Objective: The aim of this study was to build a SVM classifier using ResNet-3D algorithm by artificial intelligence for prediction of synchronous PC. Background: Adequate detection and staging of PC from CRC remain difficult. Methods: The primary tumors in synchronous PC were delineated on preoperative contrast-enhanced computed tomography (CT) images. The features of adjacent peritoneum were extracted to build a ResNet3D + SVM classifier. The performance of ResNet3D + SVM classifier was evaluated in the test set and was compared to routine CT which was evaluated by radiologists. Results: The training set consisted of 19,814 images from 54 patients with PC and 76 patients without PC. The test set consisted of 7837 images from 40 test patients. The ResNet-3D spent only 34 seconds to analyze the test images. To increase the accuracy of PC detection, we have built a SVM classifier by integrating ResNet-3D features with twelve PC-specific features (P < 0.05). The ResNet3D + SVM classifier showed accuracy of 94.11% with AUC of 0.922 (0.912–0.944), sensitivity of 93.75%, specificity of 94.44%, positive predictive value (PPV) of 93.75%, and negative predictive value (NPV) of 94.44% in the test set. The performance was superior to routine contrast-enhanced CT (AUC: 0.791). Conclusions: The ResNet3D + SVM classifier based on deep learning algorithm using ResNet-3D framework has shown great potential in prediction of synchronous PC in CRC.

Background: Plasma microRNAs (miRNAs) are promising non-invasive biomarkers for colorectal cancer (CRC) prognosis. However, the published studies to date have yielded conflicting and inconsistent results for specific plasma miRNAs. Methods: We have conducted a study using robust assays to assess a panel of nine miRNAs for CRC prognosis and early detection of recurrence. Plasma samples from 144 patients in a prospective CRC cohort study were collected at diagnosis, 6, 12, and 24 months after diagnosis. miRNAs were assayed by Taqman qRT–PCR to generate miRNA normalised copy numbers. Results: Preoperative high plasma miRNA levels were associated with increased recurrence risk for miR-200b (HR [95% CI]=2.04 [1.00, 4.16], P=0.05), miR-203 (HR=4.2 [1.48, 11.93], P=0.007), miR-29a (HR=2.61 [1.34,5.07], P=0.005), and miR-31 (HR=4.03 [1.76, 9.24], P=0.001). Both plasma miR-31 (AUC: 0.717) and miR-29a (AUC: 0.703) could discriminate recurrence from these patients without recurrence. In addition, high levels of miR-31 during surveillance was associated with a three-fold increased risk of recurrence across all time points. Dynamic postoperative plasma miR-141 and 16 levels correlated with recurrence in the surveillance samples. Conclusions: Pre-operative plasma miR-29a, 200b, 203, and 31 are potential CRC prognosis biomarkers. In addition, dynamic postoperative miR-31, 141 and 16 levels are potential biomarkers for the early detection of recurrence during CRC surveillance.

Background: The screening biomarkers for early detection of colorectal cancer (CRC) is lacking. The aim is to identify epigenetic silenced genes and clarify its roles and underlying mechanism in CRC. We conducted integrative analyses of epigenome-wide Human Methylation 450 K arrays and transcriptome to screen out candidate epigenetic driver genes with transcription silencing. Methylated silencing HAND2 were identified and verified in large CRC cohort. The mechanism of HAND2 expression by promoter inhibition were clarified both in vitro and vivo assays. Cell biofunctional roles of HAND2 methylation was investigated in CRC cells. HAND2 reconstitution were constructed by lentivirus plasmid and tumor xenograft model of HAND2 were built subcutaneously. Genomic mRNA analysis by RNA-sequencing and subsequent GSEA analysis were performed to identify potential target of HAND2 and qPCR/WB was conducted to identify the results. Results: We firstly reported high frequency of HAND2 methylation in promoter in CRC and hypermethylation was negatively correlated with expression silencing and leaded to poor survival in several CRC cohort patients. 5-Aza treatment to demethylated HAND2 could revert its expression in CRC cells. Functionally, HAND2 reconstitution can inhibit cell proliferation, invasion and migration in vitro. In tumor xenograft, HAND2 reconstruction significantly repressed tumor growth when compared to control vector. Thousands of aberrant expressed genes were observed in the heatmap of RNA-sequencing data. HAND2 reconstitution could bind to ERK and reduce its phosphorylation by CoIP assay. These above results showed HAND2 reconstitution perturbed the activation of MAPK/ERK signaling by reduction of ERK phosphorylation. Conclusions: HAND2 is one tumor suppressor by targeting ERK signaling and one potential epigenetic driver gene in CRC.

Purpose: Synchronous peritoneal metastasis (S-PM) is considered a poor prognostic factor for colorectal cancer (CRC) and there is no nomogram to predict the survival of these patients. In this study, we aimed to use a multicenter data to identify the factors associated with S-PM of CRC to construct a nomogram for predicting the overall survival (OS) of these patients. Methods: CRC patients with S-PM from two medical centers were enrolled between September 2007 and June 2017. Multivariate analysis was used to identify independent factors associated with OS for the nomogram to predict the 1-, 2-, and 3-year OS rates in the development group. The concordance index (C-index), calibration plot, relative operating characteristic (ROC) curve with area under the curve (AUC) were calculated to evaluate the performance of the nomogram in both the development and an external validation group. Results: 277 CRC patients with S-PM in the development group and 68 patients in the validation group were eligible for this study. In multivariate analysis of development group, age, carbohydrate antigen 19-9 (CA19-9), carbohydrate antigen 125 (CA125), cytoreductive surgery (CRS), hyperthermic intraperitoneal chemotherapy (HIPEC), and chemotherapy were independent variables for OS, based on which the nomogram was built. The C-index of the nomogram in the development and validation group was 0.701 (95% Cl, 0.666–0.736) and 0.716 (95% Cl, 0.622–0.810); demonstrating good discriminative ability. The calibration plots showed satisfactory consistency between actual observation and nomogram-predicted OS probabilities in the development and external validation group. The nomogram showed good predictive accuracy for 1-, 2-, and 3-year OS rates in both groups with AUC >0.70. An online dynamic webserver was also developed for increasing the ease of the nomogram. Conclusions: We developed and validated a predictive nomogram with good discriminative and high accuracy to predict the OS in CRC patients with S-PM.

Patients of colorectal cancer (CRC) with BRAF V600E mutation obtain poor prognosis. This study aimed to explore the role and mechanism of BRAF V600E mutation in angiogenesis of tumor micro-environment (TME). It has been reported that CXCL16 expression in TME is closely related to BRAF mutation. Clinicopathological features of CRC with BRAF V600E mutant or wild type were collected in this study. Immunohistochemistry (IHC) assays were conducted to test the expressions of vascular endothelial growth factor (VEGF), CD31 and CXCL16. ROC curve was used to determine the optimal cut off values of CXCL16. A total of 680 patients including 141 BRAF V600E type and 679 wild type were included. BRAF V600E mutant tumors were presented with significant worse clinicopathological features and a shorter overall survival (OS) than wild-type. Besides, chemokines CXCL16 was up-regulated in BRAF V600E mutant tissues and was associated with poorer prognosis. In addition, VEGF levels and vascular endothelial cell density was significantly increased in BRAF mutation. At last, CXCL16 was positively correlated with VEGF expression and vascular endothelial cell density. In conclusion, BRAF V600E mutations may promote metastasis of CRC by regulating CXCL16 expression and promoting angiogenesis in the TME.