Image Data Processing Research Articles

Detecting damage in composites using volume decomposition analysis of tomographic data

Detection of damage in a single tow ceramic matrix composite specimen has been achieved using orthogonal decomposition of volumetric tomographic datasets collected at four tensile loads. This decomposition approach has been applied at two different length scales: (i) individual fibres and (ii) bulk volumes containing fibres and matrix material. Volumes were first decomposed to feature vectors, orders of magnitude smaller than the original volume they describe, and then comparisons between datasets at different load levels were made in feature vector space. The results show quantitative measurements of damage location, damage morphology and the relative growth of this damage with increased load when compared with a dataset with less or no damage. No prior knowledge of the dataset or training of algorithms is required for damage to be detected, it is only necessary that at least two datasets are available for comparison, e.g. from in situ or repeated scanning measurements. Results are generated on significantly shorter timescales when compared with previous automated approaches to tomography data processing. This approach has the potential to be applied to damage detection in a range of materials through comparisons of volumetric datasets from a range of measurement or computational techniques.

Mixed reality combined with surgical navigation technology assisted in parapharyngeal space tumors surgery: a clinical study

Objective: To assess the feasibility and application of mixed reality combined with surgical navigation technology in parapharyngeal space tumor surgery, and to provide a reference for the development and promotion of this technology. Methods: In this study, retrospective data collection was conducted on 16 patients with parapharyngeal space tumors who were treated at the Department of Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology from June 2020 to June 2023. The patient's age was (39.6±17.8) years, with 4 males and 12 females. Mixed reality combined with surgical navigation technology was utilized to assist physicians in the treatment of these patients. Mixed reality combined with surgical navigation technology was used to assist physicians in treatment of these patients. The application steps included acquisition of image data, processing of image data [three-dimensional (3D) reconstruction, image fusion, and virtual surgical design], development of surgical navigation plan, connection of mixed reality and navigation system, automatic registration and intraoperative guidance and validation. In the preoperative plan, landmark points were placed on the virtual tumor and surrounding important structures reconstructed using digital software, serving to guide the localization of crucial anatomical structures. Intraoperative positioning deviation, surgical time, intraoperative blood loss, and postoperative complications were recorded and analyzed to evaluate the clinical application effectiveness of mixed reality combined with surgical navigation technology. Results: With the assistance of mixed reality combined with surgical navigation technology, 16 patients successfully underwent tumor resection. All patients were accurately diagnosed preoperatively by 3D reconstruction and image fusion technology, and a comprehensive preoperative plan was formulated; intraoperatively, mixed reality combined with surgical navigation technology was utilized for the localization of important structures. The average localization deviation of 38 landmark points during the operation were (4.43±1.96) mm, with 62% (26/42) of the points having a deviation of ≥0 and<5 mm. The average duration of the operation was (149.6±53.9) min and the blood loss was 70 (45, 150) ml. The average postoperative follow-up was 16 months, and five patients experienced postoperative complications involving facial paralysis, hoarseness, and choking. Conclusions: Mixed reality combined with surgical navigation technology can achieve the three-dimensional visualization of oral and maxillofacial anatomical structures to achieve precise preoperative diagnosis. During surgery, the technology can real-time display the relationship between soft tissue tumors and the surrounding important anatomical structures, guide surgical operation, and enhance the safety of surgery.

Online Optical Axis Parallelism Measurement Method for Continuous Zoom Camera Based on High-Precision Spot Center Positioning Algorithm

Ensuring precise alignment of the optical axis is critical for achieving high-quality imaging in continuous zoom cameras. However, existing methods for measuring optical axis parallelism often lack accuracy and fail to assess parallelism across the entire focal range. This study introduces an online measurement method designed to address these limitations by incorporating two enhancements. First, image processing methodologies enable sub-pixel-level extraction of the spot center, achieved through improved morphological processing and the incorporation of an edge tracing algorithm. Second, measurement software developed using Qt Creator can output real-time data on optical axis parallelism across the full focal range post-measurement. This software features a multi-threaded architecture that facilitates the concurrent execution of image acquisition, data processing, and serial communication. Experimental results derived from simulations and real data indicate that the maximum average error in extracting the center of the spot is 0.13 pixels. The proposed system provides critical data for optical axis calibration during camera adjustment and inspection.

Design of pattern image generation technique based on self-attentive residual conditional generative adversarial network

Image generation techniques have made remarkable progress in the digital image processing and computer vision. However, traditional generation models cannot meet the complexity and diversity requirements of patterned images. In view of this, the study aims to enhance the quality of generated pattern images, which uses improved residual block, and introduces a self-attention mechanism to compute the weight parameters of the input features to enhance the accuracy. Comparing with three image generation models, the research model shows lower Frechette initial distance, which is better than the other three methods, and the average Frechette initial distance values in the four scenes are 175.23, 176.41, 174.41, and 165.23. Generated mouths and eyes: the average values of Frechette initial distances reach 98.23 and 97.24, respectively. For emotion classification, the Frechette initial distance averages for sad, excited, and calm emotions were 82.34, 75.63, and 70.21, respectively. The model was trained up to 2500 iterations, and the loss value was reduced to 0.54, with an accuracy of 98.23%, confirming its effectiveness and high performance. The self attention residual network enhances the model's ability to capture image details, effectively improving the quality and accuracy of image generation, and providing a new technological path for radiation imaging data processing and analysis in radiation science.

Image processing tools for petabyte-scale light sheet microscopy data.

Light sheet microscopy is a powerful technique for high-speed three-dimensional imaging of subcellular dynamics and large biological specimens. However, it often generates datasets ranging from hundreds of gigabytes to petabytes in size for a single experiment. Conventional computational tools process such images far slower than the time to acquire them and often fail outright due to memory limitations. To address these challenges, we present PetaKit5D, a scalable software solution for efficient petabyte-scale light sheet image processing. This software incorporates a suite of commonly used processing tools that are optimized for memory and performance. Notable advancements include rapid image readers and writers, fast and memory-efficient geometric transformations, high-performance Richardson-Lucy deconvolution and scalable Zarr-based stitching. These features outperform state-of-the-art methods by over one order of magnitude, enabling the processing of petabyte-scale image data at the full teravoxel rates of modern imaging cameras. The software opens new avenues for biological discoveries through large-scale imaging experiments.

Image Restoration of Electrical Well Logging Based on Fourier Convolution

Imaging logging is an important technical means in logging evaluation of complex reservoirs. Through imaging logging, a two-dimensional image of the resistivity distribution around the well can be obtained, which can be used to evaluate the development of well wall fractures and caves and the formation sedimentary structure. However, due to the characteristics of resistivity imaging logging instruments, blank strips will appear on the resistivity logging image, which increases the difficulty of computer processing of electrical imaging data. The current image repair method and the existing neural network image repair method are not effective enough when the part to be filled is large. Therefore, there is an urgent need for an intelligent repair method based on deep learning. Based on a fast Fourier convolution-based imaging logging image blank strip filling network, this paper constructs the electrical imaging logging images of the southwest oil and gas field as a data set, and trains a new deep learning algorithm for intelligent filling of blank strips in imaging logging images based on fast Fourier convolution. The time of various algorithms is compared. The results show that the algorithm has a better repair effect in imaging logging images with large strip widths, and the repair efficiency is significantly improved. This method can realize the rapid, accurate and intelligent repair of blank strips in imaging logging, achieve the rapid generation of full-borehole images, and solve the difficulties in obtaining full-borehole images.

EFFICIENCY AND ACCURACY OF CONVOLUTIONAL AND FOURIER TRANSFORM LAYERS IN NEURAL NETWORKS FOR MEDICAL IMAGE CLASSIFICATION

In an era where information flow is moving at a rapid pace, image data processing is becoming increasingly important as technology advances, including in healthcare. Convolutional Neural Network (CNN) has been a common approach in image classification, but the larger the volume of data and the complexity of the task, the more expensive the computational cost of CNN. With the rapid growth in the amount of image data, efficiency in data processing is becoming increasingly important. In this study, the performance of neural network models using the convolution layer and Fourier transform layer in medical image data classification was compared. The results show that models with a Fourier transform layer tend to provide higher accuracy and better Area Under Curve (AUC) compared to models using a convolution layer. In addition, the model with the Fourier transform layer also shows faster execution time per epoch, which indicates efficiency in data processing. However, the convolution layer has an advantage in terms of model size, although it is not significantly different from the Fourier transform layer. In conclusion, the Fourier transform layer has an advantage in the classification of medical image data.

