Medical image analysis plays a pivotal role in the evaluation of diseases, including screening, surveillance, diagnosis, and prognosis. Liver is one of the major organs responsible for key functions of metabolism, protein and hormone synthesis, detoxification, and waste excretion. Patients with advanced liver disease and Hepatocellular Carcinoma (HCC) are often asymptomatic in the early stages; however delays in diagnosis and treatment can lead to increased rates of decompensated liver diseases, late-stage HCC, morbidity and mortality. Ultrasound (US) is commonly used imaging modality for diagnosis of chronic liver diseases that includes fibrosis, cirrhosis and portal hypertension. In this paper, we first provide an overview of various diagnostic methods for stages of liver diseases and discuss the role of Computer-Aided Diagnosis (CAD) systems in diagnosing liver diseases. Second, we review the utility of machine learning and deep learning approaches as diagnostic tools. Finally, we present the limitations of existing studies and outline future directions to further improve diagnostic accuracy, as well as reduce cost and subjectivity, while also improving workflow for the clinicians.

Hepatocellular carcinoma (HCC) is a deadly and burdensome form of liver cancer with an increasing global prevalence. Its course is unpredictable as it frequently occurs in the context of underlying end-stage liver disease, and the associated symptoms and adverse effects of treatment cause severe suffering for patients. Palliative care (PC) is a medical specialty that addresses the physical, emotional, and spiritual needs of patients and their carers in the context of life-limiting illness. In other cancers, a growing body of evidence has demonstrated that the early introduction of PC at diagnosis improves patient and carer outcomes. Despite this, the integration of palliative care at the diagnosis of HCC remains suboptimal, as patients usually receive PC only at the very terminal phase of their disease, even when diagnosed early. Significant barriers to the uptake of palliative care in the treatment algorithm of hepatocellular carcinoma fall under four main themes: data limitations, disease, clinician, and patient factors. Barriers relating to data limitations mainly encapsulated the risk of bias inherent in published work in the field of PC. Clinician-reported barriers related to negative attitudes towards PC and a lack of time for PC discussions. Barriers related to the disease align with prognostic uncertainty due to the unpredictable course of HCC. Significantly, there exists a paucity of evidence exploring patient-perceived barriers to timely PC implementation in HCC. Given that patients are often the underrepresented stakeholder in the delivery of PC, future research should explore the patient perspective in adequately designed qualitative studies as the first step.