The rice panicle seed setting rate is extremely important for calculating rice yield and performing genetic analysis. Unlike machine vision, X‐ray computed tomography (CT) imaging is a nondestructive technique that provides direct information on the internal and external structure of rice panicles. However, occlusion and adhesion of panicles and grains in a CT image sequence make these objects difficult to identify, which in turn hinders accurate determination of the seed setting rate of rice panicles. Therefore, this paper proposes a method based on a mask region convolutional neural network (Mask R‐CNN) for feature extraction and three‐dimensional (3‐D) recognition of CT images of rice panicles. X‐ray CT feature characterization was combined with the Mask R‐CNN algorithm to perform feature extraction and classification of a panicle and grains in each layer of the CT sequence. The Euclidean distance between adjacent layers was minimized to extract the features of a 3‐D panicle and grains. The results were used to calculate the rice panicle seed setting rate. The proposed method was experimentally verified using eight sets of different rice panicles. The results showed that the proposed method can efficiently identify and count plump grains and blighted grains to achieve an accuracy above 99% for the seed setting rate.
To develop low-cost and low-dose computed tomography (CT) scanners for developing countries, recently a parallel translational computed tomography (PTCT) is proposed, and the source and detector are translated oppositely with respect to the imaging object without a slip-ring. In this paper, we develop an analytic filtered-backprojection (FBP)-type reconstruction algorithm for two dimensional (2D) fan-beam PTCT and extend it to three dimensional (3D) cone-beam geometry in a Feldkamp-type framework. Particularly, a weighting function is constructed to deal with data redundancy for multiple translations PTCT to eliminate image artifacts. Extensive numerical simulations are performed to validate and evaluate the proposed analytic reconstruction algorithms, and the results confirm their correctness and merits.Recently, a translation-based data acquisition method has attracted an increased interest in the CT field [10]. This translational data acquisition scheme is based on a linear and translational only movement of the x-ray source, and it does not need the expensive slip-ring component. Aiming to develop low-cost and low-dose CT scanners for developing countries, Liu et al. proposed another linear, translational data acquisition scheme, namely parallel translational computed tomography (PTCT), in which an x-ray source and detector (linear array or flat panel detector) can be oppositely translated in parallel while an object is fixed between them [11]. Furthermore, an iterative algorithm based on compressive sensing (CS) [12][13][14][15][16] was developed to reconstruct the images [11]. Unfortunately, the corresponding analytic filtered-backprojection(FBP)-type reconstruction algorithms are not available yet. While the single-source scanning strategy is similar to the well-known tomosynthesis [17][18][19][20] in which projections can be acquired from a limited rotational angle (15-60 degrees), the analytic reconstruction algorithms for tomosynthesis are different from CT and cannot be directly applied to CT. Therefore, here we will develop analytic FBP-type algorithms for PTCT. Because one translation only covers a limited angle for data acquisition in practical applications, we will only consider two orthogonal translations (2T) or three symmetric translations (3T) which satisfy the exact reconstruction conditions for two dimensional (2D) fan-beam geometry. In order to deal with the redundancy in the projections acquired from multiple translations, a weight function [21-23] will be introduced in the reconstruction formulas. Regarding the special case of 2T PTCT, it basically is equivalent to the conventional linogram proposed by Herman and his collaborators [24]. Different from the proposed PTCT and FBP-type reconstruction algorithms, the linogram was developed to avoid interpolation operations [25] in the conventional Fourier transform based analytic reconstruction methods [24].The rest of this paper is organized as follows. In Section 2, we will introduce the data acquisition scheme and derive 2D fan-beam FBP-type...
Photon-counting detector based spectral computed tomography (CT) can obtain energydiscriminative attenuation map of an object in different energy channels, extending the conventional volumetric image along a spectral dimension. However, compared with the full spectrum data, the noise in a narrower energy channel is significantly increased. In order to improve image quality of spectral CT images, this paper proposes an iterative reconstruction algorithm based on the prior image constrained compressed sensing (PICCS) and dictionary learning (DL) theories, which is called PICCS-DL. The PICCS-DL utilizes the correlation of the images reconstructed from different energy channels by taking the broad spectrum image as a prior constraint, and it utilizes the sparse of the images by taking the total variation (TV) and DL as prior constraints. The alternating minimization, Split-Bregman and the steepest descent (SD) methods are used to solve the objective function. The effectiveness of the proposed method is validated with numerical simulations and preclinical applications. The results demonstrate that the proposed algorithm generally produces superior image quality, especially for noisy and sparse projection data. INDEX TERMS Spectral CT, prior image constrained compressed sensing, total variation, dictionary learning.
Inspired by the Compressed Sensing (CS) theory, it has been proved that the interior problem of computed tomography (CT) can be accurately and stably solved if a region-of-interest (ROI) is piecewise constant or polynomial, resulting in the CS-based interior tomography. The key is to minimize the total variation (TV) of the ROI under the constraint of the truncated projections. Coincidentally, the Split-Bregman (SB) method has attracted a major attention to solve the TV minimization problem for CT image reconstruction. In this paper, we apply the SB approach to reconstruct an ROI for the CS-based interior tomography assuming a piecewise constant imaging model. Furthermore, the ordered subsets (OS) technique is used to accelerate the convergence of SB algorithm, leading to a new OS-SB algorithm for interior tomography. The conventional OS simultaneous algebraic reconstruction technique (OS-SART) and soft-threshold filtering (STF) based OS-SART are also implemented as references to evaluate the performance of the proposed OS-SB algorithm for interior tomography. Both numerical simulations and clinical applications are performed and the results confirm the advantages of the proposed OS-SB method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.