Medical image analysis of 3D CT images based on extension of Haralick texture features.

PURPOSE: A new approach to the segmentation of 3D CT images is proposed in an attempt to provide texture-based segmentation of organs or disease diagnosis. 3D extension of Haralick texture features was studied calculating co-occurrences of all voxels in a small cubic region around the voxel. RESULTS: For verification, the proposed method was tested on a set of abdominal 3D volumes of patients. Statistically, the improvement in segmentation was significant for most of the organs considered herein. CONCLUSIONS: The proposed method has potential application in medical image segmentation, including diagnosis of diseases.

Future CAD in multi-dimensional medical images--project on multi-organ, multi-disease CAD system.

A large research project on the subject of computer-aided diagnosis (CAD) entitled "Intelligent Assistance in Diagnosis of Multi-dimensional Medical Images" was initiated in Japan in 2003. The objective of this research project is to develop a multi-organ, multi-disease CAD system that incorporates anatomical knowledge of the human body and diagnostic knowledge of various types of diseases. The present paper provides an overview of the project and clarifies the trend of future CAD technologies in Japan.

A novel registration method for interval change detection between two chest X-ray images with different rotation angles.

RATIONALE AND OBJECTIVES: Registration is an important process to detect interval changes between two chest x-ray images. However, the conventional registration methods suffer from misregistration because of the difference in rotation angles of human body around an axis parallel to the x-ray films, such as anteroposterior inclination. Such difference causes permutation of the shadows between the two images, which makes registration difficult. This article proposes a novel registration method in cases where two chest x-ray images have different rotation angles. MATERIALS AND METHODS: Twelve x-ray images taken from a chest phantom and four chest photofluorograms of two patients were used to evaluate the performance. First, the proposed algorithm estimates the rotation angles of the body from the pair of two x-ray images based on the function describing the relationship between a point in the current image and that in the previous image, which is derived from a three-dimensional rotational model of the body. Then it aligns two images according to the function. RESULTS: From the results of estimating rotation angles, it was found that proposed method can estimate the angles with an error of less than 1 degrees. Then two physicians evaluated the subtraction images and confirmed that this approach makes it possible to detect the interval changes accurately even if there are permutations of shadows in the x-ray image. CONCLUSIONS: The proposed method is superior to the conventional one when two chest x-ray images have different rotation angles.

Statistical shape model of a liver for autopsy imaging.

PURPOSE: Modeling the postmortem liver for autopsy imaging is a challenging problem owing to the variation in organ deformation found in cadavers and limited availability of postmortem liver CT scans. An algorithm was developed to construct a statistical shape model (SSM) for the adult postmortem liver in autopsy imaging. METHODS: First, we investigated the relationship between SSMs obtained from in vivo liver CT scans and those from postmortem cases. Liver shapes were embedded in level set functions and statistically modeled using a spatially weighted principal components analysis. The performance of the SSMs was evaluated in terms of generalization and specificity. Several algorithms for the transformation from in vivo livers to postmortem livers were proposed to enhance the performance of an SSM for a postmortem liver, followed by a comparative study on SSMs. Specifically, five SSMs for a postmortem liver were constructed and evaluated using 32 postmortem liver labels, and postmortem liver labels synthesized from 144 in vivo liver labels were constructed using the proposed transformation algorithms. We also compared the proposed SSMs with three conventional SSMs trained from postmortem liver labels and/or in vivo liver labels. RESULTS: The investigation showed that the performance of an SSM constructed using in vivo liver labels suffered when describing postmortem liver shapes. Two of the five proposed SSMs trained using synthesized postmortem livers showed the best performance with no significant differences between them, and they statistically outperformed all conventional SSMs tested. CONCLUSIONS: The performance of conventional SSMs can be improved by using both postmortem liver shape labels and artificial shape labels synthesized from in vivo liver shape labels.

Multi-shape graph cuts with neighbor prior constraints and its application to lung segmentation from a chest CT volume.

