当前位置： SCI文献检索 > RADIOLOGY期刊下所有文献 > CT colonography: preliminary assessment of a double-read paradigm that uses computer-aided detection as the first reader.

CT colonography: preliminary assessment of a double-read paradigm that uses computer-aided detection as the first reader.

Abstract：

PURPOSE:To compare diagnostic performance and time efficiency of double-reading first-reader computer-aided detection (CAD) (DR FR CAD) followed by radiologist interpretation with that of an unassisted read using segmentally unblinded colonoscopy as reference standard. MATERIALS AND METHODS:The local ethical committee approved this study. Written consent to use examinations was obtained from patients. Three experienced radiologists searched for polyps 6 mm or larger in 155 computed tomographic (CT) colonographic studies (57 containing 10 masses and 79 polyps ≥ 6 mm). Reading was randomized to either unassisted read or DR FR CAD. Data sets were reread 6 weeks later by using the opposite paradigm. DR FR CAD consists of evaluation of CAD prompts, followed by fast two-dimensional review for mass detection. CAD sensitivity was calculated. Readers' diagnoses and reviewing times with and without CAD were compared by using McNemar and Student t tests, respectively. Association between missed polyps and lesion characteristics was explored with multiple regression analysis. RESULTS:With mean rate of 19 (standard deviation, 14; median, 15; range, 4-127) false-positive results per patient, CAD sensitivity was 90% for lesions 6 mm or larger. Readers' sensitivity and specificity for lesions 6 mm or larger were 74% (95% confidence interval [CI]: 65%, 84%) and 93% (95% CI: 89%, 97%), respectively, for the unassisted read and 77% (95% CI: 67%, 85%) and 90% (95% CI: 85%, 95%), respectively, for DR FR CAD (P = .343 and P = .189, respectively). Overall unassisted and DR FR CAD reviewing times were similar (243 vs 239 seconds; P = .623); DR FR CAD was faster when the number of CAD marks per patient was 20 or fewer (187 vs 220 seconds, P <01). Odds ratio of missing a polyp with CAD decreased as polyp size increased (0.6) and for polyps visible on both prone and supine scans (0.12); it increased for flat lesions (9.1). CONCLUSION:DR FR CAD paradigm had similar performance compared with unassisted interpretation but better time efficiency when 20 or fewer CAD prompts per patient were generated.

journal_name

Radiology

journal_title

Radiology

authors

Iussich G,Correale L,Senore C,Segnan N,Laghi A,Iafrate F,Campanella D,Neri E,Cerri F,Hassan C,Regge D

doi

10.1148/radiol.13121192

subject

Has Abstract

pub_date

2013-09-01 00:00:00

pages

743-51

issue

eissn

0033-8419

issn

1527-1315

pii

radiol.13121192

journal_volume

268

pub_type

杂志文章

在线工具

CT colonography: preliminary assessment of a double-read paradigm that uses computer-aided detection as the first reader.