Liver cancer can be divided into hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and rare types of liver cancer. HCC starts in the hepatoma cells, while ICC occurs in the liver's small bile ducts. HCC accounts for the majority of liver cancers, followed by ICC. Although HCC, ICC, and rare types share some risk factors and clinical manifestations, they differ molecularly and in relation to carcinogenic mechanisms, resulting in differing optimal treatment strategies. Therefore, identifying and differentiating liver cancer types is essential to facilitate clinical decision-making and optimize patient outcomes.
Typically, liver cancer is diagnosed based on imaging, serological, and pathological features. Naked eye analysis of conventional images can identify limited information and is highly subjective and dependent on the radiologist’s experience, which can lead to misclassifications. Ultrasound imaging is the first-line tool for tumor detection and follow-up in high-risk patients as it has the advantages of low cost, simple operation, immediate results, and no radiation exposure. Moreover, it has proven effective for early diagnosis, preoperative grading prediction, efficacy evaluation, and prognostication. Developing and validating new technologies that assist in imaging-based liver cancer differentiation would be beneficial to clinical management.
Radiomics is a high-throughput emerging technology that can extract a large amount of information from liver cancer images and has the potential to assist in highly accurate diagnoses. In addition to tumor diagnosis, radiomics has recently been applied to pathology grade, vascular invasion, therapeutic evaluation, and prognostic prediction. Recent advances in computational analysis, such as machine learning and deep learning, have expanded the use of radiomics to the development and validation of imaging-based nomograms in clinical research. Nomograms are models that take multiple, disease-specific inputs and use those factors in cancer prognosis. Nomograms have already been established and validated in various cancer types; however, few studies have explored their application in differentiating between HCC, ICC, and rare types of liver cancer.
This Research Topic aims to expand and accelerate research on radiomics and image-based nomograms to differentiate liver cancer types and drive personalized liver cancer therapeutics.
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) are out of scope for this section and will not be accepted as part of this Research Topic.
Liver cancer can be divided into hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and rare types of liver cancer. HCC starts in the hepatoma cells, while ICC occurs in the liver's small bile ducts. HCC accounts for the majority of liver cancers, followed by ICC. Although HCC, ICC, and rare types share some risk factors and clinical manifestations, they differ molecularly and in relation to carcinogenic mechanisms, resulting in differing optimal treatment strategies. Therefore, identifying and differentiating liver cancer types is essential to facilitate clinical decision-making and optimize patient outcomes.
Typically, liver cancer is diagnosed based on imaging, serological, and pathological features. Naked eye analysis of conventional images can identify limited information and is highly subjective and dependent on the radiologist’s experience, which can lead to misclassifications. Ultrasound imaging is the first-line tool for tumor detection and follow-up in high-risk patients as it has the advantages of low cost, simple operation, immediate results, and no radiation exposure. Moreover, it has proven effective for early diagnosis, preoperative grading prediction, efficacy evaluation, and prognostication. Developing and validating new technologies that assist in imaging-based liver cancer differentiation would be beneficial to clinical management.
Radiomics is a high-throughput emerging technology that can extract a large amount of information from liver cancer images and has the potential to assist in highly accurate diagnoses. In addition to tumor diagnosis, radiomics has recently been applied to pathology grade, vascular invasion, therapeutic evaluation, and prognostic prediction. Recent advances in computational analysis, such as machine learning and deep learning, have expanded the use of radiomics to the development and validation of imaging-based nomograms in clinical research. Nomograms are models that take multiple, disease-specific inputs and use those factors in cancer prognosis. Nomograms have already been established and validated in various cancer types; however, few studies have explored their application in differentiating between HCC, ICC, and rare types of liver cancer.
This Research Topic aims to expand and accelerate research on radiomics and image-based nomograms to differentiate liver cancer types and drive personalized liver cancer therapeutics.
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) are out of scope for this section and will not be accepted as part of this Research Topic.
