Image Clarity Research Articles

Deep Deblurring in Teledermatology: Deep Learning Models Restore the Accuracy of Blurry Images' Classification.

Background: Blurry images in teledermatology and consultation increased the diagnostic difficulty for both deep learning models and physicians. We aim to determine the extent of restoration in diagnostic accuracy after blurry images are deblurred by deep learning models. Methods: We used 19,191 skin images from a public skin image dataset that includes 23 skin disease categories, 54 skin images from a public dataset of blurry skin images, and 53 blurry dermatology consultation photos in a medical center to compare the diagnosis accuracy of trained diagnostic deep learning models and subjective sharpness between blurry and deblurred images. We evaluated five different deblurring models, including models for motion blur, Gaussian blur, Bokeh blur, mixed slight blur, and mixed strong blur. Main Outcomes and Measures: Diagnostic accuracy was measured as sensitivity and precision of correct model prediction of the skin disease category. Sharpness rating was performed by board-certified dermatologists on a 4-point scale, with 4 being the highest image clarity. Results: The sensitivity of diagnostic models dropped 0.15 and 0.22 on slightly and strongly blurred images, respectively, and deblurring models restored 0.14 and 0.17 for each group. The sharpness ratings perceived by dermatologists improved from 1.87 to 2.51 after deblurring. Activation maps showed the focus of diagnostic models was compromised by the blurriness but was restored after deblurring. Conclusions: Deep learning models can restore the diagnostic accuracy of diagnostic models for blurry images and increase image sharpness perceived by dermatologists. The model can be incorporated into teledermatology to help the diagnosis of blurry images.

A Study of Classroom Behavior Recognition Incorporating Super-Resolution and Target Detection.

With the development of educational technology, machine learning and deep learning provide technical support for traditional classroom observation assessment. However, in real classroom scenarios, the technique faces challenges such as lack of clarity of raw images, complexity of datasets, multi-target detection errors, and complexity of character interactions. Based on the above problems, a student classroom behavior recognition network incorporating super-resolution and target detection is proposed. To cope with the problem of unclear original images in the classroom scenario, SRGAN (Super Resolution Generative Adversarial Network for Images) is used to improve the image resolution and thus the recognition accuracy. To address the dataset complexity and multi-targeting problems, feature extraction is optimized, and multi-scale feature recognition is enhanced by introducing AKConv and LASK attention mechanisms into the Backbone module of the YOLOv8s algorithm. To improve the character interaction complexity problem, the CBAM attention mechanism is integrated to enhance the recognition of important feature channels and spatial regions. Experiments show that it can detect six behaviors of students-raising their hands, reading, writing, playing on their cell phones, looking down, and leaning on the table-in high-definition images. And the accuracy and robustness of this network is verified. Compared with small-object detection algorithms such as Faster R-CNN, YOLOv5, and YOLOv8s, this network demonstrates good detection performance on low-resolution small objects, complex datasets with numerous targets, occlusion, and overlapping students.

DM-AHR: A Self-Supervised Conditional Diffusion Model for AI-Generated Hairless Imaging for Enhanced Skin Diagnosis Applications.

Accurate skin diagnosis through end-user applications is important for early detection and cure of severe skin diseases. However, the low quality of dermoscopic images hampers this mission, especially with the presence of hair on these kinds of images. This paper introduces DM-AHR, a novel, self-supervised conditional diffusion model designed specifically for the automatic generation of hairless dermoscopic images to improve the quality of skin diagnosis applications. The current research contributes in three significant ways to the field of dermatologic imaging. First, we develop a customized diffusion model that adeptly differentiates between hair and skin features. Second, we pioneer a novel self-supervised learning strategy that is specifically tailored to optimize performance for hairless imaging. Third, we introduce a new dataset, named DERMAHAIR (DERMatologic Automatic HAIR Removal Dataset), that is designed to advance and benchmark research in this specialized domain. These contributions significantly enhance the clarity of dermoscopic images, improving the accuracy of skin diagnosis procedures. We elaborate on the architecture of DM-AHR and demonstrate its effective performance in removing hair while preserving critical details of skin lesions. Our results show an enhancement in the accuracy of skin lesion analysis when compared to existing techniques. Given its robust performance, DM-AHR holds considerable promise for broader application in medical image enhancement.

