Medical image segmentation and registration are two fundamental and highly related tasks. However, current works focus on the mutual promotion between the two at the loss function level, ignoring the feature information generated by the encoder-decoder network during the task-specific feature mapping process and the potential inter-task feature relationship. This paper proposes a unified multi-task joint learning framework based on bi-fusion of structure and deformation at multi-scale, called BFM-Net, which simultaneously achieves the segmentation results and deformation field in a single-step estimation. BFM-Net consists of a segmentation subnetwork (SegNet), a registration subnetwork (RegNet), and the multi-task connection module (MTC). The MTC module is used to transfer the latent feature representation between segmentation and registration at multi-scale and link different tasks at the network architecture level, including the spatial attention fusion module (SAF), the multi-scale spatial attention fusion module (MSAF) and the velocity field fusion module (VFF). Extensive experiments on MR, CT and ultrasound images demonstrate the effectiveness of our approach. The MTC module can increase the Dice scores of segmentation and registration by 3.2%, 1.6%, 2.2%, and 6.2%, 4.5%, 3.0%, respectively. Compared with six state-of-the-art algorithms for segmentation and registration, BFM-Net can achieve superior performance in various modal images, fully demonstrating its effectiveness and generalization.
During the infusion process of a glass-fiber-reinforced thermosetting composite hose, the viscosity of its resin matrix undergoes temporal variations. Consequently, if the impact of resin viscosity changes over time on the internal resin fluidity is not considered during the infusion process, this may result in the incomplete impregnation of the hose, characterized by the presence of numerous voids. This phenomenon adversely affects the quality of the pipe's curing and forming process. Therefore, based on the characteristic variations in resin viscosity, this paper considers the changes in fluidity caused by the resin's temporal evolution within the material. We establish a finite element simulation model to calculate and analyze the overall infusion effects of resin viscosity changes during the hose infusion process. Furthermore, based on the predicted analysis, a variable parameter infusion strategy is proposed to increase resin impregnation in the hose, thereby reducing internal void content and subsequently improving the quality of material curing and forming.
Accurately reconstructing 4D critical organs contributes to the visual guidance in X-ray image-guided interventional operation. Current methods estimate intraoperative dynamic meshes by refining a static initial organ mesh from the semantic information in the single-frame X-ray images. However, these methods fall short of reconstructing an accurate and smooth organ sequence due to the distinct respiratory patterns between the initial mesh and X-ray image. To overcome this limitation, we propose a novel dual-stage complementary 4D organ reconstruction (DSC-Recon) model for recovering dynamic organ meshes by utilizing the preoperative and intraoperative data with different respiratory patterns. DSC-Recon is structured as a dual-stage framework: 1) The first stage focuses on addressing a flexible interpolation network applicable to multiple respiratory patterns, which could generate dynamic shape sequences between any pair of preoperative 3D meshes segmented from CT scans. 2) In the second stage, we present a deformation network to take the generated dynamic shape sequence as the initial prior and explore the discriminate feature (i.e., target organ areas and meaningful motion information) in the intraoperative X-ray images, predicting the deformed mesh by introducing a designed feature mapping pipeline integrated into the initialized shape refinement process. Experiments on simulated and clinical datasets demonstrate the superiority of our method over state-of-the-art methods in both quantitative and qualitative aspects.
BACKGROUND: The existing face matching method requires a point cloud to be drawn on the real face for registration, which results in low registration accuracy due to the irregular deformation of the patient's skin that makes the point cloud have many outlier points. METHODS: This work proposes a non-contact pose estimation method based on similarity aspect graph hierarchical optimization. The proposed method constructs a distance-weighted and triangular-constrained similarity measure to describe the similarity between views by automatically identifying the 2D and 3D feature points of the face. A mutual similarity clustering method is proposed to construct a hierarchical aspect graph with 3D pose as nodes. A Monte Carlo tree search strategy is used to search the hierarchical aspect graph for determining the optimal pose of the facial 3D model, so as to realize the accurate registration of the facial 3D model and the real face. RESULTS: The proposed method was used to conduct accuracy verification experiments on the phantoms and volunteers, which were compared with four advanced pose calibration methods. The proposed method obtained average fusion errors of 1.13 ± 0.20 mm and 0.92 ± 0.08 mm in head phantom and volunteer experiments, respectively, which exhibits the best fusion performance among all comparison methods. CONCLUSIONS: Our experiments proved the effectiveness of the proposed pose estimation method in facial augmented reality.
