Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Background: /Aim: Gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid-enhanced magnetic resonance imaging (EOBMRI) further enhances the identification of additional hepatic nodules compared with computed tomography (CT) alone; however, the optimal treatment for such additional nodules remains unclear. We investigated the long-term oncological effect of aggressive treatment strategies for additional lesions identified using EOB-MRI in patients with hepatocellular carcinoma (HCC). Methods: Data from 522 patients diagnosed with solitary HCC using CT between January 2008 and December 2012 were retrospectively reviewed. Propensity score-matched (PSM) analysis was used to compare the oncologic outcomes between patients with solitary HCC and those with additional nodules on EOB-MRI after aggressive treatment (resection or radiofrequency ablation [RFA]). Results: Among the 383 patients included, 59 had additional nodules identified using EOB-MRI. Compared with patients with solitary HCC, those with additional nodules on EOB-MRI had elevated total bilirubin, aspartate transaminase, and alanine transaminase; had a lower platelet count, higher MELD score, and highly associated with liver cirrhosis (P<0.05). Regarding long-term outcomes, 59 patients with solitary HCC and those with additional nodules after PSM were compared. Disease-free survival (DFS) and overall survival (OS) were comparable between the two groups (DFS, 60.4 vs. 44.3 months, P=0.071; OS, 82.8 vs. 84.8 months, P=0.986). Conclusion The aggressive treatment approach, either resection or RFA, for patients with additional nodules identified on EOBMRI was associated with long-term survival comparable with that for solitary HCC. However, further studies are required to confirm these findings.

Purpose: The aim of the present study was to evaluate the per-lesion sensitivity and specificity of the Korean Liver Cancer Association–National Cancer Center (KLCA-NCC) 2022 criteria for the noninvasive diagnosis of hepatocellular carcinoma (HCC), with intraindividual comparison of the diagnostic performance of magnetic resonance imaging with extracellular agents (ECA-MRI) and hepatobiliary agents (HBA-MRI). Materials and Methods: Patients at high risk for HCC who were referred to a tertiary academic institution for hepatic lesions with size ≥ 10 mm between July 2019 and June 2022 were enrolled. A total of 91 patients (mean age, 58.1 years; 76 men and 15 women) with 118 lesions who underwent both ECA-MRI and HBA-MRI were eligible for final analysis. The per-lesion sensitivities and specificities of the KLCA-NCC 2022 criteria using ECA-MRI and HBA-MRI were compared using McNemar’s test. Results: The 118 lesions were 93 HCCs, 4 non-HCC malignancies, and 21 benign lesions. On HBA-MRI, the “definite” HCC category showed significantly higher sensitivity than ECA-MRI (78.5% vs. 58.1%, p < 0.001), with identical specificity (92.0% vs. 92.0%, p > 0.999). For “probable” or “definite” HCC categories, there were no differences in the sensitivity (84.9% vs. 84.9%, p > 0.999) and specificity (84.0% vs. 84.0%, p > 0.999) between ECA-MRI and HBA-MRI. Conclusion The “definite” HCC category of the KLCA-NCC 2022 criteria showed higher sensitivity in diagnosing HCC on HBA-MRI compared with ECA-MRI, without compromising specificity. There were no significant differences in the sensitivity and specificity of “probable” or “definite” HCC categories according to ECA-MRI and HBA-MRI.

Gastrointestinal stromal tumors (GISTs) are rare mesenchymal tumors derived from precursors of the interstitial cells of Cajal that commonly arise from the stomach or small intestine. These tumors usually contain KIT and/or PDGFRA mutations, which encode type III receptor tyrosine kinases. Approximately 10% of GISTs originate from sites other than the gastrointestinal tract, such as the mesentery, urinary bladder, retroperitoneum, pancreas, gallbladder, and liver. These tumors are hypothesized to originate from interstitial Cajal-like cells or undifferentiated pluripotent mesenchymal cells outside the gastrointestinal tract. Primary hepatic GISTs are rare, with most hepatic GISTs being secondary.Here, we report the case of a 69-year-old woman with a rare primary hepatic GIST. The hepatic GIST, measuring 13.5 cm, was incidentally discovered in the right liver lobe and exhibited heterogeneous arterial phase hyperenhancement, washout, diffusion restriction, low signal intensity in the hepatobiliary phase, intratumoral hemorrhage, necrosis, and fluid-fluid levels. Imaging revealed no evidence of extrahepatic primary lesions. GIST was pathologically confirmed via percutaneous biopsy and subsequent surgical resection.Despite adjuvant imatinib therapy, the tumor recurred with peritoneal seeding 15 months postoperatively.

