Image retrieval with principal component analysis for breast cancer diagnosis on various ultrasonic systems

Abstract

ObjectivesWe present a computer-aided diagnostic (CAD)

Computer-aided diagnosis with textural features for breast lesions in sonograms

“…The transformed vector, the principal vector, was performed as new textural features to retrieve images from the US database by using the similarity measure of Euclidean distance. The retrieved images were supplied as the reference resources to identify benign and malignant lesions [10]. From the simulations, the proposed CAD system achieved a satisfied diagnostic performance by using image retrieval techniques [11][12][13][14][15] with PCA on the textural features.…”

Computer‐aided diagnosis using morphological features for classifying breast lesions on ultrasound

“…Medical costs and adverse reactions will be reduced as well. In the future, we hope to improve the performance of the proposed CAD system by adding other features (such as echo‐texture, spiculations, blood flow)9, 31, 32 of breast tumors. Additionally, three‐dimensional sonography is being used increasingly in the clinical setting.…”

“…The textural variation between benign and malignant tumors is deemed a useful characteristic for their differentiation on ultrasound9–11. Common weaknesses of the previous CAD systems employing textural analysis are that they only work effectively with specific ultrasound systems.…”

Multiview Locally Linear Embedding for Effective Medical Image Retrieval

“…To reduce the dimension of feature vectors, one conventional solution is to concatenate these feature vectors into a long vector, and then use traditional dimension reduction techniques, e.g., locally linear embedding (LLE) [20], principal component analysis (PCA) [21] or laplacian eigenmaps (LE) [22], to project the concatenated vector to a low-dimensional subspace. Huang et al [23] built a computer-aided breast cancer diagnosis system using PCA to project original high-dimensional textual features into a low-dimensional feature space. Zhang et al [24] proposed a brain midsagittal plane image recognition system that employed PCA to perform dimensionality reduction.…”