Algorithms , Augmented Reality , Humans , Imaging, Three-Dimensional/methods
In recent years, 4D medical image involving structural and motion information of tissue has attracted increasing attention. The key to the 4D image reconstruction is to stack the 2D slices based on matching the aligned motion states. In this study, the distribution of the 2D slices with the different motion states is modeled as a manifold graph, and the reconstruction is turned to be the graph alignment. An embedding-alignment fusion-based graph convolution network (GCN) with a mixed-learning strategy is proposed to align the graphs. Herein, the embedding and alignment processes of graphs interact with each other to realize a precise alignment with retaining the manifold distribution. The mixed strategy of self- and semi-supervised learning makes the alignment sparse to avoid the mismatching caused by outliers in the graph. In the experiment, the proposed 4D reconstruction approach is validated on the different modalities including Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Ultrasound (US). We evaluate the reconstruction accuracy and compare it with those of state-of-the-art methods. The experiment results demonstrate that our approach can reconstruct a more accurate 4D image.
Algorithms , Imaging, Three-Dimensional , Humans , Imaging, Three-Dimensional/methods , Neural Networks, Computer , Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , Ultrasonography/methods , Machine Learning
Feature matching of monocular laparoscopic videos is crucial for visualization enhancement in computer-assisted surgery, and the keys to conducting high-quality matches are accurate homography estimation, relative pose estimation, as well as sufficient matches and fast calculation. However, limited by various monocular laparoscopic imaging characteristics such as highlight noises, motion blur, texture interference and illumination variation, most exiting feature matching methods face the challenges of producing high-quality matches efficiently and sufficiently. To overcome these limitations, this paper presents a novel sequential coupling feature descriptor to extract and express multilevel feature maps efficiently, and a dual-correlate optimized coarse-fine strategy to establish dense matches in coarse level and adjust pixel-wise matches in fine level. Firstly, a novel sequential coupling swin transformer layer is designed in feature descriptor to learn and extract multilevel feature representations richly without increasing complexity. Then, a dual-correlate optimized coarse-fine strategy is proposed to match coarse feature sequences under low resolution, and the correlated fine feature sequences is optimized to refine pixel-wise matches based on coarse matching priors. Finally, the sequential coupling feature descriptor and dual-correlate optimization are merged into the Sequential Coupling Dual-Correlate Network (SeCo DC-Net) to produce high-quality matches. The evaluation is conducted on two public laparoscopic datasets: Scared and EndoSLAM, and the experimental results show the proposed network outperforms state-of-the-art methods in homography estimation, relative pose estimation, reprojection error, matching pairs number and inference runtime. The source code is publicly available at https://github.com/Iheckzza/FeatureMatching.
Laparoscopy , Surgery, Computer-Assisted , Learning , Software
Image-based endoscopy pose estimation has been shown to significantly improve the visualization and accuracy of minimally invasive surgery (MIS). This paper proposes a method for pose estimation based on structure-depth information from a monocular endoscopy image sequence. Firstly, the initial frame location is constrained using the image structure difference (ISD) network. Secondly, endoscopy image depth information is used to estimate the pose of sequence frames. Finally, adaptive boundary constraints are used to optimize continuous frame endoscopy pose estimation, resulting in more accurate intraoperative endoscopy pose estimation. Evaluations were conducted on publicly available datasets, with the pose estimation error in bronchoscopy and colonoscopy datasets reaching 1.43 mm and 3.64 mm, respectively. These results meet the real-time requirements of various scenarios, demonstrating the capability of this method to generate reliable pose estimation results for endoscopy images and its meaningful applications in clinical practice. This method enables accurate localization of endoscopy images during surgery, assisting physicians in performing safer and more effective procedures.
