Accurate Image Research Articles

Neuropathologic Validation and Diagnostic Accuracy of Presynaptic Dopaminergic Imaging in the Diagnosis of Parkinsonism.

Degeneration of the presynaptic nigrostriatal dopaminergic system is one of the main biological features of Parkinson disease (PD), multiple system atrophy (MSA), progressive supranuclear palsy (PSP), and corticobasal degeneration (CBD), which can be measured using single-photon emission CT imaging for diagnostic purposes. Despite its widespread use in clinical practice and research, the diagnostic properties of presynaptic nigrostriatal dopaminergic (DAT) imaging in parkinsonism have never been evaluated against the diagnostic gold standard of neuropathology. The aim of this study was to evaluate the diagnostic parameters of DAT imaging compared with pathologic diagnosis in patients with parkinsonism. Retrospective cohort study of patients with DAT imaging for the investigation of a clinically uncertain parkinsonism with brain donation between 2010 and 2021 to the Queen Square Brain Bank (London). Patients with DAT imaging for investigation of pure ataxia or dementia syndromes without parkinsonism were excluded. Those with a pathologic diagnosis of PD, MSA, PSP, or CBD were considered presynaptic dopaminergic parkinsonism, and other pathologies were considered postsynaptic for the analysis. DAT imaging was performed in routine clinical practice and visually classified by hospital nuclear medicine specialists as normal or abnormal. The results were correlated with neuropathologic diagnosis to calculate diagnostic accuracy parameters for the diagnosis of presynaptic dopaminergic parkinsonism. All of 47 patients with PD, 41 of 42 with MSA, 68 of 73 with PSP, and 6 of 10 with CBD (sensitivity 100%, 97.6%, 93.2%, and 60%, respectively) had abnormal presynaptic dopaminergic imaging. Eight of 17 patients with presumed postsynaptic parkinsonism had abnormal scans (specificity 52.9%). DAT imaging has very high sensitivity and negative predictive value for the diagnosis of presynaptic dopaminergic parkinsonism, particularly for PD. However, patients with CBD, and to a lesser extent PSP (of various phenotypes) and MSA (with predominant ataxia), can show normal DAT imaging. A range of other neurodegenerative disorders may have abnormal DAT scans with low specificity in the differential diagnosis of parkinsonism. DAT imaging is a useful diagnostic tool in the differential diagnosis of parkinsonism, although clinicians should be aware of its diagnostic properties and limitations. This study provides Class II evidence that DAT imaging does not accurately distinguish between presynaptic dopaminergic parkinsonism and non-presynaptic dopaminergic parkinsonism.

A target-triggered strand displacement-assisted target recycling based on carbon dots-based fluorescent probe and MSNs@PDA nanoparticles for miRNA amplified detection and fluorescence imaging.

A target-triggered strand displacement-assisted target recycling based on carbon dots-based fluorescent probe and mesoporous silica nanoparticles@polydopamine (MSNs@PDA) was established to detect miRNA. The surface of MSNs rich in mesopores was coated with a layer of PDA, which can adsorb and quench the fluorescence of single-stranded Fuel DNA with fluorescent carbon dots (CDs) modified at the end through fluorescence resonance energy transfer (FRET). After adding double-stranded DNA-gold nanoparticles (dsDNA-AuNPs) and target let-7a, it will trigger two toehold-mediated strand displacement reactions (TSDR), leading to the recovery of fluorescence and the recycling of target let-7a (excitation wavelength: 380nm; emission wavelength: 458nm). The recovery value of fluorescence is proportional to the logarithm of the target microRNA let-7a concentration, thus realizing the sensitivity amplification detection of disease markers. The MSNs@PDA@Fuel DNA-CDs/dsDNA-AuNPs nanoplatform based on the strategy of "on-off-on" and TSDR cyclic amplification may hold great potential as an effective and safe nanoprobe for accurate fluorescence imaging of diseases related to miRNA with low abundances.

