Neoplasms

All Conditions

Digestive System Diseases

Carcinoma

Carcinoma, Hepatocellular

Neoplasms, Glandular and Epithelial

Neoplasms by Histologic Type

Adenocarcinoma

Liver Neoplasms

Gastrointestinal Neoplasms

Digestive System Neoplasms

Gastrointestinal Diseases

Liver Diseases

In this project, there is only one study group which comprises of patients with Hepatocellular Carcinoma (HCC) who will undergo preoperative Gd-EOB-DTPA enhanced magnetic resonance image.

Histologically-diagnosed primary HCC after curative hepatectomy. The magnetic resonance image will be imported into the software ,and the radiomic textural features will be automatically extracted by the Analysis-Kit software.The high-throughput extracted features will be then selected and a prediction model will be developed in the training set in which patients were collected from a retrospective study. In this project, an independent validation set will be collected and used to validate the prediction accuracy of the model.

Magnetic resonance image

Zebin Chen, MD

Jie Mei, MD

Chen Zebin

Ming Kuang, PhD

Microvascular invasion (MVI) has been well demonstrated as an unfavorable prognostic factor for hepatocellular carcinoma (HCC), and patients with MVI have a high risk of tumor recurrence after curative hepatectomy. Currently, the diagnosis of MVI is determined on the postoperative histologic examination, which greatly limits its influence on preoperative decision making. Therefore, we constructed this prospective study to develop a machine learning-based model for preoperative prediction of MVI by extracting high-dimensional magnetic resonance (MR) image features.

Histologically-diagnosed primary HCC after curative hepatectomy. The magnetic resonance image will be imported into the imaging management software (GE healthcare Analysis-Kit software),and the tumor lesions will manually delineated by two independent radiologists and then reconstruct into three-dimensional images for feature extraction. The radiomic textural features including grayscale histogram, transform matrix, wavelet transform and filter transformation are automatically extracted by the Analysis-Kit software.The high-throughput extracted features will be then selected by the univariate analysis, and a prediction model will be developed based on machine learning algorithm in a training set in which patients were collected from a retrospective study. And in the present study, an independent validation set will be collected and used to validate the prediction accuracy of the model.

Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma

Development of a Machine Learning-based Model for Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma

Postoperative histologically confirmed microvascular invasion

Ming Kuang

Professor

Pharmaceutical Solutions

All Drugs and Chemicals

Hematinics

Liver Extracts

In this project, there is only one study group which comprises of patients with Hepatocellular Carcinoma (HCC) who will undergo contrast-enhanced computed tomography (CECT) and contrast-enhanced ultrasound (CEUS).

The Aplio SSA-770A or Aplio 500 (Toshiba Medical Systems, Tokyo, Japan) equipped with a 375BT convex transducer (frequency range, 1.9 to 6.0 MHz). CHI is used with a mechanical index that ranged from 0.06 to 0.10. After activating CHI mode, a bolus injection of 2.4 ml of SonoVue (Bracco, Milan, Italy) is administered intravenously via an antecubital vein, followed immediately by a flush of 5 ml of normal saline solution. The targeted lesion should be observed continuously for 5 minutes, and the entire arterial and portal venous phases and several repetitions of the late phase are stored on the hard disk. The arterial, portal venous and late phases are defined as 0-30 s, 31-120 s and 121-360 s after the injection, respectively.

contrast-enhanced ultrasound

The Aquilion 64-slice helical CT machine (Tokyo, Japan) is used. The imaging protocol for CT examinations is as follows: 0.5 mm × 64 mm collimation, 120 kV, 150-200 mAs for 64-slice helical CT examination. The standard triphasic scan procedure is used. An unenhanced helical sequence scan through the liver will be performed first; thereafter nonionic iodinated contrast material (Ultravist, Schering, Berlin, Germany) (1.5 mL/kg) will be administered via antecubital vein with power injection at a rate of 4 mL/s for 64-slice helical CT. The arterial phase sequence is obtained 25-32 s after contrast material administration, followed by a portal venous phase sequence 70 s after contrast agent administration.

contrast-enhanced computed tomography

Wei Wang, MD, PhD

Hang-Tong Hu, MD

Presence of microvascular invasion can be estimated preoperatively, by some clinical imaging features such as patient characteristics, serum biomarkers and radiological features. Contrast-enhanced ultrasonography (CEUS) and contrast-enhanced computed tomography (CECT) are routine preoperative conventional examinations for hepatocellular carcinoma (HCC) patients in China. Combining features of CEUS, CECT and clinical factors may improve preoperative MVI assessment. The purpose of this study is to construct a nomogram for preoperative MVI risk estimation with these possible factors.

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization	Link
Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma	NCT03198975	Hepatocellular ...	Magnetic resona...	18 Years - 80 Years	Sun Yat-sen University
Preoperative Estimation of Microvascular Invasion in Hepatocellular Carcinoma	NCT03110068	Hepatocellular ...	contrast-enhanc... contrast-enhanc...	18 Years - 80 Years	Sun Yat-sen University

Spots Global Cancer Trial Database for pathological differentiation