Clinical Research Directory

AI-Based Prediction of Liver Metastasis in Colorectal Cancer (A Retrospective Study)

This multicenter, retrospective study aims to develop and validate a multimodal deep learning model for predicting the risk of metachronous liver metastasis in patients with stage I-III colorectal cancer following curative resection. The model will integrate preoperative contrast-enhanced CT imaging, digitized histopathological whole-slide images, and standard clinical-pathological data. The primary objective is to assess the model's discriminatory performance, measured by the area under the receiver operating characteristic curve (AUC), and to compare its predictive accuracy against traditional prognostic factors such as TNM staging and serum carcinoembryonic antigen levels. This research utilizes existing archival data; no direct patient contact or intervention is involved. The ultimate goal is to provide a robust, data-driven tool for improved risk stratification, which could potentially guide personalized surveillance strategies and adjuvant therapy decisions in the future.

Exosome-derived Extrahepatic Metastasis Detection By Liquid Biopsy In Colorectal Cancer Liver Metastases

Colorectal cancer is the third most common malignancy worldwide, and prognosis largely depends on how effectively metastatic disease is managed. The liver is the most frequent and prognostically important site of metastasis, and patients responding well to chemotherapy may become candidates for curative hepatic resection. However, the presence of extrahepatic metastasis (EHM) critically influences treatment eligibility and survival. Although clinical scores such as the Fong and Beppu systems include EHM as a determinant, its detection by imaging remains limited, especially for small or occult lesions. Accurate identification of EHM is also essential when considering liver transplantation for unresectable colorectal liver metastases (CRLM), where EHM remains an exclusion criterion. The EXELION Study aims to develop a non-invasive diagnostic model using serum exosomal microRNAs (miRNAs) to detect both hepatic and extrahepatic metastases in patients with CRLM. By integrating circulating miRNA profiling with machine learning-based analysis, this study seeks to supplement imaging diagnostics, improve treatment stratification, and enhance clinical decision-making for metastatic colorectal cancer.

MRD-Guided Surveillance in Resectable Stage IV Metastatic Colorectal Cancer (SURVEILLANCE-II)

This study aims to explore the relationship between minimal residual disease (MRD) status and disease recurrence in patients with resectable stage IV metastatic colorectal cancer (mCRC). MRD refers to the presence of cancer cells that remain in the body after treatment but are undetectable by traditional imaging methods. The study will use a blood-based circulating tumor DNA (ctDNA) methylation test to assess its ability to predict cancer recurrence and survival outcomes. Patients who are newly diagnosed with resectable stage IV mCRC and have not yet received any treatment will be enrolled. Blood samples will be collected at multiple time points, including before surgery, after surgery, and during follow-up visits over two years. The study will compare MRD status with recurrence-free survival (RFS), overall survival (OS), and the time it takes for MRD to detect recurrence compared to standard imaging methods. The goal is to determine whether MRD monitoring can provide an early warning of cancer recurrence and help guide treatment decisions. This study may offer valuable insights into improving postoperative surveillance and personalized treatment strategies for metastatic colorectal cancer patients.

The DRAGON 2 Trial

In the randomized controlled DRAGON 2 trial study subjects will be randomized between two arms, PVE alone (control group) and PVE/HVE (interventional group).