Medical image segmentation using genetic algorithms

INTERACTIVE REGISTRATION OF INTRACELLULAR VOLUMES WITH RADIAL BASIS FUNCTIONS

We propose a novel approach to 3D image registration of intracellular volumes. The approach extends a standard image registration framework to the curved cell geometry. An intracellular volume is mapped onto another intracellular domain by using two pairs of point set surfaces approximating their nuclear and plasma membranes. The mapping function consists of the affine transformation, tetrahedral barycentric interpolation, and least-squares formulation of radial basis functions for extracted cell geometry features. An interactive volume registration system is also developed based on our approach. We demonstrate that our approach is capable of creating cell models containing multiple organelles from observed data of living cells.

Patient-Specific Method of Generating Parametric Maps of Patlak K(i) without Blood Sampling or Metabolite Correction: A Feasibility Study

Currently, kinetic analyses using dynamic positron emission tomography (PET) experience very limited use despite their potential for improving quantitative accuracy in several clinical and research applications. For targeted volume applications, such as radiation treatment planning, treatment monitoring, and cerebral metabolic studies, the key to implementation of these methods is the determination of an arterial input function, which can include time-consuming analysis of blood samples for metabolite correction. Targeted kinetic applications would become practical for the clinic if blood sampling and metabolite correction could be avoided. To this end, we developed a novel method (Patlak-P) of generating parametric maps that is identical to Patlak K(i) (within a global scalar multiple) but does not require the determination of the arterial input function or metabolite correction. In this initial study, we show that Patlak-P (a) mimics Patlak K(i) images in terms of visual assessment and target-to-background (TB) ratios of regions of elevated uptake, (b) has higher visual contrast and (generally) better image quality than SUV, and (c) may have an important role in improving radiotherapy planning, therapy monitoring, and neurometabolism studies.

Image Segmentation Based on Bacterial Foraging and FCM Algorithm

This paper addresses the issue of image segmentation by clustering in the domain of image processing. The clustering algorithm taken account here is the Fuzzy C-Means which is widely adopted in this field. Bacterial Foraging Optimization Algorithm is an optimal algorithm inspired by the foraging behavior of E.coli. For the purpose to reinforce the global search capability of FCM, the Bacterial Foraging Algorithm was employed to optimize the objective criterion function which is interrelated to centroids in FCM. To evaluate the validation of the composite algorithm, cluster validation indexes were used to obtain numerical results and guide the possible best solution found by BF-FCM. Several experiments were conducted on three UCI data sets. For image segmentation, BF-FCM successfully segmented 8 typical grey scale images, and most of them obtained the desired effects. All the experiment results show that BF-FCM has better performance than that of standard FCM.

A unified set of analysis tools for uterine cervix image segmentation

Segmentation is a fundamental component of many medical image-processing applications, and it has long been recognized as a challenging problem. In this paper, we report our research and development efforts on analyzing and extracting clinically meaningful regions from uterine cervix images in a large database created for the study of cervical cancer. In addition to proposing new algorithms, we also focus on developing open source tools which are in synchrony with the research objectives. These efforts have resulted in three Web-accessible tools which address three important and interrelated sub-topics in medical image segmentation, respectively: the Boundary Marking Tool (BMT), Cervigram Segmentation Tool (CST), and Multi-Observer Segmentation Evaluation System (MOSES). The BMT is for manual segmentation, typically to collect "ground truth" image regions from medical experts. The CST is for automatic segmentation, and MOSES is for segmentation evaluation. These tools are designed to be a unified set in which data can be conveniently exchanged. They have value not only for improving the reliability and accuracy of algorithms of uterine cervix image segmentation, but also promoting collaboration between biomedical experts and engineers which are crucial to medical image-processing applications. Although the CST is designed for the unique characteristics of cervigrams, the BMT and MOSES are very general and extensible, and can be easily adapted to other biomedical image collections.

Automatic segmentation of cerebrospinal fluid, white and gray matter in unenhanced computed tomography images

RATIONALE AND OBJECTIVES

Although segmentation algorithms for cerebrospinal fluid (CSF), white matter (WM), and gray matter (GM) on unenhanced computed tomographic (CT) images exist, there is no complete research in this area. To take into account poor image contrast and intensity variability on CT scans, the aim of this study was to derive and validate a novel, automatic, adaptive, and robust algorithm.

MATERIALS AND METHODS

Unenhanced CT scans of normal subjects from two different centers were used. The algorithm developed uses adaptive thresholding, connectivity, and domain knowledge and is based on heuristics on the shape of CT histogram. The slope of the intensity histogram corresponding to the three-dimensional largest connected region in a variable CSF intensity range is tracked to determine the critical intensity, which serves as an initial classifier of CSF-WM. Thresholds of CSF, WM, and GM are then optimally derived to minimize classification overlap. Multiple, null, and erroneous classifications are resolved by applying domain knowledge.

RESULTS

The ground-truth regions with the minimal partial volume effect were used to evaluate segmentation results using the statistical markers. Average sensitivity, Dice index, and specificity, respectively, for the first center were 95.7%, 97.0%, and 98.6% for CSF; 96.1%, 97.3%, and 98.8% for WM; and 95.2%, 94.3%, and 92.8% for GM. The results were consistent for the second data center.

CONCLUSIONS

The algorithm automatically identifies CSF, WM, and GM on unenhanced CT images with high accuracy, is robust to data from different scanners, does not require any parameter setting, and takes about 5 minutes in MATLAB to process a 512 × 512 × 30 scan. The algorithm has potential use in research and clinical applications.