Current Reconstruction Algorithms Research Articles

3D Reconstruction of Laparoscope Images With Contrastive Learning Methods

The use of laparoscopic images and videos to reconstruct abdominal tissue structure overcomes the visual limitations of human eyes and provides great convenience for the detection and diagnosis of medical diseases. The method described in this paper is based on contrast learning and ORB-SLAM design. The contributions of this study are as follows. (i) A data preprocessing thread is introduced, which includes data augmentation and input frame evaluation. (ii) Encoding global information to avoid semantic information loss and eliminate mismatch by designing an improved U-NET network. (iii) The improved U-NET network was used to introduce a dual-branched Siamese network and GPU-accelerated intensive reconstruction thread. The dual-branched Siamese network structure was used to compute the depth information of the feature points and optical flow information in parallel, and the dense depth estimation was obtained without interrupting the original sparse reconstruction. (iv) An experimental system was established to conduct three-dimensional reconstruction tests on laparoscopic/endoscope /UBE videos of 186 patients. To effectively provide more accurate feature detection and matching support for the application of combat scenes, the influence of lens distortion was considered. Compared with the current mainstream three-dimension reconstruction and deep learning algorithms, the practicability and superiority of laparoscopic three-dimension reconstruction based on contrastive learning are demonstrated in clinical scenarios such as surgical navigation, auxiliary diagnosis, and surgical simulation.

Use of Deep Learning to Improve the Computational Complexity of Reconstruction Algorithms in High Energy Physics

The optimization of reconstruction algorithms has become a key aspect in the field of experimental particle physics. Since technology has allowed gradually increasing the complexity of the measurements, the amount of data taken that needs to be interpreted has grown as well. This is the case with the LHCb experiment at CERN, where a major upgrade currently undergoing will considerably increase the data processing rate. This has presented the need to search for specific reconstruction techniques that aim to accelerate one of the most time consuming reconstruction algorithms in LHCb, the electromagnetic calorimeter clustering. Together with the use of deep learning techniques and the understanding of the current reconstruction algorithm, we propose a method that decomposes the reconstruction process into small parts that can be formulated as a cellular automaton. This approach is shown to benefit the generalized learning of small convolutional neural network architectures and also simplify the training dataset. Final results applied to a complete LHCb simulation reconstruction are compatible in terms of efficiency, and execute in nearly constant time with independence on the complexity of the data.

Direction reconstruction using a CNN for GeV-scale neutrinos in IceCube

The IceCube Neutrino Observatory is designed to observe neutrinos interacting deep within the South Pole ice sheet. It consists of 5160 digital optical modules, which are arrayed over a cubic kilometer from 1450 m to 2450 m depth. At the lower center of the array is the DeepCore subdetector. It has a denser configuration which lowers the observable energy threshold to about 10 GeV and creates the opportunity to study neutrino oscillations with low energy atmospheric neutrinos. A precise reconstruction of neutrino direction is critical in the measurements of oscillation parameters. In this contribution, I will discuss a method to reconstruct the zenith angle of 10-GeV scale events in IceCube using a convolutional neural network and compare the result to that of the current likelihood-based reconstruction algorithm.

A novel phantom with dia- and paramagnetic substructure for quantitative susceptibility mapping and relaxometry.

A phantom is presented in this study that allows for an experimental evaluation of QSM reconstruction algorithms. The phantom contains susceptibility producing particles with dia- and paramagnetic properties embedded in an MRI visible medium and is suitable to assess the performance of algorithms that attempt to separate isotropic dia- and paramagnetic susceptibility at the sub-voxel level. The phantom was built from calcium carbonate (diamagnetic) and tungsten carbide particles (paramagnetic) embedded in gelatin and surrounded by agarose gel. Different mass fractions and mixing ratios of both susceptibility sources were used. Gradient echo data were acquired at 1.5T, 3T and 7T. Susceptibility maps were calculated using the MEDI toolbox and relaxation rates ΔR2∗ were determined using exponential fitting. Relaxation rates as well as susceptibility values generally coincide with the theoretical values for particles fulfilling the assumptions of the the static dephasing regime with stronger deviations for relaxation rates at higher field strength and for high susceptibility values. MRI raw data are available for free academic use as supplementary material. In this study, a susceptibility phantom is presented that might find its application in the development and quantitative validation of current and future QSM reconstruction algorithms which aim to separate the influence of isotropic dia- and paramagnetic substructure in quantitative susceptibility mapping.

