Image Converter Research Articles

Applied Research on Face Image Beautification Based on a Generative Adversarial Network

Generative adversarial networks (GANs) are widely used in image conversion tasks and have shown unique advantages in the context of face image beautification, as they can generate high-resolution face images. When used alongside potential spatial adjustments, it becomes possible to control the diversity of the generated images and learn from small amounts of labeled data or unsupervised data, thus reducing the costs associated with data acquisition and labeling. At present, there are some problems in terms of face image beautification processes, such as poor learning of the details of a beautification style, the use of only one beautification effect, and distortions being present in the generated face image. Therefore, this study proposes the facial image beautification generative adversarial network (FIBGAN) method, in which images with different beautification style intensities are generated with respect to an input face image. First, a feature pyramid network is used to construct a pre-encoder to generate multi-layer feature vectors containing the details of the face image, such that it can learn the beautification details of the face images during the beautification style transmission. Second, the pre-encoder combines the separate style vectors generated with respect to the original image and the style image to transfer the beautification style, such that the generated images have different beautification style intensities. Finally, the weight demodulation method is used as the beautification style transmission module in the generator, and the normalization operation on the feature map is replaced with the convolution weight to eliminate any artifacts from the feature map and reduce distortions in the generated images. The experimental results show that the FIBGAN model not only transmits the beautification style to face images in a detailed manner but also generates face images with different beautification intensities while reducing the distortion of the generated face images. Therefore, it can be widely used in the beauty and fashion industry, advertising, and media production.

Arthroscopically assisted suture osteosynthesis of tibial eminence fractures in children and adolescents

The surgical goal is the arthroscopically assisted, closed reduction, and suture osteosynthesis of fractures of the tibial eminence in children and adolescents. Fractures of the tibial eminence type (II)-III according to Meyers & McKeever or typeIV according to Zaricznyj. Fracture of the tibial eminence typeI, conservatively treatable fracture typeII according to Meyers & McKeever and ligamentous rupture of the anterior cruciate ligament. Supine position. Securing the leg with alateral support on the thigh and aroll to support the foot in90° kneeflexion. Unwrap for blood evacuation with cuff on the thigh. Creation of the anterolateral portal and filling of the joint with Ringer's solution. Usually, extensive irrigation of the hemarthrosis is required first to gain visibility. Then the anteromedial portal is created. Adiagnostic walk-around is performed to rule out concomitant injuries to the cartilage and menisci. The fracture bed is then debrided with the shaver and the fracture is reduced on atrial basis using the cruciate ligament targeting device. Remove the cruciate ligament targeting device and reinforce the anterior cruciate ligament (ACL) with asuture shuttle forceps with two 1PolysorbTM sutures (Medtronic, Minneapolis, MN, USA), which are discharged and secured via the anteromedial portal. Now reinsert the cruciate ligament targeting device via the anteromedial portal. This is set to an angle of a good 60°. The image converter is used for control. Skin incision in the area of the 3 mm drill sleeve. Now a 2.4 mm cannulated drill with a core is used to predrill into the joint medial to the tibial eminence, strictly epiphyseal depending on the age. After removing the core of the drill, a wire loop is inserted into the joint, grasped with the forceps and also passed out via the anteromedial portal. Now remove the drill while leaving the wire loop in place. The medial thread legs are now threaded through the lasso loop and passed out distally via the drill channel. The analogous procedure is performed via the anterolateral portal so that the legs of both sutures meet ventrally at the tibial epiphysis/metaphysis. Now complete extension of the knee, reduction of the fracture with the cruciate ligament targeting device, under image converter control hand-tight knotting and, thus, firm reduction of the fracture. Suction of the joint. Layered wound closure. Application of a femoral cast sleeve in full extension. Removal of the osteosynthesis material is unnecessary with this method. Immobilization is in the femoral cast sleeve for 6 weeks. Removal of the femoral cast sleeve and radiological consolidation control 6 weeks postoperatively. Then start physiotherapy to restore the anatomical range of motion and strengthen thigh muscles. We operated on 10 patients between 2019 and 2022. Of these, 60% were boys. Age ranged from 5-14 years with a median of 8 years and a mean of 8.6 years. The right and left knee were affected half each; 20% of the patients presented a type II injury and 80% a type III according to Meyers & McKeever. One patient had to be revised in the course due to a cyclops lesion. One patient also presented a partial ACL rupture intraoperatively, but this has not shown any clinical relevance in the postoperative course to date. In the Lysholm score, we achieved a mean of 90.4 points and a median of 97.5 points. The International Knee Documentation Committee (IKDC) score resulted in a mean of 90.9% and a median of 90.25%. In addition, the pre- and postoperative tibial slope and the postoperative range-of-motion values were collected.

