Categorization of breast masses based on deep belief network parameters optimized using chaotic krill herd optimization algorithm for frequent diagnosis of breast abnormalities. Issue 5 (12th March 2022)

• Record Type: Journal Article
• Authors: Chandraraju, Thirumarai Selvi; Jeyaprakash, Amudha
• Is Part Of: International journal of imaging systems and technology. Volume 32:Issue 5(2022)
• Page Start: 1561
• Page End: 1576
• Publication Date: 2022-03-12
• Subjects: altered phase preserving dynamic range compression (APPDRC) -- breast cancer -- chaotic krill herd optimization (CKHO) -- classification -- deep belief network (DBN); Imaging systems -- Periodicals; Image processing -- Periodicals; 621.367
• DOI: 10.1002/ima.22718
• Languages: English
• ISSNs: 0899-9457

Abstract

Abstract: Several deep learning techniques are utilized for classification of the masses in mammogram images. But the existing method doesnot provide sufficient accuracy . for breast masses classification in mammogram images. In this manuscript, an efficient breast cancer image classification framework utilizing the deep belief network (DBN) through chaotic krill herd optimization (CKHO) algorithm for classification of masses in mammogram images is proposed. Initially the input mammogram images are pre‐processed by altered phase preserving dynamic range compression (APPDRC) method for removing the unwanted noise and artifacts. Then these pre‐processed images are assumed with DBN for classifying that mass in the mammogram images into normal, benign, and malignant lesions. Generally, DBN does not reveal any acceptance of optimization techniques for computing optimal parameters that guarantee an accurate classification. Therefore in this work, proposed CKHO algorithm is employed for optimizing weight parameters of the self‐attention convolutional neural network (SACNN). The simulation process is performed under MATLAB platform. Finally, the proposed DBN with chaotic krill herd optimization algorithm (DBN‐CKHO) attains high accuracy 44.5%, 33.42%, 55.23%, 62.35%, and 43.42% when compared with the existing method such as extreme learning machine classifier with moth flame optimization (ELMC‐MFO), Kernel extreme learning machine classifier with Chaotic salp swarm algorithm (KELMC‐CSSA), Extreme learning machine classifier with fruit fly optimization algorithm (ELMC‐FOA), Kernel extreme learning machine classifier with grasshopper optimization algorithm (KELMC‐GOA) and deep neural network with non‐dominated sorting genetic algorithm‐based classification approach.