Center for Biomedical Imaging

1
Center for Biomedical Imaging Informatics
University of Medicine Dentistry of New Jersey
Anthony E. Grygotis, M.D. for David J. Foran,
Ph.D.
2
Problem and Motivation

• Subtle visible cues exhibited by some malignant
  lymphomas and leukemia give rise to a significant
  number of false negatives during routine
  microscopic evaluation.
• Mantle Cell Lymphoma (MCL) is particularly
  problematic in this regard
• recently identified (1992), often misdiagnosed as
• Chronic Lymphocytic Leukemia (CLL)
• Folicular Center Cell Lymphoma (FCC)
• much more aggressive clinical course than CLL or
  FCC
• standard therapy for CLL and FCC is ineffective
  with MCL

David J. Foran, Ph.D.
3
Hypothesis

• Hypothesis By exploiting a set of
  non-traditional image metrics, statistical
  pattern recognition and data fusion an image
  guided screening system can be developed which
  reduces the frequency of false negatives while
  improving the accuracy of differential diagnoses.

David J. Foran, Ph.D.
4

• System ArchitectureLogical Blocks Data Flow

David J. Foran, Ph.D.
5
Distributed Telemicroscopy Client/Server
Functions

• Server (C/ JAVA)
• Image acquisition rates resolution
• Coordinates communications among users
• Coordinates communications w/ robotics
• Serializes digitized pathology
• Controls client/server, CPP/JAVA socket
  communications
• Performs entropy-based auto-focusing operations
• Client (JAVA)
• Image distribution and update requests
• Primary client / secondary clients functionality
• Dynamic slider for variable image resolution
• Dynamic text messaging
• Shared graphical pointers

David J. Foran, Ph.D.
6
Distributed Control of RoboticsImplemented with
Software Tokens
David J. Foran, Ph.D.
7
Distributed Telemicroscopy Intelligent Image
Archival Module
Animated Diagram
Features Distributed Telemicroscopy Remote
Control of Robotics Controls Passed as
Token Platform-Independent Shared Graphical
Pointers White-boarding Text-based
Messaging Auto-focusing Distributed Image
Archiving Auto Feature Extraction Auto Database
Management
David J. Foran, Ph.D.
8
Distributed Telemicroscopy Client Interface
Telemicroscopy Demo Video
David J. Foran, Ph.D.
9
Image Guided Decision Support Module

• Supports submission of queries from local and
  remote sites.
• Client-server communications supports
  multi-threaded, multi-user environments.
• Real-time analysis of query images at client
  side.
• Spectral and spatial signatures used to formulate
  multivariate query vector.

• Decisions based on Ground truth database of cases
  for which diagnosis has been independently
  confirmed w/ immunophenotyping and/or molecular
  studies.
• Statistical pattern recognition and data fusion
  determine similarity between unknown and ground
  truth cases.
• Automatically retrieve images and correlated
  clinical data of statistically best matches.
• Speech recognition voice feedback support.

David J. Foran, Ph.D.
10
Multivariate Feature Extraction
Client side computation and generation of query
vector

• Spectral Spatial Signatures
• Chromaticity (LUV Color Space)
• Pixel Area of Cellular Components
• Shape (Elliptic Fourier Descriptors)
• Texture (Multi-scale Simultaneous
  Auto-regression Model)

David J. Foran, Ph.D.
11
Robust Color Segmentation

• Based on non-parametric analysis of feature
  spaces
• Algorithm detects significant modes in Luv
  space
• based on the gradient ascent mean-shift procedure
• randomly tessellates the space with search
  windows
• moves windows till convergence and prune mode
  candidates

Commaniciu and Meer, 1998
David J. Foran, Ph.D.
12
Elliptic Fourier Descriptors
Elliptic Fourier descriptors of a closed curve
are given by
where
,
,
,
The phase shift from the major axis is given by
David J. Foran, Ph.D.
13
Elliptic Fourier Descriptors
To make the Fourier descriptors independent of
starting point,
can be limited to the interval
by using the transformation given by
. Further, to make the Fourier descriptors
independent of scaling, each of
and
are divided by a scaling
The EFDs are then computed by
factor
.
David J. Foran, Ph.D.
14
Elliptic Fourier Descriptors
Invariant to start point, rotation, scale

