Survey of methods and principles in three-dimensional reconstruction from two-dimensional medical images

Three-dimensional(3D)reconstruction of human organs has gained attention in recent years due to advances in the Internet and graphics processing units.In the coming years,most patient care will shift toward this new paradigm.However,development of fast and accurate 3D models from medical images or a set of medical scans remains a daunting task due to the number of pre-processing steps involved,most of which are dependent on human expertise.In this review,a survey of pre-processing steps was conducted,and reconstruction techniques for several organs in medical diagnosis were studied.Various methods and principles related to 3D reconstruction were highlighted.The usefulness of 3D reconstruction of organs in medical diagnosis was also highlighted.

Research and Realization of Medical Image Fusion Based on Three-Dimensional Reconstruction

A new medical image fusion technique is presented.The method is based on three-dimensional reconstruction.After reconstruction,the three-dimensional volume data is normalized by three-dimensional coordinate conversion in the same way and intercepted through setting up cutting plane including anatomical structure,as a result two images in entire registration on space and geometry are obtained and the images are fused at last.Compared with traditional two-dimensional fusion technique,three-dimensional fusion technique can not only resolve the different problems existed in the two kinds of images,but also avoid the registration error of the two kinds of images when they have different scan and imaging parameter.The research proves this fusion technique is more exact and has no registration,so it is more adapt to arbitrary medical image fusion with different equipments.

Evaluating the use of three-dimensional reconstruction visualization technology for precise laparoscopic resection in gastroesophageal junction cancer

BACKGROUND Laparoscopic gastrectomy for esophagogastric junction(EGJ)carcinoma enables the removal of the carcinoma at the junction between the stomach and esophagus while preserving the gastric function,thereby providing patients with better treatment outcomes and quality of life.Nonetheless,this surgical technique also presents some challenges and limitations.Therefore,three-dimensional reconstruction visualization technology(3D RVT)has been introduced into the procedure,providing doctors with more comprehensive and intuitive anatomical information that helps with surgical planning,navigation,and outcome evaluation.AIM To discuss the application and advantages of 3D RVT in precise laparoscopic resection of EGJ carcinomas.METHODS Data were obtained from the electronic or paper-based medical records at The First Affiliated Hospital of Hebei North University from January 2020 to June 2022.A total of 120 patients diagnosed with EGJ carcinoma were included in the study.Of these,68 underwent laparoscopic resection after computed tomography(CT)-enhanced scanning and were categorized into the 2D group,whereas 52 underwent laparoscopic resection after CT-enhanced scanning and 3D RVT and were categorized into the 3D group.This study had two outcome measures:the deviation between tumor-related factors(such as maximum tumor diameter and infiltration length)in 3D RVT and clinical reality,and surgical outcome indicators(such as operative time,intraoperative blood loss,number of lymph node dissections,R0 resection rate,postoperative hospital stay,postoperative gas discharge time,drainage tube removal time,and related complications)between the 2D and 3D groups.RESULTS Among patients included in the 3D group,27 had a maximum tumor diameter of less than 3 cm,whereas 25 had a diameter of 3 cm or more.In actual surgical observations,24 had a diameter of less than 3 cm,whereas 28 had a diameter of 3 cm or more.The findings were consistent between the two methods(χ^(2)=0.346,P=0.556),with a kappa consistency coefficient of 0.808.With respect to infiltration length,in the 3D group,23 patients had a length of less than 5 cm,whereas 29 had a length of 5 cm or more.In actual surgical observations,20 cases had a length of less than 5 cm,whereas 32 had a length of 5 cm or more.The findings were consistent between the two methods(χ^(2)=0.357,P=0.550),with a kappa consistency coefficient of 0.486.Pearson correlation analysis showed that the maximum tumor diameter and infiltration length measured using 3D RVT were positively correlated with clinical observations during surgery(r=0.814 and 0.490,both P<0.05).The 3D group had a shorter operative time(157.02±8.38 vs 183.16±23.87),less intraoperative blood loss(83.65±14.22 vs 110.94±22.05),and higher number of lymph node dissections(28.98±2.82 vs 23.56±2.77)and R0 resection rate(80.77%vs 61.64%)than the 2D group.Furthermore,the 3D group had shorter hospital stay[8(8,9)vs 13(14,16)],time to gas passage[3(3,4)vs 4(5,5)],and drainage tube removal time[4(4,5)vs 6(6,7)]than the 2D group.The complication rate was lower in the 3D group(11.54%)than in the 2D group(26.47%)(χ^(2)=4.106,P<0.05).CONCLUSION Using 3D RVT,doctors can gain a more comprehensive and intuitive understanding of the anatomy and related lesions of EGJ carcinomas,thus enabling more accurate surgical planning.