Characterization of the in-situ degradation process of P3HT:PCBM based on hyperspectral and neural networks

In situ online observation of surface morphology during degradation processes is of paramount importance for exploring the stability of organic photovoltaic materials. In this study, we designed an in situ online characterization system based on hyperspectral and neural network technologies, and observed the degradation processes of P3HT:PCBM thin film materials. The system is capable of collecting hyperspectral image data from 101 channels within the 400–700 nm wavelength range for characterizing detailed surface features of materials. Additionally, to automate the processing of hyperspectral image data, we designed a spectral image segmentation algorithm based on neural networks and proposed a foreground attention mechanism to improve the segmentation accuracy of the algorithm. The experimental results indicate that the system can achieve high spectral characterization of P3HT:PCBM thin film materials and automate image data processing through artificial intelligence algorithms, with an image segmentation accuracy of 99.62 %. Furthermore, owing to the higher spectral resolution of this system and its computer-assisted analysis capabilities for material image data, not only are the in-situ variations in size, density, and formation rate of aggregates formed during the thermal degradation process of P3HT:PCBM thin film materials experimentally analyzed, but also the fluorescence changes at the edges of aggregates during the photodegradation process are revealed. The reliable code can be found at the following link: https://github.com/HyperSystemAndImageProc/IONFMDP-UHHNN.

Melanoma Skin Cancer Detection Using Deep learning, Neural Network and Classical Machine Learning Techniques

Melanoma is one of the deadliest types of skin cancer and requires an early check-up for survival. Though earlier diagnosis was primarily dependent on dermatological checks and histopathological reports, automation of the same may be highly time-efficient. With that interest, in the following paper, we propose a hybrid approach which attempts to utilize deep learning with some classical machine learning methods to automate melanoma detection. The feature extraction and classification were done using CNN because it is the most efficient in processing image data. Besides, SVM and KNN were used as comparative models. A very well-preprocessed dataset of images was used to see how well models could work in terms of accuracy, precision, and recall. We observe strong over-performance by CNNs compared to the more traditional methods and an ensemble of models that yield a higher confidence of diagnostics. The technique has much promise for supporting clinicians with quicker and more precise diagnosing of melanoma, thus enabling better patient care. Keywords: Melanoma detection, dermatological, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Convolutional Neural Networks (CNNs).

Investigating the Applications of AI in Oncology from NIH Funded Projects: Case study of Lung Cancer and Pancreatic Cancer

ABSTRACTThis poster aims to conduct an examination of the applications of Artificial Intelligence (AI) in oncology. We collect projects from National Institutes of Health (NIH) which delve into how AI applications and techniques are used in cancer research between 2018 to 2024. Results show AI's ability to enhance lung and pancreatic cancer through novel imaging techniques and data processing. We find that refined medical imaging can be done with AI‐driven techniques such as machine learning or deep learning to improve diagnostic accuracy potentially leading to better survival rates for patients involved. Additionally, this reveals how AI transformed oncology studies underlining the movement toward complex diagnostic algorithms that allow accurate stage assignments. Consequently, these forms of teamwork are essential when determining as well as making reliable Cancer care systems by developing strong AI systems with interpretation abilities using supportive NIH funding.

Dual-stream fusion network with multi-head self-attention for multi-modal fake news detection

With the rapid advancement of social media platforms like Weibo and WeChat, alongside the emergence of deepfake technologies, tackling fake information has become a major challenge for society and government institutions. To address this, developing efficient and intelligent methods for fake news detection is crucial. This paper introduces a dual-stream fusion network model (DSF-MHSA) based on deep learning, designed to detect fake news across web pages, images, and text. The model tackles issues such as cross-lingual discrepancies, data imbalance, and multimodal information fusion by integrating deep learning models like ERNIE-M, AlexNet, and ShuffleNet, along with three multi-head self-attention mechanisms. It processes textual and image data separately to capture long-range dependencies and global information, enhancing understanding and recognition. A unified multi-head self-attention mechanism then merges these insights to strengthen cross-modal correlation detection. The model is tested on datasets from Twitter, Weibo, and IKCEST-2023, which includes real online news from various social media sources. Results show that the DSF-MHSA model achieves over 90 % accuracy, surpassing traditional models in news detection tasks. This research offers significant practical value for the identification and understanding of news content.