TO-LAB model: Real time Touchless Lung Abnormality detection model using USRP based machine learning algorithm.

Due to the increasing prevalence of respiratory diseases and the importance of early diagnosis. The need for non-invasive and touchless medical diagnostic solutions has become increasingly crucial in modern healthcare to detect lung abnormalities. Existing methods for lung abnormality detection often rely on invasive and time-consuming procedures limiting their effectiveness in real-time diagnosis. This work introduces a novel Touchless Lung Abnormality (TO-LAB) detection model utilizing universal software radio peripherals (USRP) and machine learning algorithms. The TO-LAB model integrates a blood pressure meter and an RGB-D depth-sensing camera to gather individual data without physical contact. Heart rate (HR) is analyzed through image conversion to IPPG signals, while blood pressure (BP) is obtained via analog conversion from the blood pressure meter. This touchless imaging setup facilitates the extraction of essential signal features crucial for respiratory pattern analysis. Advanced computer vision algorithms like Mel-frequency cepstral coefficients (MFCC) and Principal Component Analysis (PCA) process the acquired data to focus on breathing abnormalities. These features are then combined and inputted into a machine learning-based Multi-class SVM for breathing activity analysis. The Multi-class SVM categorizes breathing abnormalities as normal, shallow, or elevated based on the fused features. The efficiency of this TO-LAB model is evaluated with the simulated and real-time data. According to the findings, the proposed TO-LAB model attains the maximum accuracy of 96.15% for real time data; however, the accuracy increases to 99.54% for simulated data for the efficient classification of breathing abnormalities. From this analysis, our model attains better results in simulated data but it declines the accuracy while processing with real-time data. Moreover, this work has a significant medical impact since it presents a solution to the problem of gathering enough data during the epidemic to create a realistic model with a large dataset.

Evaluation of coarse aggregate properties in hardened concrete based on segment anything model (SAM)

The applicability of the segment anything model (SAM) algorithm, a novel technique for analyzing the characteristics of coarse aggregate from RGB images of concrete cross-sections, was evaluated. Unlike traditional deep learning method, the SAM algorithm effectively and clearly separates coarse aggregate and mortar without requiring a large database, extensive pre-training, conversion of RGB images to grayscale, or manual threshold setting. Additionally, a new technique was applied to separate the pores recognized as aggregates by using the image difference according to the change in vertical and side lighting. Consequently, the area ratio of coarse aggregate, after the separation and removal of pores from the aggregate area, exhibited an error of approximately 7.0 % when compared to the actual volume ratio of the aggregate. However, in contrast to the calculation of the area ratio of coarse aggregate, the SAM algorithm demonstrated significant errors in size analysis, leading to distortions in the sieve curve. Nevertheless, the SAM algorithm indicates potential for application in various concrete-related fields of concrete in the future.

Multi-layer feature fusion based image style transfer with arbitrary text condition

Style transfer refers to the conversion of images in two different domains. Compared with the style transfer based on the style image, the image style transfer through the text description is more free and applicable to more practical scenarios. However, the image style transfer method under the text condition needs to be trained and optimized for different text and image inputs each time, resulting in limited style transfer efficiency. Therefore, this paper proposes a multi-layer feature fusion based style transfer method (MlFFST) with arbitrary text condition. To address the problems of distortion and missing semantic content, we also introduce a multi-layer attention normalization module. The experimental results show that the method in this paper can generate stylized results with high quality, good effect and high stability for images and videos. And this method can meet real-time requirements to generate more artistic and aesthetic images and videos.