GPU-accelerated three-dimensional reconstruction method of the Compton camera and its application in radionuclide imaging

A novel and fast three-dimensional reconstruction method for a Compton camera and its performance in radionuclide imaging is proposed and analyzed in this study. The conical surface sampling back-projection method with scattering angle correction(CSS-BP-SC) can quickly perform the back-projection process of the Compton cone and can be used to precompute the list-mode maximum likelihood expectation maximization(LM-MLEM). A dedicated parallel architecture was designed for the graphics processing unit acceleration of the back-projection and iteration stage of the CSS-BP-SC-based LM-MLEM. The imaging results of the two-point source Monte Carlo(MC) simulation demonstrate that by analyzing the full width at half maximum along the three coordinate axes, the CSS-BP-SC-based LM-MLEM can obtain imaging results comparable to those of the traditional reconstruction algorithm, that is, the simple back-projection-based LM-MLEM. The imaging results of the mouse phantom MC simulation and experiment demonstrate that the reconstruction results obtained by the proposed method sufficiently coincide with the set radioactivity distribution, and the speed increased by more than 664 times compared to the traditional reconstruction algorithm in the mouse phantom experiment. The proposed method will further advance the imaging applications of Compton cameras.

Training image analysis for three-dimensional reconstruction of porous media

In order to obtain a better sandstone three-dimensional （3D） reconstruction result which is more similar to the original sample, an algorithm based on stationarity for a two-dimensional （2D） training image is proposed. The second-order statistics based on texture features are analyzed to evaluate the scale stationarity of the training image. The multiple-point statistics of the training image are applied to obtain the multiple-point statistics stationarity estimation by the multi-point density function. The results show that the reconstructed 3D structures are closer to reality when the training image has better scale stationarity and multiple-point statistics stationarity by the indications of local percolation probability and two-point probability. Moreover, training images with higher multiple-point statistics stationarity and lower scale stationarity are likely to obtain closer results to the real 3D structure, and vice versa. Thus, stationarity analysis of the training image has far-reaching significance in choosing a better 2D thin section image for the 3D reconstruction of porous media. Especially, high-order statistics perform better than low-order statistics.

Three-dimensional positions of scattering centers reconstruction from multiple SAR images based on radargrammetry

A method and procedure is presented to reconstruct three-dimensional(3D) positions of scattering centers from multiple synthetic aperture radar(SAR) images. Firstly, two-dimensional(2D) attribute scattering centers of targets are extracted from 2D SAR images. Secondly, similarity measure is developed based on 2D attributed scatter centers' location, type, and radargrammetry principle between multiple SAR images. By this similarity, we can associate 2D scatter centers and then obtain candidate 3D scattering centers. Thirdly, these candidate scattering centers are clustered in 3D space to reconstruct final 3D positions. Compared with presented methods, the proposed method has a capability of describing distributed scattering center, reduces false and missing 3D scattering centers, and has fewer restrictionson modeling data. Finally, results of experiments have demonstrated the effectiveness of the proposed method.

Three-Dimensional Model Reconstruction of Nonwovens from Multi-Focus Images

The three-dimensional(3D)model is of great significance to analyze the performance of nonwovens.However,the existing modelling methods could not reconstruct the 3D structure of nonwovens at low cost.A new method based on deep learning was proposed to reconstruct 3D models of nonwovens from multi-focus images.A convolutional neural network was trained to extract clear fibers from sequence images.Image processing algorithms were used to obtain the radius,the central axis,and depth information of fibers from the extraction results.Based on this information,3D models were built in 3D space.Furthermore,self-developed algorithms optimized the central axis and depth of fibers,which made fibers more realistic and continuous.The method with lower cost could reconstruct 3D models of nonwovens conveniently.

A rapid micro-magnetic resonance imaging scanning for three-dimensional reconstruction of peripheral nerve fascicles

