Deep learning for dual detection of microsatellite instability and POLE mutations in colorectal cancer histopathology.

In the spectrum of colorectal tumors, microsatellite-stable (MSS) tumors with DNA polymerase ε (POLE) mutations exhibit a hypermutated profile, holding the potential to respond to immunotherapy similarly to their microsatellite-instable (MSI) counterparts. Yet, due to their rarity and the associated testing costs, systematic screening for these mutations is not commonly pursued. Notably, the histopathological phenotype resulting from POLE mutations is theorized to resemble that of MSI. This resemblance not only could facilitate their detection by a transformer-based Deep Learning (DL) system trained on MSI pathology slides, but also indicates the possibility for MSS patients with POLE mutations to access enhanced treatment options, which might otherwise be overlooked. To harness this potential, we trained a Deep Learning classifier on a large dataset with the ground truth for microsatellite status and subsequently validated its capabilities for MSI and POLE detection across three external cohorts. Our model accurately identified MSI status in both the internal and external resection cohorts using pathology images alone. Notably, with a classification threshold of 0.5, over 75% of POLE driver mutant patients in the external resection cohorts were flagged as "positive" by a DL system trained on MSI status. In a clinical setting, deploying this DL model as a preliminary screening tool could facilitate the efficient identification of clinically relevant MSI and POLE mutations in colorectal tumors, in one go.

Artificial intelligence in liver cancer - new tools for research and patient management.

Liver cancer has high incidence and mortality globally. Artificial intelligence (AI) has advanced rapidly, influencing cancer care. AI systems are already approved for clinical use in some tumour types (for example, colorectal cancer screening). Crucially, research demonstrates that AI can analyse histopathology, radiology and natural language in liver cancer, and can replace manual tasks and access hidden information in routinely available clinical data. However, for liver cancer, few of these applications have translated into large-scale clinical trials or clinically approved products. Here, we advocate for the incorporation of AI in all stages of liver cancer management. We present a taxonomy of AI approaches in liver cancer, highlighting areas with academic and commercial potential, and outline a policy for AI-based liver cancer management, including interdisciplinary training of researchers, clinicians and patients. The potential of AI in liver cancer is immense, but effort is required to ensure that AI can fulfil expectations.

Macroscopic Characterization of Hepatocellular Carcinoma: An Underexploited Source of Prognostic Factors.

The macroscopic appearance of a tumor such as hepatocellular carcinoma (HCC) may be defined as its phenotype which is de facto dictated by its genotype. Therefore, macroscopic characteristics of HCC are unlikely random but rather reflect genomic traits of cancer, presumably acting as a valuable source of information that can be retrieved and exploited to infer prognosis. This review aims to provide a comprehensive overview of the available data on the prognostic value of macroscopic characterization in HCC. A total of 57 studies meeting eligible criteria were identified, including patients undergoing liver resection (LR; 47 studies, 83%) or liver transplant (LT; 9 studies, 16%). The following macroscopic variables were investigated: tumor size (n = 42 studies), number of nodules (n = 28), vascular invasion (n = 24), bile duct invasion (n = 6), growth pattern (n = 15), resection margin (n = 11), tumor location (n = 6), capsule (n = 2) and satellite (n = 1). Although the selected studies provided insightful data with notable prognostic performances, a lack of standardization and substantial gaps were noted in the report and the analysis of gross findings. This topic remains incompletely covered. While the available studies underscored the value of macroscopic variables in HCC prognostication, important lacks were also observed. Macroscopic characterization of HCC is likely an underexploited source of prognostic factors that must be actively explored by future multidisciplinary research.

Regression-based Deep-Learning predicts molecular biomarkers from pathology slides.