A pilot study of upcycled smartphone-based colposcopy for visual inspection of cervix performed by community healthcare workers in rural Vietnam.

This study assessed the feasibility of smartphone-based colposcopy (SBC) for visual inspection of the cervix by community healthcare workers in low-resource areas. This was a retrospective study conducted in community villages in rural Vietnam, where 177 participants were enrolled for a cervical cancer screening. Cervical images were obtained by pre-trained community healthcare workers using a portable, upcycled SBC (Samsung Galaxy Note 20). Images were taken before and after the visual inspection after acetic acid (VIA) examination. Captured images were stored on a web server through an Android-based application and later reviewed independently by two experienced gynecologists. Image quality was assessed, and kappa statistics were calculated for the measurement of agreement in VIA findings. Cervical images of 177 women obtained between July and August 2020 were analyzed. The mean age of women was 42 ± 9.1 years, and 20.3% were postmenopausal. The percentage of adequate visibility of the squamocolumnar junction (SCJ) in the captured images was 83.1%. The kappa value for interobserver reliability was 0.61 for VIA positivity agreement between the two gynecologists. Image clarity was rated as average or above in 77.3%. The reasons for suboptimal clarity were poor focusing (15.3%), inadequate SCJ visibility (18%), and obscuring of the transformation zone due to blood (11.3%), discharge (14.7%), or artifacts such as intrauterine devices or polyps (5.1%). Upcycled SBC was feasible when performed by pre-trained healthcare workers in a low-resource setting. VIA findings by SBC showed adequate agreement between two independent assessments, suggesting its potential as a method to aid cervical cancer screening.

Curcumin Analogues as Organic Fluorophores for Latent Fingerprint Imaging

AbstractSynthesis and characterization of two curcumin analogues BAA and Br‐AA via a condensation reaction was reported. Both the synthesized organic luminophores exhibited aggregation‐induced emission (AIE) with bright yellow and green emission respectively. Increase in the water% enhanced the emission by both the compounds confirmed the AIE property. A detailed study of latent fingerprints visualization was also carried out for both the analogues. Both the compounds showed good to normal capability to develop latent fingerprints (LFPs). Compound BAA performed better as a fluorescent material to develop LFPs compared to Br‐AA. The LFPs developed were analyzed to obtain 1–3 level of fingerprint patterns under UV 365 nm illumination. The LFPs developed using BAA exhibited excellent efficiency, sensitivity, high contrast with low background interreference. All three levels of fingerprint patterns were identified by BAA. However, Br‐AA showed inability to develop high clarity images of latent fingerprints. The solid‐state emission nature of the analogues was also evaluated from their emission spectra and CIE coordinates were found to be were (0,187, 0.518) and (0.265, 0.484) for BAA and Br‐AA respectively.

The use of non-invasive tomographic imaging to monitor lung condition

The development of ultrasound tomography (UST) aimed to significantly enhance the precision and safety of non-invasive UST imaging, particularly for studying crystallization processes in biological tissues. The initiative sought to address the limitations of previous versions by incorporating advanced technological upgrades and providing a more user-friendly interface. The revised system comprises eight four-channel measurement cards interconnected via a high-speed FD CAN bus capable of 8 MBPS data transfer. Each card features a dedicated square wave generator, band-pass filters tailored to specific ultrasonic transducer frequencies, and a sophisticated signal envelope processing unit. The core processing unit is built around a 32-bit STM32G474RE microcontroller, ensuring robust data handling and image reconstruction capabilities. The UST device presented demonstrates improved image clarity and reduced noise interference. The measurement card redesign has achieved a sampling rate of 4 MBPS per channel and includes a two-stage amplification for dynamic range management. Upgraded power components, comprehensive shielding, and the integration of advanced analog switches have led to an enhanced signal-to-noise ratio, pivotal for high-resolution imaging. The advancements presented in the UST device mark a noteworthy progression in ultrasound imaging technology, extending beyond traditional applications. High-speed data collection, precise signal processing, and user-centered design have all come together to make a system that can image crystallization processes more accurately and accurately over and over again.