Deep learning\u2013based reconstruction may improve non-contrast cerebral CT imaging compared to other current reconstruction algorithms

ObjectivesTo evaluate image quality and reconstruction times of a commercial deep learning reconstruction algorithm (DLR) compared to hybrid-iterative reconstruction (Hybrid-IR) and model-based iterative reconstruction (MBIR) algorithms for cerebral non-contrast CT (NCCT).MethodsCerebral NCCT acquisitions of 50 consecutive patients were reconstructed using DLR, Hybrid-IR and MBIR with a clinical CT system. Image quality, in terms of six subjective characteristics (noise, sharpness, grey-white matter differentiation, artefacts, natural appearance and overall image quality), was scored by five observers. As objective metrics of image quality, the noise magnitude and signal-difference-to-noise ratio (SDNR) of the grey and white matter were calculated. Mean values for the image quality characteristics scored by the observers were estimated using a general linear model to account for multiple readers. The estimated means for the reconstruction methods were pairwise compared. Calculated measures were compared using paired t tests.ResultsFor all image quality characteristics, DLR images were scored significantly higher than MBIR images. Compared to Hybrid-IR, perceived noise and grey-white matter differentiation were better with DLR, while no difference was detected for other image quality characteristics. Noise magnitude was lower for DLR compared to Hybrid-IR and MBIR (5.6, 6.4 and 6.2, respectively) and SDNR higher (2.4, 1.9 and 2.0, respectively). Reconstruction times were 27 s, 44 s and 176 s for Hybrid-IR, DLR and MBIR respectively.ConclusionsWith a slight increase in reconstruction time, DLR results in lower noise and improved tissue differentiation compared to Hybrid-IR. Image quality of MBIR is significantly lower compared to DLR with much longer reconstruction times.Key Points• Deep learning reconstruction of cerebral non-contrast CT results in lower noise and improved tissue differentiation compared to hybrid-iterative reconstruction.• Deep learning reconstruction of cerebral non-contrast CT results in better image quality in all aspects evaluated compared to model-based iterative reconstruction.• Deep learning reconstruction only needs a slight increase in reconstruction time compared to hybrid-iterative reconstruction, while model-based iterative reconstruction requires considerably longer processing time.

Compressed Sensing-Based Simultaneous Recovery of Magnitude and Phase MR Images via Dual Trigonometric Sparsity

Complex-valued Magnetic Resonance Imaging (MRI) is widely used in clinical diagnosis. The magnitude images are mainly used for structure visualization, and the phase images reveal tissue properties, such as magnetic susceptibility and fluid flow information. While MRI is slow, compressed sensing (CS) can be used to reconstruct the accelerated acquisitions. Current CS-based MRI reconstruction algorithms mostly focus on magnitude image recovery, with less attention to the recovery of phase images. In this paper, we propose a novel CS algorithm to simultaneously recover the magnitude and phase MR images based on the sparsity of the trigonometric function. The CS method requires a sparse representation of the original images, and it is observed the trigonometric functions of phase images in the Wavelet domain promote sparsity. Therefore, rather than transforming the phase images directly into the Wavelet domain, we calculate the sine and cosine of the phase images whose Wavelet transforms are set as the L1-norm regularization term. The combination of the dual trigonometric functions captures a unique, faithful four-quadrant phase information, which also improves the reconstructed magnitude images through an alternating optimization procedure. Reconstructions of simulated images and in vivo images are studied, and both show the superiority of the proposed method over compared phase recovery algorithms.

Phase Current Reconstruction With Dual-Sensor for Switched Reluctance Motor Drive System

Due to the rugged construction, high starting torque, wide speed range, inherent fault-tolerance and high operating efficiency, switched reluctance motors (SRMs) have been used in many fields such as household appliances, electric vehicles and industrial drives. At low and medium speeds, the current chopping control (CCC) are usually used for SRMs. The current sensors must be connected in series with each phase winding for detecting the phase current, and the number of sensors is usually equal to the number of motor phases. In order to reduce the number of current sensors and the cost of the drive system, this paper propose a general phase current reconstruction method for SRM drive system with two current sensors. Firstly, the excitation, freewheeling and demagnetization circuits of the asymmetric half-bridge power converter are separated into two different paths. The sensors placement method, winding connection method and calculation formula of each phase current are introduced in detail. Then the influence of the turn-off angles on the overlap interval of each phase current is analyzed, and the proposed reconstruction method is further extended to multi-phase SRM. This method can simplify the current decoupling process and is easy to implement without changing the asymmetric half-bridge topology and operating states. Finally, the feasibility of the proposed phase current reconstruction algorithm is verified by simulation and experiment.

