Search

Background: In today's digital age, various diseases drastically reduce people's quality of life. Arthritis is one amongst the most common and debilitating maladies. Osteoarthritis affects several joints, including the hands, knees, spine, and hips. This study focuses on the medical disorder underlying Knee Osteoarthritis (KOA) which severely impairs people's quality of life. KOA is characterised by restricted mobility, stiffness, and terrible pain and can be caused by a range of factors such as ageing, obesity, and traumas. This degenerative disorder leads to progressive wear and tear of the knee joint., Methods: To combat arthritis in the kneecap, this study employs a 12-layer Convolutional Neural Network (CNN) to reach deep learning capabilities. A collection of data from the Osteoarthritis Initiative (OAI) is used to classify KOA. Through the use of medical image processing; the study ascertains whether an individual has this ailment. A sophisticated CNN architecture created especially for binary classification and KOA severity utilising deep learning algorithms is the main component of this work., Results: The cross-entropy loss function is an important component of the model's laborious design that classifies data into two groups. The remaining section uses the Kellgren-Lawrence (KL) grade to classify the disease's severity. In the binary classification, the proposed algorithm outperforms previous methods with an accuracy rate of 92.3%, and in the multiclassification, its accuracy rate is 78.4% which is superior to the previous findings., Conclusion: Looking ahead, the research broadens the scope of this work by gathering information from various sources and using these methods on a wider range of datasets and situations. The potential for major advancements in the field of osteoarthritis detection and classification is highlighted by this forward-looking approach. Furthermore, this method reduces the intervention of medical practitioners and ultimately results in accurate diagnosis., Clinical Trial Number: Not applicable., (© 2024. The Author(s).)

Leukemia is a type of blood tumour that occurs because of abnormal enhancement in WBCs (white blood cells) in the bone marrow of the human body. Blood-forming tissue cancer influences the lymphatic and bone marrow system. The early diagnosis and detection of leukaemia, i.e., the accurate difference of malignant leukocytes with little expense at the beginning of the disease, is a primary challenge in the disease analysis field. Despite the higher occurrence of leukemia, there is a lack of flow cytometry tools, and the procedures accessible at medical diagnostics centres are time-consuming. Distinct researchers have implemented computer-aided diagnostic (CAD) and machine learning (ML) methods for laboratory image analysis, aiming to manage the restrictions of late leukemia analysis. This study proposes a new Falcon optimization algorithm with deep convolutional neural network for Leukemia detection and classification (FOADCNN-LDC) technique. The main objective of the FOADCNN-LDC technique is to classify and recognize leukemia. The FOADCNN-LDC technique utilizes a median filtering (MF) based noise removal process to eradicate the image noise. Besides, the FOADCNN-LDC technique employs the ShuffleNetv2 model for the feature extraction process. Moreover, the detection and classification of the leukemia process are performed by utilizing the convolutional denoising autoencoder (CDAE) model. The FOA is implemented to select the hyperparameter of the CDAE model. The simulation process of the FOADCNN-LDC approach is performed on a benchmark medical dataset. The investigational analysis of the FOADCNN-LDC approach highlighted a superior accuracy value of 99.62% over existing techniques., (© 2024. The Author(s).)

Objective: We developed a deep learning model for distinguishing radiation therapy (RT)-related changes and tumour recurrence in patients with lung cancer who underwent RT, and evaluated its performance., Methods: We retrospectively recruited 308 patients with lung cancer with RT-related changes observed on 18 F-fluorodeoxyglucose positron emission tomography-computed tomography ( 18 F-FDG PET/CT) performed after RT. Patients were labelled as positive or negative for tumour recurrence through histologic diagnosis or clinical follow-up after 18 F-FDG PET/CT. A two-dimensional (2D) slice-based convolutional neural network (CNN) model was created with a total of 3329 slices as input, and performance was evaluated with five independent test sets., Results: For the five independent test sets, the area under the curve (AUC) of the receiver operating characteristic curve, sensitivity, and specificity were in the range of 0.98-0.99, 95-98%, and 87-95%, respectively. The region determined by the model was confirmed as an actual recurred tumour through the explainable artificial intelligence (AI) using gradient-weighted class activation mapping (Grad-CAM)., Conclusion: The 2D slice-based CNN model using 18 F-FDG PET imaging was able to distinguish well between RT-related changes and tumour recurrence in patients with lung cancer., (© 2024. The Author(s), under exclusive licence to The Author(s) under exclusive licence to The Japanese Society of Nuclear Medicine.)

