A review of automatic mass detection and segmentation in mammographic images.

This versatile reference provides a wide-ranging look at basic and advanced biostatistical concepts and methods in a format calibrated to individual interests and levels of proficiency. Written with an eye toward the use of computer applications, the book examines the design of medical studies, descriptive statistics, and introductory ideas of probability theory and statistical inference; explores more advanced statistical methods; and illustrates important current uses of biostatistics.

Biostatistics: a Methodology for the Health Sciences

Computer-aided detection of breast cancer on mammograms

https://www.thelancet.com/pdfs/journals/lanres/PIIS2213-2600(14)70239-5.pdf

Mortality prediction in intensive care units with the Super ICU Learner Algorithm (SICULA): a population-based study

This paper introduces a new unsharp masking (UM) scheme, called nonlinear UM (NLUM), for mammogram enhancement. The NLUM offers users the flexibility 1) to embed different types of filters into the nonlinear filtering operator; 2) to choose different linear or nonlinear operations for the fusion processes that combines the enhanced filtered portion of the mammogram with the original mammogram; and 3) to allow the NLUM parameter selection to be performed manually or by using a quantitative enhancement measure to obtain the optimal enhancement parameters. We also introduce a new enhancement measure approach, called the second-derivative-like measure of enhancement, which is shown to have better performance than other measures in evaluating the visual quality of image enhancement. The comparison and evaluation of enhancement performance demonstrate that the NLUM can improve the disease diagnosis by enhancing the fine details in mammograms with no a priori knowledge of the image contents. The human-visual-system-based image decomposition is used for analysis and visualization of mammogram enhancement.

Nonlinear Unsharp Masking for Mammogram Enhancement

The current study investigates texture properties of the tissue surrounding microcalcification (MC) clusters on mammograms for breast cancer diagnosis. The case sample analyzed consists of 85 dense mammographic images, originating from the digital database for screening mammography. mammograms analyzed contain 100 subtle MC clusters (46 benign and 54 malignant). The tissue surrounding MCs is defined on original and wavelet decomposed images, based on a redundant discrete wavelet transform. Gray-level texture and wavelet coefficient texture features at three decomposition levels are extracted from surrounding tissue regions of interest (ST-ROIs). Specifically, gray-level first-order statistics, gray-level cooccurrence matrices features, and Lawspsila texture energy measures are extracted from original image ST-ROIs. Wavelet coefficient first-order statistics and wavelet coefficient cooccurrence matrices features are extracted from subimages ST-ROIs. The ability of each feature set in differentiating malignant from benign tissue is investigated using a probabilistic neural network. Classification outputs of most discriminating feature sets are combined using a majority voting rule. The proposed combined scheme achieved an area under receiver operating characteristic curve (Az) of 0.989. Results suggest that MCspsila ST texture analysis can contribute to computer-aided diagnosis of breast cancer.

Breast Cancer Diagnosis: Analyzing Texture of Tissue Surrounding Microcalcifications

The performance of separate Intensive Care Unit (ICU) status scoring systems vis-a-vis prediction of outcome is not satisfactory. Computer-based predictive modeling techniques may yield good results but their performance has seldom been extensively compared to that of other mature or emerging predictive models. The objective of the present study was twofold: to propose a prototype meta-level predicting approach concerning Intensive Care Unit (ICU) survival and to evaluate the effectiveness of typical mining models in this context. Data on 158 men and 46 women, were used retrospectively (75% of the patients survived). We used Glasgow Coma Scale (GCS), Acute Physiology And Chronic Health Evaluation II (APACHE II), Sequential Organ Failure Assessment (SOFA) and Injury Severity Score (ISS) values to structure a decision tree (DTM), a neural network (NNM) and a logistic regression (LRM) model and we evaluated the assessment indicators implementing Receiver Operating Characteristics (ROC) plot analysis. Our findings indicate that regarding the assessment of indicators' capacity there are specific discrete limits that should be taken into account. The Az score ± SE was 0.8773± 0.0376 for the DTM, 0.8061± 0.0427 for the NNM and 0.8204± 0.0376 for the LRM, suggesting that the proposed DTM achieved a near optimal Az score. The predicting processes of ICU survival may go "one step forward", by using classic composite assessment indicators as variables.

/pdf/predicting-icu-survival-a-meta-level-approach-xn9y1omloh.pdf

Predicting ICU survival: a meta-level approach.

Automated detection of masses on mammograms is challenged by the presence of dense breast parenchyma. The aim of this study is to investigate the feasibility of wavelet-based feature analysis in identifying spiculated and circumscribed masses in dense breast parenchyma. The method includes an edge detection step for breast border identification and employs Gaussian mixture modeling for dense parenchyma labeling. Subsequently, wavelet decomposition is performed and intensity as well as orientation features are extracted from approximation and detail subimages, respectively. Logistic regression analysis (LRA) is employed to differentiate spiculated and circumscribed masses from normal dense parenchyma. The proposed method is tested in 90 dense mammograms containing spiculated masses (30), circumscribed masses (30) and normal parenchyma (30). Free-response receiver operating characteristic (FROC) analysis is used to evaluate the performance of the method, achieving 83.3% sensitivity at 1.5 and 1.8 false positives per image for identifying spiculated and circumscribed masses, respectively.

Using wavelet-based features to identify masses in dense breast parenchyma

A method that performs multiresolution enhancement, adaptive to breast components, for optimal visualization of the entire breast area is presented. The method includes an edge detection step to distinguish breast area from mammogram background and employs Gaussian mixture modeling to segment breast components (uncompressed fat, fat and dense). The original image is decomposed using a redundant discrete wavelet transform and magnitude coefficients corresponding to each breast component are linearly mapped for contrast enhancement. Coefficient mapping is controlled by a gain factor provided by the parameters of the modeled breast components. The processed image is derived by reconstruction of the modified wavelet coefficients. The algorithm is compared with two enhancement methods proposed for soft-copy display, in a dataset of 68 mammograms containing lesions. The proposed method demonstrates increased performance in accentuating lesions embedded in fatty or dense parenchyma, as well as in visualization of anatomical features in the entire breast area.

Breast component adaptive wavelet enhancement for soft-copy display of mammograms

In presence of dense mammographic parenchyma, microcalcifications (MCs) are obscured by anatomical structures, resulting in missed or/and false detections. Image analysis methods applied to improve visualization, detection and/or characterization of MCs, are targeted to MC SNR improvement and are unavoidably accompanied by MC background over-enhancement or false positive (FP) detections. A set of new features is proposed, extracted statistically with Principal Component Analysis from the wavelet coefficients of real subtle MCs in dense parenchyma. Candidate MCs are segmented and classified with the proposed features, using Linear Discriminant Analysis. Our method achieved 69% true positive fraction of MC clusters with 0.2 FPs per image in a dataset with 54 subtle MC clusters in extremely dense parenchyma.

/pdf/microcalcification-features-extracted-from-principal-37s53cffu9.pdf

Filippos Sakellaropoulos

Papers

Breast Cancer Diagnosis: Analyzing Texture of Tissue Surrounding Microcalcifications

Predicting ICU survival: a meta-level approach.

Using wavelet-based features to identify masses in dense breast parenchyma

Breast component adaptive wavelet enhancement for soft-copy display of mammograms

Microcalcification Features Extracted from Principal Component Analysis in the Wavelet Domain