GCTI-SN is a Geometry-inspired Chemical-invariant and Tissue Invariant Stain Normalization method. The proposed GCTI-SN method corrects for illumination variation, stain chemical, and stain quantity variation in a unified framework by exploiting the underlying color vector space’s geometry. While existing stain... [Read More]

EDNFC-Net is a CNN architecture for nuclei-instance segmentation. The architecture utilizes a fundamental building block called FCC and uses intra-FCC as well as inter-FCC features concatenation. The architecture is trained with a loss function that encourages better foreground and background separation. The full article is available [here].... [Read More]

SDCT-AuxNet$^\theta$: DCT Augmented Stain Deconvolutional CNN with Auxiliary Classifier for Cancer Diagnosis is an architecture developed for acute lymphoblastic leukemia $(ALL)$ cell classification. The architecture employs a small CNN boosted with domain-specific initial layers and a novel ensembling approach. The... [Read More]