Feldman

Document Sample
Feldman Powered By Docstoc
					The Future of Diagnostic Medicine:
 Radiology-Pathology-Molecular
          Convergence

    Michael Feldman, MD, PhD
 feldmanm@mail.med.upenn.edu




Diagnostic Imaging Challenges in 2017


 Provide Diagnostically Informative
 Data from Non-Invasive or
 Minimally Invasive Techniques
 Provide Dense Multi-dimensional
 Data
 Provide Quantitative Data Which
 Integrates with Clinical and
 Molecular Information
             Diagnostic Imaging today…

   MRI


              In Vivo Optical




                                Pathology


                                            Molecular




                                                        Proteomic




High Resolution Quantitative Imaging


            A Use Case:
“Finding Significant Prostate Cancer”
             Non Invasive Imaging

                 Machine Vision
    Computer Assisted Diagnosis ( CAD)
         Molecular Analysis of Tissues
              High Resolution Magnetic Resonance
                  Imaging ( MR Microscopy)
              of Radical Prostatectomy Specimens




    Prostatectomy
    specimen is
    placed on
    Endorectal coil.

    Coil is then
    placed within
    4T MRI




           MRI of Prostatectomy #1 with 4T Magnet at 3 mm
               Slice Thickness using 2D Fast spin echo
                               Specimen #1
Resolution
234m     234m
234mm x 234mm In plane
                                                      BPH
3 mm thick slices

2D Fast spin echo
Custom Bird Cage
Transmit & receive coil
TE 34 ms                  8          9
TR 3000 ms
                                                      Cancer




                          11         10
   MRI of Prostatectomy #1 with 4T Magnet at 3 mm:
    MR & Histopathology Correlation Specimen #1


                                                                                             10




               BPH
                                   Adenocarcinoma interrupts normal
                                   curvilinear duct architecture




   MRI of Prostatectomy #1 with 4T Magnet at 3 mm:
    MR & Histopathology Correlation Specimen #1




               V



                                                                              12(8):619-
                                      American Journal of Surgical Pathology. 12(8):619-33, 1988


Adenocarcinoma interrupts normal
curvilinear gland architecture
                                        Normal radial gland distribution
    MRI of Prostatectomy #2 with 4T Magnet at 0.8 mm
         Slice Thickness using 3D Fast spin echo



                  17                     18                         19                        20




                  21                          22                         23                        24




                  25                          26                         27                         28


                     234m
         Resolution: 234mm x 188 mm in plane; 0.8 mm thick slices
         3D Fast spin echo; Custom Bird Cage Transmit & receive coil; TE 102 ms; TR 3000 ms




    MRI of Prostatectomy #2 with 4T Magnet at 0.8 mm:
     MR & Histopathology Correlation Specimen #2

                                                      17

                                                                                   *
                                                                                          *   *
                                                                         *
                                                                                        * *
                                                                                          *
                                                                                        *
                                                                                    * *

                                                  Adenocarcinoma interrupts
                                               normal curvilinear architecture    *
                                                   BPH with adenocarcinoma
                                                      impinging on one edge        *
Fig. 8                                               BPH without carcinoma
                                                                                   *
    MRI of Prostatectomy #2 with 4T Magnet at 0.8 mm:
     MR & Histopathology Correlation Specimen #2
                                           27

                                                              *
                                                      *               *


                                                      *               *


                                                          Adenocarcinoma = *
                                              sign”
Capsular distortion by adenocarcinoma, “Bulge sign”
                                                                     BPH = *




                                Conclusions


     Magnetic resonance imaging provides signal contrast (MR
     stain) that allows for the identification of carcinoma and
                                       2-           lens.
     benign hyperplasia similar to a 2-4X optical lens.

     Features associated with carcinoma are similar to
                      power”
     recognized “low power” histopathological features and
     include:
        A. Interruption of normal curvilinear duct structure
        B. Intermediate T2 weighted signal with a smudged
                      glass”
             “ground glass” texture
                                                     Sign”
        C. Interruption of capsular contour “Bulge Sign”
Computer Assisted Diagnostic (CAD) Analysis:
      Can Machine Vision See More ?




         CAD Analysis: Texture Features




  Madabhushi A, Feldman M, Metaxas D, Tomaszewski JE, Chute D:
  Automated detection of prostatic adenocarcinoma from high resolution
  Ex vivo MRI. IEEE Transactions on Medical Imaging 24:1611, 2005
    CAD Analysis: Gradient Features




Madabhushi A, Feldman M, Metaxas D, Tomaszewski JE, Chute D:
Automated detection of prostatic adenocarcinoma from high resolution
Ex vivo MRI. IEEE Transactions on Medical Imaging 24:1611, 2005




         CAD Analysis: Gabor Filters




Madabhushi A, Feldman M, Metaxas D, Tomaszewski JE, Chute D:
Automated detection of prostatic adenocarcinoma from high resolution
Ex vivo MRI. IEEE Transactions on Medical Imaging 24:1611, 2005
CAD Identification of Prostate Carcinoma from
4T MRI Images Using Multiple Classifier Ensembles
                                                              2006
Madabhushi A, Shi J, Rosen M, Tomaszewski JE, Feldman M. IEEE 2006