PURPOSE: This work proposes a robot-assisted augmented reality (AR) surgical navigation system for mandibular reconstruction. The system accurately superimposes the preoperative osteotomy plan of the mandible and fibula into a real scene. It assists the doctor in osteotomy quickly and safely under the guidance of the robotic arm. METHODS: The proposed system mainly consists of two modules: the AR guidance module of the mandible and fibula and the robot navigation module. In the AR guidance module, we propose an AR calibration method based on the spatial registration of the image tracking marker to superimpose the virtual models of the mandible and fibula into the real scene. In the robot navigation module, the posture of the robotic arm is first calibrated under the tracking of the optical tracking system. The robotic arm can then be positioned at the planned osteotomy after the registration of the computed tomography image and the patient position. The combined guidance of AR and robotic arm can enhance the safety and precision of the surgery. RESULTS: The effectiveness of the proposed system was quantitatively assessed on cadavers. In the AR guidance module, osteotomies of the mandible and fibula achieved mean errors of 1.61 ± 0.62 and 1.08 ± 0.28 mm, respectively. The mean reconstruction error of the mandible was 1.36 ± 0.22 mm. In the AR-robot guidance module, the mean osteotomy errors of the mandible and fibula were 1.47 ± 0.46 and 0.98 ± 0.24 mm, respectively. The mean reconstruction error of the mandible was 1.20 ± 0.36 mm. CONCLUSIONS: The cadaveric experiments of 12 fibulas and six mandibles demonstrate the proposed system's effectiveness and potential clinical value in reconstructing the mandibular defect with a free fibular flap.
Augmented Reality , Free Tissue Flaps , Mandibular Reconstruction , Robotics , Surgery, Computer-Assisted , Humans , Mandibular Reconstruction/methods , Surgery, Computer-Assisted/methods , Free Tissue Flaps/surgery , Mandible/diagnostic imaging , Mandible/surgery
Polyguluronate (PG) is a fermentable polysaccharide from edible algae. The present study was designed to investigate the therapeutic effect of PG on ulcerative colitis (UC) and its underlying mechanisms. Our results suggest that oral intake of PG attenuates UC and improves gut microbiota dysbiosis by promoting the growth of Lactobacillus spp. in dextran sulfate sodium-fed mice. Five different species of Lactobacillus were isolated from the feces of PG-treated mice and L. murinus was identified to have the best anti-colitis effect, suggesting a critical role for L. murinus in mediating the therapeutic effect of PG. Furthermore, PG was degraded potentially by the beta-glucuronidase from L. murinus and adding PG to the culture medium of L. murinus remarkably increased its production of anti-inflammatory metabolites, including itaconic acid, cis-11,14-eicosadienoic acid, and 3-amino-3-(2-chlorophenyl)-propionic acid. Additionally, L. salivarius, a human intestine-derived PG-utilizing species that is closely related to L. murinus, was also demonstrated to have potent anti-colitis effects, suggesting that it is a candidate target of PG in the human gut. Altogether, our study illustrates an unprecedented application of PG in the treatment of UC and establishes the basis for understanding its therapeutic effect from the perspective of L. murinus and its metabolites.