High-Resolution SAR-to-Multispectral Image Translation Based on S2MS-GAN

Synthetic aperture radar (SAR) has been extensively applied in remote sensing applications. Nevertheless, it is a challenge to process and interpret SAR images. The key to interpreting SAR images lies in transforming them into other forms of remote sensing images to extract valuable hidden remote sensing information. Currently, the conversion of SAR images to optical images produces low-quality results and incomplete spectral information. To address these problems, an end-to-end network model, S2MS-GAN, is proposed for converting SAR images into multispectral images. In this process, to tackle the issues of noise and image generation quality, a TV-BM3D module is introduced into the generator model. Through TV regularization, block-matching, and 3D filtering, these two modules can preserve the edges and reduce the speckle noise in SAR images. In addition, spectral attention is added to improve the spectral features of the generated MS images. Furthermore, we construct a very high-resolution SAR-to-MS image dataset, S2MS-HR, with a spatial resolution of 0.3 m, which is currently the most comprehensive dataset available for high-resolution SAR-to-MS image interpretation. Finally, a series of experiments are conducted on the relevant dataset. Both quantitative and qualitative evaluations demonstrate that our method outperforms several state-of-the-art models in translation performance. The solution effectively facilitates high-quality transitions of SAR images across different types.

Autonomous Landing Strategy for Micro-UAV with Mirrored Field-of-View Expansion.

Positioning and autonomous landing are key technologies for implementing autonomous flight missions across various fields in unmanned aerial vehicle (UAV) systems. This research proposes a visual positioning method based on mirrored field-of-view expansion, providing a visual-based autonomous landing strategy for quadrotor micro-UAVs (MAVs). The forward-facing camera of the MAV obtains a top view through a view transformation lens while retaining the original forward view. Subsequently, the MAV camera captures the ground landing markers in real-time, and the pose of the MAV camera relative to the landing marker is obtained through a virtual-real image conversion technique and the R-PnP pose estimation algorithm. Then, using a camera-IMU external parameter calibration method, the pose transformation relationship between the UAV camera and the MAV body IMU is determined, thereby obtaining the position of the landing marker's center point relative to the MAV's body coordinate system. Finally, the ground station sends guidance commands to the UAV based on the position information to execute the autonomous landing task. The indoor and outdoor landing experiments with the DJI Tello MAV demonstrate that the proposed forward-facing camera mirrored field-of-view expansion method and landing marker detection and guidance algorithm successfully enable autonomous landing with an average accuracy of 0.06 m. The results show that this strategy meets the high-precision landing requirements of MAVs.

Neutrosophic set and optimized deep learning for classification of chicken Eimeria species: a practical solution for poultry industry

AbstractTo optimize infection control and bolster productivity within the poultry industry, it is imperative to accurately classify Chicken Eimeria species. There are several methods for determining Eimeria disease in chickens. Traditional methods involve watching for clinical symptoms, and macroscopic lesions, and studying the parasite’s biology and oocyst morphology. These methods are frequently time-consuming and labor-intensive, necessitating the manual collection and analysis of samples, which can be especially difficult in large chicken farms. Deep learning algorithms, on the other hand, provide automated, accurate, and non-invasive methods for the detection of Eimeria. This paper proposed a classification model for the automatic classification of chicken Eimeria species. The proposed model is mainly based on integrating neutrosophic set theory and InceptionV3 deep-learning architecture. Three primary phases make up the proposed chicken Eimeria species classification model: the data preprocessing phase, the neutrosophic image conversion phase, and the image classification phase. To address the issue of class imbalance in the adopted dataset and enhance the model’s generalizability, the random oversampling method, and data augmentation techniques are employed during the data preprocessing phase. The preprocessed data is considered to feed the neutrosophic set-based segmentation algorithm, where true, false, and intermediate subsets are extracted. Finally, the true subset is utilized to feed the optimized InceptionV3. To determine the optimal hyperparameter values for InceptionV3, a modified version of the Brown Bear optimization algorithm is proposed in this paper. To evaluate the effectiveness of the proposed model, a real benchmark dataset comprising images of different Eimeria species is adopted. The experimental results revealed that the proposed model offers a more efficient and accurate alternative to traditional methods and state-of-the-art models, enabling faster and more effective diagnosis and treatment of Eimeria infections. It achieved an overall accuracy, specificity, sensitivity, and F1-score of nearly 100%. Additionally, the results showed that the high performance of the proposed model can reduce labor costs and boost throughput, thereby enhancing economic viability even more.

