Evolutionary intelligence for breast lesion detection in ultrasound images: A wavelet modulus maxima and SVM based approach
Intelligent lesion detection system for medical ultrasound images are aimed at reducing physicians’ effort during cancer diagnosis process. Automatic separation and classification of tumours in ultrasound images is challenging owing to the low contrast and noisy behavior of the image. A Computer aid...
Gespeichert in:
Veröffentlicht in: | Journal of intelligent & fuzzy systems 2020-01, Vol.38 (5), p.6279-6290 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Intelligent lesion detection system for medical ultrasound images are aimed at reducing physicians’ effort during cancer diagnosis process. Automatic separation and classification of tumours in ultrasound images is challenging owing to the low contrast and noisy behavior of the image. A Computer aided detection (CAD) system that automatically segment and classify breast tumours in ultrasound (US) images is proposed in this paper. The proposed method is invariant to scale changes and does not require an operator defined initial region of interest. Wavelet modulus maxima points of the US image are analyzed to extract the tumour seed point. The lesions segmented using a region-based approach are classified using a support vector machine (SVM) classifier. Evaluation of various performance measures show that the performance of the proposed CAD system is promising. |
---|---|
ISSN: | 1064-1246 1875-8967 |
DOI: | 10.3233/JIFS-179709 |