Colitis, Ulcerative , Colitis , Polysaccharides, Bacterial , Humans , Animals , Mice , Colitis, Ulcerative/chemically induced , Colitis, Ulcerative/drug therapy , Colitis, Ulcerative/metabolism , Lactobacillus , Colitis/metabolism , Anti-Inflammatory Agents/pharmacology , Anti-Inflammatory Agents/metabolism , Dextran Sulfate , Disease Models, Animal , Colon/metabolism , Mice, Inbred C57BL
Driven by the development of X-ray optics, the spatial resolution of the full-field transmission X-ray microscope (TXM) has reached tens of nanometers and plays an important role in promoting the development of biomedicine and materials science. However, due to the thermal drift and the radial/axial motion error of the rotation stage, TXM computed tomography (CT) data are often associated with random image jitter errors along the horizontal and vertical directions during CT measurement. A nano-resolution 3D structure information reconstruction is almost impossible without a prior appropriate alignment process. To solve this problem, a fully automatic gold particle marker-based alignment approach without human intervention was proposed in this study. It can automatically detect, isolate, and register gold particles for projection image alignment with high efficiency and accuracy, facilitating a high-quality tomographic reconstruction. Simulated and experimental results confirmed the reliability and robustness of this method.
BACKGROUND: Clinical practice guidelines (CPGs) are designed to assist doctors in clinical decision making. High-quality research articles are important for the development of good CPGs. Commonly used manual screening processes are time-consuming and labor-intensive. Artificial intelligence (AI)-based techniques have been widely used to analyze unstructured data, including texts and images. Currently, there are no effective/efficient AI-based systems for screening literature. Therefore, developing an effective method for automatic literature screening can provide significant advantages. METHODS: Using advanced AI techniques, we propose the Paper title, Abstract, and Journal (PAJO) model, which treats article screening as a classification problem. For training, articles appearing in the current CPGs are treated as positive samples. The others are treated as negative samples. Then, the features of the texts (e.g., titles and abstracts) and journal characteristics are fully utilized by the PAJO model using the pretrained bidirectional-encoder-representations-from-transformers (BERT) model. The resulting text and journal encoders, along with the attention mechanism, are integrated in the PAJO model to complete the task. RESULTS: We collected 89,940 articles from PubMed to construct a dataset related to neck pain. Extensive experiments show that the PAJO model surpasses the state-of-the-art baseline by 1.91% (F1 score) and 2.25% (area under the receiver operating characteristic curve). Its prediction performance was also evaluated with respect to subject-matter experts, proving that PAJO can successfully screen high-quality articles. CONCLUSIONS: The PAJO model provides an effective solution for automatic literature screening. It can screen high-quality articles on neck pain and significantly improve the efficiency of CPG development. The methodology of PAJO can also be easily extended to other diseases for literature screening.
Deep Learning , Practice Guidelines as Topic , Humans , Artificial Intelligence , Clinical Decision-Making , Neck Pain , Review Literature as Topic
A novel and efficient mesoporous nano-absorbent for U(VI) removal was developed through an environment-friendly route by inducing the biomimetic mineralization of hydroxyapatite (HAP) on the bioinspired surface of polydopamine-graphene oxide (PDA-GO). PDA-GO/HAP exhibited the greatly rapid and efficient U(VI) removal within 2 min, and much higher U(VI) adsorption capacity of 433.07 mg·g-1 than that of GO and PDA-GO. The enhanced adsorption capacity was mainly attributed to the synergistic effect of O-H, -C=N-, and PO43- functional groups and the incorporation of uranyl ions by the formation of a new phase (chernikovite, H2(UO2)2(PO4)2·8H2O). The adsorption process of U(VI) fitted well with pseudo-second-order kinetic and Langmuir isotherm model. Moreover, PDA-GO/HAP showed a high U(VI) adsorption capacity in a broad range of pH values and owned good thermal stability. PDA-GO/HAP with various excellent properties made it a greatly promising adsorbent for extracting uranium. Our work developed a good strategy for constructing fast and efficient uranium-adsorptive biomimetic materials.
