Automatic Identification of Ambiguous Prostate Capsule Boundary Lines

Automatic Identification of Ambiguous Prostate Capsule Boundary Lines Using Shape Information and Least Squares Curve Fitting Technique Rania Hussein, Ph. D. Department of Computer Engineering Digi. Pen Institute of Technology Seattle, WA Frederic (Rick) D. Mc. Kenzie, Ph. D. Department of Electrical and Computer Engineering Old Dominion University Norfolk, VA fmckenzi@ece. odu. edu 1

Old Dominion University • Located near Virginia Beach – 3 hours south of Washington, DC – Over 25, 000 students • Engineering College has over 100 Faculty • Electrical & Computer Engineering Dept. – – 26 faculty members 240 undergraduate students 140 graduate students: 50 Ph. D, 90 Masters 2003 R&D Expenditure National Ranking of ECE at ODU according to NSF: 29 – 2004 R&D Expenditure National Ranking of ECE at ODU according to NSF: 28 2

Virginia Modeling Analysis and Simulation Center • Enterprise Center, Old Dominion University • 12 Faculty, ~55 research & admin staff • Multidisciplinary: activities include faculty and students from all six academic colleges • ~$7. 5 M in funded research in FY 2005 • Modeling & Simulation Graduate Programs – Over 100 Masters. Staffand Doctorate students and Activities

Outline • • • Motivation Problem definition Background Approach Results Conclusion 4

Motivation • Assessment of different surgical approaches to prostatectomy using objective parameters (such as extracapsular tissue coverage) • Reconstruct the prostate capsule and its extra-capsular tissue from excised specimen histology • Capsule contour is needed and is currently drawn manually by the pathologist • Subjective and therefore may affect the accuracy of the quantitation results 5

Problem definition • This research focuses on developing an algorithm that automatically identifies this capsule contour • Validation is performed by comparing with the hand-drawn contour of the pathologist 6

Problem Definition • Slices are serially cut from apex to base at precise and parallel 5 mm intervals • Sections of four microns in thickness are mounted on large glass slides stained with Eosin and Hematoxilin The capsule is manually marked by a pathologist as shown by the dashed line in the figure 7

Background Epithelial cells Parenchymal contour • The prostate capsule is a fibromuscular band of transversely oriented collagenous fibers, and it lies between the parenchymal contour and the periprostatic tissues 8

Prostatic tissues that can be automatically classified • Diamond et al [19] used whole-mount radical prostatectomy histology captured at 40 x magnification (58 k x 42 k image size) • Subimage sizes of 100 x 100 for processing • The authors were able to correctly classify 79. 3% of tissue in subregions 9

Detectable Constraints • The prostate capsule has a mean thickness of 0. 5 to 2 mm [Sattar et al. ] • However, it is unrecognizable in areas – Naturally occurring intrusion of muscle into the prostate gland at the anterior apex. – Fusion of extraprostatic connective tissue with the prostate gland at its base. 10

Limacon shape equation • Limacon equation is r = b + a cos θ (a) (b) (c) Limacon curves (a) when a< b, (b) when a<b<2 a, and (c) when 2 a<=b. • To take rotation into consideration, the equation becomes r = b + a cos (θ+Φ) 11

Least squares algorithm Assuming that we have a number n of discrete data (x 1, y 1), (x 2, y 2), …(xn, yn) and f(x) is a function for fitting a curve. Therefore, f(x) has the deviation (error) d from each data point, i. e. d 1 = y 1 -f(x 1), d 2 = y 2 -f(x 2), …, dn = yn-f(xn) Using Limacon Equation • Select range of values for the center of the curve (cx, cy) • Select range of values for the curve parameters (a, b) • Select range of values for the curve rotation angle (theta)12

a b a) Arrows point to the detected parts of the prostate capsule, (b) Arrow points to the curve representing the prostate shape located as close as possible to the capsule parts. 13

Merging arcs (least squares) • Once the curve is positioned, this shape curve is combined with the true capsule segments 14

Curve Constraint Violation • The generated curve can violate the constraints – Prostate capsule is typically located between the parenchymal contour and the prostate perimeter 15

Curve Constraint Adjustment • Flood fill algorithm used to relocate the curve sections that violate constraints – New points are generated between the 2 contours – Least square algorithm executed again for better results 16

Experiment Results • 13 specimens were used • Tested on Pentium 4 machines with dual processors of 3. 4 GHz and 1. 00 GB of RAM • Parts where capsule is expected to exist (as figure shows) were manually outlined. • Tested using 3 shape equations: Circle, Limacon, and ellipse 17

Least squares testing example a) Capsule parts d) New points generated by flood-fill algorithm b) LS Generated curve e) Curve generated after the 2 nd run of LS c) Arcs merging f) Final curve after merging arcs from the 2 nd run 18

Performance evaluation • Used both the root mean square error RMSE and the percentage of error Where n is the number of points in the curve, di is the min distance from point i in the curve to the reference curve. Where m is the number of points in the reference curve, di is the min distance from point i in the reference curve to the curve 19

Performance evaluation • Thresholds considered in our study are equal to 1%, 1. 5%, and 2% of the number of pixels of the image diagonal. Figure illustrates the size that each threshold contributes to the actual size of a prostate slice. The squares that appear on the top left represent the number of pixels that are equal to 1%, 1. 5%, 2% of the image diagonal respectively. The %matching between our generated curve and the reference curve is calculated where, %matching = 1 - percentage error 20

Results 21

Results 22

How to improve the results • Use more complex shape equations with greater degree of freedom • A standard shape of a prostate slice can be defined by 23

Conclusion • The algorithm provides better results as better shape equations are used. • The least squares algorithm gave better results on average than a GHT algorithm. • GHT achieved zero error within our threshold on one of the specimens, which shows that more complex equations with greater degree of freedom is likely to give better results in the GHT. • The combination of the two algorithms within the overall process allows a tradeoff between faster processing time and smaller errors in using more complicated and flexible prostate shapes. 24

Thank You! 25