NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentation
Abstract
High-resolution mapping of cells and tissue structures provides a foundation for developing interpretable machine-learning models for computational pathology. Deep learning algorithms can provide accurate mappings given large numbers of labeled instances for training and validation. Generating adequate volume of quality labels has emerged as a critical barrier in computational pathology given the time and effort required from pathologists. In this paper we describe an approach for engaging crowds of medical students and pathologists that was used to produce a dataset of over 220,000 annotations of cell nuclei in breast cancers. We show how suggested annotations generated by a weak algorithm can improve the accuracy of annotations generated by non-experts and can yield useful data for training segmentation algorithms without laborious manual tracing. We systematically examine interrater agreement and describe modifications to the MaskRCNN model to improve cell mapping. We also describe a technique we call Decision Tree Approximation of Learned Embeddings (DTALE) that leverages nucleus segmentations and morphologic features to improve the transparency of nucleus classification models. The annotation data produced in this study are freely available for algorithm development and benchmarking at: https://sites.google.com/view/nucls.
Cite
@article{arxiv.2102.09099,
title = {NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentation},
author = {Mohamed Amgad and Lamees A. Atteya and Hagar Hussein and Kareem Hosny Mohammed and Ehab Hafiz and Maha A. T. Elsebaie and Ahmed M. Alhusseiny and Mohamed Atef AlMoslemany and Abdelmagid M. Elmatboly and Philip A. Pappalardo and Rokia Adel Sakr and Pooya Mobadersany and Ahmad Rachid and Anas M. Saad and Ahmad M. Alkashash and Inas A. Ruhban and Anas Alrefai and Nada M. Elgazar and Ali Abdulkarim and Abo-Alela Farag and Amira Etman and Ahmed G. Elsaeed and Yahya Alagha and Yomna A. Amer and Ahmed M. Raslan and Menatalla K. Nadim and Mai A. T. Elsebaie and Ahmed Ayad and Liza E. Hanna and Ahmed Gadallah and Mohamed Elkady and Bradley Drumheller and David Jaye and David Manthey and David A. Gutman and Habiba Elfandy and Lee A. D. Cooper},
journal= {arXiv preprint arXiv:2102.09099},
year = {2022}
}