Towards Automatic Image Analysis for Computerised Mammography

Mammographic screening is an effective way to detect breast cancer. Early detection of breast cancer depends to a high degree on the adequacy of the mammogram from which the diagnosis is made. Today, most of the analysis of the mammogram is performed by radiologists. Computer-aided diagnosis (CAD) systems have been proposed as an aid to increase the efficiency and effectiveness of the screening procedure by automatically indicating abnormalities in the mammograms. However, in order for a CAD system to be stable and efficient, the input images need to be adequate. Criteria for adequacy include: high resolution, low image noise and high image contrast. Additionally, the breast needs to be adequately positioned and compressed to properly visualise the entire breast and especially the glandular tissue. This thesis addresses questions regarding the automatic determination of mammogram adequacy with the focus on breast positioning and segmentation evaluation. The goal and, thus, the major technical challenge is to develop algorithms that support fully automatic quality checks. The relevant quality criteria are discussed in Chapter 2. The aim of this discussion is to compile a comprehensive list of necessary criteria that a system for automatic assessment of mammographic adequacy must satisfy. Chapter 3 gives an overview of research performed in computer-aided analysis of mammograms. It also provides basic knowledge about image analysis involved in the research area of computerized mammography in general, and in the papers of this thesis, in particular. In contrast, Chapter 4 describes basic knowledge about segmentation evaluation, which is a highly important component in image analysis. Papers I–IV propose algorithms for measuring the quality of a mammogram according to certain criteria and addresses problems related to them. A method for automatic analysis of the shape of the pectoralis muscle is presented in Paper I. Paper II proposes a fully automatic method for extracting the breast border. A geometric assumption used by radiologists is that the nipple is located at the point on the breast border being furthest away from the pectoralis muscle. This assumption is investigated in Paper III, and a method for automatically restricting the search area is proposed. There has been an increasing need to develop an automated segmentation algorithm for extracting the glandular tissue, where the majority of breast cancer occur. In Paper IV, a novel approach for solving this problem in a robust and accurate way is proposed. Paper V discusses the challenges involved in evaluating the quality of segmentation algorithms based on ground truths provided by an expert panel. A method to relate ground truths provided by several experts to each other in order to establish levels of agreement is proposed. Furthermore, this work is used to develop an algorithm that combines an ensemble of markings into one surrogate ground truth