The most common methods for three-dimensional reconstruction of peripheral nerve fascicles include histological and radiology techniques. Histological techniques have many drawbacks including an enormous manual workload and poor image registration. Micro-magnetic resonance imaging（Micro-MRI）, an emerging radiology technique, has been used to report results in the brain, liver and tumor tissues. However, micro-MRI usage for obtaining intraneural structures has not been reported. The aim of this study was to present a new imaging method for three-dimensional reconstruction of peripheral nerve fascicles by ~1T micro-MRI. Freshly harvested sciatic nerve samples from an amputated limb were divided into four groups. Two different scanning conditions（Mannerist Solution/GD-DTPA contrast agent, distilled water） were selected, and both T1 and T2 phases programmed for each scanning condition. Three clinical surgeons evaluated the quality of the images via a standardized scale. Moreover, to analyze deformation of the two-dimensional image, the nerve diameter and total area of the micro-MRI images were compared after hematoxylin-eosin staining. The results show that rapid micro-MRI imaging method can be used for three-dimensional reconstruction of the fascicle structure. Nerve sample immersed in contrast agent（Mannerist Solution/GD-DTPA） and scanned in the T1 phase was the best. Moreover, the nerve sample was scanned freshly and can be recycled for other procedures. MRI images show better stability and smaller deformation compared with histological images. In conclusion, micro-MRI provides a feasible and rapid method for three-dimensional reconstruction of peripheral nerve fascicles, which can clearly show the internal structure of the peripheral nerve.

New Virtual Cutting Algorithms for 3D Surface Model Reconstructed from Medical Images

This paper proposes a practical algorithms of plane cutting, stereo clipping and arbitrary cutting for 3D surface model reconstructed from medical images. In plane cutting and stereo clipping algorithms, the 3D model is cut by plane or polyhedron. Lists of edge and vertex in every cut plane are established. From these lists the boundary contours are created and their relationship of embrace is ascertained. The region closed by the contours is triangulated using Delaunay triangulation algorithm. Arbitrary cutting operation creates cutting curve interactively. The cut model still maintains its correct topology structure. With these operations, tissues inside can be observed easily and it can aid doctors to diagnose. The methods can also be used in surgery planning of radiotherapy.

Construction and application of a three-dimensional vascular variation-based nephrometry scoring system for completely endophytic renal tumors

Background:Completely endophytic renal tumors(CERT)pose significant challenges due to their anatomical complexity and loss of visual clues about tumor location.A facile scoring model based on three-dimensional(3D)reconstructed images will assist in better assessing tumor location and vascular variations.Methods:In this retrospective study,80 patients diagnosed with CERT were included.Forty cases underwent preoperative assessment using 3D reconstructed imaging(3D-Cohort),while the remaining 40 cases were assessed using two-dimensional imaging(2D-Cohort).Vascular variations were evaluated by ascertaining the presence of renal arteries>1,prehilar branching arteries,and arteries anterior to veins.The proposed scoring system,termed RAL,encompassed three critical components:(R)adius(maximal tumor diameter in cm),(A)rtery(occurrence of arterial variations),and(L)ocation relative to the polar line.Comparison of the RAL scoring system was made with established nephrometry scoring systems.Results:A total of 48(60%)patients exhibited at least one vascular variation.In the 2D-Cohort,patients with vascular variations experienced significantly prolonged operation time,increased bleeding volume,and extended warm ischemia time compared with those without vascular variations.Conversely,the presence of vascular vari-ations did not significantly affect operative parameters in the 3D-Cohort.Furthermore,the 2D-Cohort demon-strated a notable decline in both short-and long-term estimated glomerular filtration rate(eGFR)changes com-pared with the 3D-Cohort,a trend consistent across patients with warm ischemia time≥25 min and those with vascular variations.Notably,the 2D-Cohort exhibited a larger margin of normal renal tissue compared with the 3D-Cohort.Elevated RAL scores correlated with larger tumor size,prolonged operation time,extended warm is-chemia time,and substantial postoperative eGFR decrease.The RAL scoring system displayed superior predictive capabilities in assessing postoperative eGFR changes compared with conventional nephrometry scoring systems.Conclusions:Our proposed 3D vascular variation-based nephrometry scoring system offers heightened proficiency in preoperative assessment,precise prediction of surgical complexity,and more accurate evaluation of postoper-ative renal function in CERT patients.

Reduction of artifacts in dental cone beam CT images to improve the three dimensional image reconstruction

Cone-beam CT (CBCT) scanners are based on volumetric tomography, using a 2D extended digital array providing an area detector [1,2]. Compared to traditional CT, CBCT has many advantages, such as less X-ray beam limitation, and rapid scan time, etc. However, in CBCT images the x-ray beam has lower mean kilovolt (peak) energy, so the metal artifact is more pronounced on. The position of the shadowed region in other views can be tracked by projecting the 3D coordinates of the object. Automatic image segmentation was used to replace the pixels inside the metal object with the boundary pixels. The modified projection data, using synthetically Radon Transformation, were then used to reconstruct a new back projected CBCT image. In this paper, we present a method, based on the morphological, area and pixel operators, which we applied on the Radon transformed image, to reduce the metal artifacts in CBCT, then we built the Radon back project images using the radon invers transformation. The artifacts effects on the 3d-reconstruction is that, the soft tissues appears as bones or teeth. For the preprocessing of the CBCT images, two methods are used to recognize the noisy black areas that the first depends on thresholding and closing algorithm, and the second depends on tracing boundaries after using thresholding algorithm too. The intensity of these areas is the lowest in the image than other tissues, so we profit this property to detect the edges of these areas. These two methods are applied on phantom and patient image data. It deals with reconstructed CBCT dicom images and can effectively reduce such metal artifacts. Due to the data of the constructed images are corrupted by these metal artifacts, qualitative and quantitative analysis of CBCT images is very essential.

