NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentation

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 adequ...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-02
Hauptverfasser: Mohamed, Amgad, Atteya, Lamees A, Hagar Hussein, Kareem Hosny Mohammed, Hafiz, Ehab, Elsebaie, Maha A T, Alhusseiny, Ahmed M, Mohamed Atef AlMoslemany, Elmatboly, Abdelmagid M, Pappalardo, Philip A, Rokia Adel Sakr, Mobadersany, Pooya, Ahmad, Rachid, Saad, Anas M, Alkashash, Ahmad M, Ruhban, Inas A, Alrefai, Anas, Elgazar, Nada M, Abdulkarim, Ali, Abo-Alela Farag, Etman, Amira, Elsaeed, Ahmed G, Alagha, Yahya, Amer, Yomna A, Raslan, Ahmed M, Nadim, Menatalla K, Elsebaie, Mai A T, Ayad, Ahmed, Hanna, Liza E, Gadallah, Ahmed, Elkady, Mohamed, Drumheller, Bradley, Jaye, David, Manthey, David, Gutman, David A, Elfandy, Habiba, Cooper, Lee A D
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2102.09099