This paper presents a method to analyze volumetrically evolutions of pulmonary nodules for discrimination between malignant and benign nodules. Our method consists of four steps; (1) The 3-D rigid registration of the two successive 3-D thoracic CT images, (2) the 3-D affine registration of the two successive region-of-interest (ROI) images, (3) non-rigid registration between local volumetric ROIs, and (4) analysis of the local displacement field between successive temporal images. In the preliminary study, the method was applied to the successive 3-D thoracic images of two pulmonary nodules including a metastasis malignant nodule and a inflammatory benign nodule to quantify evolutions of the pulmonary nodules and their surrounding structures. The time intervals between successive 3-D thoracic images for the benign and malignant cases were 150 and 30 days, respectively. From the display of the displacement fields and the contrasted image by the vector field operator based on the Jacobian, it was observed that the benign case reduced in the volume and the surrounding structure was involved into the nodule. It was also observed that the malignant case expanded in the volume. These experimental results indicate that our method is a promising tool to quantify how the lesions evolve their volume and surrounding structures.

In this paper, we present some contributions to improve a previous work's approach presented for the segmentation of magnetic resonance images of the human brain, based on the unsupervised Hopfield neural network. We formulate the segmentation problem as a minimization of an energy function constructed with two terms, the cost-term as a sum of errors' squares, and the second term is a temporary noise added to the cost-term as an excitation to the network to escape from certain local minimums and be more close to the global minimum. Also, to ensure the convergence of the network and its utility in clinic with useful results, the minimization is achieved with a step function permitting the network to reach its stability corresponding to a local minimum close to the global minimum in a prespecified period of time. We present here our approach segmentations results of a patient data diagnosed with a metastatic tumor in the brain, and we compare them to those obtained based on, previous works using Hopfield neural networks, Boltzmann machine and the conventional ISODATA clustering technique.

In this paper, we present a computer-aided diagnosis (CAD) system to automatically detect lung cancer candidates at an early stage using a present and a past helical CT screening. We have developed a slice matching algorithm that can automatically match the slice images of a past CT scan to those of a present CT scan in order to detect changes in the lung fields over time. The slice matching algorithm consists of two main process: the process of extraction of the lungs, heart, and descending aorta and the process of matching slices of the present and past CT images using the information of the lungs, heart, and descending aorta. To evaluate the performance of this algorithm, we applied it to 50 subjects (total of 150 scans) screened between 1993 and 1998. From these scans, we selected 100 pairs for evaluation (each pair consisted of scans for the same subject). The algorithm correctly matched 88 out of the 100 pairs. The slice images for the present and past CT scans are displayed in parallel on the CRT monitor. Feature measurements of the suspicious regions are shown on the relevant images to facilitate identification of changes in size, shape, and intensity. The experimental results indicate that the CAD system can be effectively used in clinical practice to increase the speed and accuracy of routine diagnosis.

The aim of this study was to quantify the effects of inhomogeneities on magnetocardiography (MCG) forward solutions. It can serve to guide the selection of inhomogeneities to include in any geometric model used to compute magnetocardiographics fields. A numerical model of a human torso was used which construction included geometry for major anatomical structures such as subcutaneous fat, skeletal muscle, lungs, major arteries and veins, and the bones. Simulations were done with a single current dipole placed at different sites of heart. The boundary element method (BEM) was utilized for numerical treatment of magnetic field calculations. Comparisons of the effects of different conductivity on MCG forward solution followed one of two basic schemes: 1) consider the difference between the magnetic fields of the homogeneous torso model and the same model with one inhomogeneity of a single organ or tissue added; 2) consider the difference between the magnetic fields of the full inhomogeneous model and the same model with one inhomogeneity of individual organ or tissue removed. When single inhomogeneities were added to an otherwise homogeneous model, the skeletal muscle, the right lung, the both lungs and the left lung had larger average effects (15.9, 15.1, 14.9, 14.4% relative error (RE), respectively) than the other inhomogeneities tested. When single inhomogeneities were removed from an otherwise full inhomogeneneous model, the both lungs, the left lung, and the skeletal muscle and the right lung had larger effects (17.3, 14.9, 14.3, 14.2% relative error (RE) respectively) than other inhomogeneities tested. The results of this study suggested that accurate representation of tissue inhomogeneity has a significant effect on the accuracy of the MCG forward solution. Our results showed that the inclusion of the boundaries also had effects on the topology of the magnetic fields and on the MCG inverse solution accuracy.

In our current work, we attempt to make an automatic diagnostic system of lung cancer based on the analysis of the sputum color images. In order to form general diagnostic rules, we have collected a database with thousands of sputum color images from normal and abnormal subjects. As a first step, in this paper, we present a segmentation method of sputum color images prepared by the Papanicalaou standard staining method. The segmentation is performed based on an energy function minimization using an unsupervised Hopfield neural network (HNN). This HNN have been used for the segmentation of magnetic resonance images (MRI). The results have been acceptable, however the method have some limitations due to the stuck of the network in an early local minimum because the energy landscape in general has more than one local minimum due to the nonconvex nature of the energy surface. To overcome this problem, we have suggested in our previous work some contributions. Similarly to the MRI images, the color images can be considered as multidimensional data as each pixel is represented by its three components in the RGB image planes. To the input of HNN we have applied the RGB components of several sputum images. However, the extreme variations in the gray-levels of the images and the relative contrast among nuclei due to unavoidable staining variations among individual cells, the cytoplasm folds and the debris cells, make the segmentation less accurate and impossible its automatization as the number of regions is difficult to be estimated in advance. On the other hand, the most important objective in processing cell clusters is the detection and accurate segmentation of the nuclei, because most quantitative procedures are based on measurements of nuclear features. For this reason, based on our collected database of sputum color images, we found an algorithm for NonSputum cell masking. Once these masked images are determined, they are given, with some of the RGB components of the raw image, to the input of HNN to make a crisp segmentation by assigning each pixel to label such as Background, Cytoplasm, and Nucleus. The proposed technique has yielded correct segmentation of complex scene of sputum prepared by ordinary manual staining method in most of the tested images selected from our database containing thousands of sputum color images.

The direct two-dimensional Fourier transform method enables a fast image reconstruction. The key problem of this method is in the interpolation from polar to Cartesian samples. In this paper we present a more efficient interpolation method than the previous one without decreasing the accuracy of the reconstructed image.

Accurately segmenting and quantifying pulmonary nodule structure is a key issue in three-dimensional (3-D) computer-aided diagnosis (CAD) schemes. This paper presents a nodule segmentation method from 3-D thoracic CT images based on a deformable surface model. In this method, first, a statistical analysis of the observed intensity is performed to measure differences between the nodule and other regions. Based on this analysis, the boundary and region information are represented by boundary and region likelihood, respectively. Second, an initial surface in the nodule is manually set. Finally, the deformable surface model moves the initial surface so that the surface provides high boundary likelihood and high posterior segmentation probability with respect to the nodule. For the purpose, the deformable surface model integrates the boundary and region information. This integration makes it possible to cope with inappropriate position or size of an initial surface in the nodule. Using the practical 3-D thoracic CT images, we demonstrate the effectiveness of the proposed method.