Grading of invasive breast carcinoma through Grassmannian VLAD encoding
| Autor: | Kalliopi Patsiaoura, Christina Zioga, Nikos Grammalidis, Panagiotis Barmpoutis, Athanasios Kamas, Kosmas Dimitropoulos |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Pathology
Medical Doctors Computer science Health Care Providers lcsh:Medicine Datasets as Topic 02 engineering and technology Systems Science Topology Linear dynamical system 0302 clinical medicine Grassmannian Breast Tumors 0202 electrical engineering electronic engineering information engineering Medicine and Health Sciences Medical Personnel lcsh:Science Manifolds Multidisciplinary Histological Techniques Linear model Manifold Dynamical Systems Professions Oncology 030220 oncology & carcinogenesis Physical Sciences 020201 artificial intelligence & image processing Anatomy Algorithms Research Article medicine.medical_specialty Computer and Information Sciences Histology Dynamical systems theory Imaging Techniques Breast Neoplasms Research and Analysis Methods 03 medical and health sciences Breast cancer Diagnostic Medicine Image Interpretation Computer-Assisted Breast Cancer medicine Cancer Detection and Diagnosis Humans Neoplasm Invasiveness Grading (tumors) business.industry lcsh:R Biology and Life Sciences Cancers and Neoplasms Pattern recognition medicine.disease Pathologists Health Care People and Places Linear Models lcsh:Q Population Groupings Artificial intelligence Neoplasm Grading business Mathematics |
| Zdroj: | PLoS ONE PLoS ONE, Vol 12, Iss 9, p e0185110 (2017) |
| ISSN: | 1932-6203 |
| Popis: | In this paper we address the problem of automated grading of invasive breast carcinoma through the encoding of histological images as VLAD (Vector of Locally Aggregated Descriptors) representations on the Grassmann manifold. The proposed method considers each image as a set of multidimensional spatially-evolving signals that can be efficiently modeled through a higher-order linear dynamical systems analysis. Subsequently, each H&E (Hematoxylin and Eosin) stained breast cancer histological image is represented as a cloud of points on the Grassmann manifold, while a vector representation approach is applied aiming to aggregate the Grassmannian points based on a locality criterion on the manifold. To evaluate the efficiency of the proposed methodology, two datasets with different characteristics were used. More specifically, we created a new medium-sized dataset consisting of 300 annotated images (collected from 21 patients) of grades 1, 2 and 3, while we also provide experimental results using a large dataset, namely BreaKHis, containing 7,909 breast cancer histological images, collected from 82 patients, of both benign and malignant cases. Experimental results have shown that the proposed method outperforms a number of state of the art approaches providing average classification rates of 95.8% and 91.38% with our dataset and the BreaKHis dataset, respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|