• Corpus ID: 228063887

Automated Scoring of Nuclear Pleomorphism Spectrum with Pathologist-level Performance in Breast Cancer

  title={Automated Scoring of Nuclear Pleomorphism Spectrum with Pathologist-level Performance in Breast Cancer},
  author={Caner Mercan and Maschenka C. A. Balkenhol and Roberto Salgado and Mark E. Sherman and Philippe Vielh and W. Vreuls and Ant{\'o}nio Pol{\'o}nia and Hugo M. Horlings and Wilko Weichert and Jodi M. Carter and Peter Bult and Matthias Christgen and Carsten Denkert and Koen van de Vijver and Jeroen van der Laak and Francesco Ciompi},
Nuclear pleomorphism is the degree of change in nuclear morphology, one of the components of the three-tiered breast cancer grading, along with tubular differentiation and mitotic counting. We consider the degree of nuclear pleomorphism as a continuum; a continuous spectrum of change in tumor morphology. We train a deep learning network on a large variety of tumor regions from the collective knowledge of several pathologists without constraining the network to the traditional three-category… 


Automated Nuclear Pleomorphism Scoring in Breast Cancer Histopathology Images Using Deep Neural Networks
This study proposes a practical application of the deep belief based deep neural net-work DBN-DNN model to determine the nuclear pleomorphism score of breast cancer tissue.
Detection of high-grade atypia nuclei in breast cancer imaging
This work proposes the use of Convolutional Neural Networks for the automated detection of cell nuclei, using images from the three grades of breast cancer for training and results show that mostly all atypical nuclei were correctly detected.
Assessment of algorithms for mitosis detection in breast cancer histopathology images
The results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described and the top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.
Automatic glandular and tubule region segmentation in histological grading of breast cancer
An automated algorithm to detect glandular regions and detect the presence of tubules in these regions is proposed, and the ratio of the tubule area to the total glandular area for 353 H and E images of the three TSs is calculated.
Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study
This study proposes COMPASS (COMputer-assisted analysis combined with Pathologist’s ASSessment) for reproducible nuclear atypia scoring of breast cancer, which relies on both cytological criteria assessed subjectively by pathologists as well as computer-extracted textural features.
Predicting breast tumor proliferation from whole‐slide images: The TUPAC16 challenge
The achieved results are promising given the difficulty of the tasks and weakly‐labeled nature of the ground truth, however, further research is needed to improve the practical utility of image analysis methods for this task.
Deep learning assisted mitotic counting for breast cancer
It is concluded that manual mitotic counting is not affected by assessment modality (glass slides, WSI) and that counting mitotic figures in WSI is feasible and using a predefined hotspot area considerably improves reproducibility.
Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks
This paper developed a method to automatically detect mitotic figures in breast cancer tissue sections based on convolutional neural networks (CNNs) based on a reference standard for mitosis detection in entire H&E WSIs requiring minimal manual annotation effort.
Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer
A deep learning system for Gleason scoring whole-slide images of prostatectomies, developed using 112 million pathologist-annotated image patches from 1226 slides, and evaluated on an independent validation dataset of 331 slides, achieves a significantly higher diagnostic accuracy and trended towards better patient risk stratification in correlations to clinical follow-up data.
Automated Tubule Nuclei Quantification and Correlation with Oncotype DX risk categories in ER+ Breast Cancer Whole Slide Images
A deep learning classifier to automatically identify tubule nuclei from whole slide images (WSI) of ER+ BCa is developed, the hypothesis being that the ratio of tubuleuclei to overall number of nuclei (a tubule formation indicator - TFI) correlates with the corresponding ODX risk categories.