly deployed in second reader mode. 3.Measure the improvement in performance of a radiologist with CAD. 4.Several independent clinical studies/trials have been conducted by our collaborators worldwide.

28 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 28 Lung CAD 1.FDA clinical validation study with17 radiologists,196 cases from 4 hospitals. Average reader AUC increased by (p<0.001) because of CAD. 2.Recent study at NYU by Godoy et al New prototype also helps detect different kinds of nodules.. Mean sensitivity without CAD Mean sensitivity with CAD Increase in sensitivity Solid Nodules60%85%15 % Part-solid Nodules80%95%15% Ground Glass Opacities75%86%11% Sensitivity without CADSensitivity with CADIncrease in sensitivity Reader %66.0 %9.8 % Reader %89.8 %10.6 %

29 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 29 Colon PEV Colon PEV (Polyp Enhanced Viewer) was evaluated by Baker, et al Study with seven less-experienced readers Without PEV average sensitivity was With PEV average sensitivity was A 9.8% increase in average sensitivity (p=0.0152)..

30 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 30 PE CAD Das et al conducted a study with 43 patients to asses the sensitivity of detection of pulmonary embolism.. Sensitivity without CAD Sensitivity with CAD Increase in sensitivity Reader 187%98%11% Reader 282%93%11% Reader 377%92%15%

31 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 31 Key data mining lessons 1.True measure of impact is how much does CAD help the radiologists. 2.Design algorithms to optimize the metric you care about 3.Careful analysis of the assumptions behind off-the-shelf data-mining algorithms. In CAD most of these assumptions break down. Need to design new methods. 4.Domain knowledge is very important. Collaboration with radiologists is crucial in eliciting the domain knowledge.

32 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 32 Conclusions 1.Radiologists have access to orders of magnitude more data for diagnosing various cancers. 2. Difficult and time-consuming to identify key clinical findings. 3. We described the data-mining challenges in a commercially deployed CAD software. 4. Use of CAD as second reader improves radiologist's detection performance. 5. Key opportunity for data mining technologies to impact patient care worldwide.

33 Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Page 33 Acknowledgements Dr. D. Naidich, MD, of New York University Dr. M. E. Baker, MD, of the Cleveland Clinic Foundation Dr. M. Das, MD, of the University of Aachen Dr. U. J. Schoepf, MD, of the Medical University of South Carolina Dr. Peter Herzog, MD, of Klinikum Grossharden, Munich. Alok Gupta, Ph.D., Ingo Schmuecking, MD, Harald Steck, Ph.D., Stefan Niculescu, Ph.D., Romer Rosales, Ph.D., Sangmin Park, Ph.D., Gerardo Valadez Ph.D. Maleeha Qazi, and the entire SISL team.


Download ppt "Copyright © 2009 Siemens Medical Solutions USA, Inc. All rights reserved. Mining Medical Images R. Bharat Rao Glenn Fung Balaji Krishnapuram Jinbo Bi Murat."

Similar presentations


Ads by Google