Prognostic analysis based on multi-features calculation and clinical information fusion of colorectal cancer whole slide pathological image

Abstract Background: Colorectal cancer (CRC) is a malignant tumor within digestive tract with both high incidence rate and and mortality. Early detection and intervention could improve patient clinical outcome and survival. Methods: This study computationally investigate a set of prognostic tissue and celluer features from diagnostic tissue slide. With the combination of clinical prognostic variable, the pathological image features could predict the prognosis in CRC patients.ur CRC prognosis prediction pipeline is sequentially consisted of three modules: (1) A DeepTissue Net to delineate outlines of different tissue types within the WSI of CRC for further ROI selection by pathologist; (2) Development of three-level quantitative image metrics related to tissue compositions, cell shape and hidden features from deep network; (3) Fusion of multi-level features to build a prognostic CRC model for predicting survival for CRC. Results: Experimental results suggest that each group of features has a certain relationship with the prognosis of patients in the independent test set. In the fusion features combination experiment, the accuracy rate of predicting patients' prognosis and survival status is 81.52%, and the AUC value is 0.77. Conclusion: This paper constructs a model that can predict postoperative survival of patients by using image features and clinical information.Some features were found to be associated with the prognosis and survival of patients.