Tomographic examination of the head model through image reconstruction from measurement data

This study aims to integrate ultrasound tomography with numerical algorithms to significantly enhance brain sensing capabilities for diagnosing critical brain abnormalities. Advanced ultrasound tomography, employing a high-frequency transducer array, captures intricate brain structures. The echoes processed by multi-channel receivers allow for three-dimensional imaging. Deep learning models, particularly convolutional neural networks, undergo rigorous training on extensive datasets. Hyperparameter tuning and regularization are key to model optimization. Algorithms handle large datasets, detecting subtle pathological changes in ultrasound images. The system demonstrates proficient image reconstruction and analysis. Implementing deep learning algorithms rectifies operator-dependent inconsistencies and imaging artifacts. The analysis shows significant improvements in diagnostic accuracy and processing time. The convergence of ultrasound tomography and deep learning faces challenges such as image quality variation, computational demands, and clinical integration. Despite these, the enhanced image clarity and the ability to conduct real-time analytics are promising. The study sets a new standard in neurological diagnostics, indicating the potential for sophisticated diagnostic tools to become accessible in diverse healthcare settings.

A Comprehensive Approach for an Interpretable Diabetic Macular Edema Grading System Based on ConvUNext

Diabetic macular edema (DME) is a leading cause of vision impairment in diabetic patients, necessitating a timely and accurate diagnosis. This paper proposes a comprehensive system for DME grading using retinal fundus images. Our approach integrates multiple deep learning modules, each designed to address key aspects of the diagnostic process. The first module employs the ConvUNeXt model for segmenting hard exudates (HaEx), crucial indicators of DME. The second module uses RetinaNet for precise optic disc (OD) localization, which is essential for subsequent macula localization. The third module refines macula localization, leveraging preprocessing techniques to enhance image clarity. Finally, our system consolidates these results to provide interpretable DME grading. Experimental evaluations were conducted on the Messidor dataset, demonstrating the system’s robust performance. The HaEx segmentation module achieved a mean IoU of 70.5% and a Dice coefficient of 0.64. The OD localization module showed perfect accuracy, recall, and precision at 1.0. For macula localization, our method satisfied the 1R criterion with 99.38% accuracy. The DME grading module achieved an overall accuracy of 91.12%, with an AUC of 0.9334. Our method offers a balanced performance across accuracy, sensitivity, and specificity compared to other non-interpretable and partially interpretable methods.

Comparison of the Image Quality of Turbo Spin Echo and Echo-Planar Diffusion-Weighted Imaging of the Head and Neck Region.

Magnetic resonance imaging (MRI) of the head and neck region is notably challenging due to the complex anatomy and the critical need for high-resolution imaging to accurately diagnose various pathologies. The two prominent MRI techniques used in this context are turbo spin echo (TSE) and echo-planar diffusion-weighted imaging (EP-DWI). TSE is recognized for providing high-resolution anatomical images, whereas EP-DWI offers functional imaging that highlights the diffusion of water molecules, essential for detecting early pathological changes. This study aims to compare the image quality of TSE and EP-DWI in the head and neck region to assess their diagnostic efficacy and clinical utility. This retrospective study was conducted at Saveetha Medical College and Hospital over six months. A total of 100 patients (50 males and 50 females, aged 18-65 years) with various head and neck pathologies were included. Patients underwent both TSE and EP-DWI sequences using a Philips MULTIVA 1.5 T scanner. Image quality was assessed based on signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), artifact presence, and lesion detection. Two experienced radiologists independently reviewed the images, with inter-observer agreement calculated using Cohen's kappa coefficient. The mean SNR for TSE was significantly higher than EP-DWI (45.2 vs. 28.7, p<0.01), indicating superior image clarity and detail in TSE images. TSE demonstrated a higher mean CNR compared to EP-DWI (25.4 vs. 15.8, p<0.01), suggesting better differentiation between different tissue types and pathologies. Artifacts were more frequent in EP-DWI images (45% vs. 15%), with motion artifacts being the most common. TSE detected more lesions (120 vs. 95), with more precise delineation of lesions. The inter-observer agreement was excellent for both TSE and EP-DWI, with kappa values of 0.85 and 0.80, respectively. TSE MRI provides superior image quality compared to EP-DWI for evaluating the head and neck region. The enhanced SNR and CNR in TSE images result in clearer and more detailed visualizations of anatomical structures and pathological changes, with fewer artifacts. While EP-DWI is valuable for functional imaging, its role should be complementary to TSE. The study suggests that TSE should be the preferred modality for detailed anatomical assessment in the head and neck region. Further studies with larger sample sizes and advanced imaging techniques may provide additional insights into optimizing MRI protocols for head and neck imaging.

