EUVIMEDEUVIMED entdecken
Open Access

Imitating Pathologist Based Assessment With Interpretable and Context Based Neural Network Modeling of Histology Images

Arunima Srivastava, Chaitanya Kulkarni, Kun Huang, Anil Parwani, Parag Mallick, Raghu Machiraju

Biomedical Informatics Insights · 2018

DOI: 10.1177/1178222618807481 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Informatics Insights, 2018. Verfasst von Arunima Srivastava und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Convolutional neural networks (CNNs) have gained steady popularity as a tool to perform automatic classification of whole slide histology images. While CNNs have proven to be powerful classifiers in this context, they fail to explain this classification, as the network engineered features used for modeling and classification are ONLY interpretable by the CNNs themselves. This work aims at enhancing a traditional neural network model to perform histology image modeling, patient classification, and interpretation of the distinctive features identified by the network within the histology whole slide images (WSIs). We synthesize a workflow which (a) intelligently samples the training data by automatically selecting only image areas that display visible disease-relevant tissue state and (b) isolates regions most pertinent to the trained CNN prediction and translates them to observable and qualitative features such as color, intensity, cell and tissue morphology and texture. We use the Cancer Genome Atlas’s Breast Invasive Carcinoma (TCGA-BRCA) histology dataset to build a model predicting patient attributes (disease stage and node status) and the tumor proliferation challenge (TUPAC 2016) breast cancer histology image repository to help identify disease-relevant tissue state (mitotic activity). We find that our enhanced CNN based workflow both increased patient attribute predictive accuracy (~2% increase for disease stage and ~10% increase for node status) and experimentally proved that a data-driven CNN histology model predicting breast invasive carcinoma stages is highly sensitive to features such as color, cell size, and shape, granularity, and uniformity. This work summarizes the need for understanding the widely trusted models built using deep learning and adds a layer of biological context to a technique that functioned as a classification only approach till now.

Schlagwörter

Stichwörter der Autor:innen

CNNcancer histologymodelingneural networks

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA.
  • School of Medicine, Indiana University, Indianapolis, IN, USA.
  • Department of Pathology, The Ohio State University, Columbus, OH, USA.
  • Canary Center at Stanford for Cancer Early Detection, Stanford University, Palo Alto, CA, USA.

Förderung

  • NIGMS NIH HHS
  • NCI NIH HHS

Zitieren

APA

Srivastava, A., Kulkarni, C., Huang, K., Parwani, A., Mallick, P., & Machiraju, R. (2018). Imitating Pathologist Based Assessment With Interpretable and Context Based Neural Network Modeling of Histology Images. Biomedical Informatics Insights. https://doi.org/10.1177/1178222618807481

Vancouver

Srivastava A, Kulkarni C, Huang K, Parwani A, Mallick P, Machiraju R. Imitating Pathologist Based Assessment With Interpretable and Context Based Neural Network Modeling of Histology Images. Biomedical Informatics Insights. 2018. doi:10.1177/1178222618807481

BibTeX
@article{Srivastava2018,
  author = {Srivastava, Arunima and Kulkarni, Chaitanya and Huang, Kun and Parwani, Anil and Mallick, Parag and Machiraju, Raghu},
  title = {Imitating Pathologist Based Assessment With Interpretable and Context Based Neural Network Modeling of Histology Images},
  journal = {Biomedical Informatics Insights},
  year = {2018},
  doi = {10.1177/1178222618807481}
}
Kostenlos starten →