Semantic segmentation (SS) is one of the most powerful tools to extract particular regions from medical images. Several studies succeeded to increase the segmentation accuracy of SS by combining with preprocessing. The present study proposed an extraction method of cervical intervertebral disks from videofluorography (VF), which is commonly used for the diagnosis of dysphagia, based on SS combined with 45 linear and nonlinear image filters. The combination of the image filters was optimized by the simulated annealing algorithm. In this study, five fully convolutional networks (FCNs), i.e. U-Net, feature pyramid network, LinkNet, pyramid scene parsing network and M-Net, were applied to the VF dataset of 19 patients and 39 healthy participants. When the image filters were not used, the mean F measures of the five FCNs were 0.660, 0.752, 0.803, 0.750 and 0.768, respectively, whereas when used, they were increased to 0.747, 0.794, 0.813, 0.765 and 0.799, respectively. This experimental results demonstrated that the optimal combinations of image filters were effective to improve the segmentation accuracy of FCNs.

We propose a new approach using Deep Convolution Neural Network (DCNN) to correct for image degradations due to statistical noise and photon attenuation in Emission Tomography (ET). The proposed approach first reconstructs an image by the standard Filtered Backprojection (FBP) without correcting for the degradations followed by inputting the degraded image into DCNN to obtain an improved image. We consider two different scenarios. The first scenario inputs an ET image only into DCNN, whereas the second scenario inputs a pair of degraded ET image and CT/MRI image to improve accuracy of the correction. The simulation result demonstrates that both the scenarios can improve image quality compared to the FBP without correction, and, in particular, accuracy of the second scenario is comparable to that of the standard iterative reconstruction such as Maximum Likelihood Expectation Maximization (MLEM) and Ordered-Subsets EM (OSEM) methods. The proposed method is able to output an image in very short time, because it does not rely on iterative computations.

We present a novel image boundary extension and mean value extension (MVE) for directional lapped transforms, particularly cosine-sine modulated lapped transforms (CSMLTs). Lapped transforms are usually used with an extension technique, such as periodic extension (PE) or symmetric extension (SE), for nonexpansive convolution at signal boundaries. When directional textures (oblique lines and curves) appear at the 2D signal (image) boundaries, both PE and SE produce directional discontinuities, which degrade the sparsity of the transformed coefficients, especially in the case of directional lapped transforms. MVE reduces the discontinuities for directional textures better than PE or SE do; it thus improves the efficiency of the sparse representation based on directional lapped transforms. Moreover, to reduce computational costs compared with those of directional lapped transforms, we introduce new directional block transforms called cosine-sine modulated block transforms. These new transforms are derived from a minimum tile processing (tiling) of M-band CSMLTs with 2M filter lengths and nonexpansive convolutions. The resulting directional block transforms, particularly in the case of the MVE, have richer directional selectivity and have better performance compared with a discrete Fourier transform as shown in experiments.

This paper redefines a block-lifting structure of M-channel (M ∈ N, M ≥ 2) filter banks and proposes an efficient reversible nonexpansive convolution at the boundaries for lossy-to-lossless image coding. The previous studies left two problems. One is that the conventional lifting-based filter banks (FBs) are restricted to having equal analysis/synthesis filter lengths. We derive block-lifting-based FBs (BLFBs) with not only equal analysis/synthesis filter lengths but also the longer synthesis filter lengths than those of the analysis banks. The other problem is that the conventional lifting-based FBs without the linear-phase property, such as BLFBs, cannot implement the conventional smooth nonexpansive convolution at the boundaries because of the rounding error in each lifting. We solve the boundary problem by using an efficient reversible nonexpansive convolution derived from a nonexpansive convolution for nonlinear-phase FBs with paraunitariness. We show that the redefined BLFBs with the efficient reversible nonexpansive convolution perform well at lossy-to-lossless image coding.

This study presents a pseudo reversible symmetric extension (P-RevSE) that solves the signal boundary problem of lifting-based nonlinear-phase paraunitary filter banks (L-NLPPUFBs), which have high compression rates thanks to their not having a constraint on the linear-phase property unlike the existing transforms used in image coding standards. The conventional L-NLPPUFBs with a periodic extension (PE) yield annoying artifacts at the signal boundaries. However, the P-RevSE is implemented smoothly at the signal boundaries by using a nonexpansive convolution of a symmetric extension (SE) and determinant control for the lifting factorization. Although the determinant control causes a pseudo SE, not a true SE, the resulting L-NLPPUFB with P-RevSE outperforms not only the L-NLPPUFB with PE but also the current transform used in JPEG XR.