Unsupervised domain adaptation for remote sensing semantic segmentation with the 2D discrete wavelet transform

There would be the differences in spectra, scale and resolution between the Remote Sensing datasets of the source and target domains, which would lead to the degradation of the cross-domain segmentation performance of the model. Image transfer faced two problems in the process of domain-adaptive learning: overly focusing on style features while ignoring semantic information, leading to biased transformation results, and easily overlooking the true transfer characteristics of remote sensing images, resulting in unstable model training. To address these issues, we proposes a novel dual-space generative adversarial domain adaptation segmentation framework, DS-DWTGAN, to minimize the differences between the source domain and the target domain. DS-DWTGAN aims to mitigate the distinctions between the source and target domains, thereby rectifying the imbalances in style and semantic representation.The framework introduces a network branch leveraging wavelet transform to capture comprehensive frequency domain and semantic information. It aims to preserve semantic details within the frequency domain space, mitigating image conversion deviations. Furthermore, our proposed method integrates output adaptation and data enhancement training strategies to reinforce the acquisition of domain-invariant features. This approach effectively diminishes noise interference during the migration process, bolsters model stability, and elevates the model’s adaptability to remote sensing images within different domains. Experimental validation was conducted on the publicly available Potsdam and Vaihingen datasets. The findings reveal that in the PotsdamIRRG to Vaihingen task, the proposed method attains outstanding performance with mIoU and mF1 values reaching 56.04% and 67.28%, respectively. Notably, these metrics surpass the corresponding values achieved by state-of-the-art (SOTA) methods, registering an increase of 2.81% and 2.08%. In comparison to alternative approaches, our proposed framework exhibits superior efficacy in the domain of unsupervised semantic segmentation for UAV remote sensing images.

Accuracy of pelvic bone segmentation for 3d printing: a study of segmentation accuracy based on anatomic landmarks to evaluate the influence of the observer.

3D printing has a wide range of applications and has brought significant change to many medical fields. However, ensuring quality assurance (QA) is essential for patient safety and requires a QA program that encompasses the entire production process. This process begins with imaging and continues on with segmentation, which is the conversion of Digital Imaging and Communications in Medicine (DICOM) data into virtual 3D-models. Since segmentation is highly influenced by manual intervention the influence of the users background on segmentation accuracy should be thoroughly investigated. Seventeen computed tomography (CT) scans of the pelvis with physiological bony structures were identified, anonymized, exported as DICOM data sets, and pelvic bones were segmented by four observers with different backgrounds. Landmarks were measured on DICOM images and in the segmentations. Intraclass correlation coefficients (ICCs) were calculated to assess inter-observer agreement, and the trueness of the segmentation results was analyzed by comparing the DICOM landmark measurements with the measurements of the segmentation results. The correlation between segmentation trueness and segmentation time was analyzed. The lower limits of the 95% confidence intervals of the ICCs for the seven landmarks analyzed ranged from 0.511 to 0.986. The distance between the iliac crests showed the highest agreement between observers, while the distance between the ischial tuberosities showed the lowest. The distance between the upper edge of the symphysis and the promontory showed the lowest deviation between DICOM measurements and segmentation measurements (mean deviations < 1mm), while the intertuberous distance showed the highest deviation (mean deviations 14.5-18.2mm). Investigators with diverse backgrounds in segmentation and varying experience with slice images achieved pelvic bone segmentations with landmark measurements of mostly high agreement in a setup with high realism. In contrast, high variability was observed in the segmentation of the coccyx. In general, interobserver agreement was high, but due to measurement inaccuracies, landmark-based approaches cannot conclusively show that segmentation accuracy is within a clinically tolerable range of 2mm for the pelvis. If the segmentation is performed by a very inexperienced user, the result should be reviewed critically by the clinician in charge.

Symmetrically Fluorinated D-π-A Structured Cyanine Dye for Highly Efficient NIR-II Imaging-Guided Cancer Phototheranostics.

Near-infrared-II (NIR-II) fluorescence imaging-guided photothermal therapy (PTT) represents a cutting-edge approach for precise tumor diagnosis and treatment, providing real-time therapeutic efficacy evaluation. However, a significant challenge lies in the creation of phototheranostic agents that provide robust imaging and efficient photothermal conversion. To address this, a donor-π-acceptor (D-π-A) structure heptamethine cyanine derivative, IR1116, that confers a strong intramolecular charge transfer effect is developed. To enhance its applicability, IR1116 is formulated with DSPE-PEG to create a water-dispersible NIR-II phototheranostic nanoheater, NPIR1116. This nanoheater benefits from the incorporation of an electron-withdrawing group, leading to reduced photooxidation activity and significantly improved photostability. NPIR1116 exhibits strong NIR-II absorption and fluorescence, peaking at 1004 and 1116nm, respectively, as well as a photothermal conversion efficiency of 79% under 1064nm lasers. In vitro and in vivo studies showed the efficacy of NPIR1116 in tumor imaging via NIR-II fluorescence and its ability to effectively induce tumor cell apoptosis under 1064nm laser irradiation. These findings underscore the potential of NPIR1116 in NIR-II fluorescence imaging-guided PTT for tumor treatment, paving the way for further advancements in NIR-II dye development and bioimaging technologies.

