Deep learning and digital pathology powers prediction of HCC development in steatotic liver disease.

BACKGROUND AND AIMS: Identifying patients with steatotic liver disease who are at a high risk of developing HCC remains challenging. We present a deep learning (DL) model to predict HCC development using hematoxylin and eosin-stained whole-slide images of biopsy-proven steatotic liver disease. APPROACH AND RESULTS: We included 639 patients who did not develop HCC for ≥7 years after biopsy (non-HCC class) and 46 patients who developed HCC <7 years after biopsy (HCC class). Paired cases of the HCC and non-HCC classes matched by biopsy date and institution were used for training, and the remaining nonpaired cases were used for validation. The DL model was trained using deep convolutional neural networks with 28,000 image tiles cropped from whole-slide images of the paired cases, with an accuracy of 81.0% and an AUC of 0.80 for predicting HCC development. Validation using the nonpaired cases also demonstrated a good accuracy of 82.3% and an AUC of 0.84. These results were comparable to the predictive ability of logistic regression model using fibrosis stage. Notably, the DL model also detected the cases of HCC development in patients with mild fibrosis. The saliency maps generated by the DL model highlighted various pathological features associated with HCC development, including nuclear atypia, hepatocytes with a high nuclear-cytoplasmic ratio, immune cell infiltration, fibrosis, and a lack of large fat droplets. CONCLUSIONS: The ability of the DL model to capture subtle pathological features beyond fibrosis suggests its potential for identifying early signs of hepatocarcinogenesis in patients with steatotic liver disease.

HNF1B-driven three-dimensional chromatin structure for molecular classification in pancreatic cancers.

The molecular subtypes of pancreatic cancer (PC), either classical/progenitor-like or basal/squamous-like, are currently a major topic of research because of their direct association with clinical outcomes. Some transcription factors (TFs) have been reported to be associated with these subtypes. However, the mechanisms by which these molecular signatures of PCs are established remain unknown. Epigenetic regulatory processes, supported by dynamic changes in the chromatin structure, are essential for transcriptional profiles. Previously, we reported the importance of open chromatin profiles in the biological features and transcriptional status of PCs. Here, we aimed to analyze the relationships between three-dimensional (3D) genome structures and the molecular subtypes of human PCs using Hi-C analysis. We observed a correlation of the specific elements of 3D genome modules, including compartments, topologically associating domains, and enhancer-promoter loops, with the expression of related genes. We focused on HNF1B, a TF that is implicated in the progenitor subtype. Forced expression of HNF1B in squamous-type PC organoids induced the upregulation and downregulation of genes associated with progenitor and squamous subtypes, respectively. Long-range genomic interactions induced by HNF1B were accompanied by compartment modulation and H3K27ac redistribution. We also found that these HNF1B-induced changes in subtype-related gene expression required an intrinsically disordered region, suggesting a possible involvement of phase separation in compartment modulation. Thus, mapping of 3D structural changes induced by TFs, such as HNF1B, may become a useful resource for further understanding the molecular features of PCs.

Machine learning for individualized prediction of hepatocellular carcinoma development after the eradication of hepatitis C virus with antivirals.

BACKGROUND AND AIMS: Accurate risk stratification for hepatocellular carcinoma (HCC) after achieving a sustained viral response (SVR) is necessary for optimal surveillance. We aimed to develop and validate a machine learning (ML) model to predict the risk of HCC after achieving an SVR in individual patients. METHODS: In this multicenter cohort study, 1742 patients with chronic hepatitis C who achieved an SVR were enrolled. Five ML models were developed including DeepSurv, gradient boosting survival analysis, random survival forest (RSF), survival support vector machine, and a conventional Cox proportional hazard model. Model performance was evaluated using Harrel' c-index and was externally validated in an independent cohort (977 patients). RESULTS: During the mean observation period of 5.4 years, 122 patients developed HCC (83 in the derivation cohort and 39 in the external validation cohort). The RSF model showed the best discrimination ability using seven parameters at the achievement of an SVR with a c-index of 0.839 in the external validation cohort and a high discriminative ability when the patients were categorized into three risk groups (P <0.001). Furthermore, this RSF model enabled the generation of an individualized predictive curve for HCC occurrence for each patient with an app available online. CONCLUSIONS: We developed and externally validated an RSF model with good predictive performance for the risk of HCC after an SVR. The application of this novel model is available on the website. This model could provide the data to consider an effective surveillance method. Further studies are needed to make recommendations for surveillance policies tailored to the medical situation in each country. IMPACT AND IMPLICATIONS: A novel prediction model for HCC occurrence in patients after hepatitis C virus eradication was developed using machine learning algorithms. This model, using seven commonly measured parameters, has been shown to have a good predictive ability for HCC development and could provide a personalized surveillance system.

