Viable and necrotic tumor assessment from whole slide images of osteosarcoma using machine-learning and deep-learning models.

Authors:
Harish Babu Arunachalam
Harish Babu Arunachalam
University of Texas at Dallas
Ovidiu Daescu
Ovidiu Daescu
University of Texas at Dallas
Dinesh Rakheja
Dinesh Rakheja
University of Texas Southwestern Medical Center
Dallas | United States
Anita Sengupta
Anita Sengupta
University Dental Hospital of Manchester
David Leonard
David Leonard
Grand Valley State University
United States
Rami Hallac
Rami Hallac
University of Texas Southwestern Medical Center

PLoS One 2019 17;14(4):e0210706. Epub 2019 Apr 17.

The University of Texas Southwestern Medical Center, Dallas, TX, United States of America.

Pathological estimation of tumor necrosis after chemotherapy is essential for patients with osteosarcoma. This study reports the first fully automated tool to assess viable and necrotic tumor in osteosarcoma, employing advances in histopathology digitization and automated learning. We selected 40 digitized whole slide images representing the heterogeneity of osteosarcoma and chemotherapy response. With the goal of labeling the diverse regions of the digitized tissue into viable tumor, necrotic tumor, and non-tumor, we trained 13 machine-learning models and selected the top performing one (a Support Vector Machine) based on reported accuracy. We also developed a deep-learning architecture and trained it on the same data set. We computed the receiver-operator characteristic for discrimination of non-tumor from tumor followed by conditional discrimination of necrotic from viable tumor and found our models performing exceptionally well. We then used the trained models to identify regions of interest on image-tiles generated from test whole slide images. The classification output is visualized as a tumor-prediction map, displaying the extent of viable and necrotic tumor in the slide image. Thus, we lay the foundation for a complete tumor assessment pipeline from original histology images to tumor-prediction map generation. The proposed pipeline can also be adopted for other types of tumor.

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0210706PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6469748PMC
April 2019

Publication Analysis

Top Keywords

necrotic tumor
16
slide images
12
viable necrotic
12
tumor
10
viable tumor
8
tumor assessment
8
tumor-prediction map
8
viable
5
data set
4
set computed
4
computed receiver-operator
4
architecture trained
4
deep-learning architecture
4
receiver-operator characteristic
4
trained data
4
tumor conditional
4
discrimination necrotic
4
necrotic viable
4
tumor models
4
conditional discrimination
4

References

(Supplied by CrossRef)
Primary osteogenic sarcoma: pathologic aspects in 20 patients after treatment with chemotherapy en bloc resection, and prosthetic bone replacement
A Huvos et al.
Archives of pathology & laboratory medicine 1977
Prognostic significance of serum alkaline phosphatase in osteosarcoma of the extremity treated with neoadjuvant chemotherapy: recent experience at Rizzoli Institute
G Bacci et al.
Oncology reports 2002
Pediatric and Adolescent Osteosarcoma
N Marina et al.
2009

Similar Publications