Paper Reading AI Learner

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

2021-02-18 01:17:17
Mohamed Amgad (1), Lamees A. Atteya (2), Hagar Hussein (3), Kareem Hosny Mohammed (4), Ehab Hafiz (5), Maha A.T. Elsebaie (6), Ahmed M. Alhusseiny (7), Mohamed Atef AlMoslemany (8), Abdelmagid M. Elmatboly (9), Philip A. Pappalardo (10), Rokia Adel Sakr (11), Pooya Mobadersany (1), Ahmad Rachid (12), Anas M. Saad (13), Ahmad M. Alkashash (14), Inas A. Ruhban (15), Anas Alrefai (12), Nada M. Elgazar (16), Ali Abdulkarim (17), Abo-Alela Farag (12), Amira Etman (8), Ahmed G. Elsaeed (16), Yahya Alagha (17), Yomna A. Amer (8), Ahmed M. Raslan (18), Menatalla K. Nadim (19), Mai A.T. Elsebaie (12), Ahmed Ayad (20), Liza E. Hanna (3), Ahmed Gadallah (12), Mohamed Elkady (21), Bradley Drumheller (22), David Jaye (22), David Manthey (23), David A. Gutman (24), Habiba Elfandy (25, 26), Lee A.D. Cooper (1, 27, 28) ((1) Department of Pathology, Northwestern University, Chicago, IL, USA, (2) Cairo Health Care Administration, Egyptian Ministry of Health, Cairo, Egypt, (3) Department of Pathology, Nasser institute for research and treatment, Cairo, Egypt, (4) Department of Pathology and Laboratory Medicine, University of Pennsylvania, PA, USA, (5) Department of Clinical Laboratory Research, Theodor Bilharz Research Institute, Giza, Egypt, (6) Department of Medicine, Cook County Hospital, Chicago, IL, USA, (7) Department of Pathology, Baystate Medical Center, University of Massachusetts, Springfield, MA, USA, (8) Faculty of Medicine, Menoufia University, Menoufia, Egypt, (9) Faculty of Medicine, Al-Azhar University, Cairo, Egypt, (10) Consultant for The Center for Applied Proteomics and Molecular Medicine (CAPMM), George Mason University, Manassas, VA, USA, (11) Department of Pathology, National Liver Institute, Menoufia University, Menoufia, Egypt, (12) Faculty of Medicine, Ain Shams University, Cairo, Egypt, (13) Cleveland Clinic Foundation, Cleveland, OH, USA, (14) Department of Pathology, Indiana University, Indianapolis, IN, USA, (15) Faculty of Medicine, Damascus University, Damascus, Syria, (16) Faculty of Medicine, Mansoura University, Mansoura, Egypt, (17) Faculty of Medicine, Cairo University, Cairo, Egypt, (18) Department of Anaesthesia and Critical Care, Menoufia University Hospital, Menoufia, Egypt, (19) Department of Clinical Pathology, Ain Shams University, Cairo, Egypt, (20) Research Department, Oncology Consultants, PA, Houston, TX, USA, (21) Siparadigm Diagnostic Informatics, Pine Brook, NJ, USA, (22) Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA, USA, (23) Kitware Inc., Clifton Park, NY, USA, (24) Department of Neurology, Emory University School of Medicine, Atlanta, GA, USA, (25) Department of Pathology, National Cancer Institute, Cairo, Egypt, (26) Department of Pathology, Children's Cancer Hospital Egypt CCHE 57357, Cairo, Egypt, (27) Lurie Cancer Center, Northwestern University, Chicago, IL, USA, (28) Center for Computational Imaging and Signal Analytics, Northwestern University Feinberg School of Medicine, Chicago, IL, USA)
arXiv_CV
           
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: this https URL.

Abstract (translated)

URL

https://arxiv.org/abs/2102.09099

PDF

https://arxiv.org/pdf/2102.09099.pdf

Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot