Target Image Research Articles

SAC-GAN: Structure-Aware Image Composition.

We introduce an end-to-end learning framework for image-to-image composition, aiming to plausibly compose an object represented as a cropped patch from an object image into a background scene image. As our approach emphasizes more on semantic and structural coherence of the composed images, rather than their pixel-level RGB accuracies, we tailor the input and output of our network with structure-aware features and design our network losses accordingly, with ground truth established in a self-supervised setting through the object cropping. Specifically, our network takes the semantic layout features from the input scene image, features encoded from the edges and silhouette in the input object patch, as well as a latent code as inputs, and generates a 2D spatial affine transform defining the translation and scaling of the object patch. The learned parameters are further fed into a differentiable spatial transformer network to transform the object patch into the target image, where our model is trained adversarially using an affine transform discriminator and a layout discriminator. We evaluate our network, coined SAC-GAN, for various image composition scenarios in terms of quality, composability, and generalizability of the composite images. Comparisons are made to state-of-the-art alternatives, including Instance Insertion, ST-GAN, CompGAN and PlaceNet, confirming superiority of our method.

Motion-Compensated MR CINE Reconstruction With Reconstruction-Driven Motion Estimation.

In cardiac CINE, motion-compensated MR reconstruction (MCMR) is an effective approach to address highly undersampled acquisitions by incorporating motion information between frames. In this work, we propose a novel perspective for addressing the MCMR problem and a more integrated and efficient solution to the MCMR field. Contrary to state-of-the-art (SOTA) MCMR methods which break the original problem into two sub-optimization problems, i.e. motion estimation and reconstruction, we formulate this problem as a single entity with one single optimization. Our approach is unique in that the motion estimation is directly driven by the ultimate goal, reconstruction, but not by the canonical motion-warping loss (similarity measurement between motion-warped images and target images). We align the objectives of motion estimation and reconstruction, eliminating the drawbacks of artifacts-affected motion estimation and therefore error-propagated reconstruction. Further, we can deliver high-quality reconstruction and realistic motion without applying any regularization/smoothness loss terms, circumventing the non-trivial weighting factor tuning. We evaluate our method on two datasets: 1) an in-house acquired 2D CINE dataset for the retrospective study and 2) the public OCMR cardiac dataset for the prospective study. The conducted experiments indicate that the proposed MCMR framework can deliver artifact-free motion estimation and high-quality MR images even for imaging accelerations up to 20x, outperforming SOTA non-MCMR and MCMR methods in both qualitative and quantitative evaluation across all experiments. The code is available at https://github.com/JZPeterPan/MCMR-Recon-Driven-Motion.

Enabling Space-Based Computed Cloud Tomography with a Mixed Integer Linear Programming Scheduler

Cumuliform clouds in Earth’s lower atmosphere play important roles in the radiative balance and hydrological cycle of the climate system. Yet key processes unfolding in these clouds, such as aerosol interactions and precipitation initiation, are still poorly understood. Current space-based cloud observation methods are inadequate for inferring the internal structure of clouds outside of a narrow transect that is probed actively by radar and lidar. Cloud tomography is an emerging technique that uses passive imaging of a cloud target from multiple locations with a large angular range to infer internal cloud structure. Many low convective clouds only have a lifetime of 15–25 min, necessitating autonomous scheduling of observation targets as they appear. Onboard autonomous scheduling is formulated as a mixed-integer optimization problem (MILP) with a finite time horizon and a reward scheme designed to maximize the angular range of the observations. A finite time horizon MILP scheduler is well suited to this mission because the short lifetime of low convective clouds creates a natural time horizon. This MILP can solve for an optimal observation schedule in a maximum time of 15 ms on a desktop CPU. The MILP scheduler is able to observe nearly 60% more targets than a conventional push-broom camera configuration. This initial result is promising and demonstrates the need for continued research in this area.