Evaluating UAV-Based Remote Sensing for Hay Yield Estimation.

(1) Background: Yield-monitoring systems are widely used in grain crops but are less advanced for hay and forage. Current commercial systems are generally limited to weighing individual bales, limiting the spatial resolution of maps of hay yield. This study evaluated an Uncrewed Aerial Vehicle (UAV)-based imaging system to estimate hay yield. (2) Methods: Data were collected from three 0.4 ha plots and a 35 ha hay field of red clover and timothy grass in September 2020. A multispectral camera on the UAV captured images at 30 m (20 mm pixel-1) and 50 m (35 mm pixel-1) heights. Eleven Vegetation Indices (VIs) and five texture features were calculated from the images to estimate biomass yield. Multivariate regression models (VIs and texture features vs. biomass) were evaluated. (3) Results: Model R2 values ranged from 0.31 to 0.68. (4) Conclusions: Despite strong correlations between standard VIs and biomass, challenges such as variable image resolution and clarity affected accuracy. Further research is needed before UAV-based yield estimation can provide accurate, high-resolution hay yield maps.

AI-driven pseudo-light source for achieving high coherence and low speckle noise simultaneously in dual-wavelength digital holographic microscopy

Digital holography, a promising technology for optical imaging, is limited by the fundamental challenge of speckle noise when based on coherent lasers. These approaches often compromise either coherence, affecting surface depth measurement capabilities, or introduce excessive noise, degrading image clarity. To eliminate this trade-off, this study introduces a novel solution based on an AI-driven pseudo-light source that simultaneously achieves high coherence and low speckle noise in holographic imaging. Consisting of conditional generative adversarial networks, the AI model was trained on paired holograms from both highly coherent laser light and partially coherent quantum dot (QD)-based light sources to generate holograms that mimicked the low-noise characteristics of QD-based light while retaining the high coherence length of laser. The effectiveness of the pseudo-light source was validated through holographic observations on a reflective 8.0-µm-deep specimen. Compared to the laser, the AI-driven pseudo-light source achieved substantial improvement in interference pattern clarity and reduced speckle noise contrast from 0.602 to 0.0873. Moreover, the standard deviation of the surface depth distribution was notably reduced from 215.3 nm to 44.7 nm. Quantitative phase evaluations further confirmed the preservation of accurate phase information in the generated holograms, verifying the successful reconstruction of the three-dimensional specimen structure.

Influence of network latency and bandwidth on robot-assisted laparoscopic telesurgery: A pre-clinical experiment.

