Hepatocellular carcinoma (HCC) remains the most common malignancy to threaten public health globally. With advances in artificial intelligence techniques, radiomics for HCC management provides a novel perspective to solve unmet needs in clinical settings, and reveals pixel-level radiological information for medical imaging big data, correlating the radiological phenotype with targeted clinical issues. Conventional radiomics pipelines depend on handcrafted engineering features, and further deep learning-based radiomics pipelines are supplemented with deep features calculated via self-learning strategies. During the past decade, radiomics has been widely applied in accurate diagnoses and pathological or biological behavior evaluation, as well as in prognosis prediction. In this review, we systematically introduce the main pipelines of artificial intelligence-based radiomics and their efficacy in the clinical studies of HCC.

Cancer phototheranostics involving optical imaging-guided photodynamic therapy (PDT) and photothermal therapy (PTT) is a localized noninvasive approach in treating cancer. Mitochondria-targeted near-infrared (NIR) cyanines are excellent therapeutic photosensitizers of cancer. However, most mitochondria-targeted cyanines exist in the form of hydrophobic structures, which in vivo may cause cyanine aggregation during blood circulation, resulting in poor biocompatibility and limited therapeutic efficacy. Therefore, we developed a trade-off strategy by encapsulating mitochondria-targeted cyanines into liposomal bilayers (CyBI7-LPs), which balanced hydrophilicity that favored blood circulation and hydrophobicity that enhanced mitochondria tumor targeting. Moreover, CyBI7-LPs greatly minimized photobleaching of cyanine as self-generated reactive oxygen species (ROS) could rapidly escape from the liposomal bilayer, affording enhanced PTT/PDT efficacy. Bioorthogonal-mediated targeting strategy was further employed to improve uptake of tumor cells by modifying the liposomal surface to generate CyBI7-LPB. The CyBI7-LPB probe produced a tumor-to-background ratio (TBR) of approximately 6.4 at 24 HPI. Guiding by highly sensitive imaging resulted in excellent anti-tumor therapy outcomes using CyBI7-LPB due to the enhanced photothermal and photodynamic effects. This proposed liposomal nanoplatform exhibited a simple and robust approach as an imaging-guided synergistic anti-tumor therapeutic strategy.