Advancing automobile dry clutch fault diagnosis through innovative imaging techniques and Vision transformer integration

The study investigates the significance of clutch condition monitoring in automotive transmissions to preempt mechanical failures, enhance efficiency, and mitigate risks to human safety and maintenance costs. It explores the integration of Vision Transformer (ViT) with imaging techniques, such as scalograms, spectrograms, polar plots, radar plots, and Hilbert-Huang transforms, to diagnose faults in dry friction clutches. By transforming vibration signals into image representations and utilizing ViT for fault classification, the study aims to identify the most effective imaging technique and optimal hyperparameters for accurate fault diagnosis. Experimental studies on a test rig with varying fault conditions demonstrate the effectiveness of ViT in diagnosing clutch faults when coupled with different image conversion techniques. The results highlight the potential of integrating spectrogram image processing with ViT, achieving a 100% accuracy in fault diagnosis for clutch systems, thus advancing the analysis of faults in clutch systems.

Arbitrary style transformation algorithm based on multi-scale fusion and compressed attention in art and design

In art and design, style conversion algorithms can fuse the content of one image with the style of another image, thereby generating images with new artistic styles. However, traditional style conversion algorithms suffer from high computational complexity and loss of details during row image conversion. Therefore, this study introduces VGG16 multi-scale fusion feature extraction in any style transition algorithm and introduces a compressed attention mechanism to improve its computational complexity. Then it designs an arbitrary style transformation algorithm on the ground of multi-scale fusion and compressed attention. The results showed that the designed algorithm took 0.014 s and 0.021 s to process tasks on the COCO Stuff dataset and WikiArt dataset, respectively, proving its high computational efficiency. The loss values of the designed algorithm are 0.046 and 0.052, respectively, indicating strong fitting performance and good generalization ability. The IS score and FID score of the design algorithm are 2.36 and 91.67, respectively, proving that the generated images have high diversity and quality. The above results demonstrate the effectiveness and practicality of design algorithms in art and design. It has important theoretical and practical value in promoting the development of style conversion technology, enhancing the creativity and expressiveness of art and design.

Broadband infrared imaging governed by guided-mode resonance in dielectric metasurfaces

Nonlinear metasurfaces have experienced rapid growth recently due to their potential in various applications, including infrared imaging and spectroscopy. However, due to the low conversion efficiencies of metasurfaces, several strategies have been adopted to enhance their performances, including employing resonances at signal or nonlinear emission wavelengths. This strategy results in a narrow operational band of the nonlinear metasurfaces, which has bottlenecked many applications, including nonlinear holography, image encoding, and nonlinear metalenses. Here, we overcome this issue by introducing a new nonlinear imaging platform utilizing a pump beam to enhance signal conversion through four-wave mixing (FWM), whereby the metasurface is resonant at the pump wavelength rather than the signal or nonlinear emissions. As a result, we demonstrate broadband nonlinear imaging for arbitrary objects using metasurfaces. A silicon disk-on-slab metasurface is introduced with an excitable guided-mode resonance at the pump wavelength. This enabled direct conversion of a broad IR image ranging from >1000 to 4000 nm into visible. Importantly, adopting FWM substantially reduces the dependence on high-power signal inputs or resonant features at the signal beam of nonlinear imaging by utilizing the quadratic relationship between the pump beam intensity and the signal conversion efficiency. Our results, therefore, unlock the potential for broadband infrared imaging capabilities with metasurfaces, making a promising advancement for next-generation all-optical infrared imaging techniques with chip-scale photonic devices.

