Automatic identification of the boundaries of

Chapter 8, Problem 8.27

(choose chapter or problem)

Automatic identification of the boundaries of significantstructures within a medical image is an area of ongoingresearch. The paper Automatic Segmentation of MedicalImages Using Image Registration: Diagnostic and SimulationApplications (J. of Medical Engr. and Tech.,2005: 5363) discussed a new technique for such identification.A measure of the accuracy of the automatic regionis the average linear displacement (ALD). The paper gavethe following ALD observations for a sample of 49 kidneys(units of pixel dimensions).1.38 0.44 1.09 0.75 0.66 1.28 0.510.39 0.70 0.46 0.54 0.83 0.58 0.641.30 0.57 0.43 0.62 1.00 1.05 0.821.10 0.65 0.99 0.56 0.56 0.64 0.450.82 1.06 0.41 0.58 0.66 0.54 0.830.59 0.51 1.04 0.85 0.45 0.52 0.581.11 0.34 1.25 0.38 1.44 1.28 0.51a. Summarize/describe the data.b. Is it plausible that ALD is at least approximately normallydistributed? Must normality be assumed prior tocalculating a CI for true average ALD or testing hypothesesabout true average ALD? Explain.c. The authors commented that in most cases the ALD isbetter than or of the order of 1.0. Does the data in factprovide strong evidence for concluding that true averageALD under these circumstances is less than 1.0? Carryout an appropriate test of hypotheses.d. Calculate an upper confidence bound for true average ALDusing a confidence level of 95%, and interpret this bound.