Dual-Stream CoAtNet models for accurate breast ultrasound image segmentation

Dual-Stream CoAtNet models for accurate breast ultrasound image segmentation

Exploring the Differences in Tree Species Classification between Typical Forest Regions in Northern and Southern China

Focusing on the trend of continuously seeking high-precision tree species classification results in small areas from the perspectives of sensors and classification algorithms. This study aimed to explore the effects of data sources, classifiers, and seasons on classification accuracy in regions with significant environmental variation, examining patterns of tree species classification to enhance the transferability of classification. Considering two typical forest distribution regions in the north and south of China, this study utilized the revisitation cycle and open-source advantages of Sentinel-2 and Landsat-8. Leveraging the Google Earth Engine (GEE) platform, this study captured spectral features, vegetation indices, and texture features for single seasonal and seasonal combination images. With the assistance of Sentinel-1A and SRTM (Shuttle Radar Topography Mission) DEM (Digital Elevation Model), backscattering coefficient features and topographical features were extracted and input with features captured from Sentinel-2 and Landsat-8 into three types of classifiers: random forest (RF), support vector machine (SVM), and gradient tree boosting (GTB) for major tree species classification. In this research, we discovered that the best classification for single season in the northern study area was spring, whereas, for the southern study area, it was winter. Seasonal combination images effectively improved the classification accuracy of single seasonal images, with Sentinel-2 imagery displaying better classification performance compared to Landsat-8, and the optimal classifier differing between the north and the south. The inclusion of topographical or backscattering coefficient features in the four-season combination imagery contributed to improvements in classification accuracy, with topographical features significantly enhancing the classification performance in the topographically varied southern study area. The evaluation of feature importance indicated that elevation was the most critical feature for classification, while spectral features and vegetation indices were also significant. In the southern study area with large topographical discrepancies, subdividing into different terrain units led to improved tree species classification accuracy in medium-altitude, gentle slope areas. These findings provide insights into the regularity of enhancing tree species classification accuracy in environmentally diverse areas through the use of multi-source remote sensing data and multi-seasonal imagery. Consequently, the results offer a reference for the identification of tree species across large areas and the creation of spatial distribution maps.

DNA-Mediated Magnetic-Dimer Assembly for Fault-Free Ultra-High-Field Magnetic Resonance Imaging of Tumors.

Ultra-high-field (UHF) magnetic resonance imaging (MRI) stands as a pivotal cornerstone in biomedical imaging, yet the challenge of false imaging persists, constraining its full potential. Despite the development of dual-mode contrast agents improving conventional MRI, their effectiveness in UHF remains suboptimal due to the high magnetic moment, resulting in diminished T1 relaxivity and excessively enhanced T2 relaxivity. Herein, we report a DNA-mediated magnetic-dimer assembly (DMA) of iron oxide nanoparticles that harnesses UHF-tailored nanomagnetism for fault-free UHF-MRI. DMA exhibits a dually enhanced longitudinal relaxivity of 4.42 mM-1·s-1 and transverse relaxivity of 26.23 mM-1·s-1 at 9 T, demonstrating a typical T1-T2 dual-mode UHF-MRI contrast agent. Importantly, DMA leverages T1-T2 dual-modality image fusion to achieve artifact-free breast cancer visualization, effectively filtering interference from hundred-micrometer-level false-positive signals with unprecedented precision. The UHF-tailored T1-T2 dual-mode DMA contrast agents hold promise for elevating the accuracy of MR imaging in disease diagnosis.

Accuracy of optical diagnosis with narrow band imaging in the surveillance of ulcerative colitis: a prospective study comparing Kudo, Kudo-IBD and NICE classifications

