Establishment and clinical application value of an automatic diagnosis platform for rectal cancer T-staging based on a deep neural network.

BACKGROUND: Colorectal cancer is harmful to the patient's life. The treatment of patients is determined by accurate preoperative staging. Magnetic resonance imaging (MRI) played an important role in the preoperative examination of patients with rectal cancer, and artificial intelligence (AI) in the learning of images made significant achievements in recent years. Introducing AI into MRI recognition, a stable platform for image recognition and judgment can be established in a short period. This study aimed to establish an automatic diagnostic platform for predicting preoperative T staging of rectal cancer through a deep neural network. METHODS: A total of 183 rectal cancer patients' data were collected retrospectively as research objects. Faster region-based convolutional neural networks (Faster R-CNN) were used to build the platform. And the platform was evaluated according to the receiver operating characteristic (ROC) curve. RESULTS: An automatic diagnosis platform for T staging of rectal cancer was established through the study of MRI. The areas under the ROC curve (AUC) were 0.99 in the horizontal plane, 0.97 in the sagittal plane, and 0.98 in the coronal plane. In the horizontal plane, the AUC of T1 stage was 1, AUC of T2 stage was 1, AUC of T3 stage was 1, AUC of T4 stage was 1. In the coronal plane, AUC of T1 stage was 0.96, AUC of T2 stage was 0.97, AUC of T3 stage was 0.97, AUC of T4 stage was 0.97. In the sagittal plane, AUC of T1 stage was 0.95, AUC of T2 stage was 0.99, AUC of T3 stage was 0.96, and AUC of T4 stage was 1.00. CONCLUSION: Faster R-CNN AI might be an effective and objective method to build the platform for predicting rectal cancer T-staging. TRIAL REGISTRATION: chictr.org.cn: ChiCTR1900023575; http://www.chictr.org.cn/showproj.aspx?proj=39665.

Accuracy of endoscopic ultrasound in rectal cancer and its use in transanal endoscopic microsurgery.

Introduction: This study evaluated the accuracy of endoscopic ultrasound (EUS) for preoperative staging of rectal cancer and guiding the treatment of transanal endoscopic microsurgery (TEM) in early rectal cancer.Material and methods: One-hundred-twenty-six patients with rectal cancer were staged preoperatively using EUS and the results were compared with postoperative histopathology results. Radical surgeries, including low anterior resection (LAR), abdominal-perineal resection (APR) and Hartmann surgeries, were performed on patients with advanced rectal cancers, and TEM was performed on patients with stage T1. The Kappa statistic was used to determine agreement between EUS-based staging and pathology staging.Results: The overall accuracies of EUS for T and N stage were 90.8% (Kappa = 0.709) and 76.7% (Kappa = 0.419), respectively. The accuracies of EUS for uT1, uT2, uT3, and uT4 stages were 96.8%, 92.1%, 84.1%, and 88.9%, respectively, and for uN0, uN1, and uN2 stages, they were 71.9%, 64.9%, and 93.0%, respectively. Twelve patients underwent TEM and received confirmed pathology results of early rectal cancer. After postoperative follow-up, there were no local recurrences or distant metastases.Conclusion: EUS is a good and comparable technique for postoperative staging of rectal cancer. Moreover, EUS is used as indicator for preoperative staging and tumor assessment strategy when considering TEM.

Exosomes as critical mediators of cell-to-cell communication in cancer pathogenesis and their potential clinical application.

Exosomes are small membrane vesicles that measure 20 to 100 nm in diameter and are released by many cell types, including lymphocytes, dendritic cells (DCs) and tumor cells. As efficient messengers in cell-to-cell communication, exosomes released by tumors play an important role in regulating tumor malignancy. Tumor-derived exosomes contain proteins, mRNAs, and miRNAs, which can be delivered between different types of cells and even transferred to distant locations to influence the biological activities of tumors, such as proliferation, invasion and metastasis, immunoregulation, generation of a premetastatic niche and stimulation of angiogenesis. This review highlights advances in the understanding of exosome secretion and the role of exosomes in cancer molecular behavior. Moreover, we also discuss the potential clinical application of exosomes as biomarkers and therapeutic tools. Tumor-derived exosomes may represent a target for therapeutic intervention and for the development of early diagnostic biomarkers.

Clinicopathologic significance of slug expression in human intrahepatic cholangiocarcinoma.

AIM: To explore the expression and function of slug, a transcriptional repressor, in human intrahepatic cholangiocarcinoma (IHCC) and identify its role in IHCC progression. METHODS: Expression of slug was detected in 36 cases of IHCC and 12 cases of normal intrahepatic bile ducts and liver parenchyma by immunohistochemistry. The patients were divided into low slug expression group (< 20% of carcinoma cells stained) and high slug expression group (> or = 20% of carcinoma cells stained). Slug expression was correlated with clinicopathological parameters of IHCC patients. The patients were defined as short-term survivors if their survival time was < 12 mo and as long-term survivors if their survival time was > or = 12 mo. RESULTS: Slug was not expressed in normal liver epithelium samples, lowly expressed in 15 tissue samples (10 -, 5 +) and highly expressed in 21 tissue samples (16 ++; 5 +++) from IHCC patients. The survival rate of patients with a low slug expression was 33.3% (n = 5) and 66.7% (n = 10), respectively. The survival rate of patients with a high slug expression was 61.9% (n = 13) and 38.1% (n = 8), respectively (P = 0.02). Lymph node metastasis was found in 4 (26.7%) out of the 15 patients with a low slug expression and in 14 (66.7%) out of the 21 patients with a high slug expression, respectively. The incidence rate of lymph node metastasis increased with the increasing slug expression level (P = 0.003), and higher in patients with a high slug expression than in those with a low slug expression. Slug expression did not significantly correlate with the tumor size and stage or histologic grade, or with the gender and age of patients CONCLUSION: Slug expression is a novel prognostic marker for IHCC with lymph node metastasis.