Improving detection performance of hepatocellular carcinoma and interobserver agreement for liver imaging reporting and data system on CT using deep learning reconstruction

Abstract

Purpose This study aimed to compare the hepatocellular carcinoma (HCC) detection performance, interobserver agreement for Liver Imaging Reporting and Data System (LI-RADS) categories, and image quality between deep learning reconstruction (DLR) and conventional hybrid iterative reconstruction (Hybrid IR) in CT. Methods This retrospective study included patients who underwent abdominal dynamic contrast-enhanced CT between October 2021 and March 2022. Arterial, portal, and delayed phase images were reconstructed using DLR and Hybrid IR. Two blinded readers independently read the image sets with detecting HCCs, scoring LI-RADS, and evaluating image quality. Results A total of 26 patients with HCC (mean age, 73 years ± 12.3) and 23 patients without HCC (mean age, 66 years ± 14.7) were included. The figures of merit (FOM) for the jackknife alternative free-response receiver operating characteristic analysis in detecting HCC averaged for the readers were 0.925 (reader 1, 0.937; reader 2, 0.913) in DLR and 0.878 (reader 1, 0.904; reader 2, 0.851) in Hybrid IR, and the FOM in DLR were significantly higher than that in Hybrid IR (p = 0.038). The interobserver agreement (Cohen’s weighted kappa statistics) for LI-RADS categories was moderate for DLR (0.595; 95% CI, 0.585–0.605) and significantly superior to Hybrid IR (0.568; 95% CI, 0.553–0.582). According to both readers, DLR was significantly superior to Hybrid IR in terms of image quality (p ≤ 0.021). Conclusion DLR improved HCC detection, interobserver agreement for LI-RADS categories, and image quality in evaluations of HCC compared to Hybrid IR in abdominal dynamic contrast-enhanced CT. Graphical Abstract

Improved vascular depiction and image quality through deep learning reconstruction of CT hepatic arteriography during transcatheter arterial chemoembolization

“…Thus, DLR with higher reconstruction strength appears suitable for CTHA during TACE. The qualitative score for tumor contrast was better on DLR-S than on DLR-M and hybrid-IR, which is consistent with a previous report that showed that DLR improved HCC detection on abdominal CT [24].…”

“…MBIR images show high spatial resolution and low image noise [21,22], and therefore, AiCE also results in low image noise, good edge preservation, and good image detail preservation. In this study, DLR significantly decreased the SD of CT values in subcutaneous fat tissue and improved the qualitative scores for image granulation and artifact, indicating that DLR [23,24]. We also found that DLR significantly increased the CT values of hepatic arteries, which is in accord with a previous report on dynamic abdominal CT that found CT values to be increased with DLR [25].…”

Assessing the Effects of Deep Learning Reconstruction on Abdominal CT Without Arm Elevation

“…12,16 DLR has been shown to reduce image noise and improves image quality compared to conventional Hybrid-IR and FBP. 10,17 Based on our study, it became evident that streak artifacts caused by arms alongside the torso could also be significantly reduced compared with Hybrid-IR and FBP using both the quantitative and qualitative analyses.…”

Deep learning reconstruction for high-resolution computed tomography images of the temporal bone: comparison with hybrid iterative reconstruction

“…In supervised training of DLR, low-quality data and high-quality images are respectively used as the input and reference data. A trained DLR is known to reduce image noise [ 19 ], thereby improving the quality of CT images in regions as varied as the head [ 20 , 21 ], chest [ 9 ], abdomen [ 10 , 19 , 22 , 23 ], and vertebrae [ 11 , 24 , 25 ]. We therefore hypothesized that DLR can also improve the quality of high-resolution CT of the temporal bone.…”