Tumor collagen framework from bright-field histology images predicts overall survival of breast carcinoma patients

Autor: Aida Laurinaviciene, Povilas Treigys, Mindaugas Morkunas, Dovile Zilenaite, Arvydas Laurinavicius
Rok vydání: 2021
Předmět:
0301 basic medicine
Pathology
chemistry.chemical_compound
Breast cancer
0302 clinical medicine
Neoplasms
Image Processing
Computer-Assisted
Tumor Microenvironment
Breast
Lymph node
Aged
80 and over
Multidisciplinary
Tissue microarray
Carcinoma
Ductal
Breast
Middle Aged
Prognosis
Primary tumor
Extracellular Matrix
Gene Expression Regulation
Neoplastic
Treatment Outcome
medicine.anatomical_structure
030220 oncology & carcinogenesis
Medicine
Female
Collagen
Breast carcinoma
Adult
Diagnostic Imaging
medicine.medical_specialty
Science
Breast Neoplasms
Article
03 medical and health sciences
Biomarkers
Tumor
medicine
Humans
Sirius Red
Aged
Proportional Hazards Models
business.industry
Histology
medicine.disease
030104 developmental biology
chemistry
Tumor progression
Cancer imaging
Neural Networks
Computer
business
Zdroj: Scientific reports, Berlin : Nature research, 2021, vol. 11, no. 1, art. no. 15474, p. [1-13]
Scientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
Scientific Reports
ISSN: 2045-2322
Popis: Within the tumor microenvironment, specifically aligned collagen has been shown to stimulate tumor progression by directing the migration of metastatic cells along its structural framework. Tumor-associated collagen signatures (TACS) have been linked to breast cancer patient outcome. Robust and affordable methods for assessing biological information contained in collagen architecture need to be developed. We have developed a novel artificial neural network (ANN) based approach for tumor collagen segmentation from bright-field histology images and have tested it on a set of tissue microarray sections from early hormone receptor-positive invasive ductal breast carcinoma stained with Sirius Red (1 core per patient, n = 92). We designed and trained ANNs on sets of differently annotated image patches to segment collagen fibers and extracted 37 features of collagen fiber morphometry, density, orientation, texture, and fractal characteristics in the entire cohort. Independent instances of ANN models trained on highly differing annotations produced reasonably concordant collagen segmentation masks and allowed reliable prognostic Cox regression models (with likelihood ratios 14.11–22.99, at p-value
Databáze: OpenAIRE
Externí odkaz: