An efficient Algorithm for medical image classification using Deep Convolutional Network
| Autor: | Ben Ahmed Mohamed, Anouar Boudhir Abdelhakim, Dahdouh Yousra |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0303 health sciences
Contextual image classification Computer science business.industry Deep learning Feature extraction Pattern recognition 02 engineering and technology 021001 nanoscience & nanotechnology Convolutional neural network Random forest 03 medical and health sciences Feature (computer vision) Artificial intelligence 0210 nano-technology Transfer of learning business F1 score 030304 developmental biology |
| Zdroj: | NISS |
| DOI: | 10.1145/3386723.3387896 |
| Popis: | Automatic classification of medical images especially of tissue images is an important task in computer aided diagnosis (CAD) systems. Deep learning methods such as convolutional networks (ConvNets) outperform other state of-the-art methods in images classification tasks. This article describes an accurate and efficient algorithms for this challenging problem, and aims to present different convolutional neural networks to classify the tissue images. first, we built a model that consist of feature extraction and the classification with simple CNN, the second model consist of a CNN as feature extractor by removing the classification layers and using the activations of the last fully connected layer to train Random Forest, and the last one using transfer learning --Fine-Tuning-- pre-trained CNN "DenseNet201". Finally, we have evaluated our models using three metrics: accuracy, Precision and F1 Score. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|