This will count as one of your downloads.
You will have access to both the presentation and article (if available).
We evaluate the Pre-Whitening Matched Filter (PWMF), “Eye-Filtered” Non-Pre-Whitening (NPWE) and Sparse-Channelized Difference-of-Gaussian (SDOG) models for predictive performance, and we compare various training and testing regimens. These include “training” by using reported values from the literature, training and testing on the same set of experimental conditions, and training and testing on different sets of experimental conditions. Of this latter category, we use both leave-one-condition-out for training and testing as well as a leave-one-factor-out strategy, where all conditions with a given factor level are withheld for testing. Our approach may be considered a fixed-reader approach, since we use all available readers for both training and testing.
Our results show that training models improves predictive accuracy in these tasks, with predictive errors dropping by a factor of two or more in absolute deviation. However, the fitted models are not fully capturing the effects apodization and other factors in these tasks.
This will count as one of your downloads.
You will have access to both the presentation and article (if available).
Short of a clinical trial, observer studies are used to measure the performance of radiologists and to compare different imaging technologies with the aim of understanding how the technology might be used clinically. The goal of this course is to provide guidance on how to design, conduct, and analyze an observer study. We will examine how to plan an observer study, step by step, and then how to implement the plan in detail. The focus will be on pitfalls and common mistakes.
We will review basic ROC analysis and commonly used methods for analyzing multireader, multicase (MRMC) ROC observer data. Related software and sample-size estimation will also be discussed and demonstrated using real datasets.
The participants will take part in some simulated reader studies using a computer interface, compete for prizes, and depart with a better understanding of reader studies of diagnostic imaging devices.
View contact details
No SPIE Account? Create one