Three-Dimensional Measurement and Reconstruction of Fabric Drape Shape

This paper introduces a new method of measuring the three-dimensional drape shape of fabrics with structural light. First, we apply parallel annular structural light to form light and shade alternating contour stripes on the surface of fabrics. We then collect the images of contour stripes using Charge Coupled Device (CCD). Subsequently, we process the images to identify the contour stripes and edges of fabrics, and obtain the fabric contour lines of curved surfaces. Finally, we apply three-dimensional curved surface modeling method based on a network of polar coordinates, and reconstruct the three-dimensional drape shape of fabrics. Experiments show that our method is effective in testing and reconstructing three-dimensional drape shape of fabrics.

Multidetector computed tomography three-dimensional and multiplanar reconstruction diagnosis of a rare cause of gastrointestinal bleeding: A case report

BACKGROUND Anastomosis of the testicular vein with the superior mesenteric vein rarely causes severe gastrointestinal bleeding.To date,there have been few studies describing its appearance on medical imaging.Here,we present multidetector computed tomography three-dimensional and multiplanar reconstruction(MPR)images of a typical digital subtraction angiography showing proven ectopic bleeding and provide the first review of the image performance.CASE SUMMARY A 68-year-old man who had been rushed to the hospital with a four-day history of melena and fainting underwent multiple esophagogastroduodenoscopy procedures that failed to identify the source of bleeding.We used MPR combined with three-dimensional reconstruction images,and found that the testicular vein had anastomosed with the superior mesenteric vein,and they clustered together in the jejunal vessel wall,which caused severe gastrointestinal bleeding.Digital subtraction angiography confirmed the location of bleeding.After transfusion and embolization therapy,the patient’s condition improved.CONCLUSION Computed tomography-MPR combined with three-dimensional images offers significant value in the localization and qualitative assessment of rare gastrointestinal hemorrhage.The features of multiphase spiral scanning can improve the accuracy of the diagnosis.

3-D Visualization of Medical Images with Arbitrary Sections

In this paper, with the general retrospect to the research on surface reconstruction and the marching cubes algorithm, we gave detailed description of an algorithm on the construction of object surfaces. The possible ambiguity problem in the original marching cubes algorithm was eliminated by its index mechanism. Some results on the MRI images were presented. Based on extracting and clipping contours from a set of medial slice images and setting the patch vertices values according to the gray images, this algorithm may be applied to form the arbitrary section images with three dimensional effects. It can also enhance the visual effect and interpretation of medical data.

Three-dimensional reconstructed magnetic resonance scans:Accuracy in identifying and defining knee meniscal tears

AIM To determine whether three-dimensional(3D) reconstruction from conventional magnetic resonance imaging(MRI) is able to accurately detect a meniscal tear, and define the configuration.METHODS Thirty-three patients' 3T MRI scan data were collected and sagittal uni-planar 3D reconstructions performed from the preoperative MRI. There were 24 meniscal tears in 24 patients, and nine controls. All patients had arthroscopic corroboration of MRI findings. Two independent observers prospectively reported on all 33 reconstructions. Meniscal tear presence or absence was noted, and tear configuration subsequently categorised as either radial, bucket-handle, parrot beak, horizontal or complex.RESULTS Identification of control menisci or meniscal tear presence was excellent(Accuracy: observer 1 = 90.9%; observer 2 = 81.8%). Of the tear configurations, bucket handle tears were accurately identified(Accuracy observer 1 and 2 = 80%). The remaining tear configurations were notaccurately discernable.CONCLUSION Uni-planar 3D reconstruction from 3T MRI knee scan sequences are useful in identifying normal menisci and menisci with bucket-handle tears. Advances in MRI sequencing and reconstruction software are awaited for accurate identification of the remaining meniscal tear configurations.

