Petra Perner

Medical applications in case-based reasoning

This commentary summarizes case-based reasoning research applied in the medical domain. In this commentary the term ‘medical’ is used in an all-encompassing manner. It comprises all aspects of health, for example, from diagnosis to nutrition planning. This article provides references to researchers in the field, systems, workshops, and landmark publications.

An Architecture for a CBR Image Segmentation System

Image Segmentation is a crucial step if extracting information from a digital image. It is not easy to set up the segmentation parameter so that it fits best over the entire set of images, which should be segmented. In the paper, we propose a novel architecture for image segmentation method based on CBR, which can adapt to changing image qualities and environmental conditions. We describe the whole architecture, the methods used for the various components of the systems and show how it performs on medical images.

An architecture for a CBR image segmentation system

Abstract Image segmentation is a crucial step in extracting information from a digital image. It is not easy to set up the segmentation parameter so that it gives the best fit over the entire set of images that need to be segmented. This paper proposes a novel method for image segmentation based on CBR. It describe the whole architecture, as well as the methods used for the various components of the systems, and shows how the technique performs on medical images.

A comparison between neural networks and decision trees based on data from industrial radiographic testing

Abstract In this paper, we are empirically comparing the performance of neural nets and decision trees based on a data set for the detection of defects in welding seams. This data set was created by image feature extraction procedures working on digitized X-ray films. We introduce a framework for distinguishing classification methods. We found that more detailed analysis of the error rate is necessary in order to judge the performance of the learning and classification method. However, the error rate cannot be the only criterion for comparing between the different learning methods. This is a more complex selection process that involves more criteria that we are describing in this paper.

Image mining: issues, framework, a generic tool and its application to medical-image diagnosis

Abstract A tool and a methodology for data mining in picture-archiving systems are presented. It is intended to discover the relevant knowledge for picture analysis and diagnosis from the data base of image descriptions. Knowledge-engineering methods are used to obtain a list of attributes for symbolic image descriptions. An expert describes images according to this list and stores descriptions in the data base. Digital-image processing can be applied to improve imaging of specific image features, or to get expert-independent feature evaluation. Decision-tree induction is used to learn the expert knowledge, presented in the form of image descriptions in the data base. A constructed decision tree presents effective models of decision-making, which can be learned to support image classification by the expert. A tool for data mining and image processing is presented and its application to image mining is shown on the task of Hep-2 cell-image classification. However, the tool and the methodology are generic and can be used for other image-mining tasks. We applied the developed methodology of data mining in other medical tasks, such as in lung-nodule diagnosis in X-ray images, lymph-node diagnosis in MRI and investigation of breast MRI.

Multi-interval Discretization Methods for Decision Tree Learning

Properly addressing the discretization process of continuos valued features is an important problem during decision tree learning. This paper describes four multi-interval discretization methods for induction of decision trees used in dynamic fashion. We compare two known discretization methods to two new methods proposed in this paper based on a histogram based method and a neural net based method (LVQ). We compare them according to accuracy of the resulting decision tree and to compactness of the tree. For our comparison we used three data bases, IRIS domain, satellite domain and OHS domain (ovariel hyper stimulation).

Why Case-Based Reasoning Is Attractive for Image Interpretation

The development of image interpretation systems is concerned with tricky problems such as a limited number of observations, environmental influence, and noise. Recent systems lack robustness, accuracy, and flexibility. The introduction of case-based reasoning (CBR) strategies can help to overcome these drawbacks. The special type of information (i.e., images) and the problems mentioned above provide special requirements for CBR strategies. In this paper we review what has been achieved so far and research topics concerned with case-based image interpretation. We introduce a new approach for an image interpretation system and review its components.

Different Learning Strategies in a Case-Based Reasoning System for Image Interpretation

In our previous work, we introduced the basic structure of a case-based reasoning system for image interpretation, a structural similarity measure, and some fundamental learning techniques. In this paper, we describe more sophisticated learning techniques that are different in abstraction level. We evaluate our method on a set of images from the non-destructive testing domain and show the feasibility of the approach. As result, we can show that conventional image processing methods combined with machine learning techniques form a powerful tool for image interpretation.

Are case-based reasoning and dissimilarity-based classification two sides of the same coin?

Abstract Case-based reasoning (CBR) is used when generalized knowledge is lacking. The method works on a set of cases formerly processed and stored in the case base. A new case is interpreted based on its similarity to cases in the case base. The closest case with its associated result is selected and presented as output of the system. Recently, dissimilarity-based classification (DSC) has been introduced due to the curse of dimensionality of feature spaces and the problem arising when trying to make image features explicitly. The approach classifies samples based on their dissimilarity value to all training samples. In this paper we are reviewing the basic properties of these two approaches. We show the similarity of dissimilarity-based classification to case-based reasoning. Finally, we conclude that dissimilarity-based classification is a variant of case-based reasoning and that most of the open problems in dissimilarity-based classification are research topics of case-based reasoning.

Case-Based Reasoning on Images and Signals

This book is the first edited book that deals with the special topic of signals and images within Case-Based Reasoning (CBR). Signal-interpreting systems are becoming increasingly popular in medical, industrial, ecological, biotechnological and many other applications. Existing statistical and knowledge-based techniques lack robustness, accuracy and flexibility. New strategies are needed that can adapt to changing environmental conditions, signal variation, user needs and process requirements. Introducing CBR strategies into signal-interpreting systems can satisfy these requirements. CBR can be used to control the signal-processing process in all phases of a signal-interpreting system to derive information of the highest possible quality. Beyond this CBR offers different learning capabilities, for all phases of a signal-interpreting system, that satisfy different needs during the development process of a signal-interpreting system. The structure of the book is divided into a theoretical part and into an application-oriented part. Scientists and computer science experts from industry, medicine and biotechnology who like to work on the special topics of CBR for signals and images will find this work useful. Although case-based reasoning is often not a standard lecture at universities we hope we to also inspire PhD students to deal with this topic.