Lesion detection on a combined “All-in-One” window compared to conventional window settings in thoracic oncology chest CT examinations - 09/08/19

Doi : 10.1016/j.diii.2019.07.009

A. Snoeckx ^a,⁎ , P. Vuylsteke ^b, B.J.G. Broeckx ^c, K. Carpentier ^a, R. Corthouts ^a, E.A. Luyckx ^a, S. Nicolay ^a, A.V. Hoyweghen ^a, M.J. Spinhoven ^a, J. Cant ^b, P.M. Parizel ^a
^a Department of Radiology, Antwerp University Hospital and University of Antwerp, 2650 Edegem, Belgium
^b Agfa Medical Imaging, 2640 Mortsel, Belgium
^c Ghent University, 9820 Merelbeke, Belgium

^⁎Corresponding author at: Department of Radiology, Antwerp University Hospital and University of Antwerp, Wilrijkstraat 10, 2650 Edegem, Belgium.Department of Radiology, Antwerp University Hospital and University of AntwerpWilrijkstraat 10Edegem2650Belgium

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Friday 09 August 2019
Cet article a été publié dans un numéro de la revue, cliquez ici pour y accéder

Abstract

Purpose

The purpose of this study was to investigate if lesion detection using a single “All-in-One” (AIO) window was non-inferior to lesion detection on conventional window settings in thoracic oncology chest computed tomography (CT) examinations.

Materials and methods

In a retrospective study, 50 consecutive chest CT examinations of 50 patients (31 men, 19 women; mean age 64±10 [SD] years, range: 35–82 years) containing 417 lesions, were reviewed by 6 radiologists, subdivided into 2 groups of 3 radiologists each, with similar levels of expertise in each group (senior staff member, junior staff member and radiology resident). All examinations were reviewed in conventional or AIO window settings by one of the groups. A ‘lesion’ was defined as any abnormality seen on the chest CT examination, including both benign and malignant lesions, findings in chest and upper abdomen, and measurable and non-measurable disease. Lesions were listed as ‘missed’ when they were not seen by at least two out of three observers. F-tests were used to evaluate the significance of the variables of interest within a mixed model framework and kappa statistics to report interobserver agreement.

Results

On a reader level, 54/417 lesions (12.9%) were not detected by the senior staff member reading the studies in conventional window settings and 45/417 (10.8%) by the senior staff member reading the AIO images. For the junior staff member and radiology resident this was respectively 55/417 (13.2%) and 67/417 (16.1%) for the conventional window settings and 43/417 (10.3%) and 61/417 (14.6%) for the AIO window. On a lesion level, 68/417 (16.3%) were defined as ‘missed’ lesions (lesions not detected by at least 2 readers): 21/68 (30.9%) on the AIO-window, 30/68 (44.1%) on conventional views and 17/68 (25.0%) on both views. The use of the AIO window did not result in an increase of missed lesions (P>0.99). Interobserver agreement in both groups was similar (P=0.46). Regarding lesions that were categorized as ‘missed’ on the AIO window or on conventional window settings, there was no effect of location (chest or upper abdomen) (P=0.35), window (P=0.97) and organ (P=0.98).

Conclusions

A single AIO-window is non-inferior to multiple conventional window settings for lesion detection on chest CT examinations in thoracic oncology patients.

Le texte complet de cet article est disponible en PDF.

Keywords : Diagnosis, Computed tomography (CT), Computer-assisted image processing, Computer-assisted image interpretation, Lung neoplasms