Conversion of images of 3D friction maps to study the coupling between coefficient of friction, velocity and contact temperature of the disc brake

The coefficient of friction during braking is not constant. Determining its variability requires measurements in real conditions. This paper presents a methodology of conversion of the measured time profiles of the sliding velocity Veq, contact temperature T, and coefficient of friction f, into analytical formulation of two variables z = f(x,y). This was executed in the following steps: 1) creating a three-column table Veq, T, f from experimental measurements; 2) interpolation using Kriging; 3) creating a contour map of the coefficient of friction dependent on the sliding velocity and temperature, 4) import of a grey scale image of the friction map into the finite element (FE) software, and 5) definition of a function z = f(x,y). The studies were carried out for five composite organic friction materials and cast-iron brake disc of a railway vehicle. The developed five friction maps for each friction pair were based the data from the full-scale bench tests during braking from the initial vehicle velocity of 80 kmh−1, 120 kmh−1, 140 kmh−1, 160 kmh−1, 200 kmh−1 to a stop. In the second part of the study the initial-value problem for the equation of motion combined with the heat conduction problem were formulated and solved numerically using special functionalities of the FE software, e.g. Deformed Geometry, Mathematics. Changes in the vehicle velocity and time profiles of the coefficient of friction were determined from the solution of the coupled thermal problem. The computational FE model was verified by comparing the measured and calculated changes in the vehicle velocity, coefficient of friction and evolutions of the brake disc temperature during single braking. The maximum calculated temperature 1 mm under the contact surface of the brake disc, during braking from initial vehicle velocity of 80 kmh−1, was obtained for the base friction material and was equal to T1,3,5Num.= 72 °C. The corresponding experimental value was T1-6Exp.= 66.1 °C. When braking from 140 kmh−1, for the same material it was T1,3,5Num.= 129.7 °C and T1-6Exp.= 130.7 °C. The obtained differences in braking times calculated and measured did not exceed 1.7 %. The corresponding temperature differences of the disc at the stopping time were lower than 5.5 %.

Classification and identification of extreme wind events by CNNs based on Shapelets and improved GASF-GADF

In this manuscript, we propose an automatic classification and recognition method for extreme wind events based on Convolutional Neural Networks (CNNs) and combining the Shapelet Transform (ST) algorithm with the improved Gramian Angular Summation Field - Gramian Angular Difference Field (GASF-GADF) 2D images construction format. First, a CNN model suitable for wind speed time series 2D images classification and recognition among five mainstream CNNs (ResNet-50, ShuffleNet0.5 × , DenseNet-121, EfficientNet-B2, and EfficientNetV2-S) is preferred based on the basic Gramian Angular Field (GAF) method; then, the improved GASF-GADF images construction format is proposed, and the optimal CNN is used to compare the classification and recognition results based on other three image conversion methods: Markov Transition Field (MTF), GASF, GADF. Last, it is proposed to utilize the ST algorithm to extract the feature subsequence Shapelets of wind speed time series to further improve the classification and recognition effect on extreme wind events. The effectiveness and applicability of the proposed method were verified through three extreme wind event datasets in this paper.The results show that the combination of Shapelets and the improved GASF-GADF images transformation method proposed in this paper can effectively enhance the classification and recognition of extreme wind events by CNNs. Among them, EfficientNetV2-S combined with the method proposed in this paper achieves 99.50%, 99.50% and 97.50% recognition Accuracy for thunderstorm, gust front and typhoon, respectively. Meanwhile, it still has good robustness for extreme wind events disturbed by noise.

Traffic Object Detection and Recognition Systems

You are already known about automatic vehicles in which the car can control itself. Cars must clearly understand and recognize all traffic signals. Many organizations named Uber, Google, Tesla, Toyota, Mercedes-Benz, Ford, Audi and others are getting involved on this technology to enhance their experience by adding features like autonomous driving and putting efforts in maximum innovation in this field. As a result, if we want to work with this technology accurately it depends on how the vehicle can distinguish between different signs such as no entry, height limit, turning signs, school signs, hospital signs, and many others. Traffic sign recognition is the process of differentiating the traffic signals into similar classes. Here we created a deep-neural-network system that can differentiate traffic signs. Using this system, we can analyze and process different traffic signals which plays a major role in all automatic vehicles. By using CNN, we propose an automated system for traffic sign detection, firstly conversion of original image to grey scale image takes place with the help of some vector machines used there, after that the convolutional-neural network is applied with limited and learnable layer for analyzing. Here it tries to crop the image boundary as per the original have.