Deep Learning (DL) can predict biomarkers from cancer histopathology. Several clinically approved applications use this technology. Most approaches, however, predict categorical labels, whereas biomarkers are often continuous measurements. We hypothesize that regression-based DL outperforms classification-based DL. Therefore, we develop and evaluate a self-supervised attention-based weakly supervised regression method that predicts continuous biomarkers directly from 11,671 images of patients across nine cancer types. We test our method for multiple clinically and biologically relevant biomarkers: homologous recombination deficiency score, a clinically used pan-cancer biomarker, as well as markers of key biological processes in the tumor microenvironment. Using regression significantly enhances the accuracy of biomarker prediction, while also improving the predictions' correspondence to regions of known clinical relevance over classification. In a large cohort of colorectal cancer patients, regression-based prediction scores provide a higher prognostic value than classification-based scores. Our open-source regression approach offers a promising alternative for continuous biomarker analysis in computational pathology.

Association of LI-RADS and Histopathologic Features with Survival in Patients with Solitary Resected Hepatocellular Carcinoma.

Background Both Liver Imaging Reporting and Data System (LI-RADS) and histopathologic features provide prognostic information in patients with hepatocellular carcinoma (HCC), but whether LI-RADS is independently associated with survival is uncertain. Purpose To assess the association of LI-RADS categories and features with survival outcomes in patients with solitary resected HCC. Materials and Methods This retrospective study included patients with solitary resected HCC from three institutions examined with preoperative contrast-enhanced CT and/or MRI between January 2008 and December 2019. Three independent readers evaluated the LI-RADS version 2018 categories and features. Histopathologic features including World Health Organization tumor grade, microvascular and macrovascular invasion, satellite nodules, and tumor capsule were recorded. Overall survival and disease-free survival were assessed with Cox regression models. Marginal effects of nontargetoid features on survival were estimated using propensity score matching. Results A total of 360 patients (median age, 64 years [IQR, 56-70 years]; 280 male patients) were included. At CT and MRI, the LI-RADS LR-M category was associated with increased risk of recurrence (CT: hazard ratio [HR] = 1.83 [95% CI: 1.26, 2.66], P = .001; MRI: HR = 2.22 [95% CI: 1.56, 3.16], P < .001) and death (CT: HR = 2.47 [95% CI: 1.72, 3.55], P < .001; MRI: HR = 1.80 [95% CI: 1.32, 2.46], P < .001) independently of histopathologic features. The presence of at least one nontargetoid feature was associated with an increased risk of recurrence (CT: HR = 1.80 [95% CI: 1.36, 2.38], P < .001; MRI: HR = 1.93 [95% CI: 1.81, 2.06], P < .001) and death (CT: HR = 1.51 [95% CI: 1.10, 2.07], P < .010) independently of histopathologic features. In matched samples, recurrence was associated with the presence of at least one nontargetoid feature at CT (HR = 2.06 [95% CI: 1.15, 3.66]; P = .02) or MRI (HR = 1.79 [95% CI: 1.01, 3.20]; P = .048). Conclusion In patients with solitary resected HCC, LR-M category and nontargetoid features were negatively associated with survival independently of histopathologic characteristics. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Kartalis and Grigoriadis in this issue.

Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery.

Hepatocellular carcinoma (HCC) is among the most common cancers worldwide, and tumor recurrence following liver resection or transplantation is one of the highest contributors to mortality in HCC patients after surgery. Using artificial intelligence (AI), we developed an interdisciplinary model to predict HCC recurrence and patient survival following surgery. We collected whole-slide H&E images, clinical variables, and follow-up data from 300 patients with HCC who underwent transplant and 169 patients who underwent resection at the Cleveland Clinic. A deep learning model was trained to predict recurrence-free survival (RFS) and disease-specific survival (DSS) from the H&E-stained slides. Repeated cross-validation splits were used to compute robust C-index estimates, and the results were compared to those obtained by fitting a Cox proportional hazard model using only clinical variables. While the deep learning model alone was predictive of recurrence and survival among patients in both cohorts, integrating the clinical and histologic models significantly increased the C-index in each cohort. In every subgroup analyzed, we found that a combined clinical and deep learning model better predicted post-surgical outcome in HCC patients compared to either approach independently.

Differential diagnosis of small hepatocellular nodules in cirrhosis: surrogate histological criteria of TERT promoter mutations.

