Discriminative Localized Sparse Approximations for Mass Characterization in Mammograms

Abstract

The most common form of cancer among women in both developed and developing countries is breast cancer. The early detection and diagnosis of this disease is significant because it may reduce the number of deaths caused by breast cancer and improve the quality of life of those effected. Computer-aided detection (CADe) and computer-aided diagnosis (CADx) methods have shown promise in recent years for aiding in the human expert reading analysis and improving the accuracy and reproducibility of pathology results. One significant application of CADe and CADx is for breast cancer screening using mammograms. In image processing and machine learning research, relevant results have been produced by sparse analysis methods to represent and recognize imaging patterns. However, application of sparse analysis techniques to the biomedical field is challenging, as the objects of interest may be obscured because of contrast limitations or background tissues, and their appearance may change because of anatomical variability. We introduce methods for label-specific and label-consistent dictionary learning to improve the separation of benign breast masses from malignant breast masses in mammograms. We integrated these approaches into our Spatially Localized Ensemble Sparse Analysis (SLESA) methodology. We performed 10- and 30-fold cross validation (CV) experiments on multiple mammography datasets to measure the classification performance of our methodology and compared it to deep learning models and conventional sparse representation. Results from these experiments show the potential of this methodology for separation of malignant from benign masses as a part of a breast cancer screening workflow.

Spatially localized sparse approximations of deep features for breast mass characterization

“…We utilized 10-fold cross-validation to evaluate the performance of our DF-SLESA method for classification of breast masses as benign or malignant. For comparison, we performed conventional sparse representation classification (SRC), spatially localized ensemble sparse analysis (SLESA) [ 34 , 35 ], label-specific dictionary learning SLESA (LS-SLESA) [ 36 ] and the aforementioned end-to-end CNNs on the MergedBreast dataset. In conventional SRC experiments, when no block decomposition is applied, we apply dimensionality reduction via principal component analysis (PCA).…”

Sequenced treatment alternatives to relieve adolescent depression (STAR-AD): a multicentre open-label randomized controlled trial protocol

“…Vortioxetine was selected for its multimodal mechanism of action [ 28 ]. Despite a randomized, placebo-controlled study in adolescent MDD treated with vortioxetine showing negative results compared with a placebo [ 29 ], there is an open-label study showing that vortioxetine surpass a placebo in terms of effectiveness and is regarded as safe and well-received in adolescents with MDD [ 30 ]. In addition, the efficacy of vortioxetine has been well established in adults with MDD in two meta-analyses [ 31 , 32 ].…”

Breast mass characterization using sparse approximations of patch-sampled deep features

“…Mammography is commonly used to detect and diagnose breast cancer. Computer-aided diagnosis methods like those presented in Narvaez et al 2 and in our previous work, [3][4][5] have utilized mathematical optimization and sparse analysis to make classification decisions of breast masses. Other recent methods use state of the art deep learning techniques to classify masses found in mammography.…”