Medical Image Classification using a Many to Many Relation, Multilayered Fuzzy Systems and AI

One of the research gaps in the medical sciences is the study of orphan diseases or rare diseases, due to limited data availability of rare diseases. Our previous study addressed this successfully by developing an Artificial Intelligence (AI)-based medical image classification method using a multilayer fuzzy approach (MFA), for detecting and classifying image abnormalities for large and very small datasets. A fuzzy system is an AI system used to handle imprecise data. There are more than three types of fuzziness in any image data set: 1) due to a projection of a 3D object on a 2D surface, 2) due to the digitalization of the scan, and 3) conversion of the digital image to grayscale, and more. Thus, this was referred to in the previous study as a multilayer fuzzy system, since fuzziness arises from multiple sources. The method used in MFA involves comparing normal images containing abnormalities with the same kind of image without abnormalities, yielding a similarity measure percentage that, when subtracted from a hundred, reveals the abnormality. However, relying on a single standard image in the MFA reduces efficiency, since images vary in contrast, lighting, and patient demographics, impacting similarity percentages. To mitigate this, the current study focused on developing a more robust medical image classification method than MFA, using a many-to-many relation and a multilayer fuzzy approach (MCM) that employs multiple diverse standard images to compare with the abnormal image. For each abnormal image, the average similarity was calculated across multiple normal images, addressing issues encountered with MFA, and enhancing versatility. In this study, an AI-based method of image analysis automation that utilizes fuzzy systems was applied to a cancer data set for the first time. MCM proved to be highly efficient in detecting the abnormality in all types of images and sample sizes and surpassed the gold standard, the convolutional neural network (CNN), in detecting the abnormality in images from a very small data set. Moreover, MCM detects and classifies abnormality without any training, validation, or testing steps for large and small data sets. Hence, MCM may be used to address one of the research gaps in medicine, which detects, quantifies, and classifies images related to rare diseases with small data sets. This has the potential to assist a physician with early detection, diagnosis, monitoring, and treatment planning of several diseases, especially rare diseases.

O-132 A systematic spatial HiPlex proteomics exploration of human testicular tissues from birth to adulthood

Abstract Study question Can we map the key maturation stages of human spermatogonial stem cells (SSCs) within their niche during infancy and puberty? Summary answer Using highplex spatial proteomics, we describe the key cellular events taking place during human testis maturation. What is known already The human testis is a complex “ecosystem” that matures in response to endocrine and exocrine signals and interactions between its diverse cellular components. Unlike animal models, in humans, testicular maturation is a slow process that takes place over more than a decade. In contrast to ovaries, the human testis retains its immature state until the onset of puberty. Single-cell RNA sequencing data has revealed significant developmental changes for germ cell and the somatic niche during infancy and puberty. Study design, size, duration Using the hyperplex imaging technique (CellDIVE) and a panel of 30 protein markers - selected to label key components of the developing human testis - we have systematically analyzed a time series of ∼75 testicular biopsies from boys aged 8 months to adulthood. Following sequential staining and capture of high-resolution images, our analysis pipeline involves the conversion of image into single-cell data, which allows a systematic description of the spatial SSC/niche microenvironment interactions across development. Participants/materials, setting, methods The panel of antibody markers was defined using integrated scRNAseq data and represents all key cell types, including germ cell markers (e.g., MAGEA4), Sertoli cell markers (e.g., SOX9), Leydig cell markers (e.g., INSL3), myoid cell markers (e.g., ACTA2) ... Main results and the role of chance To describe the events occurring during human testicular maturation, we build a Tissue Microarray (TMA) containing ∼75 biopsies of boys of different ages (0-16yrs old) and using an in-house panel of 30 markers for high-dimensional multiplex CELL DIVE images. Our analytical strategy uses Uniform Manifold Approximation and Projection (UMAP) maps to quantify and statistically compare single-cell data. Our marker panel allows us to phenotype testicular cells at different stages of development, including SSCs (state 0 to state 4), Sertoli cells, Leydig cells, and so on. Moreover, employing spatial-latent Dirichlet allocation (LDA), we identified recurrent cellular neighbourhoods (RCNs), revealing distinct cell clusters and their corresponding RCNs. These RCNs reflect recurring spatial arrangements of cells within testicular tissues, allowing us to infer the spatial organization and interplay among different cell types. Additionally, we explored spatial distances and neighbourhood frequencies across different tissues and conducted spatial co-occurrence analysis to assess the likelihood of finding adjacent cell types. The identification of RCNs offers valuable insights into the microenvironmental dynamics and cellular relationships taking place within the developing testis. Looking ahead, we aim to delve into the functional significance of RCNs in shaping the developmental trajectories and physiological processes within human testicular tissues. Limitations, reasons for caution Due to limitations in proteomics techniques, we could only include ∼30 protein markers on our panel. Although the biopsy samples used in our study are all from chemo-naïve patients, it possible that the conditions affecting these paediatric patients may impact the architecture or development of their testicular tissues. Wider implications of the findings Our study provides a systematic approach to study the development and organization of human testicular structures, which will allow to enumerate the cellular content of individual testicular biopsies and infer their stage of maturation, therefore providing a personalised baseline assessment for each patient at the time of cryopreservation. Trial registration number not applicable

