1. Automated detection and quantification of breast cancer brain metastases in an animal model using democratized machine learning tools
- Author
-
Jérémie P. Fouquet, Dina Sikpa, Maxime Richer, Réjean Lebel, Martin Lepage, and Phedias Diamandis
- Subjects
medicine.medical_specialty ,Computer science ,H&E stain ,lcsh:Medicine ,Breast Neoplasms ,Machine learning ,computer.software_genre ,Article ,Metastasis ,03 medical and health sciences ,chemistry.chemical_compound ,Mice ,0302 clinical medicine ,Animal model ,Breast cancer ,Image Interpretation, Computer-Assisted ,medicine ,Leverage (statistics) ,Animals ,Humans ,lcsh:Science ,030304 developmental biology ,0303 health sciences ,Mice, Inbred BALB C ,Multidisciplinary ,Eosin ,business.industry ,Brain Neoplasms ,lcsh:R ,medicine.disease ,Disease Models, Animal ,chemistry ,030220 oncology & carcinogenesis ,Histopathology ,Female ,Cancer imaging ,lcsh:Q ,Artificial intelligence ,Supervised Machine Learning ,business ,computer ,Algorithms ,Software - Abstract
Advances in digital whole-slide imaging and machine learning (ML) provide new opportunities for automated examination and quantification of histopathological slides to support pathologists and biologists. However, implementation of ML tools often requires advanced skills in computer science that may not be immediately available in the traditional wet-lab environment. Here, we propose a simple and accessible workflow to automate detection and quantification of brain epithelial metastases on digitized histological slides. We leverage 100 Hematoxylin & Eosin (H&E)-stained whole slide images (WSIs) from 25 Balb/c mice with various level of brain metastatic tumor burden. A supervised training of the Trainable Weka Segmentation (TWS) from Fiji was achieved from annotated WSIs. Upon comparison with manually drawn regions, it is apparent that the algorithm learned to identify and segment cancer cell-specific nuclei and normal brain tissue. Our approach resulted in a robust and highly concordant correlation between automated metastases quantification of brain metastases and manual human assessment (R2 = 0.8783; P
- Published
- 2019
- Full Text
- View/download PDF