A Review on Deep Learning in Medical Image Reconstruction

Medical imaging is crucial in modern clinics to provide guidance to the diagnosis and treatment of diseases.Medical image reconstruction is one of the most fundamental and important components of medical imaging,whose major objective is to acquire high-quality medical images for clinical usage at the minimal cost and risk to the patients.Mathematical models in medical image reconstruction or,more generally,image restoration in computer vision have been playing a prominent role.Earlier mathematical models are mostly designed by human knowledge or hypothesis on the image to be reconstructed,and we shall call these models handcrafted models.Later,handcrafted plus data-driven modeling started to emerge which still mostly relies on human designs,while part of the model is learned from the observed data.More recently,as more data and computation resources are made available,deep learning based models(or deep models)pushed the data-driven modeling to the extreme where the models are mostly based on learning with minimal human designs.Both handcrafted and data-driven modeling have their own advantages and disadvantages.Typical handcrafted models are well interpretable with solid theoretical supports on the robustness,recoverability,complexity,etc.,whereas they may not be flexible and sophisticated enough to fully leverage large data sets.Data-driven models,especially deep models,on the other hand,are generally much more flexible and effective in extracting useful information from large data sets,while they are currently still in lack of theoretical foundations.Therefore,one of the major research trends in medical imaging is to combine handcrafted modeling with deep modeling so that we can enjoy benefits from both approaches.The major part of this article is to provide a conceptual review of some recent works on deep modeling from the unrolling dynamics viewpoint.This viewpoint stimulates new designs of neural network architectures with inspirations from optimization algorithms and numerical differential equations.Given the popularity of deep modeling,there are still vast remaining challenges in the field,as well as opportunities which we shall discuss at the end of this article.

Three-dimensional free view reconstruction in axially distributed image sensing

Three-dimensional （3D） acquisition has been the most important technique for augmented reality or virtual reality industries. Stereo vision can obtain 3D infor- mation of objects using disparity between two images captured by a stereo camera. However, due to lack of per- spectives for 3D objects in this technique, accurate 3D information may not be generated and the number of viewing points is limited. By contrast, multi-view or super multi-view imaging techniques can obtain more accurate 3D information because they use multiple cameras for pickup of 3D objects so that more perspec- tives and viewing points of 3D objects can be recorded.

A fast, accurate and dense feature matching algorithm for aerial images

Three-dimensional(3D)reconstruction based on aerial images has broad prospects,and feature matching is an important step of it.However,for high-resolution aerial images,there are usually problems such as long time,mismatching and sparse feature pairs using traditional algorithms.Therefore,an algorithm is proposed to realize fast,accurate and dense feature matching.The algorithm consists of four steps.Firstly,we achieve a balance between the feature matching time and the number of matching pairs by appropriately reducing the image resolution.Secondly,to realize further screening of the mismatches,a feature screening algorithm based on similarity judgment or local optimization is proposed.Thirdly,to make the algorithm more widely applicable,we combine the results of different algorithms to get dense results.Finally,all matching feature pairs in the low-resolution images are restored to the original images.Comparisons between the original algorithms and our algorithm show that the proposed algorithm can effectively reduce the matching time,screen out the mismatches,and improve the number of matches.

Application of Reconstruction and Optimization Algorithms in Optical Tomography

Optical tomography is a non-invasive technique that uses visible or near infrared radiation to analyze biological tissues. Researchers take immense attention towards advancement in optical tomography because of its low cost and an advantage of providing anatomical information. Based on the information of optical characteristics, forward and inverse problem of tomography are solved. In this research, finite element method is employed for forward problem and gradient-based optimization algorithm is developed for inverse problem of optical tomography. It is found from simulations that information about imaging is processed more distinctly and in less computational time. Normal and abnormal conditions in imaging are readily distinguished.?Simulations are carried out in Matlab. Different scenarios are developed and are simulated to validate the performance of reconstruction and optimization algorithms in optical tomography.

A survey on deep learning in medical image reconstruction

Medical image reconstruction aims to acquire high-quality medical images for clinical usage at minimal cost and risk to the patients.Deep learning and its applications in medical imaging,especially in image reconstruction have received considerable attention in the literature in recent years.This study reviews records obtained elec-tronically through the leading scientific databases(Magnetic Resonance Imaging journal,Google Scholar,Scopus,Science Direct,Elsevier,and from other journal publications)searched using three sets of keywords:(1)Deep learning,image reconstruction,medical imaging;(2)Medical imaging,Deep learning,Image reconstruction;(3)Open science,Open imaging data,Open software.The articles reviewed revealed that deep learning-based re-construction methods improve the quality of reconstructed images qualitatively and quantitatively.However,deep learning techniques are generally computationally expensive,require large amounts of training datasets,lack decent theory to explain why the algorithms work,and have issues of generalization and robustness.The challenge of lack of enough training datasets is currently being addressed by using transfer learning techniques.