RJafroc (version 1.3.2)

dataset09: Nico Karssemeijer ROC dataset (CAD vs. radiologists)

Description

This is referred to in the book as the "NICO" dataset. It consists of 200 mammograms, 80 of which contain one malignant mass, interpreted by a CAD system and nine radiologists using the LROC paradigm. The first reader is CAD. The highest rating method was used to convert this to an ROC dataset. The original LROC data is datasetCadLroc. Analyzing this one-treatment data requires methods described in the book, specifically, the function StSignificanceTestingSingleFixedFactor analyzes such datasets.

Usage

dataset09

Format

A list with 8 elements:

• NL Ratings array [1, 1:10, 1:200, 1], of false positives, FPs

• LL Ratings array [1, 1:10, 1:80, 1], of true positives, TPs

• lesionVector array [1:80], number of lesions per diseased case, all set to 1

• lesionID array [1:80, 1], labels of lesions on diseased cases, all set to 1

• lesionWeight array [1:80, 1], weights (or clinical importance) of lesions, all set to 1

• dataType "ROC", the data type

• modalityID [1] "1" treatment label

• readerID [1:10] "1" "2" ..., reader labels

References

Hupse R et al. Standalone computer-aided detection compared to radiologists' performance for the detection of mammographic masses. Eur Radiol. 2013;23(1):93-100.

Examples

# NOT RUN {
str(dataset09)
PlotEmpiricalOperatingCharacteristics(dataset = dataset09, rdrs = 1:10, opChType = "ROC")$Plot


# }