Kevin Kiambe | Selcuk University (Selçuk Üniversitesi) (original) (raw)
Artificial intelligence researcher
less
Uploads
Papers by Kevin Kiambe
—Recently, Convolutional Neural Networks (CNNs) have become a preferred deep learning artificial ... more —Recently, Convolutional Neural Networks (CNNs) have become a preferred deep learning artificial neural network of choice for computer assisted medical image analysis. These models are structured as a series of multiple hierarchical processing layers that can automatically learn feature representations from raw images. CNNs have in the past not been in common use, especially in the medical imaging field, due to issues such as insufficient image datasets. The revolution in CNN models has been attributed to powerful parallel processing hardware architectures, increasing number of image datasets and improved training strategies. Utilizing these deep learning techniques are enabling medical experts such as pathologists to utilize artificial intelligence to transform the world of medicine for faster and more accurate diagnoses. In this paper, a two stage model for classifying breast histopathological images is proposed. In the first stage, a CNN is used for extracting features from the images through a feature learning process. The extracted features are then used in the second stage to training classical machine learning models that include the Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Logistic Regression (LR) models. The SVM classifier performs best with accuracies of up to 99.84%.
Bookmarks Related papers MentionsView impact
—Recently, Convolutional Neural Networks (CNNs) have become a preferred deep learning artificial ... more —Recently, Convolutional Neural Networks (CNNs) have become a preferred deep learning artificial neural network of choice for computer assisted medical image analysis. These models are structured as a series of multiple hierarchical processing layers that can automatically learn feature representations from raw images. CNNs have in the past not been in common use, especially in the medical imaging field, due to issues such as insufficient image datasets. The revolution in CNN models has been attributed to powerful parallel processing hardware architectures, increasing number of image datasets and improved training strategies. Utilizing these deep learning techniques are enabling medical experts such as pathologists to utilize artificial intelligence to transform the world of medicine for faster and more accurate diagnoses. In this paper, a two stage model for classifying breast histopathological images is proposed. In the first stage, a CNN is used for extracting features from the images through a feature learning process. The extracted features are then used in the second stage to training classical machine learning models that include the Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Logistic Regression (LR) models. The SVM classifier performs best with accuracies of up to 99.84%.
Bookmarks Related papers MentionsView impact