Deep Learning-Based Multidimensional Body Composition Mapping for Outcome Prediction in HCC Patients Undergoing TACE

Deep Learning-Based Multidimensional Body Composition Mapping for Predicting Clinical Outcomes in Hepatocellular Carcinoma Patients Undergoing TACE

Hepatocellular carcinoma (HCC) is a common liver cancer, and many patients cannot receive surgery. For these patients, transarterial chemoembolization (TACE) is an important treatment. However, patients often respond differently to TACE, and it is difficult to predict who will benefit most. This study uses deep learning to automatically analyze routine CT images taken before TACE. By measuring body composition features, such as the size and condition of different abdominal organs and tissues, we aim to better understand patients' overall health status and treatment tolerance. The goal is to develop a prediction model that can help doctors estimate survival and treatment outcomes more accurately. This may assist in making more personalized treatment decisions and improving patient care.

Inclusion Criteria:

1. Patients diagnosed with "Hepatocellular Carcinoma" from January 1, 2018 to May 31, 2024;
2. Age > 18 years old.

Exclusion Criteria:

1. Poor image quality;
2. Loss of follow-up;
3. Presence of another type of malignant tumor other than liver cancer;
4. Incomplete medical records.