Reduced-Dose Deep Learning Reconstruction for Abdominal CT of Liver                     Metastases

Jensen, Corey T.; Gupta, Shiva; Saleh, Mohammed; Liu, Xinming; Wong, Vincenzo K.; Salem, Usama; Qiao, Wei; Samei, Ehsan; Wagner‐Bartak, Nicolaus A.

doi:10.1148/radiol.211838

Cited by 54 publications

(26 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DLIR managed to reduce image noise in the LDCT protocol in this study and this finding is consistent with the results of a previous study which compared image noise in the LDCT protocol with hybrid-IR and DLIR in patient [ 13 , 14 ]. The vendor-specific DLIR was developed with high-quality FBP datasets to learn how to differentiate noise from signals and to suppress noise without changing the image texture [ 22 ].…”

Section: Discussionsupporting

confidence: 93%

“…Similarly, Singh et al [17] reported that all clinically important lesions could be detected on contrast-enhanced LDCT with DLIR. Moreover, Jensen et al [14] reported the utility of contrast-enhanced LDCT with DLIR for detecting liver lesions. Although we did not evaluate the diagnostic ability, we believe that our results provide solid evidence for the feasibility of unenhanced abdominal LDCT using DLIR.…”

Section: Discussionmentioning

confidence: 99%

“…Noda et al [ 12 , 13 ] have reported the impact of DLIR on whole-body and abdominal contrast-enhanced LDCT protocols, and achieved extremely low radiation dose (2.9 mGy and 2.3 mGy in CT dose-index volumes [CTDI vol ]), while maintaining effective image quality and lesion detectability. Jensen et al [ 14 ] reported that contrast-enhanced LDCT reconstructed with DLIR achieve 65% radiation dose reduction and while maintaining the detectability of liver lesions compared to SDCT reconstructed with FBP. To the best of our knowledge, however, no study has evaluated the use of a DLIR in an unenhanced abdominal LDCT protocol.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unenhanced abdominal low-dose CT reconstructed with deep learning-based image reconstruction: image quality and anatomical structure depiction

et al. 2022

View full text Add to dashboard Cite

Purpose To evaluate the utility of deep learning-based image reconstruction (DLIR) algorithm in unenhanced abdominal low-dose CT (LDCT). Materials and methods Two patient groups were included in this prospective study: 58 consecutive patients who underwent unenhanced abdominal standard-dose CT reconstructed with hybrid iterative reconstruction (SDCT group) and 48 consecutive patients who underwent unenhanced abdominal LDCT reconstructed with high strength level of DLIR (LDCT group). The background noise and signal-to-noise ratio (SNR) of the liver, pancreas, spleen, kidney, abdominal aorta, inferior vena cava, and portal vein were calculated. Two radiologists qualitatively assessed the overall image noise, overall image quality, and abdominal anatomical structures depiction. Quantitative and qualitative parameters and size-specific dose estimates (SSDE) were compared between SDCT and LDCT groups. Results The background noise was lower in LDCT group than in SDCT group (P = 0.02). SNRs were higher in LDCT group than in SDCT group (P < 0.001–0.004) except for the liver. Overall image noise was superior in LDCT group than in SDCT group (P < 0.001). Overall image quality was not different between SDCT and LDCT groups (P = 0.25–0.26). Depiction of almost all abdominal anatomical structures was equal to or better in LDCT group than in SDCT group (P < 0.001–0.88). The SSDE was lower in LDCT group (4.0 mGy) than in SDCT group (20.6 mGy) (P < 0.001). Conclusions DLIR facilitates substantial radiation dose reduction of > 75% and significantly reduces background noise. DLIR can maintain image quality and anatomical structure depiction in unenhanced abdominal LDCT.

show abstract

Section: Discussionsupporting

confidence: 93%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unenhanced abdominal low-dose CT reconstructed with deep learning-based image reconstruction: image quality and anatomical structure depiction

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Singh et al further demonstrated that DLR can fundamentally maintain objective image quality and detect low-contrast lesions in the liver when sub-millisievert scans are performed on the chest and abdomen; the radiation dose can be decreased to 71% of that used for low-dose scans [ 33 ]. However, current studies on DLR of the abdomen have mainly focused on low-contrast lesions such as in the liver, with almost no evaluation of high-contrast renal calculi combined with ULDCT [ 34 ]. In this study, we also assessed kidney stones and abdominal disease, and the results indicated that DLR had high diagnostic performance for both high- and low-contrast lesions on ULDCT.…”

Section: Discussionmentioning

confidence: 99%

Application of deep learning reconstruction of ultra-low-dose abdominal CT in the diagnosis of renal calculi

Zhang

et al. 2022

Insights Imaging

View full text Add to dashboard Cite

Background Renal calculi are a common and recurrent urological disease and are usually detected by CT. In this study, we evaluated the diagnostic capability, image quality, and radiation dose of abdominal ultra-low-dose CT (ULDCT) with deep learning reconstruction (DLR) for detecting renal calculi. Methods Sixty patients with suspected renal calculi were prospectively enrolled. Low-dose CT (LDCT) images were reconstructed with hybrid iterative reconstruction (LD-HIR) and was regarded as the standard for stone and lesion detection. ULDCT images were reconstructed with HIR (ULD-HIR) and DLR (ULD-DLR). We then compared stone detection rate, abdominal lesion detection rate, image quality and radiation dose between LDCT and ULDCT. Results A total of 130 calculi were observed on LD-HIR images. Stone detection rates of ULD-HIR and ULD-DLR images were 93.1% (121/130) and 95.4% (124/130). A total of 129 lesions were detected on the LD-HIR images. The lesion detection rate on ULD-DLR images was 92.2%, with 10 cysts < 5 mm in diameter missed. The CT values of organs on ULD-DLR were similar to those on LD-HIR and lower than those on ULD-HIR. Signal-to-noise ratio was highest and noise lowest on ULD-DLR. The subjective image quality of ULD-DLR was similar to that of LD-HIR and better than that of ULD-HIR. The effective radiation dose of ULDCT (0.64 ± 0.17 mSv) was 77% lower than that of LDCT (2.75 ± 0.50 mSv). Conclusion ULDCT combined with DLR could significantly reduce radiation dose while maintaining suitable image quality and stone detection rate in the diagnosis of renal calculi.

show abstract

“…Many authors have demonstrated that subjective image quality does not necessarily correlate with increased diagnostic accuracy; in fact, IR does not preserve low-contrast detectability, and there is wide variability in low-contrast detection among different IR methods for the different dose levels. 4,60 Dimmitt et al 52 evaluated the diagnostic accuracy of liver lesion detection using ASiR-V in comparison with FBP and demonstrated that ASiR-V is objectively superior to FBP, despite the readers having better identified liver lesion with FBP. Therefore, readers should adequately train to avoid any misdiagnosed liver lesions.…”

Section: Clinical Applications Oncological Applicationsmentioning

confidence: 99%