Design and Modeling of a Two-Winding Rogowski Coil Sensor for Measuring Three-Phase Currents of a Motor Fed Through a Three-Core Cable

In this article, three-phase motor currents pass through a three-core cable are measured using a two-winding Rogowski coil. The two-winding Rogowski coil is externally fitted around the three-core cable without the need for removing its insulation layers. This results in reducing the measurement complexity. Two windings are fitted around a circular non-magnetic core considering 120 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</sup> between their center points. The EMFs induced in each winding due to magnetic flux linkage between windings and cable cores are used to reconstruct the three-phase motor currents through the cable cores. In order to reconstruct cable currents, a current reconstruction algorithm is developed. Sensor design and the developed current reconstruction algorithm are theoretically and experimentally validated. Theoretical validation is carried out through Power Simulation Program (PSIM). Regarding the theoretical validation, a three-phase motor fed from a three-phase source is simulated. Motor feeding is carried out using a cable having three cores. The proposed Rogowski coil is simulated and the currents through the cable are theoretically reconstructed considering different operating conditions. Also, experimental validation is carried out considering the measurements of three-phase currents through the cable feeding a 15 HP, three-phase induction motor from a three-phase source. A designed two- winding Rogowski coil is used for sensing the measured currents and a Digital Signal Processor (DSP) is used for implementing the adopted current reconstruction algorithm. Finally, efficacy of the proposed two-winding Rogowski sensor as well as the developed current reconstruction algorithm is proved through the obtained results.

Line Scanning Thermography Reconstruction Algorithm for Defects Inspection With Novel Velocity Estimation and Image Registration

Line scanning thermography (LST) is a fast non-destructive inspection (NDI) method for large-scale components. However, the current reconstruction algorithms for LST require the match between the frame rate and the scanning velocity. Moreover, these algorithms bring in spatial distortions. This paper proposes a non-orthogonal reconstructed space for LST. In such a space, the excitation motion in the line scanning process is described as a function of time delay, the moving velocity is estimated by the derived position map, and the reconstruction is achieved by image registration. The LST data are registered spatially by allowing the temporal misalignment among the pixels within the same reconstructed frame. The effectiveness of the proposed reconstruction algorithm is validated by both numerical simulations and experiments. The reconstruction results of experimental data indicate that the velocity is finely estimated so that the temporal alignment error is controlled within one pixel. Besides, no spatial distortions occur no matter how the frame rate and scanning velocity change. Furthermore, the Fourier phase image of the reconstructed LST reaches the diameter-to-depth ratio of 1.25 when inspecting a planar specimen with flat-bottom holes.

Research on 3D Reconstruction Algorithm of Medical CT Image Based on Parallel Contour

The current three-dimensional reconstruction algorithm of medical CT images still has certain drawbacks, and it is difficult to apply it effectively to clinical practice. In view of this, based on the parallel contour line, this paper studies the three-dimensional reconstruction algorithm of medical CT image, and realizes the three-dimensional reconstruction of the aortic dissection by surface drawing and volume rendering. At the same time, through the three modules of image preprocessing, aortic segmentation, dissection segmentation and three-dimensional reconstruction, the three-dimensional reconstruction of the patient's aortic dissection is realized. The reconstructed three-dimensional aortic dissection model can observe the shape of the internal sandwich model directly through the aortic wall, and the display of the three-dimensional structure of the interlayer is more intuitive and clearer. Finally, this paper designs experiments to analyze the performance of the algorithm. The research indicates that the three-dimensional reconstruction algorithm of medical CT images proposed in this paper has certain clinical effects and can provide theoretical reference for subsequent related research.

Phasor field diffraction based reconstruction for fast non-line-of-sight imaging systems

Non-line-of-sight (NLOS) imaging recovers objects using diffusely reflected indirect light using transient illumination devices in combination with a computational inverse method. While capture systems capable of collecting light from the entire NLOS relay surface can be much more light efficient than single pixel point scanning detection, current reconstruction algorithms for such systems have computational and memory requirements that prevent real-time NLOS imaging. Existing real-time demonstrations also use retroreflective targets and reconstruct at resolutions far below the hardware limits. Our method presented here enables the reconstruction of room-sized scenes from non-confocal, parallel multi-pixel measurements in seconds with less memory usage. We anticipate that our method will enable real-time NLOS imaging when used with emerging single-photon avalanche diode array detectors with resolution only limited by the temporal resolution of the sensor.

Interpretation of myocardial perfusion SPECT with attenuation correction. Part 2

Objective: to investigate the possibilities of a combined single photon emission computed tomography/computed tomography (SPECT/CT) system during myocardial perfusion studies and to examine the features of their interpretation. Subjects and methods. In April 2013 to April 2019, the Department of Radionuclide Diagnosis, National Medical Research Center of Cardiology, performed myocardial perfusion SPECT with attenuation correction (AC) in 3144 patients with various cardiovascular diseases. Based on the experience gained, the authors expanded and adjusted the principles of processing and interpreting the results of this study, which they had first set forth in 2014. Special emphasis is placed on the interpretation of apical and septal perfusion defects and diffuse perfusion irregularity, on the demonstration of the role of current reconstruction algorithms in obtaining highest-quality myocardial images, and on the assessment of self-potentialities of lowdose CT findings at myocardial SPECT/CT, as well as on proposals to standardize quantitative parameters for perfusion assessment at myocardial SPECT/CT. Results. AC affected in large measure the interpretation of myocardial perfusion SPECT in most cases. Apical perfusion defect appeared on AC images was observed in 50% of patients without established coronary heart disease and could be interpreted as a normal variant (apical thinning). The diffuse irregularity of perfusion radiopharmaceutical tracer accumulation in the application of the current reconstruction algorithms stood out in a separate pattern as a sign of microcirculatory disturbances. Low-dose CT data allow visualization of a severe thoracic abnormality at imaging and should be reflected in the conclusion. The perfusion study descriptions based on an analysis of AC and nAC images had a greater interoperator consistency than those based on an analysis of only nAC images (w = 0.915 and 0.809, respectively; p = 0.027). At the same time, the use of arithmetic means of the extent of transient ischemia (Reversibility Extent) is better consistent with visual analysis (= 0.08Ѓ}1.46%, p = 0.49). Conclusion. The use of AC and current iterative algorithms at myocardial perfusion SPECT should be part of a mandatory study protocol, since this affects to a large extent the diagnostic value of the technique. The borderline values of disturbed perfusion parameters at AC should be reconsidered.

Technical Note: Validation of TG 233 phantom methodology to characterize noise and dose in patient CT data.

Phantoms are useful tools in diagnostic CT, but practical limitations reduce phantoms to being only a limited patient surrogate. Furthermore, a phantom with a single cross sectional area cannot be used to evaluate scanner performance in modern CT scanners that use dose reduction techniques such as automated tube current modulation (ATCM) and iterative reconstruction (IR) algorithms to adapt x-ray flux to patient size, reduce radiation dose, and achieve uniform image noise. A new multisized phantom (Mercury Phantom, MP) has been introduced, representing multiple diameters. This work aimed to ascertain if measurements from MP can predict radiation dose and image noise in clinical CT images to prospectively inform protocol design. The adult MP design included four different physical diameters (18.5, 23.0, 30.0, and 37.0cm) representing a range of patient sizes. The study included 1457 examinations performed on two scanner models from two vendors, and two clinical protocols (abdominopelvic with and chest without contrast). Attenuating diameter, radiation dose, and noise magnitude (average pixel standard deviation in uniform image) was automatically estimated in patients and in the MP using a previously validated algorithm. An exponential fit of CTDIvol and noise as a function of size was applied to patients and MP data. Lastly, the fit equations from the phantom data were used to fit the patient data. In each patient distribution fit, the normalized root mean square error (nRMSE) values were calculated in the residuals' plots as a metric to indicate how well the phantom data can predict dose and noise in clinical operations as a function of size. For dose across patient size distributions, the difference between nRMSE from patient fit and MP model data prediction ranged between 0.6% and 2.0% (mean 1.2%). For noise across patient size distributions, the nRMSE difference ranged between 0.1% and 4.7% (mean 1.4%). The Mercury Phantom provided a close prediction of radiation dose and image noise in clinical patient images. By assessing dose and image quality in a phantom with multiple sizes, protocol parameters can be designed and optimized per patient size in a highly constrained setup to predict clinical scanner and ATCM system performance.