Uranium , Uranium/analysis , Durapatite , Biomimetics , Water , Adsorption , Kinetics
Microwave ablation (MWA) is a minimally invasive procedure for the treatment of liver tumor. Accumulating clinical evidence has considered the minimal ablative margin (MAM) as a significant predictor of local tumor progression (LTP). In clinical practice, MAM assessment is typically carried out through image registration of pre- and post-MWA images. However, this process faces two main challenges: non-homologous match between tumor and coagulation with inconsistent image appearance, and tissue shrinkage caused by thermal dehydration. These challenges result in low precision when using traditional registration methods for MAM assessment. In this paper, we present a local contractive nonrigid registration method using a biomechanical model (LC-BM) to address these challenges and precisely assess the MAM. The LC-BM contains two consecutive parts: (1) local contractive decomposition (LC-part), which reduces the incorrect match between the tumor and coagulation and quantifies the shrinkage in the external coagulation region, and (2) biomechanical model constraint (BM-part), which compensates for the shrinkage in the internal coagulation region. After quantifying and compensating for tissue shrinkage, the warped tumor is overlaid on the coagulation, and then the MAM is assessed. We evaluated the method using prospectively collected data from 36 patients with 47 liver tumors, comparing LC-BM with 11 state-of-the-art methods. LTP was diagnosed through contrast-enhanced MR follow-up images, serving as the ground truth for tumor recurrence. LC-BM achieved the highest accuracy (97.9%) in predicting LTP, outperforming other methods. Therefore, our proposed method holds significant potential to improve MAM assessment in MWA surgeries.
Objective.In computer-assisted minimally invasive surgery, the intraoperative x-ray image is enhanced by overlapping it with a preoperative CT volume to improve visualization of vital anatomical structures. Therefore, accurate and robust 3D/2D registration of CT volume and x-ray image is highly desired in clinical practices. However, previous registration methods were prone to initial misalignments and struggled with local minima, leading to issues of low accuracy and vulnerability.Approach.To improve registration performance, we propose a novel CT/x-ray image registration agent (CT2X-IRA) within a task-driven deep reinforcement learning framework, which contains three key strategies: (1) a multi-scale-stride learning mechanism provides multi-scale feature representation and flexible action step size, establishing fast and globally optimal convergence of the registration task. (2) A domain adaptation module reduces the domain gap between the x-ray image and digitally reconstructed radiograph projected from the CT volume, decreasing the sensitivity and uncertainty of the similarity measurement. (3) A weighted reward function facilitates CT2X-IRA in searching for the optimal transformation parameters, improving the estimation accuracy of out-of-plane transformation parameters under large initial misalignments.Main results.We evaluate the proposed CT2X-IRA on both the public and private clinical datasets, achieving target registration errors of 2.13 mm and 2.33 mm with the computation time of 1.5 s and 1.1 s, respectively, showing an accurate and fast workflow for CT/x-ray image rigid registration.Significance.The proposed CT2X-IRA obtains the accurate and robust 3D/2D registration of CT and x-ray images, suggesting its potential significance in clinical applications.
Algorithms , Imaging, Three-Dimensional , X-Rays , Imaging, Three-Dimensional/methods , Tomography, X-Ray Computed/methods , Radiography , Image Processing, Computer-Assisted
Based on the electromagnetic induction heating method, heating and curing of Carbon Fiber Reinforced Polymer (CFRP) have the advantages of high energy utilization and no pollution. However, in the heating process, both the material weaving structure and mold material can affect the temperature field. Therefore, in this study, an electromagnetic heating finite element analysis model for CFRP circular tubes was established based on the equivalent electromagnetic thermal characteristics of CFRP. The study investigated the temperature rise mechanism of the material weaving structure under the magnetic field, and explored in-depth the influence of molds made of 45# steel and glass fiber-reinforced plastic (FRP) on the heating process of CFRP. The CFRP circular tubes with weaving structures of 89-degree winding angle, 45-degree winding angle, and plain weave were studied. The study found that when the metal mold was heated, the CFRP structure had almost no effect on the temperature distribution. However, when the glass fiber-reinforced plastic mold was heated, the temperature field changed with the CFRP structure, and the more fiber cross points, the more uniform the temperature field. The accuracy of the finite element model was verified through experiments. The aim of this research is to provide theoretical guidance for actual industrial production.
