Detection of Bone Tumours in Radiographic Images using Neural Networks
| Autor: | M. Egmont-Petersen, E. Pelikan |
|---|---|
| Rok vydání: | 1999 |
| Předmět: |
Artificial neural network
Pixel Computer science business.industry Feature vector Feature selection Pattern recognition Artificial Intelligence Feature (computer vision) Pattern recognition (psychology) Feedforward neural network Segmentation Computer vision Computer Vision and Pattern Recognition Artificial intelligence business |
| Zdroj: | Pattern Analysis & Applications. 2:172-183 |
| ISSN: | 1433-7541 |
| DOI: | 10.1007/s100440050026 |
| Popis: | We develop an approach for segmenting radiographic images of focal bone lesions possibly caused by bone tumour. A neural network is used to classify individual pixels by a convolution operation based on a feature vector. We design eight features that characterise the local texture in the neighbourhood of a pixel. Four of the features are based on co-occurrence matrices computed from the neighbourhood. The true class label of the pixels in the radiographs are obtained from annotations made by an experienced radiologist. Neural networks and self-organising feature maps are trained to perform the segmentation task. The experiments confirm the feasibility of using a feature-based neural network for finding pathologic bone changes in radiographic images. An analysis of the eight features indicates that the presence of edges and transitions, the complexity of the texture, as well as the amount of high frequencies in the texture, are the main features discriminating (soft) tissue from pathologic bone, the two classes most likely to be confused. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink