CAD in mammography: lesion-level versus case-level analysis of the effects of prompts on human decisions
- 62 Downloads
To understand decision processes in CAD-supported breast screening by analysing how prompts affect readers’ judgements of individual mammographic features (lesions). To this end we analysed hitherto unexamined details of reports completed by mammogram readers in an earlier evaluation of a CAD tool.
Material and methods
Assessments of lesions were extracted from 5,839 reports for 59 cancer cases. Statistical analyses of these data focused on what features readers considered when recalling a cancer case and how readers reacted to CAD prompts.
About 13.5% of recall decisions were found to be caused by responses to features other than those indicating actual cancer. Effects of CAD: lesions were more likely to be examined if prompted; the presence of a prompt on a cancer increased the probability of both detection and recall especially for less accurate readers in subtler cases; lack of prompts made cancer features less likely to be detected; false prompts made non-cancer features more likely to be classified as cancer.
The apparent lack of impact reported for CAD in some studies is plausibly due to CAD systematically affecting readers’ identification of individual features, in a beneficial way for certain combinations of readers and features and a damaging way for others. Mammogram readers do not ignore prompts. Methodologically, assessing CAD by numbers of recalled cancer cases may be misleading.
KeywordsComputer-assisted diagnosis Mammography Screening Computer system evaluation Decision making
Unable to display preview. Download preview PDF.
- 12.Povyakalo AA, Alberdi E, Strigini L, Ayton P (2004) Evaluating ‘Human + Advisory computer’ system: a case study. In: Dearden A, Watts L (eds) HCI2004, 18th British HCI Group Annual Conf. British HCI Group, Leeds, pp 93–96Google Scholar
- 13.Strigini L, Povyakalo AA, Alberdi E (2003) Human-machine diversity in the use of computerised advisory systems: a case study. In: 2003 Int. Conf. on Dependable Systems and Networks (DSN’03). IEEE, San FranciscoGoogle Scholar
- 16.Hartswood M, Procter R, Rouncefield M, Slack R, Soutter J, Voss A (2003) ‘Repairing’ the Machine: a Case study of the evaluation of computer-aided detection tools in breast screening. In: Kuutti K Karsten EH, Fitzpatrick G, Dourish P, Schmidt K (ed) Eighth European Conference on Computer Supported Cooperative Work (ECSCW 2003). Helsinki, FinlandGoogle Scholar