Automatic Diagnosis of Ovarian Carcinomas via Sparse Multiresolution Tissue Representation

Abstract. It has now been convincingly demonstrated that ovarian car-cinoma subtypes are not a single disease but comprise a heterogeneous group of neoplasms. Whole slide images of tissue sections are used clini-cally for diagnosing biologically distinct subtypes, as opposed to different grades of the same disease. This new grading scheme for ovarian carcino-mas results in a low to moderate interobserver agreement among pathol-ogists. In practice, the majority of cases are diagnosed at advanced stages and the overall prognosis is typically poor. In this work, we propose an automatic system for the diagnosis of ovarian carcinoma subtypes from large-scale histopathology images. Our novel approach uses an unsuper-vised feature learning framework composed of a sparse tissue represen-tation and a discriminative feature encoding scheme. We validate our model on a challenging clinical dataset of 80 patients and demonstrate its ability to diagnose whole slide images with an average accuracy of 91 % using a linear support vector machine classifier