Autonomous Trajectory Planning for Ultrasound-Guided Real-Time Tracking of Suspicious Breast Tumor Targets

Ultrasound image guidance could display the movement of soft tissue in real time, which provides an important basis for the operation path selection of tumor for examinations and interventions such as precise localization and puncture biopsy. However, factors such as tissue deformation, patient motion, and instrument contact pose great challenges for real-time smooth localization tracking of target tissues and maintaining a suitable acoustic window. Not only does it reduce the accuracy of ultrasound examination, but also may prolong the examination time. In this paper, a real-time autonomous ultrasound robot trajectory planning framework is proposed to achieve global scanning of breast tissue and real-time local tracking of suspicious tumor targets. In addition, an ultrasound suspicious tumor target next moment motion attitude and position estimation algorithm and an acceleration-continuous online trajectory generation (ACOTG) algorithm are proposed. Experiments on breast phantom showed that the fluctuation difference of both global scanning and tracking scanning force was less than 5 N <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\pm$</tex-math> </inline-formula> 15%, and ACOTG takes less than 1 microsecond to calculate the next moment state. The position, velocity, and acceleration of the tracking path did not change abruptly when the unknown target changed. The ultrasound image of the suspected tumor target could always be smoothly maintained in a suitable acoustic window, while the errors between the center of the suspected tumor target image and the center of the acoustic window in the horizontal direction and the depth direction were less than <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\pm$</tex-math> </inline-formula> 1 mm and 30 mm <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\pm$</tex-math> </inline-formula> 10%, respectively. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The motivation of this study was to solve the clinical problem of difficulty in keeping the suspected breast tumor target stably in the center of the field of view under the influence of tissue deformation, patient motion and instrument contact in ultrasound guidance. We proposed the idea of global conventional scanning and local online tracking to achieve the autonomous scanning, detecting and tracking of suspicious tumor targets within the global scope of the breast. ACOTG algorithm is proposed and implemented, which can make the ultrasound image of suspicious tumor target can be displayed stably in the center of the acoustic window. With the help of this system, the accuracy of ultrasound examination can be improved and the time of examination can be reduced. The proposed system can also be applied to ultrasound scanning of other parts of the body.

Four-of-a-kind? Comprehensive atmospheric characterisation of the HR 8799 planets with VLTI/GRAVITY

With four companions at separations from 16 to 71 au, HR 8799 is a unique target for direct imaging, presenting an opportunity for a comparative study of exoplanets with a shared formation history. Combining new VLTI/GRAVITY observations obtained within the ExoGRAVITY program with archival data, we performed a systematic atmospheric characterisation across all four planets. We explored different levels of model flexibility to understand the temperature structure, chemistry, and clouds of each planet using both petitRADTRANS atmospheric retrievals and fits to self-consistent radiative–convective equilibrium models. Using Bayesian model averaging to combine multiple retrievals (a total of 89 across all four planets), we find that the HR 8799 planets are highly enriched in metals, with [M/H] ≳1, and have stellar to superstellar atmospheric C/O ratios. The C/O ratio increases with increasing separation from 0.55−0.10+0.12 for d to 0.78−0.04+0.03 for b, with the exception of the innermost planet, which has a C/O ratio of 0.87 ± 0.03. Such high metallicities are unexpected for these massive planets, and challenge planet-formation models. By retrieving a quench pressure and using a disequilibrium chemistry model, we derive vertical mixing strengths compatible with predictions for high-metallicity, self-luminous atmospheres. Bayesian evidence comparisons strongly favour the presence of HCN in HR 8799 c and e, as well as CH4 in HR 8799 c, with detections at &gt; 5σ confidence. All of the planets are cloudy, with no evidence of patchiness. The clouds of c, d, and e are best fit by silicate clouds lying above a deep iron cloud layer, while the clouds of the cooler HR 8799 b are more likely composed of Na2S. With well-defined atmospheric properties, future exploration of this system is well positioned to unveil further details of these planets, extending our understanding of the composition, structure, and formation history of these siblings.

