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 ensemble approach utilizes two different classifiers coupled with a user-defined variable. The ensembling approach is very generic and can be easily extended to any other classification architecture. The dataset used is publicly available at [TCIA]. The article is available [here], and the code is available [here]. The BibTeX citation of the article is as follows:

@article{GEHLOT2020101661,
title = "SDCT-AuxNetθ: DCT augmented stain deconvolutional CNN with auxiliary classifier for cancer diagnosis",
journal = "Medical Image Analysis",
volume = "61",
pages = "101661",
year = "2020",
issn = "1361-8415",
doi = "https://doi.org/10.1016/j.media.2020.101661",
url = "http://www.sciencedirect.com/science/article/pii/S136184152030027X",
author = "Shiv Gehlot and Anubha Gupta and Ritu Gupta", }