Telesurgery has the potential to overcome spatial limitations for surgeons, which depends on surgical robot and the quality of network communication. However, the influence of network latency and bandwidth on telesurgery is not well understood. A telesurgery system capable of dynamically adjusting image compression ratios in response to bandwidth changes was established between Beijing and Sanya (Hainan province), covering a distance of 3000km. In total, 108 animal operations, including 12 surgical procedures, were performed. Total latency ranging from 170ms to 320ms and bandwidth from 15-20Mbps to less than 1 Mbps were explored using designed surgical tasks and hemostasis models for renal vein and internal iliac artery rupture bleeding. Network latency, jitter, frame loss, and bit rate code were systemically measured during these operations. National Aeronautics and Space Administration Task Load Index (NASA-TLX) and a self-designed scale measured the workload and subjective perception of surgeons. All 108 animal telesurgeries, conducted from January 2023 to June 2023, were performed effectively over a total duration of 3866min. The operations were completed with latency up to 320ms and bandwidths as low as 1-5Mbps. Hemostasis for vein and artery rupture bleeding models was effectively achieved under these low bandwidth conditions. The NASA-TLX results indicated that latency significantly impacted surgical performance more than bandwidth and image clarity reductions. This telesurgery system demonstrated safety and reliability. A total of 320ms latency is acceptable for telesurgery operations. Reducing image clarity can effectively mitigate the potential latency increase caused by decreased bandwidth, offering a new method to reduce the impact of latency on telesurgery.

A study on an improved laser speckle contrast blood flow imaging methodology

The laser speckle contrast imaging technique based on the dynamic light scattering theory presents a non-scanning and wide-field method for blood flow imaging. However, its accuracy in biological tissues is limited to the decreased contrast and reduced image clarity as conventional single-exposure approaches are susceptible to static scattering. In this paper, based on the adaptive window space direction contrast (awsdK) imaging method proposed by the laboratory, combined with the optimized single exposure technology, the effect of static scattering under a single exposure is reduced. The experimental results show that the method can effectively correct static scattering and eliminate the effect of system noise on speckle contrast. This method not only improves the imaging quality, but also realizes the rapid monitoring of blood flow changes by using the speckle contrast ratio measured in a single exposure, which provides an effective solution for the further development of laser speckle contrast imaging technology.

Rapid detection technology of sewing thread based on DeblurGAN-BSV3 defuzzification algorithm and ST-FPN detection algorithm

Stitch defect detection is an important means to ensure the quality of stitched fabrics. In order to realize the intellectualization of the sewing process, a rapid defect detection method based on machine vision was proposed. In order to solve the problem of motion blur caused by sewing speed, an image DeblurGAN-BSV3 algorithm is proposed. Firstly, different attention fusion mechanisms are introduced to achieve accurate extraction of image features. Secondly, the depth-separable convolution of the trunk network is replaced by blueprint convolution to ensure the processing speed of the detection algorithm and the clarity of the output image. In order to solve the difficulty of rapid detection of pin defects, a student–teacher feature pyramid matching method was proposed. Firstly, the abnormal region interpretation technology was used to explicitly visualize the defect area of the identified abnormal instances, and then the abnormal detection score was performed on the detected images to make a quality judgment. The experimental results show that the combination of the above two methods has a good ability for rapid defect detection. Rapid detection of common pin defects is realized.

Innovative Noise Extraction and Denoising in Low-Dose CT Using a Supervised Deep Learning Framework