Integrated geophysical Investigation for gold mineralization potential over southern parts of Kebbi state and its Environs, northwestern Nigeria

The potential zones of gold mineralization were identified in this study using aeromagnetic and aero-radiometric methods. The Nigerian Geological Survey Agency (NGSA) provided half-degree airborne magnetic and radiometric datasets covering the southern part of Kebbi State. Magnetic data were subjected to first vertical derivative (1VD), total gradient amplitude (TGA), total horizontal derivative (THD), source edge detection (SED), center for exploration targeting (CET), Euler deconvolution (ED) and source parameter imaging (SPI) to identify favourable structures to gold mineralization. Aero-radiometric data delineation of the region of hydrothermal alteration zones through the K/eTh ratio, K_deviation, F_parameters, and Ternary image analyses were successful. The results of the magnetic data techniques revealed the regions of major structures/or lineaments with gold mineralization attributes, trending in the NE to SW directions and the SE to NE parts of the study area. The depth to the structures of the magnetic source hosting gold mineralization was less than 5 m using algorithm ED and SPI techniques. Normalized radiometric data showed the area of anomalously high and moderate hydrothermal altered zones. The region's designation as a gold field is supported by major fault lines observed on the 1VD, a sequence of bristle fractures from the CET analysis, and high values of K_deviation and F_parameter, all of which are were visible on the Ternary images. The integrated results revealed zones of major structures and hydrothermal regions of gold fields at Agwara, Western Magama, Rijau, Fakai, Bukkuyum, and Borgu in the SE of the study area.

An attention mechanism network based on the winner-take-all

In the field of neurology, neurons compete for brain attention in winner-take-all (WTA) competitions. Inspired by this, we propose a new WTA-based attention network (called ANW), which can be extended to general neural networks. The ANW network simulates WTA behavior in biological neurons; that is, the winner neuron itself becomes excited and sends its own spike signal. Furthermore, the winner will output an inhibition signal, which will be input into the cell synapses of other neurons. The ANW network regards the update of neuron weights after backpropagation as a stimulus input to neurons. Combined with the WTA function, the neural network will continue to update until it reaches a stable state. In this way, the ANW network can find the most active neurons in the network and generate the winners among these neurons to improve the ability of the neural network to extract features. As the ANW is a small and universal network, it can be seamlessly inserted into any neural network architecture, with negligible overhead, and can be trained together with a basic CNN. We verified the neural network with ANW by using the ImageNet-100, CIFAR-100 and MS COCO detection datasets for the experiments. The experimental results show that, compared with those of the baseline network, the top-1 err gains of 0.63% and 3.85% can be achieved for ANW, with classical ResNet-50 as the backbone network, respectively, demonstrating that the method can improve the performance of the model in image classification and target detection with wide applicability. The proposed method provides an effective, and almost consumption-neutral solution, for performance improvement in the field of computer vision target detection.

Image Processing Technology Based on Machine Learning

Machine learning is a relatively new field. With the deepening of people's research in this field, the application of machine learning is increasingly extensive. On the other hand, with the development of science and technology, image has become an indispensable medium of information transmission, and image processing technology is also booming. This paper introduces machine learning into image processing, and studies the image processing technology based on machine learning. This paper summarizes the current popular image processing technology, compares various image technology in detail, and explains the limitations of each image processing method. In addition, on the basis of image processing, this paper introduces machine learning algorithm, applies convolution neural network to feature extraction of image processing, and carries out simulation test. In the test, we select voc2007 dataset for image segmentation, Imagenet dataset for target detection, cifar100 dataset for image classification, and ROC curve for performance evaluation. The results show that the algorithm based on deep learning can achieve high accuracy in image segmentation, classification and target detection. The accuracy of image segmentation is 0.984, the accuracy of image classification is 0.987, and the accuracy of target detection is 0.986. Image processing based on machine learning has great advantages.

Identity-Preserving Face Swapping via Dual Surrogate Generative Models

In this study, we revisit the fundamental setting of face-swapping models and reveal that only using implicit supervision for training leads to the difficulty of advanced methods to preserve the source identity. We propose a novel reverse pseudo-input generation approach to offer supplemental data for training face-swapping models, which addresses the aforementioned issue. Unlike the traditional pseudo-label-based training strategy, we assume that arbitrary real facial images could serve as the ground-truth outputs for the face-swapping network and try to generate corresponding input &lt; source, target &gt; pair data. Specifically, we involve a source-creating surrogate that alters the attributes of the real image while keeping the identity, and a target-creating surrogate intends to synthesize attribute-preserved target images with different identities. Our framework, which utilizes proxy-paired data as explicit supervision to direct the face-swapping training process, partially fulfills a credible and effective optimization direction to boost the identity-preserving capability. We design explicit and implicit adaption strategies to better approximate the explicit supervision for face swapping. Quantitative and qualitative experiments on FF++, FFHQ, and wild images show that our framework could improve the performance of various face-swapping pipelines in terms of visual fidelity and ID preserving. Furthermore, we display applications with our method on re-aging, swappable attribute customization, cross-domain, and video face swapping. Code is available under https://github.com/ICTMCG/CSCS.

