A deep convolutional neural network for the early detection of breast carcinoma with respect to hyper- parameter tuning

• Published in: Multimedia tools and applications Vol. 79; no. 15-16; pp. 11013 - 11038
• Main Authors: Saranyaraj, D, Manikandan, M, Maheswari, S
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-04-2020; Springer Nature B.V
• Subjects: Accuracy; Artificial neural networks; Breast cancer; Cancer; Classification; Computational grids; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Digital imaging; Feature extraction; Image analysis; Image classification; Image detection; Image processing; Mammography; Mathematical models; Medical imaging; Multilayers; Multimedia Information Systems; Neural networks; Noise reduction; Parameters; Screening; Smoothness; Special Purpose and Application-Based Systems; Tuning; Deep learning; Breast cancer detection; Deep convolutional neural network; Hyper-parameter tuning
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-018-6560-x

Medical image processing needs attention towards accurate analysis rate which directly implies on the treatment. This paper focuses on the mammogram image analysis for early prediction of breast cancer (Screening) and reduce the mortality rate rather than using an invasive diagnosis technique. To classify the mammogram images a novel network called Deep Convolutional neural network (DCNN) is utilized in which multi-layer perceptron is used in the fully connected layer to accurately classify the mammogram images as three classes benign, malignant and normal. Before classifying the breast cancer, image pre-processing and feature extraction plays a major role in preserving the useful information and extracting the desired features. The Bilateral filter with a vector grid computing is used as the noise reduction filter to preserve the edge information which is essential in differentiating the masses and the dense tissue. The Features like Area, Radius, Perimeter and smoothness are extracted to train the network and to detect the malignant tumor stating if the patient is positive or negative with the cancer. Five stages have been proposed and implemented such as: (a) Crop and resize of the original mammogram; (b) De-Noising the DDSM (Digital Database for Screening Mammography) image to preserve the edge information. (c) Train the proposed DCNN model using the features extracted, (d) Classifying the DDSM images (e) Evaluating the performance using hyper parameter tuning of the proposed system. Unstinted Observations are made to justify the listed findings and by comparing the proposed outline with the help of the literature about the several in-use image classification models. A confusion matrix is drawn with the classes based on: Those with Benign, Malignant and normal tissues. The results are discussed (benchmarked) to show that fine-tuning of the final layers or the entire network parameters leads in achieving 96.23% of overall test accuracy and 97.46% of Average Classification Accuracy.