AIMS: The differential diagnosis of small hepatocellular nodules in cirrhosis between dysplastic nodules and hepatocellular carcinoma (HCC) remains challenging on biopsy. As TERT promoter (pTERT) mutations may indicate the nodules already engaged in the malignant process, the aim of this study was to identify histological criteria associated with pTERT mutations by detecting these mutations by ddPCR in small formalin-fixed paraffin-embedded (FFPE) hepatocellular nodules arising in cirrhosis. METHODS AND RESULTS: We built a bicentric cohort data set of 339 hepatocellular nodules < 2 cm from cirrhotic samples, divided into a test cohort of 299 resected samples and a validation cohort of 40 biopsies. Pathological review, based on the evaluation of 14 histological criteria, classified all nodules. pTERT mutations were identified by ddPCR in FFPE samples. Among the 339 nodules, ddPCR revealed pTERT mutations in 105 cases (31%), including 90 and 15 cases in the test and validation cohorts, respectively. On multivariate analysis, three histological criteria were associated with pTERT mutations in the test cohort: increased cell density (P = 0.003), stromal invasion (P = 0.036) and plate-thickening anomalies (P < 0.001). With the combination of at least two of these major criteria, the AUC for predicting pTERT mutations was 0.84 in the test cohort (sensitivity: 86%, specificity: 83%) and 0.81 in the validation cohort (sensitivity: 87%, specificity: 76%). CONCLUSIONS: We identified three histological criteria as surrogate markers of pTERT mutations that may be used in routine biopsy to more clearly classify small hepatocellular nodules arising in cirrhosis.

Combined hepatocellular-cholangiocarcinoma compared to hepatocellular carcinoma and intrahepatic cholangiocarcinoma: Different survival, similar recurrence: Report of a large study on repurposed databases with propensity score matching.

BACKGROUND: Combined hepatocholangiocarcinoma is a rare cancer with a grim prognosis composed of both hepatocellular carcinoma and intrahepatic cholangiocarcinoma morphologic patterns in the same tumor. The aim of this multicenter, international cohort study was to compare the oncologic outcomes after surgery of combined hepatocholangiocarcinoma to hepatocellular carcinoma and intrahepatic cholangiocarcinoma. METHODS: Patients treated by surgery for combined hepatocholangiocarcinoma, hepatocellular carcinoma, and intrahepatic cholangiocarcinoma from 2000 to 2021 from multicenter international databases were analyzed retrospectively. Patients with combined hepatocholangiocarcinoma (cases) were compared with 2 control groups of hepatocellular carcinoma or intrahepatic cholangiocarcinoma, sequentially matched using a propensity score based on 8 preoperative characteristics. Overall and disease-free survival were compared, and predictors of mortality and recurrence were analyzed with Cox regression after propensity score matching. RESULTS: During the study period, 3,196 patients were included. Propensity score adjustment and 2 sequential matching processes produced a new cohort (n = 244) comprising 3 balanced groups was obtained (combined hepatocholangiocarcinoma = 56, intrahepatic cholangiocarcinoma = 66, and hepatocellular carcinoma = 122). Kaplan-Meier overall survival estimations at 1, 3, and 5 years were 67%, 45%, and 28% for combined hepatocholangiocarcinoma, 92%, 75%, and 55% for hepatocellular carcinoma, and 86%, 53%, and 42% for the intrahepatic cholangiocarcinoma group, respectively (P = .0014). Estimations of disease-free survival at 1, 3, and 5 years were 51%, 25%, and 17% for combined hepatocholangiocarcinoma, 63%, 35%, and 26% for the hepatocellular carcinoma group, and 51%, 31%, and 28% for the intrahepatic cholangiocarcinoma group, respectively (P = .19). Predictors of mortality were combined hepatocholangiocarcinoma subtype, metabolic syndrome, preoperative tumor markers alpha-fetoprotein and carbohydrate antigen 19-9, and satellite nodules, and recurrence was associated with satellite nodules rather than cancer subtype. CONCLUSION: Despite data limitations, overall survival among patients with combined hepatocholangiocarcinoma was worse than both groups and closer intrahepatic cholangiocarcinoma, whereas disease-free survival was similar among the 3 groups. Future research on immunophenotypic profiling may hold more promise than traditional nonmodifiable clinical characteristics (as found in this study) in predicting recurrence or response to salvage treatments.

Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression.

Programmed death-ligand 1 (PD-L1) IHC is the most commonly used biomarker for immunotherapy response. However, quantification of PD-L1 status in pathology slides is challenging. Neither manual quantification nor a computer-based mimicking of manual readouts is perfectly reproducible, and the predictive performance of both approaches regarding immunotherapy response is limited. In this study, we developed a deep learning (DL) method to predict PD-L1 status directly from raw IHC image data, without explicit intermediary steps such as cell detection or pigment quantification. We trained the weakly supervised model on PD-L1-stained slides from the non-small cell lung cancer (NSCLC)-Memorial Sloan Kettering (MSK) cohort (N = 233) and validated it on the pan-cancer-Vall d'Hebron Institute of Oncology (VHIO) cohort (N = 108). We also investigated the performance of the model to predict response to immune checkpoint inhibitors (ICI) in terms of progression-free survival. In the pan-cancer-VHIO cohort, the performance was compared with tumor proportion score (TPS) and combined positive score (CPS). The DL model showed good performance in predicting PD-L1 expression (TPS ≥ 1%) in both NSCLC-MSK and pan-cancer-VHIO cohort (AUC 0.88 ± 0.06 and 0.80 ± 0.03, respectively). The predicted PD-L1 status showed an improved association with response to ICIs [HR: 1.5 (95% confidence interval: 1-2.3), P = 0.049] compared with TPS [HR: 1.4 (0.96-2.2), P = 0.082] and CPS [HR: 1.2 (0.79-1.9), P = 0.386]. Notably, our explainability analysis showed that the model does not just look at the amount of brown pigment in the IHC slides, but also considers morphologic factors such as lymphocyte conglomerates. Overall, end-to-end weakly supervised DL shows potential for improving patient stratification for cancer immunotherapy by analyzing PD-L1 IHC, holistically integrating morphology and PD-L1 staining intensity. SIGNIFICANCE: The weakly supervised DL model to predict PD-L1 status from raw IHC data, integrating tumor staining intensity and morphology, enables enhanced patient stratification in cancer immunotherapy compared with traditional pathologist assessment.

Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma.

Primary liver cancer arises either from hepatocytic or biliary lineage cells, giving rise to hepatocellular carcinoma (HCC) or intrahepatic cholangiocarcinoma (ICCA). Combined hepatocellular- cholangiocarcinomas (cHCC-CCA) exhibit equivocal or mixed features of both, causing diagnostic uncertainty and difficulty in determining proper management. Here, we perform a comprehensive deep learning-based phenotyping of multiple cohorts of patients. We show that deep learning can reproduce the diagnosis of HCC vs. CCA with a high performance. We analyze a series of 405 cHCC-CCA patients and demonstrate that the model can reclassify the tumors as HCC or ICCA, and that the predictions are consistent with clinical outcomes, genetic alterations and in situ spatial gene expression profiling. This type of approach could improve treatment decisions and ultimately clinical outcome for patients with rare and biphenotypic cancers such as cHCC-CCA.

Atezolizumab and bevacizumab for non-resectable or metastatic combined hepatocellular-cholangiocarcinoma: A multicentric retrospective study.

