Optical projection tomography (OPT) is a tool used for three-dimensional imaging of millimeter-scale biological samples. For higher image quality, new methods will need to be researched for OPT imaging systems. To make full use of the advantages of light polarization, an OPT image system with a polarization device was built, which can provide polarized projection data. The optimum polarization angle of the polarization device was acquired by experiments. At the optimum polarization angle, the high quality polarized projection data of samples were obtained, the reconstructed tomographic images got more details of samples and the influence of the stray light was eliminated. FSRCNN(Fast Super-Resolution Convolutional Neural Network)based on deep learning was applied for the SR reconstruction of tomographic images. SR tomographic images were assessed by the metrics of image quality and subjective observation. The outline and details of the samples were considerably represented in three-dimensional images reconstructed by SR tomographic images. So, polarization technology and FSRCNN can complement the performance of OPT imaging systems, and enhance imaging ability in the micron range.
Since it was first presented in 2002, the Optical Projection Tomography(OPT) imaging system has emerged as a powerful tool for the study of a biomedical specimen on the mm to cm scale. In this paper, we present a rough and precise algorithm to further improve OPT image acquisition and tomographic reconstruction. The rough and precise algorithm combines the merits of the binarization process and the maximum correlation coefficient, and can accurately correct the displacement of the rotation axis. The tomographic images corrected by the rough and precise algorithm have higher image quality in the simulation experiments and specimen experiments. The reconstructed 3D images based on tomographic images can restore the original specimens. Thereby, the rough and precise algorithm contributes to increasing acquisition speed and quality of OPT data. More work should be performed to better understand and amend the rough and precise algorithm by abundant specimen experiments.
Prostate segmentation in computed tomography (CT) images is useful for planning and guidance of the diagnostic and therapeutic procedures. However, the low soft-tissue contrast of CT images makes the manual prostate segmentation a time-consuming task with high inter-observer variation. We developed a semi-automatic, three-dimensional (3D) prostate segmentation algorithm using shape and texture analysis and have evaluated the method against manual reference segmentations. In a training data set we defined an inter-subject correspondence between surface points in the spherical coordinate system. We applied this correspondence to model the globular and smoothly curved shape of the prostate with 86, well-distributed surface points using a point distribution model that captures prostate shape variation. We also studied the local texture difference between prostate and non-prostate tissues close to the prostate surface. For segmentation, we used the learned shape and texture characteristics of the prostate in CT images and we used a set of user inputs for prostate localization. We trained our algorithm using 23 CT images and tested it on 10 images. We evaluated the results compared with those of two experts’ manual reference segmentations using different error metrics. The average measured Dice similarity coefficient (DSC) and mean absolute distance (MAD) were 88 ± 2% and 1.9 ± 0.5 mm, respectively. The averaged inter-expert difference measured on the same dataset was 91 ± 4% (DSC) and 1.3 ± 0.6 mm (MAD). With no prior intra-patient information, the proposed algorithm showed a fast, robust and accurate performance for 3D CT segmentation.
Common CT Imaging Signs of Lung Diseases (CISL) are defined as the imaging signs that frequently appear in lung CT images from patients and play important roles in the diagnosis of lung diseases. This paper proposes a new method of multiple classifier fusion to recognize the CISLs, which is based on the confusion matrices of the classifiers and the classification confidence values outputted by the classifiers. The confusion matrix reflects the historical reliability of decision-making of a classifier, while the difference between the classification confidence values for competing classes reflects the current reliability of its decision-making. The two factors are merged to obtain the weights of the classifiers’ classification confidence values for the input pattern. Then the classifiers are fused in a weighted-sum form. In our experiments of CISL recognition, we combine three types of classifiers: the Max-Min posterior Pseudo-probabilities (MMP), the Support Vector Machine (SVM) and the Bagging. Our method behaved better than not only each of the three single classifier but also the AdaBoost with SVM based weak learners. It shows that the proposed method is effective and promising.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.