Computer-aided detection of masses at mammography: interactive decision support versus prompts
| Autor: | Ritse M. Mann, Marc B Lobbes, Rianne Hupse, Maurice Samulski, Carla Boetes, Gerard J. den Heeten, Nico Karssemeijer, Roel Mus, David Beijerinck, Ruud M. Pijnappel |
|---|---|
| Přispěvatelé: | CCA -Cancer Center Amsterdam, APH - Amsterdam Public Health, Biomedical Engineering and Physics, Radiology and Nuclear Medicine, MUMC+: DA BV Medisch Specialisten Radiologie (9), Beeldvorming, RS: GROW - School for Oncology and Reproduction |
| Jazyk: | angličtina |
| Rok vydání: | 2013 |
| Předmět: |
medicine.medical_specialty
Decision support system ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION MEDLINE CAD Breast Neoplasms Aetiology screening and detection [ONCOL 5] Risk Assessment Sensitivity and Specificity Radiographic image interpretation User-Computer Interface medicine Prevalence Mammography Humans Radiology Nuclear Medicine and imaging Medical physics cardiovascular diseases health care economics and organizations Aged Netherlands medicine.diagnostic_test business.industry Data Science Reproducibility of Results Middle Aged Decision Support Systems Clinical Computer aided detection Radiographic Image Interpretation Computer-Assisted Female Risk assessment business |
| Zdroj: | Radiology, 266(1), 123-129. Radiological Society of North America Inc. Radiology, 266(1), 123-129. Radiological Society of North America, Inc. Radiology, 266, 123-129 Radiology, 266, pp. 123-129 |
| ISSN: | 0033-8419 |
| DOI: | 10.1148/radiol.12120218 |
| Popis: | Item does not contain fulltext Purpose: To compare effectiveness of an interactive computer-aided detection (CAD) system, in which CAD marks and their associated suspiciousness scores remain hidden unless their location is queried by the reader, with the effect of traditional CAD prompts used in current clinical practice for the detection of malignant masses on full-field digital mammograms. Materials and Methods: The requirement for institutional review board approval was waived for this retrospective observer study. Nine certified screening radiologists and three residents who were trained in breast imaging read 200 studies (63 studies containing at least one screen-detected mass, 17 false-negative studies, 20 false-positive studies, and 100 normal studies) twice, once with CAD prompts and once with interactive CAD. Localized findings were reported and scored by the readers. In the prompted mode, findings were recorded before and after activation of CAD. The partial area under the location receiver operating characteristic (ROC) curve for an interval of low false-positive fractions typical for screening, from 0 to 0.2, was computed for each reader and each mode. Differences in reader performance were analyzed by using software. Results: The average partial area under the location ROC curve with unaided reading was 0.57, and it increased to 0.62 with interactive CAD, while it remained unaffected by prompts. The difference in reader performance for unaided reading versus interactive CAD was statistically significant (P = .009). Conclusion: When used as decision support, interactive use of CAD for malignant masses on mammograms may be more effective than the current use of CAD, which is aimed at the prevention of perceptual oversights. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|