AdaCS: Adaptive Compressive Sensing With Restricted Isometry Property-Based Error-Clamping.

Scene-dependent adaptive compressive sensing (CS) has been a long pursuing goal that has huge potential to significantly improve the performance of CS. However, with no access to the ground truth, how to design the scene-dependent adaptive strategy is still an open problem. In this paper, a restricted isometry property (RIP) condition-based error-clamping is proposed, which could directly predict the reconstruction error, i.e., the difference between the current-stage reconstructed image and the ground truth image, and adaptively allocate more samples to regions with larger reconstruction error at the next sampling stage. Furthermore, we propose a CS reconstruction network composed of Progressively inverse transform and Alternating Bi-directional Multi-grid Network, named PiABM-Net, that could efficiently utilize the multi-scale information for reconstructing the target image. The effectiveness of the proposed adaptive and cascaded CS method is demonstrated with extensive quantitative and qualitative experiments, compared with the state-of-the-art CS algorithms.

PMSGAN: Parallel Multistage GANs for Face Image Translation.

In this article, we address the face image translation task, which aims to translate a face image of a source domain to a target domain. Although significant progress has been made by recent studies, face image translation is still a challenging task because it has more strict requirements for texture details: even a few artifacts will greatly affect the impression of generated face images. Targeting to synthesize high-quality face images with admirable visual appearance, we revisit the coarse-to-fine strategy and propose a novel p arallel m ultistage architecture on the basis of g enerative a dversarial n etworks (PMSGAN). More specifically, PMSGAN progressively learns the translation function by disintegrating the general synthesis process into multiple parallel stages that take images with gradually decreasing spatial resolution as inputs. To prompt the information exchange between various stages, a cross-stage atrous spatial pyramid (CSASP) structure is specially designed to receive and fuse the contextual information from other stages. At the end of the parallel model, we introduce a novel attention-based module that leverages multistage decoded outputs as in situ supervised attention to refine the final activations and yield the target image. Extensive experiments on several face image translation benchmarks show that PMSGAN performs considerably better than state-of-the-art approaches.

Dotatate PET/CT and 225Ac-Dotatate Therapy for Somatostatin Receptor-expressing Metastatic Breast Cancer.

Background Somatostatin receptors, and specifically somatostatin receptor type 2 (SSTR2), have primarily been associated with neuroendocrine tumors and have revolutionized the imaging and therapy of patients with these tumors. SSTR2 is expressed on other tumors at lower prevalence. Purpose To evaluate the potential of SSTR2-targeted imaging and therapy in patients with breast cancer. Materials and Methods In a preclinical experiment, SSTR2 expression was assessed in tissue microarrays of breast cancer samples using H-score analysis. H-scores higher than 50 (0-300 scale) were considered positive. Then, a prospective phase 2 clinical trial of SSTR2-targeted tetraazacyclododecane tetraacetic acid octreotate (Dotatate) PET/CT was performed in participants with biopsy-proven estrogen receptor (ER)-positive breast cancer from January to August 2023. A positive Dotatate PET/CT scan was defined as tumors with a Krenning score of 3 (avidity greater than liver) or 4 (avidity greater than spleen). The proportion of positive scans and the 95% CI were calculated. One participant with metastatic ER-positive breast cancer and a Krenning 4 Dotatate PET/CT result underwent treatment with SSTR2-targeted actinium 225 (225Ac) Dotatate. Results Preclinical microarrays demonstrated that 63 of 123 ER-positive breast cancer tissue samples (51% [95% CI: 42, 60]) but only 22 of 121 ER-negative breast cancer tissue samples (18% [95% CI: 12, 26]) were enriched for SSTR2 (P < .001). Thirty female participants (mean age, 66 years ± 15) with metastatic ER-positive breast cancer were accrued to the phase 2 SSTR2-targeted imaging trial and underwent Dotatate PET/CT. Dotatate PET/CT demonstrated that nine of 30 participants (30% [95% CI: 15, 49]) had tumors with Krenning scores of 3 or 4, indicating strong SSTR2 expression. SSTR2-targeted therapy with alpha-emitting 225Ac-Dotatate resulted in a near complete response in a heavily pretreated participant with metastatic ER-positive breast cancer and a Krenning 4 Dotatate PET result. Conclusion Molecular imaging targeting SSTR2 and radioligand therapy with SSTR2-targeted 225Ac-Dotatate enables a new therapeutic option for patients with metastatic breast cancer. Clinical trial registration no. NCT05880394 © RSNA, 2024 See also the editorial by Lin and Choyke in this issue.

