Purpose: This study compared the diagnostic performance of two attenuation imaging (ATI) modes—low-frequency (3 MHz) and high-frequency (4 MHz)—for assessing hepatic steatosis, with histopathological hepatic fat fraction (HFF) as the reference standard. Methods: This prospective single-center study enrolled participants with suspected metabolic dysfunction-associated steatotic liver disease (MASLD) scheduled for liver biopsy or surgery between June 2023 and June 2024. Attenuation coefficient (AC) values were consecutively measured using low- and high-frequency ATI modes, while the skin-to-region of interest distance (SRD) was measured simultaneously. Spearman correlation analysis evaluated the relationships of AC with HFF and SRD, and linear regression identified factors affecting AC. Diagnostic performance was evaluated using the area under the receiver operating characteristic curve (AUROC). Results: In total, 119 participants (mean age, 37.2±12.0 years; 87 men) were included, with 73 (61.3%) diagnosed with MASLD. HFF ranged from 0% to 50%. The AC values in the lowfrequency mode were significantly higher than those in the high-frequency mode (0.61 vs. 0.54 dB/cm/MHz, P<0.001). HFF significantly influenced AC in both modes, whereas SRD affected AC only in the high-frequency mode (P<0.001). AC correlated positively with HFF in both modes (r_s≥0.514, P<0.001) and negatively with SRD in the high-frequency mode (r_s=-0.338, P<0.001). The AUROC for hepatic steatosis did not differ significantly between the two modes (0.751 vs. 0.771; P=0.609). Conclusion The low-frequency mode produced higher AC values than the high-frequency mode and demonstrated comparable diagnostic accuracy for assessing hepatic steatosis. Unlike the high-frequency mode, the low-frequency mode was not influenced by SRD.

Hepatocellular adenomas (HCAs) are benign monoclonal liver tumors. Advances in molecular studies have led to the identification of distinct subtypes of HCA with unique pathways, clinical characteristics, and complication risks, underscoring the need for precise diagnosis and tailored management. Malignant transformation and bleeding remain significant concerns. Imaging plays a crucial role in the identification of these subtypes, offering a non-invasive method to guide clinical decision-making. Most studies involving patients with HCAs have been conducted in Western populations; however, the number of studies focused on Asian population has increased in recent years. HCAs exhibit distinct features in Asian population, such as a higher prevalence among male patients and specific subtypes (e.g., inflammatory HCAs). Current clinical guidelines are predominantly influenced by Western data, which may not fully capture these regional differences in epidemiology and subtype distribution. Therefore, this review presents the updated molecular classification of HCAs and their epidemiologic differences between Asian and Western populations, and discuss the role of imaging techniques, particularly magnetic resonance imaging using hepatobiliary contrast agents, in classifying the subtypes and predicting the risk of hepatocellular carcinoma.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Purpose: This study compared the diagnostic performance of two attenuation imaging (ATI) modes—low-frequency (3 MHz) and high-frequency (4 MHz)—for assessing hepatic steatosis, with histopathological hepatic fat fraction (HFF) as the reference standard. Methods: This prospective single-center study enrolled participants with suspected metabolic dysfunction-associated steatotic liver disease (MASLD) scheduled for liver biopsy or surgery between June 2023 and June 2024. Attenuation coefficient (AC) values were consecutively measured using low- and high-frequency ATI modes, while the skin-to-region of interest distance (SRD) was measured simultaneously. Spearman correlation analysis evaluated the relationships of AC with HFF and SRD, and linear regression identified factors affecting AC. Diagnostic performance was evaluated using the area under the receiver operating characteristic curve (AUROC). Results: In total, 119 participants (mean age, 37.2±12.0 years; 87 men) were included, with 73 (61.3%) diagnosed with MASLD. HFF ranged from 0% to 50%. The AC values in the lowfrequency mode were significantly higher than those in the high-frequency mode (0.61 vs. 0.54 dB/cm/MHz, P<0.001). HFF significantly influenced AC in both modes, whereas SRD affected AC only in the high-frequency mode (P<0.001). AC correlated positively with HFF in both modes (r_s≥0.514, P<0.001) and negatively with SRD in the high-frequency mode (r_s=-0.338, P<0.001). The AUROC for hepatic steatosis did not differ significantly between the two modes (0.751 vs. 0.771; P=0.609). Conclusion The low-frequency mode produced higher AC values than the high-frequency mode and demonstrated comparable diagnostic accuracy for assessing hepatic steatosis. Unlike the high-frequency mode, the low-frequency mode was not influenced by SRD.

