Histopathological Image Classification using Discriminative Feature-oriented Dictionary Learning
| Autor: | Hojjat Seyed Mousavi, Tiep H. Vu, Vishal Monga, Ganesh Rao, U. K. Arvind Rao |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Feature extraction Computer Science - Computer Vision and Pattern Recognition Image processing 02 engineering and technology Kidney Article 030218 nuclear medicine & medical imaging Machine Learning 03 medical and health sciences 0302 clinical medicine Discriminative model Neoplasms 0202 electrical engineering electronic engineering information engineering Medical imaging Image Processing Computer-Assisted Humans Electrical and Electronic Engineering Lung Radiological and Ultrasound Technology Contextual image classification business.industry Histocytochemistry Pattern recognition Computer Science Applications 020201 artificial intelligence & image processing Artificial intelligence Neural coding business Dictionary learning Software |
| DOI: | 10.48550/arxiv.1506.05032 |
| Popis: | In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structures. In this paper, we propose an automatic feature discovery framework via learning class-specific dictionaries and present a low-complexity method for classification and disease grading in histopathology. Essentially, our Discriminative Feature-oriented Dictionary Learning (DFDL) method learns class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample. At the same time, the dictionary is designed to be poorly capable of representing samples from other classes. Experiments on three challenging real-world image databases: 1) histopathological images of intraductal breast lesions, 2) mammalian kidney, lung and spleen images provided by the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 3) brain tumor images from The Cancer Genome Atlas (TCGA) database, reveal the merits of our proposal over state-of-the-art alternatives. {Moreover, we demonstrate that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available Comment: Accepted version to Transaction on Medical Imaging, 13 pages |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|