SIMCB-Yolo: An Efficient Multi-Scale Network for Detecting Forest Fire Smoke

Forest fire monitoring plays a crucial role in preventing and mitigating forest disasters. Early detection of forest fire smoke is essential for a timely response to forest fire emergencies. The key to effective forest fire monitoring lies in accounting for the various levels of forest fire smoke targets in the monitoring images, enhancing the model’s anti-interference capabilities against mountain clouds and fog, and reducing false positives and missed detections. In this paper, we propose an improved multi-level forest fire smoke detection model based on You Only Look Once v5s (Yolov5s) called SIMCB-Yolo. This model aims to achieve high-precision detection of forest fire smoke at various levels. First, to address the issue of low precision in detecting small target smoke, a Swin transformer small target monitoring head is added to the neck of Yolov5s, enhancing the precision of small target smoke detection. Then, to address the issue of missed detections due to the decline in conventional target smoke detection accuracy after improving small target smoke detection accuracy, we introduced a cross stage partial network bottleneck with three convolutional layers (C3) and a channel block sequence (CBS) into the trunk. These additions help extract more surface features and enhance the detection accuracy of conventional target smoke. Finally, the SimAM attention mechanism is introduced to address the issue of complex background interference in forest fire smoke detection, further reducing false positives and missed detections. Experimental results demonstrate that, compared to the Yolov5s model, the SIMCB-Yolo model achieves an average recognition accuracy (mAP50) of 85.6%, an increase of 4.5%. Additionally, the mAP50-95 is 63.6%, an improvement of 6.9%, indicating good detection accuracy. The performance of the SIMCB-Yolo model on the self-built forest fire smoke dataset is also significantly better than that of current mainstream models, demonstrating high practical value.

Advanced Method for Improving Marine Target Tracking Based on Multiple-Plot Processing of Radar Images

Advancements in technology have led to the development of high-resolution radars that provide highly detailed images of targets over a wide field of view. These radar images can significantly improve filtering and tracking accuracy, especially in marine environments. However, traditional methods like the binary and barycentric methods are inadequate, as they do not capture critical information for tracking targets, such as direction. Therefore, in this article, a new method for improving the estimation of target characteristics to improve tracking accuracy based on the processing of high-resolution radar images is proposed. The proposed method consists of three modules. Firstly, the radar images of the target are decomposed into layers to determine local maximum regions and to estimate target characteristics such as reflected energy and area and the centroids of plots. In the second module, the plots are grouped using a fuzzy logic system. The inputs of the fuzzy logic system include the above-estimated parameters of the targets. The output is the chance that the plot is at the center of the target. The plots with the highest chances are considered target centers, and the other plots are grouped into their respective target. At the end, the true target center is recalculated. This process is called modified fuzzy C-means (FCM-M). In the last stage, the estimated target center coordinates are fed into a Kalman filter (KF) to solve filtering and tracking problems. The performance is evaluated using a measured radar dataset. The experimental results show that the proposed method performs better than traditional methods based on binary image processing. Additionally, the proposed method offers extra information about the targets, such as their direction, the energy of each reflected part, and the area, which traditional methods does not provide.

