ABSTRACT
Background/Aims@#To compare the performance of the Liver Imaging Reporting and Data System (LI-RADS) v2018 and Korean Liver Cancer Association-National Cancer Center (KLCANCC) 2018 criteria for diagnosing hepatocellular carcinoma (HCC) using magnetic resonance imaging (MRI) with hepatobiliary agent (HBA). @*Methods@#We searched the MEDLINE and EMBASE for studies from January 1, 2018, to October 20, 2021, that compared the diagnostic performance of two imaging criteria on HBA-MRI. A bivariate random-effects model was fitted to calculate the per-observation sensitivity and specificity, and the estimates of paired data were compared. Subgroup analysis was performed based on the observation size. Meta-regression analysis was also performed for study heterogeneity. @*Results@#Of the six studies included, the pooled sensitivity of the definite HCC category of the KLCA-NCC criteria (82%; 95% confidence interval [CI], 74% to 90%; I 2 =84%) was higher than that of LR-5 of LI-RADS v2018 (65%; 95% CI, 52% to 77%; I 2 =96%) for diagnosing HCC (p<0.001), while the specificity was lower for KLCA-NCC criteria (87%; 95% CI, 84% to 91%; I 2 =0%) than LI-RADS v2018 (93%; 95% CI, 91% to 96%; I 2 =0%) (p=0.017). For observations sized ≥20 mm, the sensitivity was higher for KLCA-NCC 2018 than for LI-RADS v2018 (84% vs 74%, p=0.012), with no significant difference in specificity (81% vs 85%, p=0.451). The reference standard was a significant factor contributing to the heterogeneity of sensitivities. @*Conclusions@#The definite HCC category of KLCA-NCC 2018 provided a higher sensitivity and lower specificity than the LR-5 of LI-RADS v2018 for diagnosing HCC using MRI with HBA.
ABSTRACT
Purpose@#A meta-analysis was conducted to determine the proportion of contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System category M (LR-M) in hepatocellular carcinomas (HCCs) and non-HCC malignancies and to investigate the frequency of individual CEUS LR-M imaging features. @*Methods@#The MEDLINE and Embase databases were searched from January 1, 2016 to July 23, 2020 for studies reporting the proportion of CEUS LR-M in HCC and non-HCC malignancies. The meta-analytic pooled proportions of HCC and non-HCC malignancies in the CEUS LR-M category were calculated. The meta-analytic frequencies of CEUS LR-M imaging features in nonHCC malignancies were also determined. Risk of bias and applicability were evaluated using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. @*Results@#Twelve studies reporting the diagnostic performance of the CEUS LR-M category were identified, as well as seven studies reporting the frequencies of individual CEUS LR-M imaging features. The pooled proportions of HCC and non-HCC malignancies in the CEUS LR-M category were 54% (95% confidence interval [CI], 44% to 65%) and 40% (95% CI, 28% to 53%), respectively. The pooled frequencies of individual CEUS LR-M imaging features in non-HCC malignancies were 30% (95% CI, 17% to 45%) for rim arterial phase hyperenhancement, 79% (95% CI, 66% to 90%) for early (<60 s) washout, and 42% (95% CI, 21% to 64%) for marked washout. @*Conclusion@#In total, 94% of CEUS LR-M lesions were malignancies, with HCCs representing 54% and non-HCC malignancies representing 40%. The frequencies of individual CEUS LR-M imaging features varied; early washout showed the highest frequency for non-HCC malignancies.