              Machine Learning for Finding CAP in
                 High Resolution MR Images




    4T MR Exam of Ex-Vivo Prostates with CAD Analysis
   High Resolution MR-Histology
         Data Convergence




Mapping and Data Co-Registration
           Diagnostic Imaging today…

MRI


            In Vivo Optical




                              Pathology


                                          Molecular




                                                      Proteomic

      New Signature
       for CAP in
          MRI




                     Identifying Significant
                        Prostate Cancer


                     Gleason Grading Identifies
                           Five Primary
                         Hisopathological
                   ( Micron Resolution) Patterns
                         of Gland Growth
                       Pattern 3 vs. Pattern 4/5




                    Gleason Sum is Strong Predictor
                        of Clinical Progression
                                               Gleason Sum 6




                                          Gleason Sum >7


                      7:202-
Pinto et al. Urol Int 7:202-208, 2006
Can CAD be Used to Find Gleason Pattern 4 CAP ?




                                                               J.
Doyle S, Hwang M, Shah K, Madabhushi A, Feldman M, Tomaszewski J.
IEEE, 2007




    An Image Analysis Approach to CAP Grading
                                           Texture Features Examining Pixels




 Graph Features Interrrogating Nuclei or Glands
                                                                  Difference
          Original Image   Sum Entropy   Average   Gabor Filter    Entropy


Grade 3
Grade 4
         Diagnostic Imaging today…

MRI
                                  Histologic signature
                                  Gr4 vs Gr 3
         In Vivo Optical




                           Pathology


                                       Molecular




                                                         Proteomic

 CAP MRI
 signature




How to Meet Diagnostic Challenges
   of the Future: An Opinion


      In Finance , the Axiom is
      “ Follow the Money

      In Medicine …………
      “ Follow the Data”
          Characteristics of Data Used in
                   Diagnostics
                   in the Future
Extremely Large and
Quantitative Data Sets
Scaled Data                Path Image Data
                           2 GB
Require Dimensionality
Reduction
Machine Learning
Different Types of Data
Converge


           Microarray Data
           30K = 7.5 MB




                 Data is “Scaled”


     There is Informative Data at Every
     Resolution of Examination
     Informative Data at Each Level of
     Resolution can be Mapped to the Other
     Levels.
     The Data at Each Level of Resolution has
     Unique Attributes
OPTICAL
1x MAGNIFICATION
RESOLUTION= 10-3m

TEXTURE & COLOR VARIGATION
SUSPICIOUS for CAP




1.5 T MR
T2
IN-VIVO
1x MAGNIFICATION
RESOLUTION=10-3m
HYPODENSE AREA
SUSPICIOUS for CAP
4T MR
T2
EX-
EX-VIVO
1x MAGNIFICATION
RESOLUTION=10-4m

HYPODENSE
AREA INTERRUPTING
NORMAL CURVILINEAR
GLAND ARCHITECTURE
DIAGNOSTIC of CAP




 OPTICAL
 200X MAGNIFICATION
 RESOLUTION=10-7m

 HAPHAZZARD PATTERN of INFILTRATING
 MICROACINI DIAGNOSTIC of
 CAP GLEASON PATTERN 3
 CGH DATA
 GENOMIC ANALYSIS
 RESOLUTION = 10-7 to 10-9




        MS2 Spectra from Paraffin Tissue of CAP




 Fatty Acid Synthase in CAP
                Mass Spec Protein Analysis
                Resolution = 10-10




Caldesmon-
Caldesmon-1 in Benign Stromal Hyperplasia
 “The Curse of Multidimensionality”

In Large Multidimensional Space One Can
Always Find Multiple Solutions to a Two Class
Problem ( CAP or Not CAP)

In Order to Avoid This Multiplicity of Solutions
One Must Reduce the Dimensions of the Data
Used for Classification

Manifold Learning Methods Reduce the
Dimensionality of a Data Set from N Dimensions
to M Dimensions where N>>>M




            Machine Learning
         Diagnostic Imaging in 2017
101                                       Vetted by Domain
                                          Knowledge Expertise


                                Integrating Information in
Convergence of                  Disease x Outcome Categories
Large, Diverse,
Scaled
Data Streams



        Facilitated by Machine Learning                 10-10




                      Future Challenges


      Tools to manage and manipulate data types with following
      characteristics (business opportunity ???)
         Multidimensional
         Scaled
         Fused
         Registered
         Clinical
      Architecture must allow new methodologies to plug in
      using standards
         Molecular imaging
         Optical imaging
                  imaging…
         Spectral imaging…
                    The Team

Image Science           Pathology

Anant Madabhushi        Mike Feldman
     Scott Doyle             Deb Chute
     M. Hwang           John Tomaszewski
     Shivang Naik            Li Ping Wang
     Kinsuk Shah
     Jianbo Shi         Radiology
Demetri Metaxas
                               Mitch Schnall
                               Mark Rosen

				
DOCUMENT INFO
Shared By:
Categories:
Stats:
views:7
posted:7/9/2011
language:English
pages:22