BACKGROUNDS: The efficacy of atezolizumab/bevacizumab has never been reported in patients with metastatic/unresectable combined hepatocellular-cholangiocarcinoma (cHCC-CCA). PATIENTS AND METHODS: We retrospectively included patients with a histological diagnosis of unresectable/metastatic cHCC-CCA and treated with atezolizumab/bevacizumab (2020-2022) in 7 centers. Clinical and radiological features were collected at the beginning of atezolizumab/bevacizumab. We reported the radiological response using RECIST criteria, overall survival (OS) and progression-free survival (PFS). RESULTS: Sixteen patients with cHCC-CCA were included and were predominantly male (75%) with advanced fibrosis/cirrhosis (69%). Nine patients received atezolizumab/bevacizumab as a first-line systemic treatment, 5 as a second line, 1 as a third line and 1 as a fifth line. Severe digestive bleeding occurred in 2 patients. Among the 9 patients treated in the first line, 4 experienced radiological progression, 3 partial response and 1 had stable disease. Patients treated with atezolizumab/bevacizumab in the first line had a median OS of 13 months and a median PFS of 3 months. Among the 7 patients receiving atezolizumab/bevacizumab as a second line or more, 4 patients harbored a stable disease, 2 a partial response, and 1 a progressive disease. CONCLUSIONS: The combination of atezolizumab and bevacizumab showed signs of anti-tumor efficacy in patients with unresectable/metastatic cHCC-CCA.

Artificial intelligence-based pathology as a biomarker of sensitivity to atezolizumab-bevacizumab in patients with hepatocellular carcinoma: a multicentre retrospective study.

BACKGROUND: Clinical benefits of atezolizumab plus bevacizumab (atezolizumab-bevacizumab) are observed only in a subset of patients with hepatocellular carcinoma and the development of biomarkers is needed to improve therapeutic strategies. The atezolizumab-bevacizumab response signature (ABRS), assessed by molecular biology profiling techniques, has been shown to be associated with progression-free survival after treatment initiation. The primary objective of our study was to develop an artificial intelligence (AI) model able to estimate ABRS expression directly from histological slides, and to evaluate if model predictions were associated with progression-free survival. METHODS: In this multicentre retrospective study, we developed a model (ABRS-prediction; ABRS-P), which was derived from the previously published clustering-constrained attention multiple instance learning (or CLAM) pipeline. We trained the model fit for regression analysis using a multicentre dataset from The Cancer Genome Atlas (patients treated by surgical resection, n=336). The ABRS-P model was externally validated on two independent series of samples from patients with hepatocellular carcinoma (a surgical resection series, n=225; and a biopsy series, n=157). The predictive value of the model was further tested in a series of biopsy samples from a multicentre cohort of patients with hepatocellular carcinoma treated with atezolizumab-bevacizumab (n=122). All samples in the study were from adults (aged ≥18 years). The validation sets were sampled between Jan 1, 2008, to Jan 1, 2023. For the multicentre validation set, the primary objective was to assess the association of high versus low ABRS-P values, defined relative to cross-validation median split thresholds in the first biopsy series, with progression-free survival after treatment initiation. Finally, we performed spatial transcriptomics and matched prediction heatmaps with in situ expression profiles. FINDINGS: Of the 840 patients sampled, 641 (76%) were male and 199 (24%) were female. Across the development and validation datasets, hepatocellular carcinoma risk factors included alcohol intake, hepatitis B and C virus infections, and non-alcoholic steatohepatitis. Using cross-validation in the development series, the mean Pearson's correlation between ABRS-P values and ABRS score (mean expression of ABRS genes) was r=0·62 (SD 0·09; mean p<0·0001, SD<0·0001). The ABRS-P generalised well on the external validation series (surgical resection series, r=0·60 [95% CI 0·51-0·68], p<0·0001; biopsy series, r=0·53 [0·40-0·63], p<0·0001). In the 122 patients treated with atezolizumab-bevacizumab, those with ABRS-P-high tumours (n=74) showed significantly longer median progression-free survival than those with ABRS-P-low tumours (n=48) after treatment initiation (12 months [95% CI 7-not reached] vs 7 months [4-9]; p=0·014). Spatial transcriptomics showed significantly higher ABRS score, along with upregulation of various other immune effectors, in tumour areas with high ABRS-P values versus areas with low ABRS-P values. INTERPRETATION: Our study indicates that AI applied on hepatocellular carcinoma digital slides is able to serve as a biomarker for progression-free survival in patients treated with atezolizumab-bevacizumab. This approach could be used in the development of inexpensive and fast biomarkers for targeted therapies. The combination of AI heatmaps with spatial transcriptomics provides insight on the molecular features associated with predictions. This methodology could be applied to other cancers or diseases and improve understanding of the biological mechanisms that drive responses to treatments. FUNDING: Institut National du Cancer, Fondation ARC, China Scholarship Council, Ligue Contre le Cancer du Val de Marne, Fondation de l'Avenir, Ipsen, and Fondation Bristol Myers Squibb Pour la Recherche en Immuno-Oncologie.

The liver in sickle cell disease.

Liver involvement in SCD patients is frequent but often misdiagnosed or underestimated, except in case of advanced liver diseases. Because of so far poorly recognized forms of chronic SCD-related vascular injury that can silently evolved towards end stages or facilitate ACLF, any persisting liver function tests abnormalities should be carefully investigated, following the above proposed algorithm. Work up and management must be considered multidisciplinary in relationship with a Hepatologist. Early SCD hepatopathy should prompt revision of SCD management to prevent further liver injury and decompensation, discussing transfusion exchanges and hydro urea when not yet initiated, and control for any cofactor of liver injury. The role of HSCT in early SCD hepatopathies also deserves evaluation. In advanced SCD hepatopathies, liver transplantation, which has been rarely performed so far, is the only therapeutic option associated with improved survival. It should definitely be discussed- either electively in case of decompensation in SCD cirrhosis or jaundice/recurrent cholangitis in cholestatic diseases, with excellent outcome, - or emergently in case of ALF or ACLF with more mitigate results. To improve knowledge and management of SCD liver diseases, creation of national and international registries, as well as longitudinal observational cohorts are encouraged.

ERS: A simple scoring system to predict early recurrence after surgical resection for hepatocellular carcinoma.

BACKGROUND: Surgical resection (SR) is a potentially curative treatment of hepatocellular carcinoma (HCC) hampered by high rates of recurrence. New drugs are tested in the adjuvant setting, but standardised risk stratification tools of HCC recurrence are lacking. OBJECTIVES: To develop and validate a simple scoring system to predict 2-year recurrence after SR for HCC. METHODS: 2359 treatment-naïve patients who underwent SR for HCC in 17 centres in Europe and Asia between 2004 and 2017 were divided into a development (DS; n = 1558) and validation set (VS; n = 801) by random sampling of participating centres. The Early Recurrence Score (ERS) was generated using variables associated with 2-year recurrence in the DS and validated in the VS. RESULTS: Variables associated with 2-year recurrence in the DS were (with associated points) alpha-fetoprotein (<10 ng/mL:0; 10-100: 2; >100: 3), size of largest nodule (≥40 mm: 1), multifocality (yes: 2), satellite nodules (yes: 2), vascular invasion (yes: 1) and surgical margin (positive R1: 2). The sum of points provided a score ranging from 0 to 11, allowing stratification into four levels of 2-year recurrence risk (Wolbers' C-indices 66.8% DS and 68.4% VS), with excellent calibration according to risk categories. Wolber's and Harrell's C-indices apparent values were systematically higher for ERS when compared to Early Recurrence After Surgery for Liver tumour post-operative model to predict time to early recurrence or recurrence-free survival. CONCLUSIONS: ERS is a user-friendly staging system identifying four levels of early recurrence risk after SR and a robust tool to design personalised surveillance strategies and adjuvant therapy trials.

Anterior Versus Classical Approach During Right Hepatectomy for Hepatocellular Carcinoma: Inverse Propensity Score Weighted Analysis.