MNX1-HNF1B Axis Is Indispensable for Intraductal Papillary Mucinous Neoplasm Lineages.

BACKGROUND & AIMS: Chromatin architecture governs cell lineages by regulating the specific gene expression; however, its role in the diversity of cancer development remains unknown. Among pancreatic cancers, pancreatic ductal adenocarcinoma (PDAC) and intraductal papillary mucinous neoplasms (IPMN) with an associated invasive carcinoma (IPMNinv) arise from 2 distinct precursors, and their fundamental differences remain obscure. Here, we aimed to assess the difference of chromatin architecture regulating the transcriptional signatures or biological features in pancreatic cancers. METHODS: We established 28 human organoids from distinct subtypes of pancreatic tumors, including IPMN, IPMNinv, and PDAC. We performed exome sequencing (seq), RNA-seq, assay for transposase-accessible chromatin-seq, chromatin immunoprecipitation-seq, high-throughput chromosome conformation capture, and phenotypic analyses with short hairpin RNA or clustered regularly interspaced short palindromic repeats interference. RESULTS: Established organoids successfully reproduced the histology of primary tumors. IPMN and IPMNinv organoids harbored GNAS, RNF43, or KLF4 mutations and showed the distinct expression profiles compared with PDAC. Chromatin accessibility profiles revealed the gain of stomach-specific open regions in IPMN and the pattern of diverse gastrointestinal tissues in IPMNinv. In contrast, PDAC presented an impressive loss of accessible regions compared with normal pancreatic ducts. Transcription factor footprint analysis and functional assays identified that MNX1 and HNF1B were biologically indispensable for IPMN lineages. The upregulation of MNX1 was specifically marked in the human IPMN lineage tissues. The MNX1-HNF1B axis governed a set of genes, including MYC, SOX9, and OLFM4, which are known to be essential for gastrointestinal stem cells. High-throughput chromosome conformation capture analysis suggested the HNF1B target genes to be 3-dimensionally connected in the genome of IPMNinv. CONCLUSIONS: Our organoid analyses identified the MNX1-HNF1B axis to be biologically significant in IPMN lineages.

Impact of a Novel Digital Therapeutics System on Nonalcoholic Steatohepatitis: The NASH App Clinical Trial.

INTRODUCTION: Management of nonalcoholic steatohepatitis (NASH) is a currently unmet clinical need. Digital therapeutics (DTx) is an emerging class of medicine that delivers evidence-based therapeutic interventions. This study was aimed at investigating the efficacy of DTx in patients with NASH. METHODS: We conducted a multicenter, single-arm, 48-week trial in 19 patients with biopsy-confirmed NASH. All patients received a DTx intervention with a newly developed smartphone application. The primary endpoint was change in the nonalcoholic fatty liver disease activity score (NAS) without worsening of liver fibrosis. The secondary endpoints included improvement of the NAS by ≥2 points without worsening of liver fibrosis, change in the body weight, and regression of fibrosis. RESULTS: After the 48-week DTx intervention, improvement of the NAS was observed in 68.4% (13/19) of patients. The mean change in the NAS from baseline to the end of the intervention was -2.05 ± 1.96 ( P < 0.001 when compared with the threshold of -0.7). A decrease in the NAS by ≥ 2 points was achieved in 11 (57.9%). The average weight loss at the end of the intervention was 8.3% ( P < 0.001). Reduction of the fibrosis stage was observed in 58.3% when the analysis was limited to patients with stage F2/3 fibrosis. There were no serious adverse events that could be considered as being related to the DTx intervention. DISCUSSION: DTx for NASH was found to be highly efficacious and well-tolerated. Further evaluation of the DTx intervention for NASH in a phase 3 trial is warranted.

