Research Article
A Pyramid Architecture-Based Deep Learning Framework for Breast Cancer Detection
Algorithm 1
Tissue-level pathological RoI extraction.
Input: WSI image I, patch level DeconvNet for scale l, Cl, layer number L, and confidence threshold t. | Output: Selected patches Ps. | 1: Generate patches PsL-1 with step w and h in IL-1, and location code LCISL-1. | 2: patches initialization with Ps = PsL-1. | 3: for i = L-2 to 2 do | 4: if Ps is empty then | 5: Break | 6: for patch p in Ps do | 7: Calculate cancer confidence of p named c with Ci | 8: if c > t then | 9: Add LCIp to LCISi | 10: for LCI in LCISido | 11: Calculate LCI in i-1 layer | 12: Generate patches with all LCIs named Psi-1 | 13: Set current patch set Ps = Psi-1 |
|