Low-dose computed tomography (LDCT) imaging is a critical tool in medical diagnostics due to its reduced radiation exposure. However, this reduction often results in increased noise levels, compromising image quality and diagnostic accuracy. Despite advancements in denoising techniques, a robust method that effectively balances noise reduction and detail preservation remains a significant need. Current denoising algorithms frequently fail to maintain the necessary balance between suppressing noise and preserving crucial diagnostic details. Addressing this gap, our study focuses on developing a deep learning-based denoising algorithm that enhances LDCT image quality without losing essential diagnostic information. Here we present a novel supervised learning-based LDCT denoising algorithm that employs innovative noise extraction and denoising techniques. Our method significantly enhances LDCT image quality by incorporating multiple attention mechanisms within a U-Net-like architecture. Our approach includes a noise extraction network designed to capture diverse noise patterns precisely. This network is integrated into a comprehensive denoising system consisting of a generator network, a discriminator network, and a feature extraction AutoEncoder network. The generator network removes noise and produces high-quality CT images, while the discriminator network differentiates real images from denoised ones, improving the realism of the outputs. The AutoEncoder network ensures the preservation of image details and diagnostic integrity. Our method improves the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) by 7.777 and 0.128 compared to LDCT, by 0.483 and 0.064 compared to residual encoder–decoder convolutional neural network (RED-CNN), by 4.101 and 0.017 compared to Wasserstein generative adversarial network–visual geometry group (WGAN-VGG), and by 3.895 and 0.011 compared to Wasserstein generative adversarial network–autoencoder (WGAN-AE). This demonstrates that our method has a significant advantage in enhancing the signal-to-noise ratio of images. Extensive experiments on multiple standard datasets demonstrate our method’s superior performance in noise suppression and image quality enhancement compared to existing techniques. Our findings significantly impact medical imaging, particularly improving LDCT scan diagnostic accuracy. The enhanced image clarity and detail preservation offered by our method open new avenues for clinical applications and research. This improvement in LDCT image quality promises substantial contributions to clinical diagnostics, disease detection, and treatment planning, ensuring high-quality diagnostic outcomes while minimizing patient radiation exposure.

Enhancing Cardiac Imaging with Deep Learning: New Frontiers in Diagnosis

The incorporation of Deep Learning (DL) in imaging represents a significant leap forward in medical diagnostics transforming the approach to identifying, diagnosing, and treating cardiovascular diseases. By utilizing algorithms and extensive datasets DL greatly enhances the precision, speed, and predictive capabilities of diagnostic methods like echocardiography, magnetic resonance imaging (MRI) and computed tomography (CT). This piece explores the influence of DL on cardiac imaging by illustrating how these technologies not only enhance image clarity and accuracy but also streamline and improve the analysis of intricate imaging data. The integration of DL enables detection of cardiac conditions with greater accuracy enabling tailored treatment strategies for individual patients and potentially saving lives. Furthermore, automating procedures reduces the risk of human errors and speeds up decision making processes ultimately enhancing patient outcomes and operational efficacy in healthcare environments. As we delve into the state and future prospects of DL in cardiac imaging, we uncover broader implications for predictive medicine and healthcare analytics that suggest a promising future, for technology driven healthcare solutions that are both groundbreaking and beneficial. Keywords: Deep Learning, Cardiac Imaging, Echocardiography, Magnetic Resonance Imaging (MRI), Computed Tomography (CT), Diagnostic Automation, Predictive Medicine, Healthcare Analytics

Super-Resolution Virtual Scene Rendering Technology Based on Generalized Huber-MRF Image Modeling

The traditional rendering technology creates virtual scenes with insufficient fidelity, which are quite different from real scenes. To address this issue, a super-resolution virtual scene rendering technology based on generalized Huber-MRF image modeling has been studied. This study preprocesses the original image through three steps: graying, filtering, and enhancement. The generalized Huber-MRF is employed for super-resolution image restoration to enhance image clarity. Corner features are extracted from the super-resolution image, and the Delaunay triangular grid method is used to construct the image's 3D model. Texture and lighting conditions of the virtual scene are then set through texture mapping, shadow rendering, and other technologies to achieve realistic scene effects. The results indicate that, when applied, the research technology yields a relatively small chamfer distance in virtual scene modeling, suggesting that the design method preserves the details and shape information of the original image, reducing the difference between the virtual scene and the real scene and increasing the fidelity of the virtual scene. Furthermore, this method achieves maximum PSNR and SSIM values of 17.54 and 0.978, respectively, with an image preprocessing time of only 1.21 s and a CPU utilization rate of only 35.5%. This method demonstrates excellent performance across multiple aspects.

Van der Waals mid-wavelength infrared detector linear array for room temperature passive imaging.