Steroid administration for ischemic complications after radiofrequency ablation: A retrospective study.

AIM: The aim of this study was to evaluate the effects of steroids on ischemic complications after radiofrequency ablation. METHODS: A total of 58 patients with ischemic complications were divided into two groups according to corticosteroid use or non-use. RESULTS: A total of 13 patients who were administered steroids had a shorter duration of fever than those who were not administered steroids (median 6.0 vs. 2.0 days; p < 0.001). Linear regression analysis showed that steroid administration was associated with a reduction of 3.9 days in the duration of fever (p = 0.008). CONCLUSIONS: Steroid administration for ischemic complications after radiofrequency ablation may reduce the risk of fatal outcomes by blocking systemic inflammatory reactions.

Clinical utility of postablation liver tumor biopsy and possibility of gene mutation analysis.

AIM: Radiofrequency ablation (RFA) is regarded as a first-line treatment for hepatocellular carcinoma (HCC) at an early stage. When treated with RFA, tumor biopsy may not be performed due to the risk of neoplastic seeding. We previously revealed that the risk of neoplastic seeding is significantly reduced by performing biopsies after RFA. In this study, we investigated the possibility of pathological evaluation and gene mutation analysis of post-RFA tumor specimens. METHODS: Radiofrequency ablation was undertaken on diethylnitrosamine-induced mouse liver tumor, and tumor samples with or without RFA were subjected to whole exome sequencing. Post-RFA human liver tumor specimens were used for detection of TERT promoter mutations and pathological assessment. RESULTS: The average somatic mutation rate, sites of mutation, and small indels and base transition patterns were comparable between the nontreated and post-RFA tumors. We identified 684 sites of nonsynonymous somatic substitutions in the nontreated tumor and 704 sites of nonsynonymous somatic substitutions in the post-RFA tumor, with approximately 85% in common. In the human post-RFA samples, the TERT promoter mutations were successfully detected in 40% of the cases. Pathological evaluation was possible with post-RFA specimens, and in one case, the diagnosis of adenocarcinoma was made. CONCLUSION: Our findings suggest that post-RFA liver tumor biopsy is a useful and safe method for obtaining tumor samples that can be used for gene mutation analysis and for pathological assessment.

Changing clinical management of NAFLD in Asia.

Non-alcoholic fatty liver disease (NAFLD) has become the leading cause of chronic liver disease, affecting approximately 25% of the world's population. Recently, because of the sedentary lifestyle and overnutrition resulting from urbanisation, the burden of NAFLD has rapidly increased in many Asian countries. Currently, the prevalence of NAFLD in Asia is approximately 30%, as is the case in many Western countries. In Asia, the prevalence and presentation of NAFLD vary widely across regions because of the substantial diversity in race, socioeconomic status and living environment. Furthermore, the dual aetiology of fatty liver, particularly with viral hepatitis in Asia, makes it complex and challenging to manage. Because Asians are likely to have central adiposity and insulin resistance, approximately 7%-20% of non-obese Asians with body mass indexes of less than 25 kg/m2 are estimated to have NAFLD. Accumulating evidence indicates that NAFLD is associated with various extrahepatic comorbidities such as cardiovascular disease, chronic kidney disease, malignancy, in addition to liver-specific complications. Therefore, NAFLD should be managed as a multisystem disease in conjunction with metabolic syndrome. Lifestyle modification remains the basis of NAFLD management, but few patients can achieve adequate weight loss and maintain it long term. While various pharmacological agents are in phase 3 trials for steatohepatitis, Asian patients are underrepresented in most trials. This article reviews the epidemiological trends, clinical features, optimal assessment and current management practices for NAFLD in Asia.

Development of novel deep multimodal representation learning-based model for the differentiation of liver tumors on B-mode ultrasound images.