Background/aims: Circulating tumor cells (CTCs) with cancer stemness have been demonstrated to be a direct cause of tumor recurrence, and only few studies have reported the role of CTCs in liver transplantation (LT) for hepatocellular carcinoma (HCC). Methods: Epithelial cell adhesion molecule+ (EpCAM+), cluster of differentiation 90+ (CD90+) and EpCAM+/CD90+ CTCs were sorted via fluorescence-activated cell sorting, and transcripts level of EpCAM, K19 and CD90 in the peripheral blood were analyzed via real-time polymerase chain reaction preoperatively and on postoperative days 1 and 7 in 25 patients who underwent living donor liver transplantation (LDLT) for HCC. EpCAM protein was assessed in HCC tissue using immunohistochemical staining. The median follow-up duration was 40 months. Results: HCC after LDLT recurred in four out of 25 patients. Detection of EpCAM+ or CD90+ CTCs correlated well with their messenger RNA levels (p<0.05). EpCAM+ CTCs were readily detected in HCC tissue expressing EpCAM protein. The detection of EpCAM+ CTCs or EpCAM+/CD90+ CTCs before surgery and on postoperative day 1 was significantly associated with HCC recurrence after LT (all p<0.05). Pretransplant serum PIVKA-II >100 mAU/mL and postoperative day 1 EpCAM+/CD90+ CTCs were independent risk factors for HCC recurrence (hazard ratio, 14.64; 95% confidence interval, 1.08 to 198.20; p=0.043 and hazard ratio, 26.88; 95% confidence interval, 1.86 to 387.51; p=0.016, respectively). Conclusions EpCAM+/CD90+ CTCs can be used preoperatively and 1 day after LDLT as key biological markers in LT candidate selection and post-LDLT management.

Background/Aims: This study aimed to investigate whether everolimus (EVR) affects long-term survival after liver transplantation (LT) in patients with hepatocellular carcinoma (HCC). Methods: The data from 303 consecutive patients with HCC who had undergone LT from January 2012 to July 2018 were retrospectively reviewed. The patients were divided into two groups: 1) patients treated with EVR in combination with calcineurin inhibitors (CNIs) (EVR group; n=114) and 2) patients treated with CNI-based therapy without EVR (non-EVR group; n=189). Time to recurrence (TTR) and overall survival (OS) after propensity score (PS) matching were compared between the groups, and prognostic factors for TTR and OS were evaluated. Results: The EVR group exhibited more aggressive tumor biology than the non-EVR group, such as a higher number of tumors (P=0.003), a higher prevalence of microscopic vascular invasion (P=0.017) and exceeding Milan criteria (P=0.029). Compared with the PS-matched non-EVR group, the PS-matched EVR group had significantly better TTR (P<0.001) and OS (P<0.001). In multivariable analysis, EVR was identified as an independent prognostic factor for TTR (hazard ratio [HR], 0.248; P=0.001) and OS (HR, 0.145; P<0.001). Conclusions Combined with CNIs, EVR has the potential to prolong long-term survival in patients undergoing LT for HCC. These findings warrant further investigation in a well-designed prospective study.

Hepatocellular carcinoma (HCC) primarily originates in the liver with hepatic differentiation. However, HCCs are not homogenous, and approximately 35% of HCC cases are classified as histopathological variants that present distinct pathologic characteristics. In particular, the lymphocyte-rich variant is the rarest subtype accounting for less than 1% of HCCs, which is not well known to date about molecular features and pathophysiology. Herein, we present a case of a patient who was suspected of metastatic liver cancer and confirmed as lymphocyte-rich HCC pathologically. A 78-year-old woman who underwent a right hemicolectomy for colon cancer was referred to our hospital for a newly detected liver mass. We could not make a decision because of insufficient evidence for diagnosis from imaging studies. After resection, we found that it was a lymphocyte-rich HCC. The pathologic features and prognostic trends of this subtype are also discussed.

Hepatocellular carcinoma (HCC) with distant metastasis is an absolute contraindication for liver transplantation (LT). However, it is still unclear whether LT is feasible or acceptable in such patients, albeit after being treated with a multidisciplinary approach and after any metastatic lesion is ruled out. We report one such successful treatment with living donor LT (LDLT) after completely controlling far-advanced HCC with inferior vena cava tumor thrombosis and multiple lung metastases. The patient has been doing well without HCC recurrence for eight years since LDLT. The current patient could be an anecdotal case, but provides a case for expanding LDLT indications in the context of advanced HCC and suchlike.