Purpose: This study compared the diagnostic performance of two attenuation imaging (ATI) modes—low-frequency (3 MHz) and high-frequency (4 MHz)—for assessing hepatic steatosis, with histopathological hepatic fat fraction (HFF) as the reference standard. Methods: This prospective single-center study enrolled participants with suspected metabolic dysfunction-associated steatotic liver disease (MASLD) scheduled for liver biopsy or surgery between June 2023 and June 2024. Attenuation coefficient (AC) values were consecutively measured using low- and high-frequency ATI modes, while the skin-to-region of interest distance (SRD) was measured simultaneously. Spearman correlation analysis evaluated the relationships of AC with HFF and SRD, and linear regression identified factors affecting AC. Diagnostic performance was evaluated using the area under the receiver operating characteristic curve (AUROC). Results: In total, 119 participants (mean age, 37.2±12.0 years; 87 men) were included, with 73 (61.3%) diagnosed with MASLD. HFF ranged from 0% to 50%. The AC values in the lowfrequency mode were significantly higher than those in the high-frequency mode (0.61 vs. 0.54 dB/cm/MHz, P<0.001). HFF significantly influenced AC in both modes, whereas SRD affected AC only in the high-frequency mode (P<0.001). AC correlated positively with HFF in both modes (r_s≥0.514, P<0.001) and negatively with SRD in the high-frequency mode (r_s=-0.338, P<0.001). The AUROC for hepatic steatosis did not differ significantly between the two modes (0.751 vs. 0.771; P=0.609). Conclusion The low-frequency mode produced higher AC values than the high-frequency mode and demonstrated comparable diagnostic accuracy for assessing hepatic steatosis. Unlike the high-frequency mode, the low-frequency mode was not influenced by SRD.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Hepatocellular adenomas (HCAs) are benign monoclonal liver tumors. Advances in molecular studies have led to the identification of distinct subtypes of HCA with unique pathways, clinical characteristics, and complication risks, underscoring the need for precise diagnosis and tailored management. Malignant transformation and bleeding remain significant concerns. Imaging plays a crucial role in the identification of these subtypes, offering a non-invasive method to guide clinical decision-making. Most studies involving patients with HCAs have been conducted in Western populations; however, the number of studies focused on Asian population has increased in recent years. HCAs exhibit distinct features in Asian population, such as a higher prevalence among male patients and specific subtypes (e.g., inflammatory HCAs). Current clinical guidelines are predominantly influenced by Western data, which may not fully capture these regional differences in epidemiology and subtype distribution. Therefore, this review presents the updated molecular classification of HCAs and their epidemiologic differences between Asian and Western populations, and discuss the role of imaging techniques, particularly magnetic resonance imaging using hepatobiliary contrast agents, in classifying the subtypes and predicting the risk of hepatocellular carcinoma.

Purpose: This study compared the diagnostic performance of two attenuation imaging (ATI) modes—low-frequency (3 MHz) and high-frequency (4 MHz)—for assessing hepatic steatosis, with histopathological hepatic fat fraction (HFF) as the reference standard. Methods: This prospective single-center study enrolled participants with suspected metabolic dysfunction-associated steatotic liver disease (MASLD) scheduled for liver biopsy or surgery between June 2023 and June 2024. Attenuation coefficient (AC) values were consecutively measured using low- and high-frequency ATI modes, while the skin-to-region of interest distance (SRD) was measured simultaneously. Spearman correlation analysis evaluated the relationships of AC with HFF and SRD, and linear regression identified factors affecting AC. Diagnostic performance was evaluated using the area under the receiver operating characteristic curve (AUROC). Results: In total, 119 participants (mean age, 37.2±12.0 years; 87 men) were included, with 73 (61.3%) diagnosed with MASLD. HFF ranged from 0% to 50%. The AC values in the lowfrequency mode were significantly higher than those in the high-frequency mode (0.61 vs. 0.54 dB/cm/MHz, P<0.001). HFF significantly influenced AC in both modes, whereas SRD affected AC only in the high-frequency mode (P<0.001). AC correlated positively with HFF in both modes (r_s≥0.514, P<0.001) and negatively with SRD in the high-frequency mode (r_s=-0.338, P<0.001). The AUROC for hepatic steatosis did not differ significantly between the two modes (0.751 vs. 0.771; P=0.609). Conclusion The low-frequency mode produced higher AC values than the high-frequency mode and demonstrated comparable diagnostic accuracy for assessing hepatic steatosis. Unlike the high-frequency mode, the low-frequency mode was not influenced by SRD.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.