Key points are not available for this paper at this time.
Radiomics allows for quantitative utilisation of radiological data and carries great potential for improving the diagnosis and management of hepatopancreatobiliary (HPB) cancers. Radiomic features represent changes at the mesoscopic scale and serve as noninvasive markers for tumour heterogeneity. Using deep learning and machine learning approaches, retrospective studies have demonstrated that radiomic signatures have the capability to improve the diagnosis of hepatocellular carcinoma (HCC), pancreatic cancer, and cholangiocarcinoma, in conjunction with radiological evaluation. Radiomic models have been successfully implemented to predict prognosis and treatment response, consistently outperforming established clinical markers. Novel pretreatment radiomic signatures predicting progression, survival and response to immunotherapy in advanced HCC demonstrate the great potential for radiomics in precision medicine. Correlation and integration of radiomics with genomic, metabolomic, and immunological data allows for noninvasive profiling of HPB cancers and the development of highly predictive integrated models. Future adoption of these works into clinical practice will allow for personalised diagnostic and treatment strategies. However, though these works show promise, further evaluation of optimal imaging strategies, image standardisation, and prospective validation across diverse patient populations is needed before widespread adoption in routine clinical practice.
Koku et al. (Mon,) studied this question.