| viperObs {viperData} | R Documentation |
The VIPER data sets were created by aggregating
all the raw reader data files from the FDA
Validation of Imaging Premarket Evaluation and Regulation (VIPER):
viperObs365 and viperObs455.
The images used in this study were selected from the DMIST images [Pisano2005_NEJM_v353p1773]. The VIPER study concept 2011. Data collection September 2013 to August 2015. Please refer to journal paper for details.
viperObs is a data frame with 12 variables:
caseType455 [str] Cancer type based on 455 days result: birads123sfm, birads0sfm, birads0ffdm, birads123ffdm, cancer
caseType365 [str] Cancer type based on 365 days result: birads123sfm, birads0sfm, birads0ffdm, birads123ffdm, cancer
cancerStatus455 [num] Cancer status based on 455 days result. 1: Cancer; 2: Not cancer
cancerStatus365 [num] Cancer status based on 365 days result. 1: Cancer; 2: Not cancer
caseID [num] case ID
readerID [str] reader ID: 44 readers
modalityID [str] modality ID: FFDM, SFM
recall [num] binary recall decision. 1: recall; 2: not recall
abnormalityType abnormality type of case
score [num] dignostic result
0-100: not recall, lower value means higher not recall confidence
101-200: recall, higer value means higher recall confidence
caseGroup [str] group of case: cgrp1, cgrp2, cgrp3, cgrp4
subStudyLabel [str] study group: screeningLowP,screeningMedP,screeningHighP, challengeMedP,challengeHighP