PurposeThe diagnostic accuracy of Narrow Band Imaging (NBI) in the endoscopic surveillance of ulcerative colitis (UC) has been disappointing in most trials which used the Kudo classification. We aim to compare the performance of NBI in the lesion characterization of UC, when applied according to three different classifications (NICE, Kudo, Kudo-IBD).MethodsIn a prospective, real-life study, all visible lesions found during consecutive surveillance colonoscopies with NBI (Exera-II CV-180) for UC were classified as suspected or non-suspected for neoplasia according to the NICE, Kudo and Kudo-IBD criteria. The sensitivity (SE), specificity (SP), positive (+LR) and negative (-LR) likelihood ratios of the three classifications were calculated, using histology as the reference standard.Results394 lesions (mean size 6 mm, range 2–40 mm) from 84 patients were analysed. Twenty-one neoplastic (5%), 49 hyperplastic (12%), and 324 inflammatory (82%) lesions were found. The diagnostic accuracy of the NICE, Kudo and Kudo-IBD classifications were, respectively: SE 76%-71%-86%; SP 55-69%-79% (p < 0.05 Kudo-IBD vs. both Kudo and NICE); +LR 1.69-2.34-4.15 (p < 0.05 Kudo-IBD vs. both Kudo and NICE); -LR 0.43-0.41-0.18.ConclusionThe diagnostic accuracy of NBI in the differentiation of neoplastic and non-neoplastic lesions in UC is low if used with conventional classifications of the general population, but it is significantly better with the modified Kudo classification specific for UC.

Robust distance measurement using illumination map estimation and MAHNet in underground coal mines

An effective binocular stereo distance measurement method is proposed to address challenges posed by low brightness and weak texture of images captured in underground coal mines for the machine vision method. This approach is based on illumination map estimation and the MobileNetV3 attention hourglass stereo matching network (MAHNet) model. First, a binocular stereo vision system is established in which infrared LEDs are uniformly distributed on both sides of the belt conveyor bracket as visual feature points. Second, images are preprocessed using illumination map estimation, and the optimization of inhomogeneous brightness image enhancement is achieved by adopting adaptive Gamma correction. Third, the YOLOv5 target detection network and Gaussian fitting fusion algorithm are utilized to detect infrared LED feature points. Fourth, the MAHNet model is employed to generate the cost volume and perform disparity regression, resulting in the acquisition of accurate disparity images. Finally, triangulation is applied to determine the depth of feature points. The experimental results of distance measurement demonstrate that an average relative ranging accuracy of 1.52% within the range of 50.0 cm to 250.0 cm can be achieved by the optimized method, thereby validating the effectiveness of this binocular distance measurement method in underground coal mines.

Development of an Optical System for Strain Drop Measurement of Osteosarcoma Cells on Substrates with Different Stiffness

Adherent cells perceive mechanical feedback from the underlying matrix and convert it into biochemical signals through a process known as mechanotransduction. The response to changes in the microenvironment relies on the cell’s mechanical properties, including elasticity, which was recently identified as a biomarker for various diseases. Here, we propose the design, development, and characterization of a new system for the measurement of adherent cells’ strain drop, a parameter correlated with cells’ elasticity. To consider the interplay between adherent cells and the host extracellular matrix, cell stretching was combined with adhesion on substrates with different stiffnesses. The technique is based on the linear stretching of silicone chambers, high-speed image acquisition, and feedback for image centering. The system was characterized in terms of the strain homogeneity, impact of collagen coating, centering capability, and sensitivity. Subsequently, it was employed to measure the strain drop of two osteosarcoma cell lines, low-aggressive osteoblast-like SaOS-2 and high-aggressive 143B, cultured on two different substrates to recall the stiffness of the bone and lung extracellular matrices. Results demonstrated good substrate homogeneity, a negligible effect of the collagen coating, and an accurate image centering. Finally, the experimental results showed an average strain drop that was lower in the 143B cells in comparison with the SaOS-2 cells in all the tested conditions.

Implementation of Text to Image using Diffusion Model

Text-to-image generation is a transformative field in artificial intelligence, aiming to bridge the semantic gap between textual descriptions and visual representations. This presents a comprehensive approach to tackle this challenging task. Leveraging the advancements in deep learning, natural language processing (NLP), and computer vision, this proposes a cutting-edge model for generating high-fidelity images from textual prompts. Trained on a vast and varied dataset of written descriptions and related images, this model combines an image decoder and a text encoder within a hierarchical framework. To enhance realism, this incorporates attention mechanisms and fine-grained semantic parsing. The model's performance is rigorously evaluated through both quantitative metrics and qualitative human assessments. Results demonstrate its ability to produce visually compelling and contextually accurate images across various domains, from natural scenes to specific object synthesis. This further explores applications in creative content generation, design automation, and virtual environments, showcasing the potential impact of our approach. Additionally, this releases a user-friendly API, empowering developers and designers to integrate our model into their projects, and fostering innovation and creativity. Key Words: image generation model, Deep learning, Natural language processing.

Bridge crack segmentation and measurement based on SOLOv2 segmentation model

With the continuous increase of vehicular traffic, the safety caused by bridge crack damage is becoming increasingly prominent. Bridge crack analysis and measurement are of great significance for promoting road traffic safety. However, existing bridge crack image segmentation methods have shortcomings in processing image detail features, resulting in the inability to better measure the actual size of bridge cracks. Therefore, to further optimize the calculation method, a bridge crack image segmentation method based on improved SOLOv2 is designed to achieve more accurate bridge image segmentation. Based on the image segmentation results and combined with the skeleton data extraction method, a bridge crack calculation method is designed. From the results, the segmentation accuracy for crack images was 92.05 % and 93.57 %, respectively. The average mIoU of AM-SOLOv2 method was 0.75, significantly lower than commonly used crack image segmentation methods. In addition, the mIoU value variation amplitude of the AM-SOLOv2 method was relatively smaller. The crack length and width errors were within 0.05 mm and 0.06 mm, significantly lower than the comparison method. It indicates that this method can achieve more accurate crack image segmentation and calculation. This is beneficial for a deeper understanding of the performance degradation and crack damage evolution of bridge structures, thereby improving bridge design and construction technology.

Art or Artifact: Evaluating the Accuracy, Appeal, and Educational Value of AI-Generated Imagery in DALL·E 3 for Illustrating Congenital Heart Diseases.

Artificial Intelligence (AI), particularly AI-Generated Imagery, has the potential to impact medical and patient education. This research explores the use of AI-generated imagery, from text-to-images, in medical education, focusing on congenital heart diseases (CHD). Utilizing ChatGPT's DALL·E 3, the research aims to assess the accuracy and educational value of AI-created images for 20 common CHDs. In this study, we utilized DALL·E 3 to generate a comprehensive set of 110 images, comprising ten images depicting the normal human heart and five images for each of the 20 common CHDs. The generated images were evaluated by a diverse group of 33 healthcare professionals. This cohort included cardiology experts, pediatricians, non-pediatric faculty members, trainees (medical students, interns, pediatric residents), and pediatric nurses. Utilizing a structured framework, these professionals assessed each image for anatomical accuracy, the usefulness of in-picture text, its appeal to medical professionals, and the image's potential applicability in medical presentations. Each item was assessed on a Likert scale of three. The assessments produced a total of 3630 images' assessments. Most AI-generated cardiac images were rated poorly as follows: 80.8% of images were rated as anatomically incorrect or fabricated, 85.2% rated to have incorrect text labels, 78.1% rated as not usable for medical education. The nurses and medical interns were found to have a more positive perception about the AI-generated cardiac images compared to the faculty members, pediatricians, and cardiology experts. Complex congenital anomalies were found to be significantly more predicted to anatomical fabrication compared to simple cardiac anomalies. There were significant challenges identified in image generation. Based on our findings, we recommend a vigilant approach towards the use of AI-generated imagery in medical education at present, underscoring the imperative for thorough validation and the importance of collaboration across disciplines. While we advise against its immediate integration until further validations are conducted, the study advocates for future AI-models to be fine-tuned with accurate medical data, enhancing their reliability and educational utility.