Passive imaging for mid-wave infrared (MWIR) is resistant to atmospheric pollutants, guaranteeing image clarity and accuracy. Arrayed photodetectors can simultaneously perform radiation sensing to improve efficiency. Room temperature van der Waals (vdWs) photodetectors without lattice matching have evolved rapidly with optimized stacking methods, primarily for single-pixel devices. The urgent need to implement arrayed devices aligns with practical demands. Here, we present an 8 by 1 black phosphorus/molybdenum sulfide (BP/MoS2) vdWs photodetector linear array with a fill-factor of ~77%, fabricated using a temperature-assisted sloping transfer method. The flat interface and uniform thickness facilitate carrier transport and minimize pixel nonuniformities, showing an average peak detectivity (D*) of 2.34 × 109 cm·Hz1/2·W-1 in the mid-wave infrared region. Compared to a single pixel, push-broom scanning passive imaging is eight times more efficient and further enhanced through mean filtering and fast Fourier transform filtering for strip noise correction. Our study offers guidance on vdWs arrayed devices for engineering applications.

Effects of Er2O3 contribution on microstructure and mechanical properties of high entropy and dual phase alloys

The study aimed to look at the differences between a high entropy alloy and a dual phase high entropy alloy with high iron and Mn content. It also wanted to find out what happened when a small amount of the rare earth element erbium oxide (Er2O3) was added to these alloys, especially on the mechanical and microstructure of the alloy. The first step in this study was to get 99 % pure metal powders, which were then made by dividing the powders into 30 g of equal weight. The powders were mixed evenly and then pressed into 10-g blocks under 6 tons of pressure. They were then set up to be melted in an arc. Four of the eight samples that were melted in an arc under vacuum were treated with heat. The four different compositions were then turned into small metallographic samples for SEM, EDX, Mapping, XRD, and microhardness tests. The study's imaging and analysis processes were also carried out. After that, SEM images were taken at various magnifications (100X, 500X, 1000X, 2500X, and 5000X), and EDS and XRD analyses were done on different structures found in these images. These analyses were based on literature research about the clarity of the metallographic images in the alloy, which showed the study's metallographic differences. The samples were put through microhardness and wear tests to see which one was stronger and less worn. The dual phase high entropy alloy (A2) was stronger and less worn than the high entropy alloy (A1). Er2O3 had little effect on the alloys' mechanical properties or microstructure. The heat treatment that was done to the samples helped the metallographic structure. In terms of physics, it didn't change the hardness much, but it did make the material wear less quickly.

Radiological segmentation of knee meniscus ultrasound images based on boundary constraints and multi-scale fusion network

Knee osteoarthritis (KOA) is one of the most popular joint diseases endangering human health because of its high incidence, disability, and younger onset. However, there is no suitable method for early diagnosis, evaluation, and treatment of KOA. In recent years, some clinical studies have found that ultrasound can detect early changes in KOA in advance, and the automatic segmentation of ultrasound images can achieve rapid and effective quantitative research on KOA. However, in ultrasound images, the soft tissue boundaries of the lesion are blurred, making lesion segmentation difficult. Although the U-Net family is one of the best networks for image segmentation, they still have defects such as blurred segmentation boundaries, distorted morphology, and insufficient accuracy when segmenting ultrasound images. To address this issue, we added attention, atrous spatial pyramid pooling (ASSP), and edge loss function terms into the Unet3+ network, which improved the contour clarity and accuracy of output images (the improved Unet3+ Dice acc = 78.74%. Then, we extract the key features of the improved Unet3+ for outputting meniscus images: calculating meniscus area and distance, where the average accuracy of the area is: area_ avg_ acc = 91.12%, with an average distance accuracy of distance_ avg_ acc = 91.14%. This thesis creates a new dataset collection from West China Hospital, Sichuan University, and automated measurement of knee meniscus protrusion area has been achieved for the first time. This article is the first to apply deep learning to ultrasound image segmentation of the knee meniscus, helping doctors conduct qualitative and quantitative analysis of the diagnosis and treatment of early KOA. The results indicate that the improved Unet3+ can assist doctors in automatically diagnosing and evaluating KOA based on meniscus ultrasound images, which is beneficial for guiding early clinical intervention.