Pedro Henrique Bugatti

Supporting content-based image retrieval and computer-aided diagnosis systems with association rule-based techniques

In this work, we take advantage of association rule mining to support two types of medical systems: the Content-based Image Retrieval (CBIR) systems and the Computer-Aided Diagnosis (CAD) systems. For content-based retrieval, association rules are employed to reduce the dimensionality of the feature vectors that represent the images and to improve the precision of the similarity queries. We refer to the association rule-based method to improve CBIR systems proposed here as Feature selection through Association Rules (FAR). To improve CAD systems, we propose the Image Diagnosis Enhancement through Association rules (IDEA) method. Association rules are employed to suggest a second opinion to the radiologist or a preliminary diagnosis of a new image. A second opinion automatically obtained can either accelerate the process of diagnosing or to strengthen a hypothesis, increasing the probability of a prescribed treatment be successful. Two new algorithms are proposed to support the IDEA method: to pre-process low-level features and to propose a preliminary diagnosis based on association rules. We performed several experiments to validate the proposed methods. The results indicate that association rules can be successfully applied to improve CBIR and CAD systems, empowering the arsenal of techniques to support medical image analysis in medical systems.

Assessing the best integration between distance-function and image-feature to answer similarity queries

The retrieval of multimedia data relies on a feature extractor to provide the intrinsic characteristics (features) from the data, and a measure to quantify the similarity between them. A challenge in multimedia database systems is how to best integrate these two key aspects in order to improve the quality of the retrieved selection when answering similarity queries. In this paper, we analyze and compare a set of distance functions and feature extractors with regard to the association and dependencies among them. The results show that the most widely used and well-known distance functions, such as the Euclidean distance, do not reach a desirable similarity assessment, and reveal that a careful choice of a distance function considerably improves the retrieval of multimedia data, which in our experiments reached up to 92%.

Content-based retrieval of medical images: From context to perception

A challenge in Content-Based retrieval of image exams is to provide a timely answer that complies to the specialists expectation. In many situations, when a specialist gets a new image to analyze, having information and knowledge from similar cases can be very helpful. However, the semantic gap between low-level image features and their high level semantics may impair the system acceptability. In this paper we propose a new method where we gather from the physicians the visual patterns they use to recognize anomalies in images and apply this knowledge not only in the preprocessing of the images, but also on building feature extractors based on these visual patterns. Moreover, our approach generates feature vectors with lower dimensionality diminishing the “dimensionality curse” problem. Experiments using computed tomography lung images show that the proposed method improves the precision of the query results up to 75%, and generates feature vectors up to 94% smaller than traditional feature extraction techniques while keeping the same representative power. This work shows that perception-based feature extraction combined with the image context can be successfully employed to perform similarity queries in medical image databases.

PRoSPer: Perceptual similarity queries in medical CBIR systems through user profiles

In this paper, we present a novel approach to perform similarity queries over medical images, maintaining the semantics of a given query posted by the user. Content-based image retrieval systems relying on relevance feedback techniques usually request the users to label relevant/irrelevant images. Thus, we present a highly effective strategy to survey user profiles, taking advantage of such labeling to implicitly gather the user perceptual similarity. The profiles maintain the settings desired for each user, allowing tuning of the similarity assessment, which encompasses the dynamic change of the distance function employed through an interactive process. Experiments on medical images show that the method is effective and can improve the decision making process during analysis.

Feature Extraction and Selection for Decision Making

This chapter presents and discusses useful algorithms and techniques of feature extraction and selection as well as the relationship between the image features, their discretization and distance functions to maximize the image representativeness when executing similarity queries to improve medical image processing, mining, indexing and retrieval. In particular, we discuss the Omega algorithm combining both, feature selection and discretization, as well as the technique of association rule mining. In addition, we present the Image Diagnosis Enhancement through Associations (IDEA) framework as an example of a system developed to be part of a computer-aided diagnosis environment, which validates the approaches discussed here.