BACKGROUND AND AIM: Recently, multimodal representation learning for images and other information such as numbers or language has gained much attention. The aim of the current study was to analyze the diagnostic performance of deep multimodal representation model-based integration of tumor image, patient background, and blood biomarkers for the differentiation of liver tumors observed using B-mode ultrasonography (US). METHOD: First, we applied supervised learning with a convolutional neural network (CNN) to 972 liver nodules in the training and development sets to develop a predictive model using segmented B-mode tumor images. Additionally, we also applied a deep multimodal representation model to integrate information about patient background or blood biomarkers to B-mode images. We then investigated the performance of the models in an independent test set of 108 liver nodules. RESULTS: Using only the segmented B-mode images, the diagnostic accuracy and area under the curve (AUC) values were 68.52% and 0.721, respectively. As the information about patient background and blood biomarkers was integrated, the diagnostic performance increased in a stepwise manner. The diagnostic accuracy and AUC value of the multimodal DL model (which integrated B-mode tumor image, patient age, sex, aspartate aminotransferase, alanine aminotransferase, platelet count, and albumin data) reached 96.30% and 0.994, respectively. CONCLUSION: Integration of patient background and blood biomarkers in addition to US image using multimodal representation learning outperformed the CNN model using US images. We expect that the deep multimodal representation model could be a feasible and acceptable tool for the definitive diagnosis of liver tumors using B-mode US.

Blocking VCAM-1 inhibits pancreatic tumour progression and cancer-associated thrombosis/thromboembolism.

OBJECTIVE: Pancreatic ductal adenocarcinoma (PDAC) is the deadliest cancer. Cancer-associated thrombosis/thromboembolism (CAT), frequently observed in PDAC, is known as a poor prognostic factor. Here, we investigated the underlying mechanisms between PDAC and CAT, and performed a trial of therapeutic approach for PDAC using a genetically engineered mouse model, PKF (Ptf1acre/+;LSL-KrasG12D/+;Tgfbr2flox/flox ). DESIGN: Presence of CAT in PKF mice was detected by systemic autopsy. Plasma cytokines were screened by cytokine antibody array. Murine and human plasma atrial natriuretic peptide (ANP) and soluble vascular cell adhesion molecule 1 (sVCAM-1) were determined by ELISA. Distribution of VCAM-1 in PKF mice and human autopsy samples was detected by immunohistochemistry. PKF mice were treated with anti-VCAM-1 antibody and the effects on survival, distribution of CAT and the tumour histology were analysed. RESULTS: We found spontaneous CAT with cardiomegaly in 68.4% PKF mice. Increase of plasma ANP and sVCAM-1 was observed in PKF mice and PDAC patients with CAT. VCAM-1 was detected in the activated endothelium and thrombi. Administration of anti-VCAM-1 antibody to PKF mice inhibited tumour growth, neutrophil/macrophage infiltration, tumour angiogenesis and progression of CAT; moreover, it dramatically extended survival (from 61 to 253 days, p<0.01). CONCLUSION: Blocking VCAM-1/sVCAM-1 might be a potent therapeutic approach for PDAC as well as CAT, which can contribute to the prognosis. Increase of plasma ANP and sVCAM-1 might be a diagnostic approach for CAT in PDAC.

Radiofrequency Ablation of Liver Tumors in Patients on Antithrombotic Therapy: A Case-Control Analysis of over 10,000 Treatments.

PURPOSE: To evaluate the safety of radiofrequency ablation (RFA) for liver tumors in patients on antithrombotic therapy. MATERIALS AND METHODS: A total of 10,653 consecutive RFA treatments in 3,485 patients with liver tumors were analyzed. The incidence of complications was analyzed on a treatment basis. The treatments for patients who had received antithrombotic medication up to 1 week prior to RFA comprised the antithrombotic therapy group (n = 806), and the others comprised the control group (n = 9,847). Antithrombotic agents were ceased prior to RFA (aspirin, ticlopidine, clopidogrel, and prasugrel ceased 7 days before RFA; cilostazol, 2 or 3 days before RFA; warfarin, 3 days before RFA; and direct oral anticoagulants, 1 day before RFA) and resumed as soon as possible after RFA. Logistic regression analysis was performed to assess whether the antithrombotic therapy increased the risk of hemorrhagic complications. RESULTS: Hemorrhagic complications were diagnosed after 6 treatments (0.7%) in the antithrombotic group and 48 (0.5%) in the control group, and there was no significant difference between the groups (P = .30). In 3 treatments, hemorrhage was diagnosed on or after 8 days of RFA, all of which were in the antithrombotic group. Thrombotic complications were diagnosed after 2 treatments (0.2%) in the antithrombotic group and after 5 (0.1%) in the control group. In a multivariate analysis, receiving antithrombotic therapy was not an independent risk factor for hemorrhagic complications (adjusted odds ratio, 1.52; 95% confidence interval, 0.60-3.87; P = .38). CONCLUSIONS: RFA of liver tumors in patients on antithrombotic therapy is generally safe with appropriate cessation and resumption. Late-onset hemorrhage should be noted in the patients on antithrombotic therapy.

