Can Computer-aided Detection Be Detrimental to Mammographic Interpretation?

被引:67
作者
Philpotts, Liane E. [1 ]
机构
[1] Yale Univ, Sch Med, Dept Diagnost Radiol, New Haven, CT 06510 USA
关键词
FIELD DIGITAL MAMMOGRAPHY; 172 SUBTLE FINDINGS; SCREENING MAMMOGRAPHY; BREAST-CANCER; DETECTION CAD; RECALL RATES; REPRODUCIBILITY; SENSITIVITY; PERFORMANCE; VARIABILITY;
D O I
10.1148/radiol.2531090689
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
In conclusion, CAD has some potential advantages but also some important and potentially serious limitations. Awareness of the limitations discussed in this article is important for optimal use. A few suggestions to protect oneself from experiencing detrimental effects from the use of CAD in screening interpretation are as follows: (a) Never use CAD as a pre-screener. The present sensitivity of CAD is not sufficient, and many cancers will be missed with this approach. (b) Never use CAD as an initial step in mammogram interpretation. Again, for the same reasons, if one concentrates primarily on areas that CAD has marked, many important findings may be missed. (c) Interpret mammograms as usual, and only use CAD as a last step in a reading protocol. Do not decide not to recall a patient for a finding just because it is not marked by CAD. It might be worth considering that if one finds that CAD is consistently marking findings that the reader had not recognized initially and that appear important (ie, potentially worthy of recall) that the reader should maybe step away from reading for a rest until his or her acuity has resumed. Understanding of the limitations of CAD is important for those interpreting mammograms; this cautious approach to the use of CAD should help optimize this presently imperfect system and minimize the possible detrimental effects. © RSNA, 2009.
引用
收藏
页码:17 / 22
页数:6
相关论文
共 38 条
[1]   Effects of incorrect computer-aided detection (CAD) output on human decision-making in mammography [J].
Alberdi, E ;
Povyakalo, A ;
Strigini, L ;
Ayton, P .
ACADEMIC RADIOLOGY, 2004, 11 (08) :909-918
[2]   Computer-aided detection in screening mammography: Variability in cues [J].
Baker, JA ;
Lo, JY ;
Delong, DM ;
Floyd, CE .
RADIOLOGY, 2004, 233 (02) :411-417
[3]   Computer-aided detection (CAD) in mammography: Does it help the junior or the senior radiologist? [J].
Balleyguier, C ;
Kinkel, K ;
Fermanian, J ;
Malan, S ;
Djen, G ;
Taourel, P ;
Helenon, O .
EUROPEAN JOURNAL OF RADIOLOGY, 2005, 54 (01) :90-96
[4]   ANALYSIS OF CANCERS MISSED AT SCREENING MAMMOGRAPHY [J].
BIRD, RE ;
WALLACE, TW ;
YANKASKAS, BC .
RADIOLOGY, 1992, 184 (03) :613-617
[5]   Computer-aided detection with screening mammography in a university hospital setting [J].
Birdwell, RL ;
Bandodkar, P ;
Ikeda, DM .
RADIOLOGY, 2005, 236 (02) :451-457
[6]   Mammographic characteristics of 115 missed cancers later detected with screening mammography and the potential utility of computer-aided detection [J].
Birdwell, RL ;
Ikeda, DM ;
O'Shaughnessy, KF ;
Sickles, EA .
RADIOLOGY, 2001, 219 (01) :192-202
[7]   A comparison of cancer detection rates achieved by breast cancer screening programmes by number of readers, for one and two view mammography: results from the UK National Health Service breast screening programme [J].
Blanks, RG ;
Wallis, MG ;
Moss, SM .
JOURNAL OF MEDICAL SCREENING, 1998, 5 (04) :195-201
[8]   Improvement in sensitivity of screening mammography with computer-aided detection: A multiinstitutional trial [J].
Brem, RF ;
Baum, J ;
Lechner, M ;
Kaplan, S ;
Souders, S ;
Naul, LG ;
Hoffmeister, J .
AMERICAN JOURNAL OF ROENTGENOLOGY, 2003, 181 (03) :687-693
[9]  
Burhenne LJW, 2000, RADIOLOGY, V215, P554
[10]  
Burhenne LJW, 2000, RADIOLOGY, V217, P353