ABSTRACT
PURPOSE: To investigate whether bevacizumab compromises early response assessment after Transarterial Chemoembolization (TACE) in patients with hepatocellular carcinoma by 3D quantitative European Association for the Study of the Liver (qEASL) criteria in comparison to other imaging-based criteria. MATERIALS AND METHODS: Each of 14 patients receiving TACE and bevacizumab was matched with two patients receiving TACE alone. Baseline and Follow-up MRI was retrospectively analyzed regarding qEASL and other imaging-based criteria. RESULTS: Percentage-based qEASL achieved significant separation in both therapy arms (p=0.046 and p=0.015). Response and Overall Survival showed similar association among treatment groups (p=0.749). CONCLUSIONS: Anti-angiogenic therapy with bevacizumab does not impede early response assessment by qEASL.
Subject(s)
Angiogenesis Inhibitors/therapeutic use , Bevacizumab/therapeutic use , Carcinoma, Hepatocellular/pathology , Chemoembolization, Therapeutic , Liver Neoplasms/pathology , Liver/pathology , Adult , Aged , Aged, 80 and over , Carcinoma, Hepatocellular/drug therapy , Carcinoma, Hepatocellular/therapy , Female , Humans , Liver Neoplasms/drug therapy , Liver Neoplasms/therapy , Magnetic Resonance Imaging/methods , Male , Middle Aged , Retrospective Studies , Treatment Outcome , Vascular Surgical ProceduresABSTRACT
This work addresses multi-class liver tissue classification from multi-parameter MRI in patients with hepatocellular carcinoma (HCC), and is among the first to do so. We propose a structured prediction framework to simultaneously classify parenchyma, blood vessels, viable tumor tissue, and necrosis, which overcomes limitations related to classifying these tissue classes individually and consecutively. A novel classification framework is introduced, based on the integration of multi-scale shape and appearance features to initiate the classification, which is iteratively refined by augmenting the feature space with both structured and rotationally invariant label context features. We study further the topic of rotationally invariant label context feature representations, and introduce a method for this purpose based on computing the energies of the spherical harmonic decompositions computed at different frequencies and radii. We test our method on full 3D multi-parameter MRI volumes from 47 patients with HCC and achieve promising results.
