Jose Santamaría

Medical Image Registration Using Evolutionary Computation: An Experimental Survey

In the last few decades, image registration (IR) has been established as a very active research area in computer vision. Over the years, IRs applications cover a broad range of real-world problems including remote sensing, medical imaging, artificial vision, and computer-aided design. In particular, medical IR is a mature research field with theoretical support and two decades of practical experience. Traditionally, medical IR has been tackled by iterative approaches considering numerical optimization methods which are likely to get stuck in local optima. Recently, a large number of medical IR methods based on the use of metaheuristics such as evolutionary algorithms have been proposed providing outstanding results. The success of the latter modern search methods is related to their ability to perform an effective and efficient global search in complex solution spaces like those tackled in the IR discipline. In this contribution, we aim to develop an experimental survey of the most recognized feature-based medical IR methods considering evolutionary algorithms and other metaheuristics. To do so, the generic IR framework is first presented by providing a deep description of the involved components. Then, a large number of the latter proposals are reviewed. Finally, the most representative methods are benchmarked on two real-world medical scenarios considering two data sets of three-dimensional images with different modalities.

Forensic identification by computer-aided craniofacial superimposition: A survey

Craniofacial superimposition is a forensic process in which a photograph of a missing person is compared with a skull found to determine its identity. After one century of development, craniofacial superimposition has become an interdisciplinary research field where computer sciences have acquired a key role as a complement of forensic sciences. Moreover, the availability of new digital equipment (such as computers and 3D scanners) has resulted in a significant advance in the applicability of this forensic identification technique. The purpose of this contribution is twofold. On the one hand, we aim to clearly define the different stages involved in the computer-aided craniofacial superimposition process. Besides, we aim to clarify the role played by computers in the methods considered. In order to accomplish these objectives, an up-to-date review of the recent works is presented along with a discussion of advantages and drawbacks of the existing approaches, with an emphasis on the automatic ones. Future case studies will be easily categorized by identifying which stage is tackled and which kind of computer-aided approach is chosen to face the identification problem. Remaining challenges are indicated and some directions for future research are given.

Modeling the Skull–Face Overlay Uncertainty Using Fuzzy Sets

Craniofacial superimposition (CS) is a forensic process where photographs or video shots of a missing person are compared with the skull that is found. By projecting both photographs on top of each other (or, even better, matching a scanned 3-D skull model against the face photo/video shot), the forensic anthropologist can try to establish whether it is the same person. The whole process is influenced by inherent uncertainty, mainly because two objects of different nature (a skull and a face) are involved. In this paper, we extend our previous evolutionary-algorithm-based method to automatically superimpose the 3-D skull model and the 2-D face photo with the aim to overcome the limitations that are associated with the different sources of uncertainty, which are present in the problem. Two different approaches to handle the imprecision will be proposed: weighted and fuzzy-set-theory-based landmarks. The performance of the new proposal is analyzed, considering five skull-face overlay problem instances that correspond to three real-world cases solved by the Physical Anthropology Laboratory, University of Granada, Granada, Spain. The experimental study that is developed shows how the fuzzy-set-based approach clearly outperforms the previous crisp solution. Finally, the proposed method is validated by the comparison of its outcomes with respect to those manually achieved by the forensic experts in nine skull-face overlay problem instances.

A CHC evolutionary algorithm for 3d image registration

Image registration has been a very active research area in the computer vision community. In the last few years, there is an increasing interest on the application of Evolutionary Computation in this field and several evolutionary approaches has been proposed obtaining promising results. In this contribution we present an advanced evolutionary algorithm to solve the 3D image registration problem based on the CHC. The new proposal will be validated using two different shapes (both synthetic and MRI), considering four different transformations for each of them and comparing the results with those from ICP and the usually applied binary coded genetic algorithms.

Intensity-based image registration using scatter search

OBJECTIVE We present a novel intensity-based algorithm for medical image registration (IR). METHODS AND MATERIALS The IR problem is formulated as a continuous optimization task, and our work focuses on the development of the optimization component. Our method is designed over an advanced scatter search template, and it uses a combination of restart and dynamic boundary mechanisms integrated within a multi-resolution strategy. RESULTS The experimental validation is performed over two datasets of human brain magnetic resonance imaging. The algorithm is evaluated in both a stand-alone registration application and an atlas-based segmentation process targeted to the deep brain structures, considering a total of 16 and 18 scenarios, respectively. Five established IR techniques, both feature- and intensity-based, are considered for comparison purposes, and ground-truth data is used to quantitatively assess the quality of the results. Our approach ranked first in both studies and it is able to outperform all competitors in 12 of 16 registration scenarios and in 14 of 18 registration-based segmentation tasks. A statistical analysis confirms with high confidence (p<0.014) the accuracy and applicability of our method. CONCLUSIONS With a proper, problem-specific design, scatter search is able to provide a robust, global optimization. The accuracy and reliability of the registration process are superior to those of classic gradient-based techniques.