Ischemic complications after percutaneous radiofrequency ablation of liver tumors: Liver volume loss and recovery.

AIM: The liver regrows after acute liver injury and liver resection. However, it is not clear whether the liver regenerates in advanced cirrhosis. This study aimed to evaluate the clinical course of, and liver volume change after, ischemic liver complications caused by radiofrequency ablation (RFA) of hepatocellular carcinoma (HCC). METHODS: We enrolled 35 patients with ischemic complications after RFA. Ischemic complications were defined as rapid elevation of aspartate aminotransferase (AST) to over 500 U/L, with typical radiological findings. Patient characteristics and the ischemic liver volume were investigated. Long-term liver volume changes at 3-8 months after ischemic complications were also assessed in 32 patients. We also assessed the overall survival rate after ischemic complications. RESULTS: The median value of peak AST was 798 U/L (range, 531-4096 U/L). The median ischemic liver volume relative to the functional liver volume before RFA was 13% (range, 3.1-46.5%). There was a strong correlation between the peak AST value and the ischemic liver volume (r = 0.84, P < 0.001). The liver volume recovered to some extent in 18 of 32 (56%) patients after ischemic complications. The survival rate after ischemic complications was 45.7% at 5 years and correlated with the functional liver volume after ischemic complications (P = 0.02). CONCLUSIONS: Ischemic complications after RFA can lead to massive liver parenchymal loss. Although the liver volume recovered to some extent in the majority of our patients, ischemic liver complications after RFA should be avoided to improve the overall survival rate.

Identification of liver fibrosis using the hepatic vein waveform in patients with Fontan circulation.

AIM: Liver fibrosis caused by congestive hepatopathy has emerged as an important complication after Fontan procedure. We evaluated the utility of the hepatic vein (HV) waveform using Doppler ultrasound for identification of liver fibrosis in Fontan patients. METHODS: We investigated the HV waveforms in 41 Fontan patients and assessed correlations with clinical parameters, liver fibrosis markers, and hemodynamic data. RESULTS: Based on our preliminary analysis of 64 adult patients with chronic liver disease who underwent liver biopsy, we classified HV waveforms into five types with reference to the degree of flattening (from type 1, normal triphasic waveform; to type 5, a monophasic waveform indicating cirrhosis), and confirmed a significant correlation between waveform pattern and fibrosis stage. Notably, we detected HV waveforms in all of the Fontan patients and classified them into five types. The HV waveform pattern positively correlated with γ-glutamyl transferase and hyaluronic acid levels, and negatively correlated with albumin level and platelet count, but did not correlate with central venous pressure or brain natriuretic peptide level, suggesting that HV waveform could reflect pathophysiological changes in the liver without being affected by hepatic congestion. The highest area under the receiver operating characteristic curve of the HV waveform for detecting advanced liver fibrosis, as defined by ultrasonic findings and clinical features, was 0.829 (81.8% sensitivity, 73.3% specificity), which was higher than that of other non-invasive fibrosis markers. CONCLUSIONS: Hepatic vein waveforms change in accordance with liver fibrosis progression in Fontan patients, and can be a useful indicator of liver fibrosis after the Fontan procedure.

CPT2 downregulation adapts HCC to lipid-rich environment and promotes carcinogenesis via acylcarnitine accumulation in obesity.

