Breast density classification in mammograms: An investigation of encoding techniques in binary-based local patterns.

We investigate various channel encoding techniques applied to breast density classification in mammograms; specifically, local binary, ternary, and quinary encoding approaches are considered. Subsequently, we propose a new encoding approach based on a seven-encoding technique, yielding a new local pattern operator called a local septenary pattern operator. Experimental results suggest that the proposed local pattern operator is robust and outperforms the other encoding techniques when evaluated on the Mammographic Image Analysis Society (MIAS) and InBreast datasets. The local septenary pattern operator achieved a maximum classification accuracy of 83.3% and 80.5% on the MIAS and InBreast datasets, respectively. The closest comparison achieved by the other local pattern operators is the local quinary operator, with maximum accuracies of 82.1% (MIAS) and 80.1% (InBreast), respectively.

Breast pectoral muscle segmentation in mammograms using a modified holistically-nested edge detection network.

This paper presents a method for automatic breast pectoral muscle segmentation in mediolateral oblique mammograms using a Convolutional Neural Network (CNN) inspired by the Holistically-nested Edge Detection (HED) network. Most of the existing methods in the literature are based on hand-crafted models such as straight-line, curve-based techniques or a combination of both. Unfortunately, such models are insufficient when dealing with complex shape variations of the pectoral muscle boundary and when the boundary is unclear due to overlapping breast tissue. To compensate for these issues, we propose a neural network framework that incorporates multi-scale and multi-level learning, capable of learning complex hierarchical features to resolve spatial ambiguity in estimating the pectoral muscle boundary. For this purpose, we modified the HED network architecture to specifically find 'contour-like' objects in mammograms. The proposed framework produced a probability map that can be used to estimate the initial pectoral muscle boundary. Subsequently, we process these maps by extracting morphological properties to find the actual pectoral muscle boundary. Finally, we developed two different post-processing steps to find the actual pectoral muscle boundary. Quantitative evaluation results show that the proposed method is comparable with alternative state-of-the-art methods producing on average values of 94.8 ±â€¯8.5% and 97.5 ±â€¯6.3% for the Jaccard and Dice similarity metrics, respectively, across four different databases.

Segmentation of breast MR images using a generalised 2D mathematical model with inflation and deflation forces of active contours.

In medical computer aided diagnosis systems, image segmentation is one of the major pre-processing steps used to ensure only the region of interest, such as the breast region, will be processed in subsequent steps. Nevertheless, breast segmentation is a difficult task due to low contrast and inhomogeneity, especially when estimating the chest wall in magnetic resonance (MR) images. In fact, the chest wall comprises fat, skin, muscles, and the thoracic skeleton, which can misguide automatic methods when attempting to estimate its location. The objective of the study is to develop a fully automated method for breast and pectoral muscle boundary estimation in MR images. Firstly, we develop a 2D breast mathematical model based on 30 MRI slices (from a patient) and identify important landmarks to obtain a model for the general shape of the breast in an axial plane. Subsequently, we use Otsu's thresholding approach and Canny edge detection to estimate the breast boundary. The active contour method is then employed using both inflation and deflation forces to estimate the pectoral muscle boundary by taking account of information obtained from the proposed 2D model. Finally, the estimated boundary is smoothed using a median filter to remove outliers. Our two datasets contain 60 patients in total and the proposed method is evaluated based on 59 patients (one patient is used to develop the 2D breast model). On the first dataset (9 patients) the proposed method achieved Jaccard = 81.1% ±6.1 % and dice coefficient= 89.4% ±4.1 % and on the second dataset (50 patients) Jaccard = 84.9% ±5.8 % and dice coefficient = 92.3% ±3.6 %. These results are qualitatively comparable with the existing methods in the literature.

Fully automated breast boundary and pectoral muscle segmentation in mammograms.

Breast and pectoral muscle segmentation is an essential pre-processing step for the subsequent processes in computer aided diagnosis (CAD) systems. Estimating the breast and pectoral boundaries is a difficult task especially in mammograms due to artifacts, homogeneity between the pectoral and breast regions, and low contrast along the skin-air boundary. In this paper, a breast boundary and pectoral muscle segmentation method in mammograms is proposed. For breast boundary estimation, we determine the initial breast boundary via thresholding and employ Active Contour Models without edges to search for the actual boundary. A post-processing technique is proposed to correct the overestimated boundary caused by artifacts. The pectoral muscle boundary is estimated using Canny edge detection and a pre-processing technique is proposed to remove noisy edges. Subsequently, we identify five edge features to find the edge that has the highest probability of being the initial pectoral contour and search for the actual boundary via contour growing. The segmentation results for the proposed method are compared with manual segmentations using 322, 208 and 100mammograms from the Mammographic Image Analysis Society (MIAS), INBreast and Breast Cancer Digital Repository (BCDR) databases, respectively. Experimental results show that the breast boundary and pectoral muscle estimation methods achieved dice similarity coefficients of 98.8% and 97.8% (MIAS), 98.9% and 89.6% (INBreast) and 99.2% and 91.9% (BCDR), respectively.

A sensor and video based ontology for activity recognition in smart environments.

Activity recognition is used in a wide range of applications including healthcare and security. In a smart environment activity recognition can be used to monitor and support the activities of a user. There have been a range of methods used in activity recognition including sensor-based approaches, vision-based approaches and ontological approaches. This paper presents a novel approach to activity recognition in a smart home environment which combines sensor and video data through an ontological framework. The ontology describes the relationships and interactions between activities, the user, objects, sensors and video data.

Dynamic iris biometry: a technique for enhanced identification.

BACKGROUND: The iris as a unique identifier is predicated on the assumption that the iris image does not alter. This does not consider the fact that the iris changes in response to certain external factors including medication, disease, surgery as well as longer term ageing changes. It is also part of a dynamic optical system that alters with light level and focussing distance. A means of distinguishing the features that do not alter over time from those that do is needed. This paper applies iris recognition algorithms to a newly acquired database of 186 iris images from four subjects. These images have greater magnification and detail than iris images in existing databases. Iris segmentation methods are tested on the database. A new technique that enhances segmentation is presented and compared to two existing methods. These are also applied to test the effects of pupil dilation in the identification process. FINDINGS: Segmentation results from all the images showed that using the proposed algorithm accurately detected pupil boundaries for 96.2% respectively of the images, which was an increase of 88.7% over the most commonly used algorithm. For the images collected, the proposed technique also showed significant improvement in detection of the limbal boundary compared to the detection rates using existing methods. With regard to boundary displacement errors, only slight errors were found with the proposed technique compared to extreme errors made when existing techniques were applied. As the pupil becomes more dilated, the success of identification is increasingly more dependent on the decision criterion used. CONCLUSIONS: The enhanced segmentation technique described in this paper performs with greater accuracy than existing methods for the higher quality images collected in this study. Implementation of the proposed segmentation enhancement significantly improves pupil boundary detection and therefore overall iris segmentation. Pupil dilation is an important aspect of iris identification; with increasing dilation, there is a greater risk of identification failure. Choice of decision criterion for identification should be carefully reviewed. It needs to be recognised that differences in the quality of images in different databases may result in variations in the performance of iris recognition algorithms.