Application of artificial intelligence in a real-world research for predicting the risk of liver metastasis in T1 colorectal cancer

Background Liver is the most common metastatic site of colorectal cancer (CRC) and liver metastasis (LM) determines subsequent treatment as well as prognosis of patients, especially in T1 patients. T1 CRC patients with LM are recommended to adopt surgery and systematic treatments rather than endoscopic therapy alone. Nevertheless, there is still no effective model to predict the risk of LM in T1 CRC patients. Hence, we aim to construct an accurate predictive model and an easy-to-use tool clinically. Methods We integrated two independent CRC cohorts from Surveillance Epidemiology and End Results database (SEER, training dataset) and Xijing hospital (testing dataset). Artificial intelligence (AI) and machine learning (ML) methods were adopted to establish the predictive model. Results A total of 16,785 and 326 T1 CRC patients from SEER database and Xijing hospital were incorporated respectively into the study. Every single ML model demonstrated great predictive capability, with an area under the curve (AUC) close to 0.95 and a stacking bagging model displaying the best performance (AUC = 0.9631). Expectedly, the stacking model exhibited a favorable discriminative ability and precisely screened out all eight LM cases from 326 T1 patients in the outer validation cohort. In the subgroup analysis, the stacking model also demonstrated a splendid predictive ability for patients with tumor size ranging from one to50mm (AUC = 0.956). Conclusion We successfully established an innovative and convenient AI model for predicting LM in T1 CRC patients, which was further verified in the external dataset. Ultimately, we designed a novel and easy-to-use decision tree, which only incorporated four fundamental parameters and could be successfully applied in clinical practice.

The effect of the low stromal ratio induced by neoadjuvant chemotherapy on recurrence patterns in borderline resectable pancreatic ductal adenocarcinoma

The optimal regimens of neoadjuvant chemotherapy (NAC) and its biological and physiological modification of the tumor microenvironment (TME) in patients with borderline resectable pancreatic ductal adenocarcinoma (BR PDAC) remain unknown. A deeper understanding of the complex stromal biology of the TME will identify new avenues to establish treatment strategies for PDAC patients. Herein, we sought to clarify whether stromal remodeling by NAC affects recurrence patterns and prognosis in BR PDAC patients. We retrospectively analyzed data from 104 BR PDAC patients who underwent pancreatectomy with or without NAC (upfront surgery [UpS], n = 44; gemcitabine + nab-paclitaxel [GnP], n = 28; and gemcitabine + S-1 [GS], n = 32) to assess the correlations of treatment with early recurrence, the stromal ratio, and Ki-67 levels. Eighty-six patients experienced recurrence, and those with liver metastasis had significantly shorter recurrence-free survival than those with other recurrence patterns. The frequency of liver metastasis was significantly higher in patients with a low stromal ratio than in those with a high stromal ratio in the NAC group but not in the UpS group. Patients in the GnP group had significantly higher Ki-67 than those in the GS and UpS groups. A low stromal ratio was positively correlated with high Ki-67 in the NAC group but not in the UpS group. The low stromal ratio induced by NAC promoted early liver metastasis in patients with BR PDAC. Our findings provide new insights into the complexity of stromal biology, leading to consideration of the optimal NAC regimen.

Radiomics and Radiogenomics in Evaluation of Colorectal Cancer Liver Metastasis

Colorectal cancer is one common digestive malignancy, and the most common approach of blood metastasis of colorectal cancer is through the portal vein system to the liver. Early detection and treatment of liver metastasis is the key to improving the prognosis of the patients. Radiomics and radiogenomics use non-invasive methods to evaluate the biological properties of tumors by deeply mining the texture features of images and quantifying the heterogeneity of metastatic tumors. Radiomics and radiogenomics have been applied widely in the detection, treatment, and prognostic evaluation of colorectal cancer liver metastases. Based on the imaging features of the liver, this paper reviews the current application of radiomics and radiogenomics in the diagnosis, treatment, monitor of disease progression, and prognosis of patients with colorectal cancer liver metastases.

Epidermal Growth Factor Receptor as Target for Perioperative Elimination of Circulating Colorectal Cancer Cells

Surgical resection of the tumor is the primary treatment of colorectal cancer patients. However, we previously demonstrated that abdominal surgery promotes the adherence of circulating tumor cells (CTC) in the liver and subsequent liver metastasis development. Importantly, preoperative treatment with specific tumor-targeting monoclonal antibodies (mAb) prevented surgery-induced liver metastasis development in rats. This study investigated whether the epidermal growth factor receptor (EGFR) represents a suitable target for preoperative antibody treatment of colorectal cancer patients undergoing surgery. The majority of patients with resectable colorectal liver metastases were shown to have EGFR + CTCs. Three different anti-EGFR mAbs (cetuximab, zalutumumab, and panitumumab) were equally efficient in the opsonization of tumor cell lines. Additionally, all three mAbs induced antibody-dependent cellular phagocytosis (ADCP) of tumor cells by macrophages at low antibody concentrations in vitro, independent of mutations in EGFR signaling pathways. The plasma of cetuximab-treated patients efficiently opsonized tumor cells ex vivo and induced phagocytosis. Furthermore, neither proliferation nor migration of epithelial cells was affected in vitro, supporting that wound healing will not be hampered by treatment with low anti-EGFR mAb concentrations. These data support the use of a low dose of anti-EGFR mAbs prior to resection of the tumor to eliminate CTCs without interfering with the healing of the anastomosis. Ultimately, this may reduce the risk of metastasis development, consequently improving long-term patient outcome significantly.