Concordance Rate of Pre-Operative Radiological Stage with Postoperative Pathological Stage in Colon Cancer

Aim: This study aimed to assess the concordance rate between pre-operative radiological staging using CT imaging and postoperative pathological staging in patients with colon cancer. Methodology: A prospective observational study was conducted at the Oncology Department of Jinnah Postgraduate Medical Center, Pakistan, with ethical committee approval between February 2023 to July 2023. Inclusion criteria involved patients diagnosed with colon adenocarcinoma aged &gt;18 receiving treatment at the center, while exclusion criteria comprised unconfirmed colon cancer, lack of consent, benign colonic polyps, metastatic cancer, chemotherapy recipients, and incomplete data. Sample size estimation yielded 227 patients. Recruitment used consecutive sampling, and data were collected using a predefined proforma. CT scans were performed, and T-stage was assessed by radiologists and pathologists. Histological analysis followed established guidelines, with final pathology serving as the gold standard. Results: The diagnostic accuracy of CT imaging was evaluated, with statistically significant concordance found between CT scans and histopathological diagnoses (p-value = 0.046). CT scans demonstrated a sensitivity of 57.14% for Stage I tumors and a specificity of 88.18% for Stage II-III tumors. The positive predictive value (PPV) was 13.3%, and the negative predictive value (NPV) was 98.48%, resulting in an overall accuracy of 87.22%. These findings suggest that CT imaging is valuable for identifying Stage II-III tumors, exhibiting good specificity and NPV, although sensitivity and PPV for Stage I tumors were comparatively lower. Chi-square testing confirmed the statistical significance of these results (p-value ≤ 0.05) Conclusion: This study highlights the utility of CT imaging in pre-operative staging of colon cancer, particularly for Stage II-III tumors, where it exhibits notable accuracy. However, improvements may be needed to enhance sensitivity and PPV for Stage I tumors. Keywords: Colon cancer, CT imaging, pathological staging, concordance rate, diagnostic accuracy.

Advances in 3D Inner Ear Reconstruction Software for Cochlear Implants: A Comprehensive Review

Auditory impairment stands as a pervasive global issue, exerting significant effects on individuals’ daily functioning and interpersonal engagements. Cochlear implants (CIs) have risen as a cutting-edge solution for severe to profound hearing loss, directly stimulating the auditory nerve with electrical signals. The success of CI procedures hinges on precise pre-operative planning and post-operative evaluation, highlighting the significance of advanced three-dimensional (3D) inner ear reconstruction software. Accurate pre-operative imaging is vital for identifying anatomical landmarks and assessing cochlear deformities. Tools like 3D Slicer, Amira and OTOPLAN provide detailed depictions of cochlear anatomy, aiding surgeons in simulating implantation scenarios and refining surgical approaches. Post-operative scans play a crucial role in detecting complications and ensuring CI longevity. Despite technological advancements, challenges such as standardization and optimization persist. This review explores the role of 3D inner ear reconstruction software in patient selection, surgical planning, and post-operative assessment, tracing its evolution and emphasizing features like image segmentation and virtual simulation. It addresses software limitations and proposes solutions, advocating for their integration into clinical practice. Ultimately, this review underscores the impact of 3D inner ear reconstruction software on cochlear implantation, connecting innovation with precision medicine.

Magnetic resonance image reconstruction based on image decomposition constrained by total variation and tight frame.

Magnetic resonance imaging (MRI) is a commonly used tool in clinical medicine, but it suffers from the disadvantage of slow imaging speed. To address this, we propose a novel MRI reconstruction algorithm based on image decomposition to realize accurate image reconstruction with undersampled k-space data. In our algorithm, the MR images to be recovered are split into cartoon and texture components utilizing image decomposition theory. Different sparse transform constraints are applied to each component based on their morphological structure characteristics. The total variation transform constraint is used for the smooth cartoon component, while the L0 norm constraint of tight frame redundant transform is used for the oscillatory texture component. Finally, an alternating iterative minimization approach is adopted to complete the reconstruction. Numerous numerical experiments are conducted on several MR images and the results consistently show that, compared with the existing classical compressed sensing algorithm, our algorithm significantly improves the peak signal-to-noise ratio of the reconstructed images and preserves more image details. Our algorithm harnesses the sparse characteristics of different image components to reconstruct MR images accurately with highly undersampled data. It can greatly accelerate MRI speed and be extended to other imaging reconstruction fields.

