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

Amgad, Mohamed; Atteya, Lamees A.; Hussein, Hagar; Mohammed, Kareem Hosny; Hafiz, Ehab; Elsebaie, Maha A. T.; Alhusseiny, Ahmed M.; AlMoslemany, Mohamed Atef; Elmatboly, Abdelmagid M.; Pappalardo, Philip A.; Sakr, Rokia Adel; Mobadersany, Pooya; Rachid, Ahmad; Saad, Anas M.; Alkashash, A M; Ruhban, Inas A.; Alrefai, Anas; Elgazar, Nada M.; Abdulkarim, Ali; Farag, Abo-Alela; Etman, Amira; Elsaeed, Ahmed G.; Alagha, Yahya; Amer, Y. A.; Raslan, Ahmed M.; Nadim, Menatalla K.; Elsebaie, Mai A. T.; Ayad, Ahmed; Hanna, Liza E.; Gadallah, Ahmed M.; El‐Kady, M. A.; Drumheller, Bradley; Jaye, David L.; Manthey, David; Gutman, David; Elfandy, Habiba; Cooper, Lee

doi:10.48550/arxiv.2102.09099

Cited by 12 publications

(23 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used two publicly available datasets: PanNuke [27,28] and NuCLS [29]. For model training and validation, PanNuke breast cancer data of four major cell types (Neoplastic, Inflammatory, Connective and Epithelial cells) available in three pre-defined folds was used.…”

Section: Datasets and Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

ALBRT: Cellular Composition Prediction in Routine Histology Images

Dawood¹,

Branson²,

Rajpoot³

et al. 2021

Preprint

View full text Add to dashboard Cite

Cellular composition prediction, i.e., predicting the presence and counts of different types of cells in the tumor microenvironment from a digitized image of a Hematoxylin and Eosin (H&E) stained tissue section can be used for various tasks in computational pathology such as the analysis of cellular topology and interactions, subtype prediction, survival analysis, etc. In this work, we propose an image-based cellular composition predictor (ALBRT) which can accurately predict the presence and counts of different types of cells in a given image patch. ALBRT, by its contrastive-learning inspired design, learns a compact and rotation-invariant feature representation that is then used for cellular composition prediction of different cell types. It offers significant improvement over existing state-of-the-art approaches for cell classification and counting. The patch-level feature representation learned by ALBRT is transferrable for cellular composition analysis over novel datasets and can also be utilized for downstream prediction tasks in CPath as well. The code and the inference webserver for the proposed method are available at the URL: https://github.com/engrodawood/ALBRT.

show abstract

Section: Datasets and Preprocessingmentioning

confidence: 99%

“…For assessing model generalization, we used NuCLS dataset [29] consisting of 1, 744 field of views (FOVs) partitioned into 5 pre-defined train and validation folds. FOVs from the corrected single-rater NuCLS dataset are of varying sizes with a spatial resolution of 0.20 MPP.…”

Section: Datasets and Preprocessingmentioning

confidence: 99%

ALBRT: Cellular Composition Prediction in Routine Histology Images

Dawood¹,

Branson²,

Rajpoot³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These settings often require highly-skilled annotators and accordingly high compensation. For instance, cell annotation in Computational Pathology requires expert physicians (pathologists), whose training involves several years of clinical residency [3,31]. Reducing cost and effort for these annotators would directly enable the collection of new large-scale tiny-object datasets, and contribute to higher model performances.…”

Section: Introductionmentioning

confidence: 99%

Interactive Multi-Class Tiny-Object Detection

Lee¹,

Park²,

Song³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Compared to other applications areas such as neuro, ophthalmic, cardiac and musculoskeletal, histopathology image analysis is one of the most dominant applications of deep learning, and the introduction of grand challenges in digital pathology (e.g. NuCLS [8], BACH [9], MoNuSeg [10]) has fostered the development of computerized digital pathology Fig. 1: Top: Graph-based representation of images for relationaware human-object interaction, image segmentation, and human pose estimation (left-to-right).…”

Section: Introductionmentioning

confidence: 99%

A Survey on Graph-Based Deep Learning for Computational Histopathology

Ahmedt-Aristizabal¹,

Armin²,

Denman³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the remarkable success of representation learning for prediction problems, we have witnessed a rapid expansion of the use of machine learning and deep learning for the analysis of digital pathology and biopsy image patches. However, traditional learning over patch-wise features using convolutional neural networks limits the model when attempting to capture global contextual information. The phenotypical and topological distribution of constituent histological entities play a critical role in tissue diagnosis. As such, graph data representations and deep learning have attracted significant attention for encoding tissue representations, and capturing intra-and inter-entity level interactions. In this review, we provide a conceptual grounding of graph-based deep learning and discuss its current success for tumor localization and classification, tumor invasion and staging, image retrieval, and survival prediction. We provide an overview of these methods in a systematic manner organized by the graph representation of the input image including whole slide images and tissue microarrays. We also outline the limitations of existing techniques, and suggest potential future advances in this domain.

show abstract

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

Cited by 12 publications

References 0 publications

ALBRT: Cellular Composition Prediction in Routine Histology Images

ALBRT: Cellular Composition Prediction in Routine Histology Images

Interactive Multi-Class Tiny-Object Detection

A Survey on Graph-Based Deep Learning for Computational Histopathology

Contact Info

Product

Resources

About