P-049 Identification of human spermatozoa with zona pellucida-binding ability using deep learning

Abstract Study question Can a deep learning model be used for identification of fertilization-competent human spermatozoa based on their distinctive morphological features? Summary answer Our results validated the clinical significance of image analysis of sperm morphology using deep learning to identify high-quality spermatozoa with zona pellucida (ZP)-binding ability. What is known already Sperm morphology is manually evaluated as part of the conventional semen analysis in clinical settings. However, the clinical predictive power of sperm morphology remains debatable due to its lack of association with the fertilization potential of spermatozoa. Human zona pellucida (ZP)-binding ability is a measurable, independent sperm parameter associated with in vitro fertilization (IVF) and pregnancy outcome. Supervised deep learning is an advanced branch to systematically identify the underlying relationship between the input images and designated output. A well-trained model with high generalization ability can generate plausible predictions for unseen images collected under the same condition as the training datasets. Study design, size, duration Human spermatozoa and oocytes were obtained with written consents from the donors attending our assisted reproduction program. Acrosome intact, ZP-bound spermatozoa were recovered after 30 min of gamete coincubation. Unbound spermatozoa were collected from clinical samples of spermatozoa with defective ZP-binding ability leading to fertilization failure following conventional insemination. Sperm images of infertile men (n = 165) with fertilization rates including 0-40% (low), 41-70% (intermediate) and 71-100% (high) following conventional insemination were collected for validation. Participants/materials, setting, methods Diff-Quik stained images of spermatozoa were processed by the K-means clustering algorithm to generate grey-scaled images of individual sperm heads. All sperm images of clinical samples were subjected an additional image conversion step using Cycle Generative Adversarial Network (CycleGAN) to ensure that their microenvironments are similar to those of the laboratory samples. A VGG 13 model was fine-tuned to classify a total of 1,083 images of ZP-bound and unbound spermatozoa over 50 epochs. Main results and the role of chance The newly fine-tuned VGG-13 model demonstrated excellent performance in classifying the ZP-bound and unbound spermatozoa, as reflected by the high sensitivity of 97.6%, specificity of 96.0%, and accuracy of 96.4%. It had a high discriminative power to distinguish between ZP-bound and unbound spermatozoa with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.992. Saliency maps indicated that the model focused on the sperm head and mid-pieces in all images, with a primary emphasis on the anterior regions (43.0%±5.0%). The model was further validated on a vast collection of over 40,000 sperm images collected from the aforementioned fertilization groups. Our results revealed that the high fertilization rate group had a significantly higher percentage of predicted ZP-binding ability than the low fertilization rate group, as determined by the model (16.8%±7.2 vs. 3.2%±1.4; p &amp;lt; 0.05). By analyzing sperm images from infertile men (n = 113) in the high and low fertilization rates groups, a clinical threshold of 4.8% was identified using ROS curve (AUC:0.970) and Youden’s index, which can be used to distinguish between ZP-bound and unbound spermatozoa of clinical samples with a specificity of 93.8% and a sensitivity of 90.9%. Limitations, reasons for caution Our deep learning model is only applicable to diff-quik stained images of spermatozoa captured at high magnification. Further investigation is needed to examine its classification performance on images captured by different platforms and settings, ensuring consistent and reliable prediction accuracy regardless of varying degrees of image quality. Wider implications of the findings Our newly fine-tuned model can be used to evaluate sperm fertilizing potential, irrespective of the parameters evaluated in conventional semen analysis and to identify normospermic patients with defective ZP-binding ability who may benefit from intracytoplasmic sperm injection (ICSI) to improve their fertilization outcome. Trial registration number not applicable