Naturally biocompatible melanin based iron-complex nanoparticles for pH-responsive magnetic resonance imaging

The sensitivity and diagnostic accuracy of magnetic resonance imaging mainly depend on the relaxation capacity of contrast agents (CAs) and their accumulated amount at the pathological region. Due to the better biocompatibility and high-spin capacity, Fe-complexes have been studied widely as an alternative to replace popular Gd-based CAs associated with potential biotoxicity. Compared with a variety of Fe complex-based CAs, such as small molecular, macrocyclic, multinuclear complexes, the form of nanoparticle exhibits outstanding longitudinal relaxation, but the clinical transformation was still limited by the inconspicuous difference of contrast between tumor and normal tissue. The enhanced effect of contrast is a positive relation as relaxation of CAs and their concentration in desired region. To specifically improve the amount of CAs accumulated in the tumor, pH-responsive polymer poly(2-ethyl-2-oxazoline) (PEOz) was modified on melanin, a ubiquitous natural pigment providing much active sites for chelating with Fe(III). The Fe(III)-Mel-PEOz we prepared could raise the tumor cell endocytosis efficiency via switching surface charge from anion to cation with the stimuli of the decreasing pH of tumor microenvironment. The change of pH has negligible effect on the r 1 of Fe(III)-Mel-PEOz, which is always maintained at around 1.0 mM−1s−1 at 0.5 T. Moreover, Fe(III)-Mel-PEOz exhibited low cytotoxicity, and satisfactory enhancement of positive contrast effect in vivo. The excellent biocompatibility and stable relaxation demonstrate the high potential of Fe(III)-Mel-PEOz in the diagnosis of tumor.

Application of deep learning algorithms in classification and localization of implant cutout for the postoperative hip.

This study aims to explore the feasibility of employing convolutional neural networks for detecting and localizing implant cutouts on anteroposterior pelvic radiographs. The research involves the development of two Deep Learning models. Initially, a model was created for image-level classification of implant cutouts using 40191 pelvic radiographs obtained from a single institution. The radiographs were partitioned into training, validation, and hold-out test datasets in a 6/2/2 ratio. Performance metrics including the area under the receiver operator characteristics curve (AUROC), sensitivity, and specificity were calculated using the test dataset. Additionally, a second object detection model was trained to localize implant cutouts within the same dataset. Bounding box visualizations were generated on images predicted as cutout-positive by the classification model in the test dataset, serving as an adjunct for assessing algorithm validity. The classification model had an accuracy of 99.7%, sensitivity of 84.6%, specificity of 99.8%, AUROC of 0.998 (95% CI: 0.996, 0.999) and AUPRC of 0.774 (95% CI: 0.646, 0.880). From the pelvic radiographs predicted as cutout-positive, the object detection model could achieve 95.5% localization accuracy on true positive images, but falsely generated 14 results from the 15 false-positive predictions. The classification model showed fair accuracy for detection of implant cutouts, while the object detection model effectively localized cutout. This serves as proof of concept of using a deep learning-based approach for classification and localization of implant cutouts from pelvic radiographs.

Robust AI-Driven Segmentation of Glioblastoma T1c and FLAIR MRI Series and the Low Variability of the MRIMath© Smart Manual Contouring Platform

Patients diagnosed with glioblastoma multiforme (GBM) continue to face a dire prognosis. Developing accurate and efficient contouring methods is crucial, as they can significantly advance both clinical practice and research. This study evaluates the AI models developed by MRIMath© for GBM T1c and fluid attenuation inversion recovery (FLAIR) images by comparing their contours to those of three neuro-radiologists using a smart manual contouring platform. The mean overall Sørensen–Dice Similarity Coefficient metric score (DSC) for the post-contrast T1 (T1c) AI was 95%, with a 95% confidence interval (CI) of 93% to 96%, closely aligning with the radiologists’ scores. For true positive T1c images, AI segmentation achieved a mean DSC of 81% compared to radiologists’ ranging from 80% to 86%. Sensitivity and specificity for T1c AI were 91.6% and 97.5%, respectively. The FLAIR AI exhibited a mean DSC of 90% with a 95% CI interval of 87% to 92%, comparable to the radiologists’ scores. It also achieved a mean DSC of 78% for true positive FLAIR slices versus radiologists’ scores of 75% to 83% and recorded a median sensitivity and specificity of 92.1% and 96.1%, respectively. The T1C and FLAIR AI models produced mean Hausdorff distances (&lt;5 mm), volume measurements, kappa scores, and Bland–Altman differences that align closely with those measured by radiologists. Moreover, the inter-user variability between radiologists using the smart manual contouring platform was under 5% for T1c and under 10% for FLAIR images. These results underscore the MRIMath© platform’s low inter-user variability and the high accuracy of its T1c and FLAIR AI models.