BACKGROUND: Eastern data highlight the oncological benefits of the anterior approach (AA) during right hepatectomy (RH) for hepatocellular carcinoma (HCC). However, to our knowledge, previous western data on this topic are scarce. In this study, the oncological outcomes of AA and classical approach (CA) during RH for HCC were compared. METHODS: A retrospective inverse propensity score-weighted fashion (IPTW) case-control study was performed in two French hepatobiliary surgery departments. Overall survival (OS), disease-free survival (DFS), and early recurrence rate (within 2 years after surgery) were analyzed. RESULTS: Survival analysis was performed for 114 patients (CA group,60 patients; AA group, 54 patients). Before IPTW adjustment, the 3-year DFS rates were 29.4% (AA group) and 44% (CA group), respectively. No significant differences were found in DFS (HR = 1.1, 95%CI:0.62-1.9, p = 0.77) and OS (HR = 1.2, 95%CI:0.54-2.6, p = 0.66). After IPTW, DFS and OS analyses showed no differences between the two groups (p = 0.77 and p = 0.46, respectively). Early recurrence rates were similar before and after IPTW. Satellite nodules were the only significant independent risk factor for recurrence. CONCLUSION: AA and CA did not result in significant differences in DFS, OS, or early recurrence after right hepatectomy for HCC before and after IPTW.

Impact of COVID-19 on the management of hepatocellular carcinoma in a high-prevalence area: What's new 12 months later?

INTRODUCTION AND OBJECTIVES: The lockdown policy introduced in 2020 to minimize the spread of the COVID-19 pandemic, significantly affected the management and care of patients affected by hepatocellular carcinoma (HCC). The aim of this follow-up study was to determine the 12 months impact of the COVID-19 pandemic on the cohort of patients affected by HCC during the lockdown, within six French academic referral centers in the metropolitan area of Paris. MATERIALS AND METHODS: We performed a 12 months follow-up of the cross-sectional study cohort included in 2020 on the management of patients affected by HCC during the first six weeks of the COVID-19 pandemic (exposed), compared to the same period in 2019 (unexposed). Overall survival were compared between the groups. Predictors of mortality were analysed with Cox regression. RESULTS: From the initial cohort, 575 patients were included (n = 263 Exposed_COVID, n = 312 Unexposed_COVID). Overall and disease free survival at 12 months were 59.9 ± 3.2% vs 74.3 ± 2.5% (p<0.001) and 40.2 ± 3.5% vs 63.5 ± 3.1% (p<0.001) according to the period of exposure (Exposed_COVID vs Unexposed_COVID, respectively). Adjusted Cox regression revealed that the period of exposure (Exposed_COVID HR: 1.79, 95%CI (1.36, 2.35) p<0.001) and BCLC stage B, C and D (BCLC B HR: 1.82, 95%CI (1.07, 3.08) p = 0.027 - BCLC C HR: 1.96, 95%CI (1.14, 3.38) p = 0.015 - BCLC D HR: 3.21, 95%CI (1.76, 5.85) p<0.001) were predictors of death. CONCLUSIONS: Disruption of routine healthcare services because of the pandemic translated to reduced 1 year overall and disease-free survival among patients affected by HCC, in the metropolitan area of Paris, France.

Deep learning-based subtyping of gastric cancer histology predicts clinical outcome: a multi-institutional retrospective study.

