|
Histopathological tissue analysis is the most effective and definitive method to prognosis cancer and stratify the aggressiveness of the disease. The Gleason Score (GS) is the most powerful grading system based on architectural tumor pattern quantification. This score characterizes cancer tumor tissue, such as the level of cell differentiation on histopathological images. The reported GS is described as the sum of two principal grades present in a particular image, and ranged from 6 (cancer grow slowly) to 10 (cancer cells spread more rapidly). A main drawback of GS is the pathological dependency on histopathological region stratification, which strongly impacts the clinical procedure to treat the disease. The agreement among experts has been quantified with a kappa index of: ~0.71. Even worse, a higher uncertainty is reported for intermediate grade stratification. This work presents a like-inception deep architecture that is able to differentiate between intermediate and close GS grades. Each image herein evaluated was split-up into regional patches that correspond to a single GS grade. A set of training patches were augmented according to appearance image variations of each grade. Then, a transfer learning scheme was implemented to adapt a bi-Gleason tumor patterns prediction among close levels. The proposed approach was evaluated on public set of 886 tissue H&E stained images with different GS grades, achieving an average accuracy of 0.73% between grades three and four.
|