We extend an original lapped transform (LT) and use block-lifting factorization to get an extended block-lifting-based LT (XBL-LT). The block-lifting structure maps integer input signals to integer output signals and results in a reversible transform that reduces rounding errors by merging many rounding operations. Although other such block-lifting-based LTs (BL-LTs) have been proposed, they are forcibly constrained by the use of discrete cosine transform (DCT) matrices. In contrast, XBL-LT is DCT-unconstrained and hence also embodies the DCT-constrained form. Furthermore, it has fewer rounding operations by merging the scaling factor with block-lifting coefficients. The both DCT-constrained and unconstrained XBL-LTs perform well at lossy-to-lossless image coding which has scalability from lossless data to lossy data.

We propose a 2D non-separable block-lifting structure (2D-NSBL) that is easily formulated from the 1D separable block-lifting structure (1D-SBL) and 2D non-separable lifting structure (2D-NSL). The 2D-NSBL can be regarded as an extension of the 2D-NSL, because a two-channel 2D-NSBL is completely equivalent to a 2D-NSL. We apply the 2D-NSBL to M-channel ( M=2(n), n ∈ N) perfect reconstruction filter banks (PRFBs). The 2D-NSBL-based PRFBs outperform 1D-SBL-based PRFBs at lossy-to-lossless coding, whose image quality is scalable from lossless data to high compressed lossy data, because their rounding errors are reduced by merging many rounding operations.

This paper presents a realization of integer fast lapped biorthogonal transform (FLBT) via applications of discrete cosine transform (DCT) matrices and dyadic-valued factors for lifting coefficient blocks. It is obtained by using the block-lifting factorization as our previous work and easy matrix manipulations. The proposed FLBT has higher coding performance and fewer rounding operations than the conventional methods. The practicality of the proposed FLBT is validated through lossy-to-lossless image compression (coding) simulation which unifies lossy and lossless image coding.

A soft contact-lens (SCL) biosensor for in-situ tear sugar monitoring was fabricated and tested. In contrast to the previously reported continuous glucose monitoring (CGM) devices, we focused on the relationship between blood glucose and tear glucose. The SCL biosensor was constructed by applying microelectromechanical systems (MEMS) techniques to functional polymers. The sensor has film electrodes on the surface of a rounded surface of polydimethyl siloxane (PDMS) contact-lens and glucose oxidase (GOD) was immobilized on the sensing region of the electrodes. Sufficiently adhesive and flexible electrodes were formed on the polymer device (PDMS and 2-methacryloyloxyethyl phosphorylcholine (MPC) polymer). In the in-vitro characterization, the SCL-biosensor showed excellent relationship between the output current and glucose concentration from 0.03 to 10.0 mmol/L, which included the reported tear glucose concentrations (0.14 mM) of humans. Based on the result, in-situ tear glucose monitoring with the SCL-biosensor was carried out. The output current of the SCL-biosensor was sufficiently stable and reflected the tear glucose levels. The static glucose level in the basal tear of a rabbit was measured and estimated to 0.13 mmol/L. Since the biosensor was also possible to be sotored for more than 50 days, daily disposable application was expected with the SCL biosensor.

We develop an approximate fan-beam algorithm to reconstruct an object with time-dependent nonrigid transformation such as the heart. The method is in the form of derivative backprojection filtering with compensation of affine transformations on a local basis. Computer simulations showed the proposed method significantly reduces image artifact due to nonrigid motion. Therefore, with very little motion artifact, the proposed method allowed us to reconstruct images from projections over about one motion cycle, resulting in reduced image noise level down to 40% of the current level.

