| Autor: |
Anand, D., Arulselvi, G., Balaji, G.N., Chandra, G Rajesh |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
International Journal of Intelligent Systems and Applications in Engineering; Vol. 10 No. 4 (2022); 39-47 |
| ISSN: |
2147-6799 |
| Popis: |
The histopathology process remains traditional in nature. Additionally, the physical process of pathologists could deal with solely restricted subjects because of extended phases. This physical process might misguide the physicians when there remain mass subjects to diagnose because of limited time and the nature of complex illnesses such as bone cancer. Addressing this study in digital histopathology remains significant by evolving computer-aided instruments for detection. Bone framework intricacy remains the chief cause to be a gray research field. Comprehension and investigation of the disparate extent of bone anatomy would serve the requirement for building study in automation. To classify the density tumor Computer-aided diagnosis systems have been developed, having as a major challenge to define the features that better represent the images to classify. To overcome the problem, this paper aims to develop a Convolutional Extreme Learning Machine (DC-ELM) algorithm for the assessment of cancer type based on analyzing histopathology images. A fusion of five important classifiers is chosen for our method. In the framework proposed, only by utilizing the karhunenloeve extraction technique, we extract such and such features of the image and, thus, for differentiation of healthy and unhealthy bone regions. These extracted features are fed to machine learning architecture with the prediction for achieving better accuracy. As a result, the suggested DC-ELM algorithm achieves 97.27% accuracy. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