INTRODUCTION: The Laurén classification is widely used for Gastric Cancer (GC) histology subtyping. However, this classification is prone to interobserver variability and its prognostic value remains controversial. Deep Learning (DL)-based assessment of hematoxylin and eosin (H&E) stained slides is a potentially useful tool to provide an additional layer of clinically relevant information, but has not been systematically assessed in GC. OBJECTIVE: We aimed to train, test and externally validate a deep learning-based classifier for GC histology subtyping using routine H&E stained tissue sections from gastric adenocarcinomas and to assess its potential prognostic utility. METHODS: We trained a binary classifier on intestinal and diffuse type GC whole slide images for a subset of the TCGA cohort (N = 166) using attention-based multiple instance learning. The ground truth of 166 GC was obtained by two expert pathologists. We deployed the model on two external GC patient cohorts, one from Europe (N = 322) and one from Japan (N = 243). We assessed classification performance using the Area Under the Receiver Operating Characteristic Curve (AUROC) and prognostic value (overall, cancer specific and disease free survival) of the DL-based classifier with uni- and multivariate Cox proportional hazard models and Kaplan-Meier curves with log-rank test statistics. RESULTS: Internal validation using the TCGA GC cohort using five-fold cross-validation achieved a mean AUROC of 0.93 ± 0.07. External validation showed that the DL-based classifier can better stratify GC patients' 5-year survival compared to pathologist-based Laurén classification for all survival endpoints, despite frequently divergent model-pathologist classifications. Univariate overall survival Hazard Ratios (HRs) of pathologist-based Laurén classification (diffuse type versus intestinal type) were 1.14 (95% Confidence Interval (CI) 0.66-1.44, p-value = 0.51) and 1.23 (95% CI 0.96-1.43, p-value = 0.09) in the Japanese and European cohorts, respectively. DL-based histology classification resulted in HR of 1.46 (95% CI 1.18-1.65, p-value < 0.005) and 1.41 (95% CI 1.20-1.57, p-value < 0.005), in the Japanese and European cohorts, respectively. In diffuse type GC (as defined by the pathologist), classifying patients using the DL diffuse and intestinal classifications provided a superior survival stratification, and demonstrated statistically significant survival stratification when combined with pathologist classification for both the Asian (overall survival log-rank test p-value < 0.005, HR 1.43 (95% CI 1.05-1.66, p-value = 0.03) and European cohorts (overall survival log-rank test p-value < 0.005, HR 1.56 (95% CI 1.16-1.76, p-value < 0.005)). CONCLUSION: Our study shows that gastric adenocarcinoma subtyping using pathologist's Laurén classification as ground truth can be performed using current state of the art DL techniques. Patient survival stratification seems to be better by DL-based histology typing compared with expert pathologist histology typing. DL-based GC histology typing has potential as an aid in subtyping. Further investigations are warranted to fully understand the underlying biological mechanisms for the improved survival stratification despite apparent imperfect classification by the DL algorithm.

RSK2 inactivation cooperates with AXIN1 inactivation or ß-catenin activation to promote hepatocarcinogenesis.

BACKGROUND & AIMS: Recurrent somatic mutations of the RPS6KA3 gene encoding for the serine/threonine kinase RSK2 were identified in hepatocellular carcinomas (HCCs), suggesting its tumour-suppressive function. Our goal was to demonstrate the tumour suppressor role of RSK2 in the liver and investigate the functional consequences of its inactivation. METHODS: We analysed a series of 1,151 human HCCs for RSK2 mutations and 20 other driver genetic alterations. We then modelled RSK2 inactivation in mice in various mutational contexts recapitulating or not those naturally found in human HCC, using transgenic mice and liver-specific carcinogens. These models were monitored for liver tumour appearance and subjected to phenotypic and transcriptomic analyses. Functional consequences of RSK2 rescue were also investigated in a human RSK2-deficient HCC cell line. RESULTS: RSK2-inactivating mutations are specific to human HCC and frequently co-occur with AXIN1-inactivating or ß-catenin-activating mutations. Modelling of these co-occurrences in mice showed a cooperative effect in promoting liver tumours with transcriptomic profiles recapitulating those of human HCCs. By contrast, there was no cooperation in liver tumour induction between RSK2 loss and BRAF-activating mutations chemically induced by diethylnitrosamine. In human liver cancer cells, we also showed that RSK2 inactivation confers some dependency to the activation of RAS/MAPK signalling that can be targeted by MEK inhibitors. CONCLUSIONS: Our study demonstrates the tumour suppressor role of RSK2 and its specific synergistic effect in hepatocarcinogenesis when its loss of function is specifically combined with AXIN1 inactivation or ß-catenin activation. Furthermore, we identified the RAS/MAPK pathway as a potential therapeutic target for RSK2-inactivated liver tumours. IMPACT AND IMPLICATIONS: This study demonstrated the tumour suppressor role of RSK2 in the liver and showed that its inactivation specifically synergises with AXIN1 inactivation or ß-catenin activation to promote the development of HCC with similar transcriptomic profiles as found in humans. Furthermore, this study highlights that activation of the RAS/MAPK pathway is one of the key signalling pathways mediating the oncogenic effect of RSK2 inactivation that can be targeted with already available anti-MEK therapies.