Distant supervision for imaging-based cancer sub-typing in Intrahepatic Cholangiocarcinoma.

Finding effective ways to perform cancer sub-typing is currently a trending research topic for therapy opti-mization and personalized medicine. Stemming from genomic field, several algorithms have been proposed. In the context of texture analysis, limited efforts have been attempted, yet imaging information is known to entail useful knowledge for clinical practice. We propose a distant supervision model for imaging-based cancer sub-typing in Intrahepatic Cholangiocar-cinoma patients. A clinically informed stratification of patients is built and homogeneous groups of patients are characterized in terms of survival probabilities, qualitative cancer variables and radiomic feature description. Moreover, the contributions of the information derived from the ICC area and from the peri tumoral area are evaluated. The findings suggest the reliability of the proposed model in the context of cancer research and testify the importance of accounting for data coming from both the tumour and the tumour-tissue interface. Clinical relevance - In order to accurately predict cancer prognosis for patients affected by ICC, radiomic variables of both core cancer and surrounding area should be exploited and employed in a model able to manage complex information.

Recurrence-specific supervised graph clustering for subtyping Hodgkin Lymphoma radiomic phenotypes.

The prediction at baseline of patients at high risk for therapy failure or recurrence would significantly impact on Hodgkin Lymphoma patients treatment, informing clinical practice. Current literature is extensively searching insights in radiomics, a promising framework for high-throughput imaging feature extraction, to derive biomarkers and quantitative prognostic factors from images. However, existing studies are limited by intrinsic radiomic limitations, high dimensionality among others. We propose an exhaustive patient representation and a recurrence-specific multi-view supervised clustering algorithm for estimating patient-to-patient similarity graph and learning recurrence probability. We stratified patients in two risk classes and characterize each group in terms of clinical variables.