Fig. 5. A comparison of the generalization performance of FIN and RH-M.

Both FIN and RH-M are trained using only human lung tissue samples and the internal generalization part uses unseen FOVs from new lung tissue samples (new patients). The external generalization tests directly apply the same trained networks to new types of samples, i.e., Pap Smear, prostate tissue and salivary gland tissue samples. The ground truth for each sample is obtained through the MH-PR algorithm that used M = 8 raw holograms captured at different sample-to-sensor distances