PULMONARY NODULE DETECTION IN CHEST CT USING A DEEP LEARNING-BASED RECONSTRUCTION ALGORITHM. Issue 3 (16th March 2021)

• Record Type: Journal Article
• Authors: Franck, C; Snoeckx, A; Spinhoven, M; El Addouli, H; Nicolay, S; Van Hoyweghen, A; Deak, P; Zanca, F
• Is Part Of: Radiation protection dosimetry. Volume 195:Issue 3/4(2021)
• Page Start: 158
• Page End: 163
• Publication Date: 2021-03-16
• Subjects: Radiation dosimetry -- Periodicals; Radiation -- Safety measures -- Periodicals; 363.1799
• DOI: 10.1093/rpd/ncab025
• Languages: English
• ISSNs: 0144-8420

Abstract

Abstract: This study's aim was to assess whether deep learning image reconstruction (DLIR) techniques are non-inferior to ASIR-V for the clinical task of pulmonary nodule detection in chest computed tomography. Up to 6 (range 3–6, mean 4.2) artificial lung nodules (diameter: 3, 5, 8 mm; density: −800, −630, +100 HU) were inserted at different locations in the Kyoto Kagaku Lungman phantom. In total, 16 configurations (10 abnormal, 6 normal) were scanned at 7.6, 3, 1.6 and 0.38 mGy CTDIvol (respectively 0, 60, 80 and 95% dose reduction). Images were reconstructed using 50% ASIR-V and a deep learning-based algorithm with low (DL-L), medium (DL-M) and high (DL-H) strength. Four chest radiologists evaluated 256 series by locating and scoring nodules on a five-point scale. No statistically significant difference was found among the reconstruction algorithms ( p = 0.987, average across readers AUC: 0.555, 0.561, 0.557, 0.558 for ASIR-V, DL-L, DL-M, DL-H).