Applications of Computer Vision, 2nd Edition

Computer vision (CV) is a broad term mainly used to refer to processing image and video data [...]

Rapid identification of white tea based on colorimetric indicator displacement assay (IDA) sensor array

The identification of white tea mainly relies on sensory evaluation and mass spectrometry methods, which have drawbacks such as strong subjectivity and complex analysis. Thus, this study established a novel approach based on colorimetric indicator displacement assay (IDA) sensor to achieve rapid and accurate white tea identification. Cost-effective dyes and phenylboronic acids with different substituents were selected as the indicator and receptor, respectively. A color-signal-responsive IDA sensor array was constructed to enable the rapid and sensitive identification of white tea. Additionally, three supervised pattern recognition algorithms were utilized to process image data. The results demonstrate that combining the IDA sensor with the random forest algorithm accurately differentiates white tea samples by origin and type, achieving a 100% recognition accuracy in both training set (n = 84) and prediction set (n = 56) when ntree = 1000. This work offers an economical and efficient method for the rapid identification of white tea products.

Application of transformer architectures in generative video modeling for neurosurgical education.

This article explores the potential impact of OpenAI's Sora, a generative video modeling technology, on neurosurgical training. It evaluates how such technology could revolutionize the field by providing realistic surgical simulations, thereby enhancing the learning experience and proficiency in complex procedures for neurosurgical trainees. The study examines the incorporation of this technology into neurosurgical education by leveraging transformer architecture and processing of video and image data. It involves compiling a neurosurgical procedure dataset for model training, aiming to create accurate, high-fidelity simulations. Our findings indicate significant potential applications in neurosurgical training, including immersive simulations for skill development and exposure to diverse surgical scenarios. The technology also promises to transform assessment and feedback, introducing a standardized, objective way to measure and improve trainee competencies. Integrating generative video modeling technology into neurosurgical education marks a progressive step toward enhancing training methodologies. Despite challenges in technical, ethical, and practical domains, continuous development and evaluation could lead to substantial advancements in surgical education, preparing neurosurgeons more effectively for their demanding roles.

The Diagnostic Ability of GPT-3.5 and GPT-4.0 in Surgery: Comparative Analysis.

ChatGPT (OpenAI) has shown great potential in clinical diagnosis and could become an excellent auxiliary tool in clinical practice. This study investigates and evaluates ChatGPT in diagnostic capabilities by comparing the performance of GPT-3.5 and GPT-4.0 across model iterations. This study aims to evaluate the precise diagnostic ability of GPT-3.5 and GPT-4.0 for colon cancer and its potential as an auxiliary diagnostic tool for surgeons and compare the diagnostic accuracy rates between GTP-3.5 and GPT-4.0. We precisely assess the accuracy of primary and secondary diagnoses and analyze the causes of misdiagnoses in GPT-3.5 and GPT-4.0 according to 7 categories: patient histories, symptoms, physical signs, laboratory examinations, imaging examinations, pathological examinations, and intraoperative findings. We retrieved 316 case reports for intestinal cancer from the Chinese Medical Association Publishing House database, of which 286 cases were deemed valid after data cleansing. The cases were translated from Mandarin to English and then input into GPT-3.5 and GPT-4.0 using a simple, direct prompt to elicit primary and secondary diagnoses. We conducted a comparative study to evaluate the diagnostic accuracy of GPT-4.0 and GPT-3.5. Three senior surgeons from the General Surgery Department, specializing in Colorectal Surgery, assessed the diagnostic information at the Chinese PLA (People's Liberation Army) General Hospital. The accuracy of primary and secondary diagnoses was scored based on predefined criteria. Additionally, we analyzed and compared the causes of misdiagnoses in both models according to 7 categories: patient histories, symptoms, physical signs, laboratory examinations, imaging examinations, pathological examinations, and intraoperative findings. Out of 286 cases, GPT-4.0 and GPT-3.5 both demonstrated high diagnostic accuracy for primary diagnoses, but the accuracy rates of GPT-4.0 were significantly higher than GPT-3.5 (mean 0.972, SD 0.137 vs mean 0.855, SD 0.335; t285=5.753; P<.001). For secondary diagnoses, the accuracy rates of GPT-4.0 were also significantly higher than GPT-3.5 (mean 0.908, SD 0.159 vs mean 0.617, SD 0.349; t285=-7.727; P<.001). GPT-3.5 showed limitations in processing patient history, symptom presentation, laboratory tests, and imaging data. While GPT-4.0 improved upon GPT-3.5, it still has limitations in identifying symptoms and laboratory test data. For both primary and secondary diagnoses, there was no significant difference in accuracy related to age, gender, or system group between GPT-4.0 and GPT-3.5. This study demonstrates that ChatGPT, particularly GPT-4.0, possesses significant diagnostic potential, with GPT-4.0 exhibiting higher accuracy than GPT-3.5. However, GPT-4.0 still has limitations, particularly in recognizing patient symptoms and laboratory data, indicating a need for more research in real-world clinical settings to enhance its diagnostic capabilities.