Single-photon lidar depth imaging based on sparsity adaptive matching pursuit method

Photon counting lidar has the ability to detect weak echo photons. However, in imaging applications, a small number of echo signals obtained in a very short acquisition time cannot get an accurate image estimation through the photon arrival time distribution histogram. Therefore, high-precision and fast imaging of an object using a small amount of weak echo photon signals is urgent to be solved. In this work, a sparse adaptive matching pursuit (SAMP) algorithm is proposed to process the echo photons without prior information to obtain the effective photon interval, which improves the reconstruction quality and imaging speed. By constructing a non-coaxial scanning imaging system to detect the face model, it has been experimentally proven that the proposed algorithm can achieve depth and reflectance image estimation under the condition of low power and low acquisition time of 4µs per pixel on average, and the mean absolute error (MAE) value is reduced by about 10 times compared to conventional reconstruction algorithm.

Identification of Damaged Canopies in Farmland Artificial Shelterbelts Based on Fusion of Unmanned Aerial Vehicle LiDAR and Multispectral Features

With the decline in the protective function for agricultural ecosystems of farmland shelterbelts due to tree withering and dying caused by pest and disease, quickly and accurately identifying the distribution of canopy damage is of great significance for forestry management departments to implement dynamic monitoring. This study focused on Populus bolleana and utilized an unmanned aerial vehicle (UAV) multispectral camera to acquire red–green–blue (RGB) images and multispectral images (MSIs), which were fused with a digital surface model (DSM) generated by UAV LiDAR for feature fusion to obtain DSM + RGB and DSM + MSI images, and random forest (RF), support vector machine (SVM), maximum likelihood classification (MLC), and a deep learning U-Net model were employed to build classification models for forest stand canopy recognition for the four image types. The model results indicate that the recognition performance of RF is superior to that of U-Net, and U-Net performs better overall than SVM and MLC. The classification accuracy of different feature fusion images shows a trend of DSM + MSI images (Kappa = 0.8656, OA = 91.55%) &gt; MSI images &gt; DSM + RGB images &gt; RGB images. DSM + MSI images exhibit the highest producer’s accuracy for identifying healthy and withered canopies, with values of 95.91% and 91.15%, respectively, while RGB images show the lowest accuracy, with producer’s accuracy values of 79.3% and 78.91% for healthy and withered canopies, respectively. This study presents a method for identifying the distribution of Populus bolleana canopies damaged by Anoplophora glabripennis and healthy canopies using the feature fusion of multi-source remote sensing data, providing a valuable data reference for the precise monitoring and management of farmland shelterbelts.

Artificial Intelligence and Privacy

Modern Artificial Intelligence (AI) technologies have a rapidly growing impact on a wide range of human activities. AI methods are being used in varied domains such as healthcare, material science, infrastructure engineering, social media, surveillance technologies, and even artistic expression. They have been used for the purposes of drug discovery via protein folding prediction, power usage optimization through reinforcement learning, and facial recognition by means of image segmentation. Their effectiveness and wide-scale, unregulated deployment within our societies pose significant risks to our fundamental rights. Multiple existing AI methods have the potential to profoundly undermine our ability to safeguard our privacy. The societal impact of such AI models can be investigated through six concentric Heuristic Zones of privacy. These AI models can perform inferences regarding highly sensitive, personal information such as race, gender, and intelligence from seemingly innocuous data sources beyond the capabilities of human experts. They are capable of generating increasingly accurate text and image recreations of our thoughts from non-invasive brain activity recordings such as magnetoencephalography and functional magnetic resonance imaging. Furthermore, prospective AI technologies pose concerns about the existential risk to our civilization which extend beyond the erosion of privacy and other fundamental human rights.