Glass Defect Detection with Improved Data Augmentation under Total Reflection Lighting

To address the technical challenge of identifying tiny defects, especially dust and point defects, on mobile phone flat glass, an automatic optical inspection system is established. The system investigates algorithms including imaging principles, target detection models, data augmentation, foreground segmentation, and image fusion. The system builds an automatic optical inspection platform to collect glass defect samples. It illuminates the glass samples with a combined total reflection–grazing light source, collects the defect sample data, segments the background and defects of the collected data, generates the defect mask, and extracts the complete defects of the cell phone flat glass. The system then seamlessly integrates the extracted defects with a flawless background using Poisson editing and outputs the location information of the defects and the label output to automatically generate the dataset. The deep learning network YOLOv5 works as the core algorithm framework, into which the Constructive Block Attention Module and the small target detection layer are specifically added to enhance the capability of the model to detect small defects. According to the experimental results, the combined lighting effectively improves the precision of detecting dust and bright spots. Additionally, with the adoption of novel data augmentation techniques, the enhanced YOLOv5 model is capable of effectively addressing the challenges posed by inefficient sample data and non-uniform distribution, thus mitigating network generalization issues. Furthermore, this data augmentation approach facilitates the rapid adaptation of the same detection tasks to diverse environmental scenarios, enabling the expedited and efficient deployment of the model across various industrial settings. The mean average precision (MAP) of the optimal model in the validation set reached 98.36%, 2.62% higher than that of the original YOLOv5. In addition, its false acceptance rate (FAR) is 1.27%, its false rejection rate (FRR) was 2.47%, its detection speed was 64 fps, and its correct detection rate in the validation set was 98.75%, which meets the current industrial detection requirements by and large. In this way, this paper achieved the automated inspection of mobile phone flat glass with high robustness, high precision, and a low false acceptance rate and false rejection rate, significantly reducing material losses in the factories and the likelihood of error occurrence in follow-on products. This method can be applied to the multi-scale and multi-type detection of glass defects.

Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection.

This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola-Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates F1 scores below 26% in both spectra, while VJ's scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms' strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach.

Evaluation of a Positron Emission Tomography Tracer Targeting Colony-Stimulating Factor 1 Receptor for Detecting Pulmonary Inflammation.

Colony-stimulating factor 1 receptor (CSF1R) is a type III receptor tyrosine kinase that is crucial for immune cell activation, survival, proliferation, and differentiation. Its expression significantly increases in macrophages during inflammation, playing a crucial role in regulating inflammation resolution and termination. Consequently, CSF1R has emerged as a critical target for both therapeutic intervention and imaging of inflammatory diseases. Herein, we have developed a radiotracer, 1-[4-((7-(dimethylamino)quinazolin-4-yl)oxy)phenyl]-3-(4-[18F]fluorophenyl)urea ([18F]17), for in vivo positron emission tomography (PET) imaging of CSF1R. Compound 17 exhibits a comparable inhibitory potency against CSF1R as the well-known CSF1R inhibitor PLX647. The radiosynthesis of [18F]17 was successfully performed by radiofluorination of aryltrimethyltin precursor with a yield of approximately 12% at the end of synthesis, maintaining a purity exceeding 98%. In vivo stability and biodistribution studies demonstrate that [18F]17 remains >90% intact at 30 min postinjection, with no defluorination observed even at 60 min postinjection. The PET/CT imaging study in lipopolysaccharide-induced pulmonary inflammation mice indicates that [18F]17 offers a more sensitive characterization of pulmonary inflammation compared to traditional [18F]FDG. Notably, [18F]17 shows a higher discrepancy in uptake ratio between mice with pulmonary inflammation and the sham group. Furthermore, the variations in [18F]17 uptake ratio observed on day 7 and day 14 correspond to lung density changes observed in CT imaging. Moreover, the expression levels of CSF1R on day 7 and day 14 follow a trend similar to the uptake pattern of [18F]17, indicating its potential for accurately characterizing CSF1R expression levels and effectively monitoring the pulmonary inflammation progression. These results strongly suggest that [18F]17 has promising prospects as a CSF1R PET tracer, providing diagnostic opportunities for pulmonary inflammatory diseases.