• A B C
•  Caption Representation of a closed contour by
  Elliptic Fourier descriptors.
• A. Input
• B. Series truncated at 16 harmonics
• C. Series truncated to 4 harmonics
•  

David J. Foran, Ph.D.
15
Similarity Invariant Boundary Representation

• Elliptic Fourier Descriptors of the chain coded
  contour
• Kuhl and Giardina, 1982.
• Resolution of the boundary representation should
• not exceed segmentation uncertainty.
  Superimposed contours for 25 segmentations
• (the darker pixel the higher certainty of
  delineation)
• Experiment
• 5 images
• segment cells using 25 different ROIs
• compute the normalized variance for
  the first 16 harmonics
  (64 coeffs)
• typical result
• first ten harmonics are reliable.

David J. Foran, Ph.D.
16
Multiscale Texture Representation

• Multiscale Simultaneous Autoregressive Model
  (MRSAR)
• Symmetric MRSAR applied to the lightness L
  component
• the pixel at any location depends linearly on its
  neighbors
• 15-dimensional feature vector (3 resolutions) and
  its covariance matrix derived for each cell in
  the database.
• Distances between cells is computed taking into
  account within and across class variations.

Examples of nuclear textures. (dynamic range
enlarged to improve reproduction)
David J. Foran, Ph.D.
17
Multivariate Fusion

• Combine feature measures for area, shape, texture
  and color of cellular components
• Optimize the sum of conditional probabilities of
  correct decision across entire data set
• Ameboid search for global max on objective
  surface
• Weighting factors computed on a dual-PIII w/ 2GB
  

J 3.4207
David J. Foran, Ph.D.
18
Man-Machine Performance Studies
IGDS Confusion Matrix
Human Observer 1
False Negatives (averaged) IGDS 4.3 Human
Observers 14.6
David J. Foran, Ph.D.
19
IGDS Client Interface
IGDS Demo Video
David J. Foran, Ph.D.
20
Unsupervised Specimen Analysis
Video demonstration of unsupervised analysis
data management
David J. Foran, Ph.D.
21
Regional, Network-Based Laboratory for Research
in Biomedical Informatics
Through HUBS, we are establishing a high speed
virtual private network link among strategic
sites at UMDNJ, the University of Pittsburgh
Medical School, Johns Hopkins University, the
University of Pennsylvania School of Medicine,
and the Pittsburgh Super Computer Center. This
network-based laboratory will be utilized to
expand our research base in collaborative
telemedicine, interactive medical education and
computer-based decision support in diagnostic
pathology and radiology.
David J. Foran, Ph.D.
22
International Telemedicine Program

• Deployed portable telemedicine systems to RWJUH
  and to sister hospital at Zhong Shan Hospital,
  Shanghai, China. The systems are used for
  conferencing, clinical training, and remote
  digital consultation in pathology and radiology.
   

David J. Foran, Ph.D.
23
Future Directions

• Conduct comprehensive, multi-site statistical
  assessment of IGDS using
• recall and precision metrics to evaluate
  retrieval effectiveness of the query
• algorithms (HUBS).
• Optimize algorithms based on recall, precision
  man-machine studies.
• Complete the modifications which enable
  submission of queries from
• Virtual Microscopes (OSU, JHMI, UMD).
• Explore the potential of multi-resolution, CBIR
  (UPitt).
• Evaluate the use of the IGDS in a broader
  spectrum of hematopathology
• and cytopathology applications (UPenn).
• Expand performance studies used to test the
  DT/IGDS core system in
• imaging, analyzing, and archiving tissue
  microarrays (CINJ).

David J. Foran, Ph.D.
24
Center for Biomedical Imaging Informatics
Video with closing credits
David J. Foran, Ph.D.