Objective.3D ultrasound non-rigid registration is significant for intraoperative motion compensation. Nevertheless, distorted textures in the registered image due to the poor image quality and low signal-to-noise ratio of ultrasound images reduce the accuracy and efficiency of the existing methods.Approach.A novel 3D ultrasound non-rigid registration objective function with texture and content constraints in both image space and multiscale feature space based on an unsupervised generative adversarial network based registration framework is proposed to eliminate distorted textures. A similarity metric in the image space is formulated based on combining self-structural constraint with intensity to strengthen the robustness to abnormal intensity change compared with common intensity-based metrics. The proposed framework takes two discriminators as feature extractors to formulate the texture and content similarity between the registered image and the fixed image in the multiscale feature space respectively. A distinctive alternating training strategy is established to jointly optimize the combination of various similarity loss functions to overcome the difficulty and instability of training convergence and balance the training of generator and discriminators.Main results.Compared with five registration methods, the proposed method is evaluated both with small and large deformations, and achieves the best registration accuracy with average target registration error of 1.089 mm and 2.139 mm in cases of small and large deformations, respectively. The performance on peak signal to noise ratio (PSNR) and structural similarity (SSIM) also proves the effective constraints on distorted textures of the proposed method (PSNR is 31.693 dB and SSIM is 0.9 in the case of small deformation; PSNR is 28.177 dB and SSIM is 0.853 in the case of large deformation).Significance.The proposed 3D ultrasound non-rigid registration method based on texture and content constraints with the distinctive alternating training strategy can eliminate the distorted textures with improving the registration accuracy.
Imaging, Three-Dimensional , Magnetic Resonance Imaging , Magnetic Resonance Imaging/methods , Imaging, Three-Dimensional/methods , Ultrasonography , Signal-To-Noise Ratio , Motion , Image Processing, Computer-Assisted/methods
Alginate has been documented to prevent the development and progression of ulcerative colitis by modulating the gut microbiota. However, the bacterium that may mediate the anti-colitis effect of alginate has not been fully characterized. We hypothesized that alginate-degrading bacteria might play a role here since these bacteria could utilize alginate as a carbon source. To test this hypothesis, we isolated 296 strains of alginate-degrading bacteria from the human gut. Bacteroides xylanisolvens AY11-1 was observed to have the best capability for alginate degradation. The degradation and fermentation of alginate by B. xylanisolvens AY11-1 produced significant amounts of oligosaccharides and short-chain fatty acids. Further studies indicated that B. xylanisolvens AY11-1 could alleviate body weight loss and contraction of colon length, reduce the incidences of bleeding and attenuate mucosal damage in dextran sulfate sodium (DSS)-fed mice. Mechanistically, B. xylanisolvens AY11-1 improved gut dysbiosis and promoted the growth of probiotic bacteria, including Blautia spp. And Prevotellaceae UCG-001, in diseased mice. Additionally, B. xylanisolvens AY11-1 showed no oral toxicity and was well-tolerated in male and female mice. Altogether, we illustrate for the first time an anti-colitis effect of the alginate-degrading bacterium B. xylanisolvens AY11-1. Our study paves the way for the development of B. xylanisolvens AY11-1 as a next-generation probiotic bacterium.