Practical utility of linked color imaging in colonoscopy: Updated literature review.

The remarkable recent developments in image-enhanced endoscopy (IEE) have significantly contributed to the advancement of diagnostic techniques. Linked color imaging (LCI) is an IEE technique in which color differences are expanded by processing image data to enhance short-wavelength narrow-band light. This feature of LCI causes reddish areas to appear redder and whitish areas to appear whiter. Because most colorectal lesions, such as neoplastic and inflammatory lesions, have a reddish tone, LCI is an effective tool for identifying colorectal lesions by clarifying the redder areas and distinguishing them from the surrounding normal mucosa. To date, eight randomized controlled trials have been conducted to evaluate the effectiveness of LCI in identifying colorectal adenomatous lesions. The results of a meta-analysis integrating these studies demonstrated that LCI was superior to white-light endoscopy for detecting colorectal adenomatous lesions. LCI also improves the detection of serrated lesions by enhancing their whiteness. Furthermore, accumulating evidence suggests that LCI is superior to white-light endoscopy for the diagnosis of the colonic mucosa in patients with ulcerative colitis. In this review, based on a comprehensive search of the current literature since the implementation of LCI, the utility of LCI in the detection and diagnosis of colorectal lesions is discussed. Additionally, the latest data, including attempts to combine artificial intelligence and LCI, are presented.

Modeling Realistic Geometries in Human Intrathoracic Airways.

Geometrical models of the airways offer a comprehensive perspective on the complex interplay between lung structure and function. Originating from mathematical frameworks, these models have evolved to include detailed lung imagery, a crucial enhancement that aids in the early detection of morphological changes in the airways, which are often the first indicators of diseases. The accurate representation of airway geometry is crucial in research areas such as biomechanical modeling, acoustics, and particle deposition prediction. This review chronicles the evolution of these models, from their inception in the 1960s based on ideal mathematical constructs, to the introduction of advanced imaging techniques like computerized tomography (CT) and, to a lesser degree, magnetic resonance imaging (MRI). The advent of these techniques, coupled with the surge in data processing capabilities, has revolutionized the anatomical modeling of the bronchial tree. The limitations and challenges in both mathematical and image-based modeling are discussed, along with their applications. The foundation of image-based modeling is discussed, and recent segmentation strategies from CT and MRI scans and their clinical implications are also examined. By providing a chronological review of these models, this work offers insights into the evolution and potential future of airway geometry modeling, setting the stage for advancements in diagnosing and treating lung diseases. This review offers a novel perspective by highlighting how advancements in imaging techniques and data processing capabilities have significantly enhanced the accuracy and applicability of airway geometry models in both clinical and research settings. These advancements provide unique opportunities for developing patient-specific models.