ABSTRACT
Objective@#To evaluate the image quality and lesion detectability of lower-dose CT (LDCT) of the abdomen and pelvis obtained using a deep learning image reconstruction (DLIR) algorithm compared with those of standard-dose CT (SDCT) images. @*Materials and Methods@#This retrospective study included 123 patients (mean age ± standard deviation, 63 ± 11 years;male:female, 70:53) who underwent contrast-enhanced abdominopelvic LDCT between May and August 2020 and had prior SDCT obtained using the same CT scanner within a year. LDCT images were reconstructed with hybrid iterative reconstruction (h-IR) and DLIR at medium and high strengths (DLIR-M and DLIR-H), while SDCT images were reconstructed with h-IR. For quantitative image quality analysis, image noise, signal-to-noise ratio, and contrast-to-noise ratio were measured in the liver, muscle, and aorta. Among the three different LDCT reconstruction algorithms, the one showing the smallest difference in quantitative parameters from those of SDCT images was selected for qualitative image quality analysis and lesion detectability evaluation. For qualitative analysis, overall image quality, image noise, image sharpness, image texture, and lesion conspicuity were graded using a 5-point scale by two radiologists. Observer performance in focal liver lesion detection was evaluated by comparing the jackknife free-response receiver operating characteristic figures-of-merit (FOM). @*Results@#LDCT (35.1% dose reduction compared with SDCT) images obtained using DLIR-M showed similar quantitative measures to those of SDCT with h-IR images. All qualitative parameters of LDCT with DLIR-M images but image texture were similar to or significantly better than those of SDCT with h-IR images. The lesion detectability on LDCT with DLIR-M images was not significantly different from that of SDCT with h-IR images (reader-averaged FOM, 0.887 vs. 0.874, respectively; p = 0.581). @*Conclusion@#Overall image quality and detectability of focal liver lesions is preserved in contrast-enhanced abdominopelvic LDCT obtained with DLIR-M relative to those in SDCT with h-IR.
ABSTRACT
Objective@#To compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists. @*Materials and Methods@#This clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured. @*Results@#A total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, p = 0.80) and radiology residents (79.46%, p = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, p < 0.001) and radiology residents (0.667, p < 0.001). @*Conclusion@#DLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.
ABSTRACT
Objective@#To assess the diagnostic performance of the Liver Imaging Reporting and Data System (LI-RADS) version 2018 treatment response algorithm (TRA) for the evaluation of hepatocellular carcinoma (HCC) treated with transarterial radioembolization. @*Materials and Methods@#This retrospective study included patients who underwent transarterial radioembolization for HCC followed by hepatic surgery between January 2011 and December 2019. The resected lesions were determined to have either complete (100%) or incomplete (< 100%) necrosis based on histopathology. Three radiologists independently reviewed the CT or MR images of pre- and post-treatment lesions and assigned categories based on the LI-RADS version 2018 and the TRA, respectively. Diagnostic performances of LI-RADS treatment response (LR-TR) viable and nonviable categories were assessed for each reader, using histopathology from hepatic surgeries as a reference standard. Inter-reader agreements were evaluated using Fleiss κ. @*Results@#A total of 27 patients (mean age ± standard deviation, 55.9 ± 9.1 years; 24 male) with 34 lesions (15 with complete necrosis and 19 with incomplete necrosis on histopathology) were included. To predict complete necrosis, the LR-TR nonviable category had a sensitivity of 73.3–80.0% and a specificity of 78.9–89.5%. For predicting incomplete necrosis, the LR-TR viable category had a sensitivity of 73.7–79.0% and a specificity of 93.3–100%. Five (14.7%) of 34 treated lesions were categorized as LR-TR equivocal by consensus, with two of the five lesions demonstrating incomplete necrosis. Interreader agreement for the LR-TR category was 0.81 (95% confidence interval: 0.66–0.96). @*Conclusion@#The LI-RADS version 2018 TRA can be used to predict the histopathologic viability of HCCs treated with transarterial radioembolization.
ABSTRACT
Objective@#To compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists. @*Materials and Methods@#This clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured. @*Results@#A total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, p = 0.80) and radiology residents (79.46%, p = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, p < 0.001) and radiology residents (0.667, p < 0.001). @*Conclusion@#DLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.
