2017
DOI: 10.1007/s00330-017-4903-z
|View full text |Cite
|
Sign up to set email alerts
|

The impact of trained radiographers as concurrent readers on performance and reading time of experienced radiologists in the UK Lung Cancer Screening (UKLS) trial

Abstract: ObjectivesTo compare radiologists’ performance reading CTs independently with their performance using radiographers as concurrent readers in lung cancer screening.Methods369 consecutive baseline CTs performed for the UK Lung Cancer Screening (UKLS) trial were double-read by radiologists reading either independently or concurrently with a radiographer. In concurrent reading, the radiologist reviewed radiographer-identified nodules and then detected any additional nodules. Radiologists recorded their independent… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
16
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
8

Relationship

1
7

Authors

Journals

citations
Cited by 24 publications
(17 citation statements)
references
References 29 publications
1
16
0
Order By: Relevance
“…The DL algorithm performed with a high AUC for positive-case classification and exceeded the average performance of radiologists but had slightly worse performance on the LUNA data set. The mean sensitivity of radiologists reading independently has been reported to be 62.2-89.2% in previous literature 47 . In the present study, the average sensitivity of the nine radiologists was 64-96%, with an average of 82%.…”
Section: Discussionmentioning
confidence: 90%
“…The DL algorithm performed with a high AUC for positive-case classification and exceeded the average performance of radiologists but had slightly worse performance on the LUNA data set. The mean sensitivity of radiologists reading independently has been reported to be 62.2-89.2% in previous literature 47 . In the present study, the average sensitivity of the nine radiologists was 64-96%, with an average of 82%.…”
Section: Discussionmentioning
confidence: 90%
“…16e18 In the NLST CT screening arm, 8.9% of cancers were missed on the initial CT. 19 Concurrent reading of scans by two reporters has been shown to improve diagnostic sensitivity, but is time-consuming and impractical in daily practice. 20 This underlines the need for machine-learning tools that assist radiologists in nodule identification, and Figure 1 Comparison of the number of articles indexed by PubMed every year mentioning the search terms "computer aided diagnosis" (left axis), or "machine learning" (right axis).…”
Section: Nodule Detectionmentioning
confidence: 99%
“…This involves radiographers 'first reporting' prior to a definitive (second) report by a radiologist; definitive (single) reporting by radiographers emerged following pilot projects in the 1990s. 43 In the papers reviewed the former practice is variously described as commenting, 44 preliminary clinical evaluation, 32 initial reporting 44 or concurrent reading, 36 the latter as definitive reporting, 45 clinical reporting, 29 reporting in clinical practice 35 or single formal written reporting. 31 The remainder of this review focuses predominantly on the practise of definitive single reporting by radiographers in the UK.…”
Section: Reporting Responsibilitymentioning
confidence: 99%
“…Most recently Nair et al 36 demonstrated that training two radiographers experienced in thoracic CT scan image acquisition to detect lung nodules could improve sensitivity and reduce reading time despite a small increase in false positive calls. The radiographers in this study (double) read 369 consecutive baseline CT examinations performed in the UK lung cancer screening trial concurrently alongside two experienced and specialist consultant thoracic radiologists.…”
Section: Computed Tomographymentioning
confidence: 99%
See 1 more Smart Citation