OBJECTIVE: Metabolic reprogramming of tumour cells that allows for adaptation to their local environment is a hallmark of cancer. Interestingly, obesity-driven and non-alcoholic steatohepatitis (NASH)-driven hepatocellular carcinoma (HCC) mouse models commonly exhibit strong steatosis in tumour cells as seen in human steatohepatitic HCC (SH-HCC), which may reflect a characteristic metabolic alteration. DESIGN: Non-tumour and HCC tissues obtained from diethylnitrosamine-injected mice fed either a normal or a high-fat diet (HFD) were subjected to comprehensive metabolome analysis, and the significance of obesity-mediated metabolic alteration in hepatocarcinogenesis was evaluated. RESULTS: The extensive accumulation of acylcarnitine species was seen in HCC tissues and in the serum of HFD-fed mice. A similar increase was found in the serum of patients with NASH-HCC. The accumulation of acylcarnitine could be attributed to the downregulation of carnitine palmitoyltransferase 2 (CPT2), which was also seen in human SH-HCC. CPT2 downregulation induced the suppression of fatty acid ß-oxidation, which would account for the steatotic changes in HCC. CPT2 knockdown in HCC cells resulted in their resistance to lipotoxicity by inhibiting the Src-mediated JNK activation. Additionally, oleoylcarnitine enhanced sphere formation by HCC cells via STAT3 activation, suggesting that acylcarnitine accumulation was a surrogate marker of CPT2 downregulation and directly contributed to hepatocarcinogenesis. HFD feeding and carnitine supplementation synergistically enhanced HCC development accompanied by acylcarnitine accumulation in vivo. CONCLUSION: In obesity-driven and NASH-driven HCC, metabolic reprogramming mediated by the downregulation of CPT2 enables HCC cells to escape lipotoxicity and promotes hepatocarcinogenesis.

Isocitrate dehydrogenase 1 mutation sensitizes intrahepatic cholangiocarcinoma to the BET inhibitor JQ1.

Cholangiocarcinoma is a life-threatening disease with a poor prognosis. Although genome analysis unraveled some genetic mutation profiles in cholangiocarcinoma, it remains unknown whether such genetic abnormalities relate to the effects of anticancer drugs. Mutations in isocitrate dehydrogenase 1 and 2 (IDH1/2) are exclusively found in almost 20% of intrahepatic cholangiocarcinoma (ICC). Recently, the anticancer effects of BET inhibitors including JQ1 have been shown in various tumors. In the present study, we report that the antigrowth effect of JQ1 differs among ICC cells and IDH1 mutation sensitizes ICC cells to JQ1. RBE cells harboring IDH1 mutation was more sensitive to JQ1 than HuCCT1 or HuH28 cells with wild-type IDH1. JQ1 induced apoptosis only in RBE cells through the upregulation of proapoptotic genes BAX and BIM. We found that the antigrowth effect was not attributed to downregulation of the MYC gene as a well-known target of JQ1 in various cancer cells. Notably, the forced expression of mutant IDH1 successfully sensitized HuCCT1 cells to JQ1. In addition, AGI-5198, a selective inhibitor of mutant IDH1 partially reversed the decrease in viability after JQ1 treatment and also suppressed the JQ1-induced apoptosis in RBE cells. These data suggest that IDH1 mutation contributed to the growth inhibitory effect of JQ1 in RBE cells. Furthermore, given that the effect of mutant IDH1 was not recapitulated in glioblastoma cells, the enhancement of JQ1 sensitivity by IDH1 mutation seems to be specific for ICC cells. Our findings propose a new stratified therapeutic strategy based on IDH1 mutation in ICC.

Sarcopenia, intramuscular fat deposition, and visceral adiposity independently predict the outcomes of hepatocellular carcinoma.