ABSTRACT
Objective@#To assess the diagnostic performance of the Liver Imaging Reporting and Data System (LI-RADS) version 2018 treatment response algorithm (TRA) for the evaluation of hepatocellular carcinoma (HCC) treated with transarterial radioembolization. @*Materials and Methods@#This retrospective study included patients who underwent transarterial radioembolization for HCC followed by hepatic surgery between January 2011 and December 2019. The resected lesions were determined to have either complete (100%) or incomplete (< 100%) necrosis based on histopathology. Three radiologists independently reviewed the CT or MR images of pre- and post-treatment lesions and assigned categories based on the LI-RADS version 2018 and the TRA, respectively. Diagnostic performances of LI-RADS treatment response (LR-TR) viable and nonviable categories were assessed for each reader, using histopathology from hepatic surgeries as a reference standard. Inter-reader agreements were evaluated using Fleiss κ. @*Results@#A total of 27 patients (mean age ± standard deviation, 55.9 ± 9.1 years; 24 male) with 34 lesions (15 with complete necrosis and 19 with incomplete necrosis on histopathology) were included. To predict complete necrosis, the LR-TR nonviable category had a sensitivity of 73.3–80.0% and a specificity of 78.9–89.5%. For predicting incomplete necrosis, the LR-TR viable category had a sensitivity of 73.7–79.0% and a specificity of 93.3–100%. Five (14.7%) of 34 treated lesions were categorized as LR-TR equivocal by consensus, with two of the five lesions demonstrating incomplete necrosis. Interreader agreement for the LR-TR category was 0.81 (95% confidence interval: 0.66–0.96). @*Conclusion@#The LI-RADS version 2018 TRA can be used to predict the histopathologic viability of HCCs treated with transarterial radioembolization.
ABSTRACT
Purpose@#To construct a standard dataset of contrast-enhanced CT images of liver tumors to test the performance and safety of artificial intelligence (AI)-based algorithms for clinical decision support systems (CDSSs). @*Materials and Methods@#A consensus group of medical experts in gastrointestinal radiology from four national tertiary institutions discussed the conditions to be included in a standard dataset. Seventy-five cases of hepatocellular carcinoma, 75 cases of metastasis, and 30–50 cases of benign lesions were retrieved from each institution, and the final dataset consisted of 300 cases of hepatocellular carcinoma, 300 cases of metastasis, and 183 cases of benign lesions.Only pathologically confirmed cases of hepatocellular carcinomas and metastases were enrolled. The medical experts retrieved the medical records of the patients and manually labeled the CT images. The CT images were saved as Digital Imaging and Communications in Medicine (DICOM) files. @*Results@#The medical experts in gastrointestinal radiology constructed the standard dataset of contrast-enhanced CT images for 783 cases of liver tumors. The performance and safety of the AI algorithm can be evaluated by calculating the sensitivity and specificity for detecting and characterizing the lesions. @*Conclusion@#The constructed standard dataset can be utilized for evaluating the machine-learningbased AI algorithm for CDSS.
ABSTRACT
Purpose@#To construct a standard dataset of contrast-enhanced CT images of liver tumors to test the performance and safety of artificial intelligence (AI)-based algorithms for clinical decision support systems (CDSSs). @*Materials and Methods@#A consensus group of medical experts in gastrointestinal radiology from four national tertiary institutions discussed the conditions to be included in a standard dataset. Seventy-five cases of hepatocellular carcinoma, 75 cases of metastasis, and 30–50 cases of benign lesions were retrieved from each institution, and the final dataset consisted of 300 cases of hepatocellular carcinoma, 300 cases of metastasis, and 183 cases of benign lesions.Only pathologically confirmed cases of hepatocellular carcinomas and metastases were enrolled. The medical experts retrieved the medical records of the patients and manually labeled the CT images. The CT images were saved as Digital Imaging and Communications in Medicine (DICOM) files. @*Results@#The medical experts in gastrointestinal radiology constructed the standard dataset of contrast-enhanced CT images for 783 cases of liver tumors. The performance and safety of the AI algorithm can be evaluated by calculating the sensitivity and specificity for detecting and characterizing the lesions. @*Conclusion@#The constructed standard dataset can be utilized for evaluating the machine-learningbased AI algorithm for CDSS.