This paper discusses image reconstruction with a tilted gantry in multislice computed tomography (CT) with helical (spiral) data acquisition. The reconstruction problem with gantry tilt is shown to be transformable into the problem of reconstructing a virtual object from multislice CT data with no gantry tilt, for which various algorithms exist in the literature. The virtual object is related to the real object by a simple affine transformation that transforms the tilted helical trajectory of the X-ray source into a nontilted helix, and the real object can be computed from the virtual object using one-dimensional interpolation. However, the interpolation may be skipped since the reconstruction of the virtual object on a Cartesian grid provides directly nondistorted images of the real object on slices parallel to the tilted plane of the gantry. The theory is first presented without any specification of the detector geometry, then applied to the curved detector geometry of third-generation CT scanners with the use of Katsevich's formula for example. Results from computer-simulated data of the FORBILD thorax phantom are given in support of the theory.

Exact reconstruction from axially truncated cone-beam projections acquired with a helical vertex path is a challenging problem for which solutions are currently under investigation by some researchers. This paper deals with a difficult class of this problem called the long-object problem. Its purpose is to reconstruct a central region of interest (ROI) of a long object when the helical path extends only a little bit above and below the ROI. By extending the authors' recent approach based on the triangular decomposition of the Grangeat formula, we derive quasi-exact reconstruction algorithms whose overall structure is of filtered backprojection (FBP) style. Unlike the previous similar approaches to the long-object problem, the proposed FBP algorithms do not require additional two circular scans at the ends of the helical path. Furthermore, the algorithms require a significantly smaller detector area and achieve improved image quality even for a large pitch compared with the approximate Feldkamp algorithms. One drawback of the proposed algorithms is the computational time, which is much longer than for the Feldkamp algorithms. We show some simulation results to demonstrate the performances of the proposed algorithms.

B.D. Smith (ibid., vol.MI-4, p.15-25, 1985; Opt. Eng., vol.29, p.524-34, 1990) and P. Grangeat (These de doctorat, 1987; Lecture Notes in Mathematics 1497, p.66-97, 1991) derived a cone-beam inversion formula that can be applied when a nonplanar orbit satisfying the completeness condition is used. Although Grangeat's inversion formula is mathematically different from Smith's one, they have similar overall structures to each other. The contribution of the present paper is two-fold. First, based on the derivation of Smith, the authors point out that Grangeat's inversion formula and Smith's one can be conveniently described using a single formula (the Smith-Grangeat inversion formula) that is in the form of space-variant filtering followed by cone-beam back projection. Furthermore, the resulting formula is reformulated for data acquisition systems with a planar detector to obtain a new reconstruction algorithm. Second, the authors make two significant modifications to the new algorithm to reduce artifacts and numerical errors encountered in direct implementation of the new algorithm. As for exactness of the new algorithm, the following fact can be stated. The algorithm based on Grangeat's intermediate function is exact for any complete orbit, whereas that based on Smith's intermediate function should be considered as an approximate inverse excepting the special case where almost every plane in 3D space meets the orbit. The validity of the new algorithm is demonstrated by simulation studies.

Deals with the tomographic image reconstruction problem from hollow projections. This kind of problem is mainly caused by an X-ray opaque obstruction contained in the object to be imaged. Based on the Cormack's (1964) inversion formula for the image reconstruction, the mathematical capability of image reconstruction from hollow projections is discussed and a new algorithm for the completion of hollow projections, which utilizes the regularized numerical evaluation of inverse CHT (Circular Harmonic Transform), is presented. In the numerical experiments, the performance of the proposed algorithm is demonstrated and significant improvement of the reconstructed image quality is obtained.>

In the CT image reconstruction, the authors investigate the obtainable information content about object to be imaged from its finite number of projections and the structure of the reconstruction error due to the insufficient number of projections. They can explicitly demonstrate that the mechanism which limits the resolution of CT image is angular aliasing. Based on this investigation, a new CT image reconstruction algorithm is developed, which produces high quality artifactless images even in the case of a small number of projections. The image quality reconstructed by the proposed algorithm is superior to that by the conventional filtered backprojection (FBP) algorithm.>

In this paper, we deal with the problem on tomographic image reconstruction from limited view angle projection data. Based on the Helgason-Ludwig consistency condition, a new procedure for completion of incomplete projection data is introduced to improve the reconstructed image quality. Using regularization method the robust algorithm to the presence of noise is presented. The performance of new algorithm was confirmed in the numerical simulation. The reconstructed images were quantitatively improved by this procedure with realistic amount of computation.