NuCLS: A scalable crowdsourcing, deep learning approach and dataset for
nucleus classification, localization and segmentation
- URL: http://arxiv.org/abs/2102.09099v1
- Date: Thu, 18 Feb 2021 01:17:17 GMT
- Title: NuCLS: A scalable crowdsourcing, deep learning approach and dataset for
nucleus classification, localization and segmentation
- Authors: 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)
- Abstract summary: 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.
We show how suggested annotations generated by a weak algorithm can improve the accuracy of annotations generated by non-experts.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- UniCell: Universal Cell Nucleus Classification via Prompt Learning [76.11864242047074]
We propose a universal cell nucleus classification framework (UniCell)
It employs a novel prompt learning mechanism to uniformly predict the corresponding categories of pathological images from different dataset domains.
In particular, our framework adopts an end-to-end architecture for nuclei detection and classification, and utilizes flexible prediction heads for adapting various datasets.
arXiv Detail & Related papers (2024-02-20T11:50:27Z) - SegPrompt: Using Segmentation Map as a Better Prompt to Finetune Deep
Models for Kidney Stone Classification [62.403510793388705]
Deep learning has produced encouraging results for kidney stone classification using endoscope images.
The shortage of annotated training data poses a severe problem in improving the performance and generalization ability of the trained model.
We propose SegPrompt to alleviate the data shortage problems by exploiting segmentation maps from two aspects.
arXiv Detail & Related papers (2023-03-15T01:30:48Z) - Clinically Acceptable Segmentation of Organs at Risk in Cervical Cancer
Radiation Treatment from Clinically Available Annotations [0.0]
We present an approach to learn a deep learning model for the automatic segmentation of Organs at Risk (OARs) in cervical cancer radiation treatment.
We employ simples for automatic data cleaning to minimize data inhomogeneity, label noise, and missing annotations.
We develop a semi-supervised learning approach utilizing a teacher-student setup, annotation imputation, and uncertainty-guided training to learn in presence of missing annotations.
arXiv Detail & Related papers (2023-02-21T13:24:40Z) - PCA: Semi-supervised Segmentation with Patch Confidence Adversarial
Training [52.895952593202054]
We propose a new semi-supervised adversarial method called Patch Confidence Adrial Training (PCA) for medical image segmentation.
PCA learns the pixel structure and context information in each patch to get enough gradient feedback, which aids the discriminator in convergent to an optimal state.
Our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation.
arXiv Detail & Related papers (2022-07-24T07:45:47Z) - Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation
and Classification [4.642724910208435]
We propose a multi-stage annotation pipeline to enable the collection of large-scale datasets for histology image analysis.
We generate the largest known nuclear instance segmentation and classification dataset, containing nearly half a million labelled nuclei.
arXiv Detail & Related papers (2021-08-25T11:58:52Z) - G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for
Biomarker Identification and Disease Classification [49.53651166356737]
We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers.
We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data.
arXiv Detail & Related papers (2021-01-27T19:28:04Z) - Weakly Supervised Deep Nuclei Segmentation Using Partial Points
Annotation in Histopathology Images [51.893494939675314]
We propose a novel weakly supervised segmentation framework based on partial points annotation.
We show that our method can achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods.
arXiv Detail & Related papers (2020-07-10T15:41:29Z) - NINEPINS: Nuclei Instance Segmentation with Point Annotations [2.19221864553448]
We propose an algorithm for instance segmentation that uses pseudo-label segmentations generated automatically from point annotations.
With the generated segmentation masks, the proposed method trains a modified version of HoVer-Net model to achieve instance segmentation.
Experimental results show that the proposed method is robust to inaccuracies in point annotations and comparison with Hover-Net trained with fully annotated instance masks shows that a degradation in segmentation performance does not always imply a degradation in higher order tasks such as tissue classification.
arXiv Detail & Related papers (2020-06-24T08:28:52Z) - A Systematic Approach to Featurization for Cancer Drug Sensitivity
Predictions with Deep Learning [49.86828302591469]
We train >35,000 neural network models, sweeping over common featurization techniques.
We found the RNA-seq to be highly redundant and informative even with subsets larger than 128 features.
arXiv Detail & Related papers (2020-04-30T20:42:17Z) - A generic ensemble based deep convolutional neural network for
semi-supervised medical image segmentation [7.141405427125369]
We propose a generic semi-supervised learning framework for image segmentation based on a deep convolutional neural network (DCNN)
Our method is able to significantly improve beyond fully supervised model learning by incorporating unlabeled data.
arXiv Detail & Related papers (2020-04-16T23:41:50Z) - Effects of annotation granularity in deep learning models for
histopathological images [5.841728014428438]
This work investigates different granularity of annotated data set including image-wise, bounding box, ellipse-wise, and pixel-wise.
In classification, state-of-the-art deep learning-based classifiers perform better when trained by pixel-wise annotation dataset.
Our study shows not only that finer-grained annotation can improve the performance of deep learning models, but also help extracts more accurate phenotypic information.
arXiv Detail & Related papers (2020-01-14T08:39:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.