BACKGROUND & AIMS: Obesity defined by body mass index (BMI) significantly increases the risk of hepatocellular carcinoma (HCC). In contrast, not only obesity but also underweight is associated with poor prognosis in patients with HCC. Differences in body composition rather than BMI were suggested to be true determinants of prognosis. However, this hypothesis has not been demonstrated conclusively. METHODS: We measured skeletal muscle index (SMI), mean muscle attenuation (MA), visceral adipose tissue index, subcutaneous adipose tissue index, and visceral to subcutaneous adipose tissue area ratios (VSR) via computed tomography in a large-scale retrospective cohort of 1257 patients with different stages of HCC, and comprehensively analyzed the impact of body composition on the prognoses. RESULTS: Among five body composition components, low SMI (called sarcopenia), low MA (called intramuscular fat [IMF] deposition), and high VSR (called visceral adiposity) were significantly associated with mortality, independently of cancer stage or Child-Pugh class. A multivariate analysis revealed that sarcopenia (hazard ratio [HR], 1.52; 95% confidence interval [CI], 1.18-1.96; p=0.001), IMF deposition (HR, 1.34; 95% CI, 1.05-1.71; p=0.020), and visceral adiposity (HR, 1.35; 95% CI, 1.09-1.66; p=0.005) but not BMI were significant predictors of survival. The prevalence of poor prognostic body composition components was significantly higher in underweight and obese patients than in normal weight patients. CONCLUSIONS: Sarcopenia, IMF deposition, and visceral adiposity independently predict mortality in patients with HCC. Body composition rather than BMI is a major determinant of prognosis in patients with HCC.

Diagnostic performance of two-dimensional shear wave elastography and attenuation imaging for fibrosis and steatosis assessment in chronic liver disease.

PURPOSE: We investigated the diagnostic performance of two-dimensional shear wave elastography (2D-SWE) and attenuation imaging (ATI) in detecting fibrosis and steatosis in patients with chronic liver disease (CLD), comparing them with established methods. METHODS: In 190 patients with CLD, 2D-SWE and vibration-controlled transient elastography (VCTE) were used for liver stiffness measurement (LSM), and ATI and controlled attenuation parameter (CAP) were used for steatosis quantification. The correlations between these new and established methods were analyzed. RESULTS: Significant correlations were found between 2D-SWE and VCTE (r = 0.78, P < 0.001), and between ATI and CAP (r = 0.70, P < 0.001). Liver stiffness tended to be lower with 2D-SWE compared with that with VCTE, especially in cases with higher LSM, and ATI was less influenced by skin-capsular distance than CAP. Area under the receiver-operating characteristics curves (AUCs) and optimal cut-offs of 2D-SWE for diagnosing liver fibrosis stages F2, F3, and F4 were 0.73 (8.7 kPa), 0.79 (9.1 kPa), and 0.88 (11.6 kPa), respectively. The AUCs and optimal cut-offs of ATI for diagnosing hepatic steatosis grades S1, S2, and S3 were 0.91 (0.66 dB/cm/MHz), 0.80 (0.79 dB/cm/MHz), and 0.88 (0.86 dB/cm/MHz), respectively. A subgroup analysis of 86 patients with metabolic dysfunction-associated steatotic liver disease also demonstrated good performance for 2D-SWE and ATI. CONCLUSION: 2D-SWE and ATI performed comparably with conventional VCTE and CAP in evaluating CLD, offering reliable alternatives for diagnosing liver fibrosis and steatosis.

Development of a transformer model for predicting the prognosis of patients with hepatocellular carcinoma after radiofrequency ablation.

INTRODUCTION: Radiofrequency ablation (RFA) is a widely accepted, minimally invasive treatment modality for patients with hepatocellular carcinoma (HCC). Accurate prognosis prediction is important to identify patients at high risk for cancer progression/recurrence after RFA. Recently, state-of-the-art transformer models showing improved performance over existing deep learning-based models have been developed in several fields. This study was aimed at developing and validating a transformer model to predict the overall survival in HCC patients with treated by RFA. METHODS: We enrolled a total of 1778 treatment-naïve HCC patients treated by RFA as the first-line treatment. We developed a transformer-based machine learning model to predict the overall survival in the HCC patients treated by RFA and compared its predictive performance with that of a deep learning-based model. Model performance was evaluated by determining the Harrel's c-index and validated externally by the split-sample method. RESULTS: The Harrel's c-index of the transformer-based model was 0.69, indicating its better discrimination performance than that of the deep learning model (Harrel's c-index, 0.60) in the external validation cohort. The transformer model showed a high discriminative ability for stratifying the external validation cohort into two or three different risk groups (p < 0.001 for both risk groupings). The model also enabled output of a personalized cumulative recurrence prediction curve for each patient. CONCLUSIONS: We developed a novel transformer model for personalized prediction of the overall survival in HCC patients after RFA treatment. The current model may offer a personalized survival prediction schema for patients with HCC undergoing RFA treatment.