Improving content-based retrieval of medical images through dynamic distance on relevance feedback

Content-based image retrieval approaches rely on automatic features extracted from images to perform similarity queries. The major drawback is that such features often do not satisfactorily represent what the users understand and expect from them, e.g. when searching for similar images. In order to deal with the gap between the user semantic interpretation of the images and what the system can automatically provide, relevance feedback techniques have been employed. However, it has been used without prior analysis about the distance function that best suits the user intention in each relevance feedback cycle and leading to the increase of such gap. Hence, in the present paper we employ user profiling in conjunction to content-based image retrieval and relevance feedback techniques to exploit the user intentions and to reach the best configuration according to the user intention in each relevance feedback cycle. To do so, we introduce a novel approach and a mediator architecture to enhance this process through user feedback and profiling, allowing to dynamically modify the distance function in each feedback cycle choosing the best one for each cycle according to the user expectation. Experiments have shown that the proposed method outperformed the traditional static distance approach, improving in up to 74% the precision of similarity search of medical images.

Feature Selection Guided by Perception in Medical CBIR Systems

This work aims at developing an efficient support to improve the precision of content-based medical image retrieval systems and also accelerate such retrieval, introducing a novel retrieval approach that integrates techniques of feature selection and relevance feedback to perform feature selection guided by perceptual similarity. Low-level features are commonly employed to represent the images by content. Feature selection is performed employing statistical association rules integrated with a relevance feedback process, tuning the mining process on the fly, according to the users perception. This integration not only improves the feature selection accuracy, but also allows personalising such process. The experiments performed show that the method improves up to 30% the query precision and decreases up to 11.6 times the number of features employed to compute the similarity in the content-based query, also decreasing the processing costs and memory requirements of the query execution.

A new method to efficiently reduce histogram dimensionality

A challenge in Computer-Aided Diagnosis based on image exams is to provide a timely answer that complies to the specialists expectation. In many situations, when a specialist gets a new image to analyze, having information and knowledge from similar cases can be very helpful. For example, when a radiologist evaluates a new image, it is common to recall similar cases from the past. However, when performing similarity queries to retrieve similar cases, the approach frequently adopted is to extract meaningful features from the images and searching the database based on such features. One of the most popular image feature is the gray-level histogram, because it is simple and fast to obtain, providing the global gray-level distribution of the image. Moreover, normalized histograms are also invariant to affine transformations on the image. Although vastly used, gray-level histograms generates a large number of features, increasing the complexity of indexing and searching operations. Therefore, the high dimensionality of histograms degrades the efficiency of processing similarity queries. In this paper we propose a new and efficient method associating the Shannon entropy and the gray-level histogram to considerably reduce the dimensionality of feature vectors generated by histograms. The proposed method was evaluated using a real dataset and the results showed impressive reductions of up to 99% in the feature vector size, at the same time providing a gain in precision of up to 125% in comparison with the traditional gray-level histogram.

Towards an Effective and Efficient Learning for Biomedical Data Classification

Nowadays a huge volume of biomedical data (images, genes, etc) are daily generated. The interpretation of such data involves a considerable expertise. The misinterpretation and/or misdetection of a suspicious clinical finding leads to increasing the negligence claims, and redundant procedures (e.g. biopsies). The analysis of biomedical data is a complex task which are performed by specialists on whose expertise degree affects the accuracy of their diagnosis. Besides, due to the huge volume of data, it is a tiresome process. To mitigate these intrinsic drawbacks Computeraided Diagnosis approaches have been proposed in the last decade, but applied without a deep analysis. It is also very common in the literature for the presentation of experimental results to rely solely on the mean of accuracy values. This procedure is not always reliable, especially for applications that require faster classifiers due to their learning-time constraints. Hence, in this paper we proposed an extensive analysis towards an effective and efficient learning for biomedical data classification. To do so, several public biomedical datasets were used against different supervised classifiers, taking into account accuracies and computational times obtained throughout the learning process.

Exploiting Evolutionary Approaches for Content-Based Medical Image Retrieval

Content-based image retrieval can be applied to assist radiologists to improve the efficiency and accuracy of interpreting the images. However, it presents some intrinsic problems. The two main problems are the so-called semantic gap that occurs due to the semantic interpretation of an image is still far to be reach, because it is based on the users perception about the image. The other one is the dimensionality curse which leads to high dimensional feature vectors used to represent an image, where many of these features present some correlation. To mitigate these problems the paper presents a novel framework for content-based medical image retrieval joining feature selection techniques and image descriptors with optimization methods. It is capable to not only capture the user intention, but also to tune the feature selection process through the optimization method according to each user.