CircRTN4 promotes pancreatic cancer progression through a novel CircRNA-miRNA-lncRNA pathway and stabilizing epithelial-mesenchymal transition protein

Background Circular RNAs (circRNAs) play important roles in many biological processes. However, the detailed mechanism underlying the critical roles of circRNAs in cancer remains largely unexplored. We aim to explore the molecular mechanisms of circRTN4 with critical roles in pancreatic ductal adenocarcinoma (PDAC). Methods CircRTN4 expression level was examined in PDAC primary tumors. The oncogenic roles of circRTN4 in PDAC tumor growth and metastasis were studied in mouse tumor models. Bioinformatics analysis, luciferase assay and miRNA pulldown assay were performed to study the novel circRTN4-miRNA-lncRNA pathway. To identify circRTN4-interacting proteins, we performed circRNA-pulldown and mass spectrometry in PDAC cells. Protein stability assay and 3-Dimensional structure modeling were performed to reveal the role of circRTN4 in stabilizing RAB11FIP1. Results CircRTN4 was significantly upregulated in primary tumors from PDAC patients. In vitro and in vivo functional studies revealed that circRTN4 promoted PDAC tumor growth and liver metastasis. Mechanistically, circRTN4 interacted with tumor suppressor miR-497-5p in PDAC cells. CircRTN4 knockdown upregulated miR-497-5p to inhibit the oncogenic lncRNA HOTTIP expression. Furthermore, we identified critical circRTN4-intercting proteins by circRNA-pulldown in PDAC cells. CircRTN4 interacted with important epithelial-mesenchymal transition (EMT)- driver RAB11FIP1 to block its ubiquitination site. We found that circRTN4 knockdown promoted the degradation of RAB11FIP1 by increasing its ubiquitination. Also, circRTN4 knockdown inhibited the expression of RAB11FIP1-regulating EMT-markers Slug, Snai1, Twist, Zeb1 and N-cadherin in PDAC. Conclusion The upregulated circRTN4 promotes tumor growth and liver metastasis in PDAC through the novel circRTN4-miR-497-5p-HOTTIP pathway. Also, circRTN4 stabilizes RAB11FIP1 to contribute EMT. Graphical abstract

Examination of The Characteristics of Long-Term Survivors Among Patients With Gallbladder Cancer With Liver Metastasis Who Underwent Surgical Treatment: A Retrospective Multicenter Study (ACRoS1406)

Background: Gallbladder cancer (GBC) with liver metastasis is considered unresectable. However, there have been infrequent reports of long-term survival in patients with GBC and liver metastases. Therefore, we examined the characteristics of long-term survivors of gallbladder cancer with liver metastasis.Methods: A retrospective multicenter study of 503 patients with GBC (mean age, 68.6 years; female, 52%) was performed. Although patients with pre-operatively diagnosed GBC and liver metastasis were generally excluded from resection, some cases identified during surgery were resected.Result: In patients with resected stage III/IV GBC (n = 228), the period 2007–2013 (vs. 2000–2006, hazard ratio 0.55), other type histology (vs. well/moderate histology, hazard ratio 2.34), ≥2 liver metastases (vs. one liver metastasis, hazard ratio 4.30), and positive margin resection (vs. complete resection with a negative margin, hazard ratio 1.57) were independent prognostic factors for overall survival, whereas one liver metastasis (vs. no liver metastasis) was not. The 5-year overall survival and median survival times in those with one liver metastasis with complete resection and a negative margin (40.9%, 28.3 months) were significantly better than those in patients with ≥2 liver metastases with complete resection and a negative margin (0%, 11.0 months, p = 0.025), and comparable to those in patients with liver metastasis with complete resection and a negative margin (37.0%, 33.0 months). According to the univariate analysis of resected patients with GBC and liver metastases (n=24), minor hepatectomy, less blood loss, less surgery time, papillary adenocarcinoma, T2, morbidity of Clavien–Dindo classification ≤ 2, and adjuvant chemotherapy were significantly associated with longer survival. Long-term survivors (n = 5) had a high frequency of T2 tumors (4/5), had small liver metastases near the gallbladder during or after surgery, underwent minor hepatectomy without post-operative complications, and received post-operative adjuvant chemotherapy.Conclusions: Although there is no surgical indication for GBC with liver metastasis diagnosed pre-operatively, minor hepatectomy and post-operative chemotherapy may be an option for selected patients with T2 GBC and liver metastasis identified during or after surgery who do not have other poor prognostic factors.