Camera Pose Estimation Using a 3D Gaussian Splatting Radiance Field

Introduction. Accurate camera pose estimation is crucial for many applications ranging from robotics to virtual and augmented reality. The process of determining agents pose from a set of observations is called odometry. This work focuses on visual odometry, which utilizes only images from camera as the input data. The purpose of the paper is to demonstrate an approach for small-scale camera pose estimation using 3D Gaussians as the environment representation. Methods. Given the rise of neural volumetric representations for the environment reconstruction, this work relies on Gaussian Splatting algorithm for high-fidelity volumetric representation. Results. For a trained Gaussian Splatting model and the target image, unseen during training, we estimate its camera pose using differentiable rendering and gradient-based optimization methods. Gradients with respect to camera pose are computed directly from image-space per-pixel loss function via backpropagation. The choice of Gaussian Splatting as representation is particularly appealing because it allows for end-to-end estimation and removes several stages that are common for more classical algorithms. And differentiable rasterization as the image formation algorithm provides real-time performance which facilitates its use in real-world applications. Conclusions. This end-to-end approach greatly simplifies camera pose estimation, avoiding compounding errors that are common for multi-stage algorithms and provides a high-quality camera pose estimation. Keywords: radiance fields, scientific computing, odometry, slam, pose estimation, Gaussian Splatting, differentiable rendering.

Tuning Tumor Targeting and Ratiometric Photoacoustic Imaging by Fine-Tuning Torsion Angle for Colorectal Liver Metastasis Diagnosis.

Photoacoustic (PA) tomography is an emerging biomedical imaging technology for precision cancer medicine. Conventional small-molecule PA probes usually exhibit a single PA signal and poor tumor targeting that lack the imaging reliability. Here, we introduce a series of cyanine/hemicyanine interconversion dyes (denoted Cy-HCy) for PA/fluorescent dual-mode probe development that features optimized ratiometric PA imaging and tunable tumor-targeting ability for precise diagnosis and resection of colorectal cancer (CRC). Importantly, Cy-HCy can be presented in cyanine (inherent tumor targeting and long NIR PA wavelength) and hemicyanine (poor tumor targeting and short NIR PA wavelength) by fine-tuning torsion angle and the ingenious transformation between cyanine and hemicyanine through regulation optically tunable group endows the NIR ratiometric PA and tunable tumor-targeting properties. To demonstrate the applicability of Cy-HCy dyes, we designed the first small-molecule tumor-targeting and NIR ratiometric PA probe Cy-HCy-H2S for precise CRC liver metastasis diagnosis, activated by H2S (a CRC biomarker). Using this probe, we not only visualized the subcutaneous tumor and liver metastatic cancers in CRC mouse models but also realized PA and fluorescence image-guided tumor excision. We expect that Cy-HCy will be generalized for creating a wide variety of inherently tumor-targeting NIR ratiometric PA probes in oncological research and practice.

A Poly(amino acid)-Based Nanomedicine Strategy: Telomere-Telomerase Axis Targeting and Magnetic Resonance Imaging in Hepatocellular Carcinoma Treatment.

Targeting telomere maintenance has emerged as a promising strategy for hepatocellular carcinoma (HCC) treatment. However, given the duality of the telomere-telomerase axis in telomere maintenance, a comprehensive strategy is urgently needed. Herein, we develop a poly(amino acid) (D-PAAs)-based strategy for spatiotemporal codelivery of telomerase inhibitor, BIBR1523, and AKT inhibitor, isobavachalcone. By leveraging D-PAAs' modifiability, we synthesize polymer-inhibitor conjugates (PB and PI) and a folic acid-decorated tumor-targeting vector (PF). These building blocks undergo micellization to fabricate a codelivery nanomedicine (P-BI@P-FA) by exploiting D-PAAs' noncovalent assembly. P-BI@P-FA improves the pharmacokinetics, tumor selectivity, and bioavailability of small molecule inhibitors and initiates a dual telomere-specific inhibition by combining telomerase deactivation with telomere disruption. Furthermore, a hybrid tumor-targeting magnetic nanosystem is designed using D-PAAs and manganese dioxide to showcase magnetic resonance imaging capacities. Our D-PAAs-based strategy addresses the pressing need for telomere-specific HCC treatment while allowing for diagnostic application, presenting a promising avenue for nanomedicine design.