Fig. 4: Workflow diagram of the proposed DL method. | npj Digital Medicine

Fig. 4: Workflow diagram of the proposed DL method.

From: Deep learning to assess microsatellite instability directly from histopathological whole slide images in endometrial cancer

Fig. 4

Firstly, a WSI in multi-resolution pyramid tile-based structure is fed into the proposed foreground patch selection (FPS) model to rapidly locate high-resolution foreground patches without marker regions annotated by medical experts. Then, the modified fully convolutional network model is applied to the selected foreground patches to further generate the tumor-like patch attention scores. Next, the proposed iterative patch sampling (IPS) method samples representative patches with high attention scores. Afterwards, individual patch probabilities of the representative patches are obtained using InceptionV3 classifier, while the individual patch decision weights of the representative patches are computed. Subsequently, the proposed weighted softmax integrated decision (WSID) model produces a reliable and robust slide level probability. Finally, the MSI status prediction is generated.

Back to article page