Separating distinct structures of multiple macromolecular assemblies from cryo-EM projections

Single particle analysis for structure determination in cryo-electron microscopy is traditionally applied to samples purified to near homogeneity as current reconstruction algorithms are not designed to handle heterogeneous mixtures of structures from many distinct macromolecular complexes. We extend on long established methods and demonstrate that relating two-dimensional projection images by their common lines in a graphical framework is sufficient for partitioning distinct protein and multiprotein complexes within the same data set. The feasibility of this approach is first demonstrated on a large set of synthetic reprojections from 35 unique macromolecular structures spanning a mass range of hundreds to thousands of kilodaltons. We then apply our algorithm on cryo-EM data collected from a mixture of five protein complexes and use existing methods to solve multiple three-dimensional structures ab initio. Incorporating methods to sort single particle cryo-EM data from extremely heterogeneous mixtures will alleviate the need for stringent purification and pave the way toward investigation of samples containing many unique structures.

Simultaneous recovery of both bright and dim structures from noisy fluorescence microscopy images using a modified TV constraint.

The quality and information content of biological images can be significantly enhanced by postacquisition processing using deconvolution and denoising. However, when imaging complex biological samples, such as neurons, stained with fluorescence labels, the signal level of different structures can differ by several orders of magnitude. This poses a challenge as current image reconstruction algorithms are focused on recovering low signals and generally have sample-dependent performance, requiring tedious manual tuning. This is one of the main hurdles for their wide adoption by nonspecialists. In this work, we modify the general constrained reconstruction method (in our case utilizing a total variation constraint) so that both bright and dim structures can drive the deconvolution with equal force. In this way, we can simultaneously obtain high-quality reconstruction across a wide range of signals within a single image or image sequence. The algorithm is tested on both simulated and experimental data. When compared with current state-of-art algorithms, our algorithm outperforms others in terms of maintaining the resolution in the high-signal areas and reducing artefacts in the low-signal areas. The algorithm was also tested on image sequences where one set of parameters are used to reconstruct all images, with blind evaluation by a group of biologists demonstrating a marked preference for the images produced by our method. This means that our method is suitable for batch processing of image sequences obtained from either spatial or temporalscanning. LAY DESCRIPTION: Fluorescence microscopy images of complex biological samples contain a wide range of signal levels. This signal variation leads current reconstruction algorithms, which aim to enhance the quality of the raw images, to have sample-dependent performance. In this work, we design a new optimization that allows the reconstruction to "pay equal eqattention to" both bright and dim structures. In this way, we can simultaneously recover both bright and dim structures within a single image or image sequence, as validated when the algorithm was quantitatively tested on both simulated and experimental data. When our method was evaluated alongside current state of art algorithms by a group of biologists, our algorithm was considered qualitativelysuperior.

The optimally designed autoencoder network for compressed sensing

Compressed sensing (CS) is a signal processing framework, which reconstructs a signal from a small set of random measurements obtained by measurement matrices. Due to the strong randomness of measurement matrices, the reconstruction performance is unstable. Additionally, current reconstruction algorithms are relatively independent of the compressed sampling process and have high time complexity. To this end, a deep learning based stacked sparse denoising autoencoder compressed sensing (SSDAE_CS) model, which mainly consists of an encoder sub-network and a decoder sub-network, is proposed and analyzed in this paper. Instead of traditional linear measurements, a multiple nonlinear measurements encoder sub-network is trained to obtain measurements. Meanwhile, a trained decoder sub-network solves the CS recovery problem by learning the structure features within the training data. Specifically, the two sub-networks are integrated into SSDAE_CS model through end-to-end training for strengthening the connection between the two processes, and their parameters are jointly trained to improve the overall performance of CS. Finally, experimental results demonstrate that the proposed method significantly outperforms state-of-the-art methods in terms of reconstruction performance, time cost, and denoising ability. Most importantly, the proposed model shows excellent reconstruction performance in the case of a few measurements.