This paper presents a novel graph cut algorithm that can take into account multi-shape constraints with neighbor prior constraints, and reports on a lung segmentation process from a three-dimensional computed tomography (CT) image based on this algorithm. The major contribution of this paper is the proposal of a novel segmentation algorithm that improves lung segmentation for cases in which the lung has a unique shape and pathologies such as pleural effusion by incorporating multiple shapes and prior information on neighbor structures in a graph cut framework. We demonstrate the efficacy of the proposed algorithm by comparing it to conventional one using a synthetic image and clinical thoracic CT volumes.

Automated pancreas segmentation from three-dimensional contrast-enhanced computed tomography.

PURPOSE: We propose an automated pancreas segmentation algorithm from contrast-enhanced multiphase computed tomography (CT) and verify its effectiveness in segmentation. METHODS: The algorithm is characterized by three unique ideas. First, a two-stage segmentation strategy with spatial standardization of pancreas was employed to reduce variations in the pancreas shape and location. Second, patient- specific probabilistic atlas guided segmentation was developed to cope with the remaining variability in shape and location. Finally, a classifier ensemble was incorporated to refine the rough segmentation results. RESULTS: The effectiveness of the proposed algorithm was validated with 20 unknown CT volumes, as well as three on-site CT volumes distributed in a competition of pancreas segmentation algorithms. The experimental results indicated that the segmentation performance was enhanced by the proposed algorithm, and the Jaccard index between an extracted pancreas and a true one was 57.9%. CONCLUSIONS: This study verified the effectiveness of two-stage segmentation with spatial standardization of pancreas in delineating the pancreas region, patient-specific probabilistic atlas guided segmentation in reducing false negatives, and a classifier ensemble in boosting segmentation performance.

A pilot study of architectural distortion detection in mammograms based on characteristics of line shadows.

OBJECTIVE: We present herein a novel algorithm for architectural distortion detection that utilizes the point convergence index with the likelihood of lines (e.g., spiculations) relating to architectural distortion. MATERIALS AND METHODS: Validation was performed using 25 computed radiography (CR) mammograms, each of which has an architectural distortion with radiating spiculations. The proposed method comprises five steps. First, the lines were extracted on mammograms, such as spiculations of architectural distortion as well as lines in the mammary gland. Second, the likelihood of spiculation for each extracted line was calculated. In the third step, point convergence index weighted by this likelihood was evaluated at each pixel to enhance distortion only. Fourth, local maxima of the index were extracted as candidates for the distortion, then classified based on nine features in the last step. RESULTS: Point convergence index without the proposed likelihood generated 84.48/image false-positives (FPs) on average. Conversely, the proposed index succeeded in decreasing this number to 12.48/image on average when sensitivity was 100%. After the classification step, number of FPs was reduced to 0.80/image with 80.0% sensitivity. CONCLUSION: Combination of the likelihood of lines with point convergence index is effective in extracting architectural distortion with radiating spiculations.

Comparison and evaluation of methods for liver segmentation from CT datasets.

This paper presents a comparison study between 10 automatic and six interactive methods for liver segmentation from contrast-enhanced CT images. It is based on results from the "MICCAI 2007 Grand Challenge" workshop, where 16 teams evaluated their algorithms on a common database. A collection of 20 clinical images with reference segmentations was provided to train and tune algorithms in advance. Participants were also allowed to use additional proprietary training data for that purpose. All teams then had to apply their methods to 10 test datasets and submit the obtained results. Employed algorithms include statistical shape models, atlas registration, level-sets, graph-cuts and rule-based systems. All results were compared to reference segmentations five error measures that highlight different aspects of segmentation accuracy. All measures were combined according to a specific scoring system relating the obtained values to human expert variability. In general, interactive methods reached higher average scores than automatic approaches and featured a better consistency of segmentation quality. However, the best automatic methods (mainly based on statistical shape models with some additional free deformation) could compete well on the majority of test images. The study provides an insight in performance of different segmentation approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.