Monitoring of Glacier Area Changes in the Ili River Basin during 1992–2020 Based on Google Earth Engine

The Ili River Basin, a crucial transboundary river in the arid region of Central Asia, plays a significant role in the region’s ecology and water resources. However, current methods for monitoring glacier area changes in this region face challenges in automation and accuracy due to the complex terrain and climatic conditions. This study aims to evaluate the effectiveness of the Google Earth Engine (GEE) platform for monitoring glacier area changes in the Ili River Basin from 1992 to 2020, with a focus on improving data accuracy and processing efficiency. Utilizing the Landsat data series, we employed the random forest (RF) classification algorithm within the GEE platform to extract glacier areas, optimizing a multidimensional feature set using the Jeffries–Matusita (JM) distance method, and applied visual interpretation for data refinement. Our results demonstrated that the GEE platform, combined with the RF algorithm, provided high accuracy in glacier monitoring, achieving an overall accuracy of 89% and a kappa coefficient of 0.85. During the study period, the glacier area in the Ili River Basin decreased by 184.76 km2, with an average annual retreat rate of 6.84 km2, most notably between 3800 and 4400 m in elevation. The analysis revealed that temperature changes had a more pronounced impact on glacier dynamics than precipitation. This approach significantly enhances image utilization efficiency and data processing speed, offering a reliable tool for monitoring glacier dynamics. Future research should focus on integrating additional environmental variables and extending the temporal scope to further refine glacier dynamics modeling and predictions.

Research on wheat broken rate and impurity rate detection method based on DeepLab-EDA model and system construction

The broken rate and impurity rate of wheat are important indicators for assessing the quality of combine harvester operations. In view of the overlapping, occlusion and dense adhesion between the scattered grains during the operation of the combine harvester, it is difficult to obtain the grain crushing characteristics and impurity mass, which leads to low detection accuracy. In this paper, a method for detecting wheat broken rate and impurity rate based on DeepLab-EDA semantic segmentation model was proposed, and a detection system was built. In the detection system, an image acquisition device was designed and developed based on the principle of electromagnetic vibration, and the deep learning model was deployed in the embedded processor. Through the human–computer interaction interface design, the online processing and analysis of wheat image data and the display of the detection results of broken rate and impurity rate were realized. Comparative experiments with traditional semantic segmentation models showed that the MIoU, MP and MR of the DeepLab-EDA model were 89.41 %, 95.97 % and 94.83 %, respectively, representing improvements of 9.94%, 7.41%, and 7.52% over the baseline model, and indicating a significant enhancement in the accurate identification and segmentation of broken grain and impurities. Based on this, indoor group matching experiments were conducted with three groups of broken rate and impurity rate levels set at 0.5%, 1.5%, and 2.5%, showing the average errors of 7.54% and 6.30% for broken rate and impurity rate detection systems, respectively. Furthermore, the detection device was installed under the grain outlet of the GM80 combine harvester for field experiments, which showed average errors of 13.32% and 9.77% for wheat broken rate and impurity rate, respectively. The effectiveness and accuracy of the wheat broken rate and impurity rate detection system meet the requirements, which can provide a data basis for intelligent control of combine harvester operation parameters by the operator.

Identification of maize seed vigor based on hyperspectral imaging and deep learning

BackgroundSeed vigor identification is critical to guaranteeing the quality and yield of maize. Although seeds with impaired vigor may germinate under normal conditions, planting under unfavorable conditions makes it difficult to produce healthy plants. Therefore, non-destructive and rapid detection of seed vigor using hyperspectral imaging (HSI) technology is crucial for improving crop production efficiency.MethodsHyperspectral images of maize seeds were acquired employing the HSI system, the original spectra were preprocessed using Savitzky–Golay smoothing and multiplicative scatter correction, and the feature wavelengths were extracted using the successive projections algorithm (SPA). Discriminant models were constructed based on support vector machine (SVM), random forest, artificial neural network (ANN), and convolutional neural network (CNN-DC).ResultsThe results showed that SVM, ANN, and CNN-DC could discriminate well between maize seeds with different vigor levels, and their accuracy rate was over 70%. The SPA algorithm showed that the RMSE value achieved a minimum of 0.3406, while the number of variables was 49. The CNN-DC model outperformed the other models, which reached the highest accuracy of 92.06%. This study demonstrates that DL combined with HSI has excellent potential for identifying seed vigor.ConclusionsThis study shows that the proposed method has excellent results for hyperspectral image data processing and can accurately identify maize seed vigor.