Sparse-view CT reconstruction based on gradient directional total variation

The sparse-view problem of image reconstruction encountered in computed tomography (CT) is an important research issue due to its considerable potential in decreasing radiation dose and improving detection efficiency. Among the current sparse-view CT reconstruction algorithms, iterative reconstruction algorithms that consider total variation (TV) regularization exhibit good performance. However, the gradient difference direction is singular or fixed in conventional TV algorithms, leading to undesired artefacts when minimizing TV in sparse-view CT. To effectively address this issue, based on TV minimization, the gradient difference directional information is introduced as additional prior information in the regularization term, and a new gradient-based directional total variation minimization algorithm is proposed, which adaptively chooses mutative gradient directions to calculate the directional difference operators, and calculates the sum of the direction difference operators. In addition, to solve the fault tolerance and computational load, considering redundant blocks of reconstructed image, we can estimate the gradient directional information of each subblock via the gradient approximation method. For simplicity, the proposed algorithm is termed the BDTV algorithm. To demonstrate the superiority of the proposed algorithm, the simulation data and actual CT data from different algorithms are compared, and the results indicate that the proposed algorithm is effective at preserving details that are lost in the TV minimization, artefact reduction and noise suppression in sparse-view CT.

Underwater Image High Definition Display Using the Multilayer Perceptron and Color Feature-Based SRCNN

High-definition display technology for underwater images is of great significance for many applications, such as marine animal observation, seabed mining, and marine fishery production. The traditional underwater visual display systems have problems, such as low visibility, poor real-time performance, and low resolution, and cannot meet the needs of real-time high-definition displays in extreme environments. To solve these issues, we propose an underwater image enhancement method and a corresponding image super-resolution algorithm. To improve the quality of underwater images, we modify the Retinex algorithm and combine it with a neural network. The Retinex algorithm is used to defog the underwater image, and then, the image brightness is improved by applying gamma correction. Then, by combining with the dark channel prior and multilayer perceptron, the transmission map is further refined to improve the dynamic range of the image. In the super-resolution process, the current convolutional neural network reconstruction algorithm is only trained on the Y channel, which will lead to problems due to the insufficient acquisition of the color feature. Therefore, an image super-resolution reconstruction algorithm that is based on color features is proposed. The experimental results show that the proposed method improves the reconstruction effect of the image edges and texture details, increases the image clarity, and enhances the image color recovery.

Adaptively Hybrid $3^{\text{rd}}$ Simplified Spherical Harmonics With Diffusion Equation-Based Multispectral Cerenkov Luminescence Tomography

Cerenkov luminescence tomography (CLT) can reproduce the location of the tumor inside the body and the physiological processes that are related to its biological behavior, it has thus attracted more attention in the field of imaging technology. The inadequacy of signals that are measured on the body surface might cause ill-posed problems during image reconstruction, thus affecting the quantitative accuracy of CLT. This can be improved using a multispectral strategy by providing more measurements. However, current reconstruction algorithms for multispectral CLT are based on the light transport model that uses a single equation (a diffusion equation or a 3 rd simplified spherical harmonics equation) for each spectrum, which cannot guarantee the accuracy and efficiency of the reconstruction. In order to make full use of the broad-spectrum characteristics of Cerenkov luminescence and ensure an accurate and efficient reconstruction, in this work we apply an adaptively hybrid model to the multispectral CLT, that can automatically select the light transport equation. Here, the hybrid model was not only applied to different spectra, but also to different tissues at a certain spectrum. The selection of the light transport equation was accomplished by automatically comparing the index with a predefined threshold. Our proposed method was evaluated with numerical simulations and mouse-based experiments and the results showed the feasibility and effectiveness of the adaptively hybrid model based multispectral CLT.

Optimization design of reconfiguration algorithm for high voltage power distribution network based on ant colony algorithm

Abstract Distribution network reconfiguration is a very complex and large-scale combinatorial optimization problem. In network reconfiguration, whether an effective solution can be obtained is a key issue. Aiming at the problems in network reconstruction by traditional algorithm, such as long time required, more times of power flow calculation and high network loss, a network optimization design algorithm based on improved ant colony algorithm for high voltage power distribution network is proposed. After analyzing the operating characteristics of the high voltage power distribution network, the network topology of the high voltage power distribution network is described by constructing a hierarchical variable-structure distribution network model. A mathematical model of distribution network reconstruction considering the opportunity constraint with the minimum network loss as the objective function is established. The power flow distribution is calculated by using the pre-push back-generation method combined with the hierarchical structure of the distribution network. The maximum and minimum ant colony algorithm is introduced to improve the pheromone updating method of the traditional ant colony algorithm, and the search range is expanded, so that the algorithm can jump out of the local optimization trap to realize the accurate solution of the power distribution network reconstruction model. The experimental results show that compared with the current network reconstruction algorithm, the proposed algorithm requires less time for convergence, less power flow calculation, and lower network loss.