Automatic 3D Modeling of Skulls by Scatter Search and Heuristic Features

In this work we propose the use of heuristic features to guide an evolutionary approach for 3D range image registration in forensic anthropology. The aim of this study is assist to the forensic experts in one of their main tasks: the cranio-facial identification. This is usually done by the superimposition of the 3D model of the skull on a facial photograph of the missing person. In this paper we focus on the first stage: the automatic construction of an accurate model of the skull. Our method includes a pre-alignment stage, that uses a scatter-search based algorithm and a refinement stage. In this paper we propose a heuristic selection of the starting points used by the algorithm. Results are presented over a set of instances of real problems.

Knowledge representation for diagnosis of care problems through an expert system: Model of the auto-care deficit situations

The caregiver role strain is today an increasing problem because of the population aging; moreover, its diagnosis is highly difficult. In this article, we summarize the design of an Expert System for the diagnosis of this health problem. The Expert System Knowledge Base is composed by a set of production rules written in classic bi-valued logic and by a set of potential facts. In order to build this Knowledge Base it has been necessary to design previously a Model of the problem treatment. The Expert System Inference Engine uses Grobner Bases and Normal Form to obtain the diagnosis from the information stored in the Knowledge Base. Furthermore, a Graphic Users Interface has been implemented to make easier the access to the System by all kinds of users.

Evolutionary Intensity-based Medical Image Registration: A Review

Metaheuristics are techniques that use approximate and intuitive strategies to quickly find near-optimal solutions of complex optimization problems. A number of outstanding examples belong to evolutionary computation, the class of methods inspired to biological and evolutionary phenomena. These techniques have been extensively and successfully applied to feature-based image registration in medicine. However, with the increase in computational power during the last decade, intensity-based (or voxel-based) image registration methods have been preferred in many medical imaging applications, due to their robustness, accuracy and applicability, in cases where landmarks or other features are not available or easy to detect. While traditional numerical optimization techniques are employed to solve the registration problem, a number of contributions in the literature support the use of metaheuristics to overcome the shortcomings of classic methods. The aim of the paper is to review the state of the art in the application of evolutionary computation and other metaheuristics to intensity-based medical image registration. The study considers both well-know techniques with a large number of references in the literature as well as recent, outstanding proposals. The analysis focuses on the design of the methods to highlight common and successful practices. In addition, recommendations and open research lines in the field are provided.

Genetic algorithms for Voxel-based medical image registration

Image registration (IR) - the task of aligning different images having a common content - is a fundamental problem in computer vision. In particular, IR is one of the key steps in medical imaging, with applications ranging from computer assisted diagnosis to computer aided therapy and surgery. As IR can be formulated as an optimization problem, a large family of metaheuristics methods can be used to improve the results obtained by classic gradient-based, continuous optimization techniques. In this work, we extend our previous intensity-based image registration (IR) technique based on a real-coded genetic algorithm with a more appropriate design. The performance evaluation of an heterogeneous group of state-of-the-art IR techniques is also extended to two experimental studies on both synthetic and real-word medical IR problems. The results prove the accuracy and applicability of our new method.

Self-Adaptive Evolution Toward New Parameter Free Image Registration Methods

Image registration (IR) is a challenging topic in both the computer vision and pattern recognition fields; its main aim is to find the optimal transformation to provide the best overlay or fitting between two or more images. Usually, the success of well-known algorithms, such as iterative closest point, highly depends on several assumptions, e.g., the user should provide an initial near-optimal pose of the images to be registered. In the last decade, a new family of registration algorithms based on evolutionary principles has been contributed in order to overcome the latter drawbacks. However, their performance highly depends on carefully tuning (usually by hand) the control parameters of the algorithm, which is an error-prone and a time-consuming task. In this paper, we propose a new self-adaptive evolution model to deal with IR problems. To our knowledge, this is the first time a self-adaptive approach has been used for tuning the control parameters of evolutionary algorithms tackling computer vision tasks. Specifically, we introduce a novel design of the proposed self-adaptive approach facing pair-wise range IR problem instances, which is a challenging real-world optimization problem. In addition, several classical approaches, as well as state-of-the-art evolutionary IR methods, have been considered for numerical comparison.