Colitis , Gastrointestinal Microbiome , Probiotics , Humans , Male , Female , Animals , Mice , Alginates/pharmacology , Colitis/chemically induced , Colitis/prevention & control , Colitis/microbiology , Colon/metabolism , Bacteria/metabolism , Dextran Sulfate/pharmacology , Mice, Inbred C57BL , Disease Models, Animal
X-ray tomography has been widely used in various research fields thanks to its capability of observing 3D structures with high resolution non-destructively. However, due to the nonlinearity and inconsistency of detector pixels, ring artifacts usually appear in tomographic reconstruction, which may compromise image quality and cause nonuniform bias. This study proposes a new ring artifact correction method based on the residual neural network (ResNet) for X-ray tomography. The artifact correction network uses complementary information of each wavelet coefficient and a residual mechanism of the residual block to obtain high-precision artifacts through low operation costs. In addition, a regularization term is used to accurately extract stripe artifacts in sinograms, so that the network can better preserve image details while accurately separating artifacts. When applied to simulation and experimental data, the proposed method shows a good suppression of ring artifacts. To solve the problem of insufficient training data, ResNet is trained through the transfer learning strategy, which brings advantages of robustness, versatility and low computing cost.
PROPOSE: Multimodal registration of 2D Ultrasound (US) and 3D Magnetic Resonance (MR) for fusion navigation can improve the intraoperative detection accuracy of lesion. However, multimodal registration remains a challenge because of the poor US image quality. In the study, a weighted self-similarity structure vector (WSSV) is proposed to registrate multimodal images. METHOD: The self-similarity structure vector utilizes the normalized distance of symmetrically located patches in the neighborhood to describe the local structure information. The texture weights are extracted using the local standard deviation to reduce the speckle interference in the US images. The multimodal similarity metric is constructed by combining a self-similarity structure vector with a texture weight map. RESULTS: Experiments were performed on US and MR images of the liver from 88 groups of data including 8 patients and 80 simulated samples. The average target registration error was reduced from 14.91 ± 3.86 mm to 4.95 ± 2.23 mm using the WSSV-based method. CONCLUSIONS: The experimental results show that the WSSV-based registration method could robustly align the US and MR images of the liver. With further acceleration, the registration framework can be potentially applied in time-sensitive clinical settings, such as US-MR image registration in image-guided surgery.
Algorithms , Magnetic Resonance Imaging , Humans , Magnetic Resonance Imaging/methods , Ultrasonography/methods , Liver/diagnostic imaging , Imaging, Three-Dimensional/methods
Background: Prostate cancer is the second leading cause of cancer-related death among males in America. The patients' survival time is significantly reduced after prostate cancer develops into castration-resistant prostate cancer (CRPC). It has been reported that AKR1C3 is involved in this progression, and that its abnormal expression is directly correlated with the degree of CRPC malignancy. Genistein is one of the active components of soy isoflavones, and many studies have suggested that it has a better inhibitory effect on CRPC. Objective: This study aimed to investigate the antitumor effect of genistein on CRPC and the potential mechanism of action. Design: A xenograft tumor mouse model established with 22RV1 cells was divided into the experimental group and the control group, and the former was given 100 mg/kg.bw/day of genistein, with 22RV1, VCaP, and RWPE-1 cells cultured in a hormone-free serum environment and treated with different concentrations of genistein (0, 12.5, 25, 50, and 100 µmol/L) for 48 h. Molecular docking was used to elucidate the molecular interactions between genistein and AKR1C3. Results: Genistein inhibits CRPC cell proliferation and in vivo tumorigenesis. The western blot analysis confirmed that the genistein significantly inhibited prostate-specific antigen production in a dose-dependent manner. In further results, AKR1C3 expression was decreased in both the xenograft tumor tissues and the CRPC cell lines following genistein gavage feeding compared to the control group, with the reduction becoming more obvious as the concentration of genistein was increased. When the genistein was combined with AKR1C3 small interfering ribonucleic acid and an AKR1C3 inhibitor (ASP-9521), the inhibitory effect on the AKR1C3 was more pronounced. In addition, the molecular docking results suggested that the genistein had a strong affinity with the AKR1C3, and that it could be a promising AKR1C3 inhibitor. Conclusion: Genistein inhibits the progression of CRPC via the suppression of AKR1C3.