Human pose estimation (HPE) is a technique used in computer vision and artificial intelligence to detect and track human body parts and poses using images or videos. Widely used in augmented reality, animation, fitness applications, and surveillance, HPE methods that employ monocular cameras are highly versatile and applicable to standard videos and CCTV footage. These methods have evolved from two-dimensional (2D) to three-dimensional (3D) pose estimation. However, in real-world environments, current 3D HPE methods trained on laboratory-based motion capture data encounter challenges, such as limited training data, depth ambiguity, left/right switching, and issues with occlusions. In this study, four 3D HPE methods were compared based on their strengths and weaknesses using real-world videos. Joint position correction techniques were proposed to eliminate and correct anomalies such as left/right inversion and false detections of joint positions in daily life motions. Joint angle trajectories were obtained for intuitive and informative human activity recognition using an optimization method based on a 3D humanoid simulator, with the joint position corrected by the proposed technique as the input. The efficacy of the proposed method was verified by applying it to three types of freehand gymnastic exercises and comparing the joint angle trajectories during motion.

In recent years, with the increasing demand for high-quality Dendrobii caulis decoction piece, the identification of D. caulis decoction piece species has become an urgent issue. However, the current methods are primarily designed for professional quality control and supervision. Therefore, ordinary consumers should not rely on these methods to assess the quality of products when making purchases. This research proposes a deep learning network called improved YOLOv5 for detecting different types of D. caulis decoction piece from images. In the main architecture of improved YOLOv5, we have designed the C2S module to replace the C3 module in YOLOv5, thereby enhancing the network's feature extraction capability for dense and small targets. Additionally, we have introduced the Reparameterized Generalized Feature Pyramid Network (RepGFPN) module and Optimal Transport Assignment (OTA) operator to more effectively integrate the high-dimensional and low-dimensional features of the network. Furthermore, a new large-scale dataset of Dendrobium images has been established. Compared to other models with similar computational complexity, improved YOLOv5 achieves the highest detection accuracy, with an average mAP@.05 of 96.5%. It is computationally equivalent to YOLOv5 but surpasses YOLOv5 by 2 percentage points in terms of accuracy., (© 2024. The Author(s).)

Background: Identifying cells engaged in fundamental cellular processes, such as proliferation or living/death statuses, is pivotal across numerous research fields. However, prevailing methods relying on molecular biomarkers are constrained by high costs, limited specificity, protracted sample preparation, and reliance on fluorescence imaging., Methods: Based on cellular morphology in phase contrast images, we developed a deep-learning model named Detector of Mitosis, Apoptosis, Interphase, Necrosis, and Senescence (D-MAINS)., Results: D-MAINS utilizes machine learning and image processing techniques, enabling swift and label-free categorization of cell death, division, and senescence at a single-cell resolution. Impressively, D-MAINS achieved an accuracy of 96.4 ± 0.5% and was validated with established molecular biomarkers. D-MAINS underwent rigorous testing under varied conditions not initially present in the training dataset. It demonstrated proficiency across diverse scenarios, encompassing additional cell lines, drug treatments, and distinct microscopes with different objective lenses and magnifications, affirming the robustness and adaptability of D-MAINS across multiple experimental setups., Conclusions: D-MAINS is an example showcasing the feasibility of a low-cost, rapid, and label-free methodology for distinguishing various cellular states. Its versatility makes it a promising tool applicable across a broad spectrum of biomedical research contexts, particularly in cell death and oncology studies.

With the development of new radiopharmaceutical therapies, quantitative SPECT/CT has progressively emerged as a crucial tool for dosimetry. One major obstacle of SPECT is its poor resolution, which results in blurring of the activity distribution. Especially for small objects, this so-called partial-volume effect limits the accuracy of activity quantification. Numerous methods for partial-volume correction (PVC) have been proposed, but most methods have the disadvantage of assuming a spatially invariant resolution of the imaging system, which does not hold for SPECT. Furthermore, most methods require a segmentation based on anatomic information. Methods: We introduce DL-PVC, a methodology for PVC of 177 Lu SPECT/CT imaging using deep learning (DL). Training was based on a dataset of 10,000 random activity distributions placed in extended cardiac-torso body phantoms. Realistic SPECT acquisitions were created using the SIMIND Monte Carlo simulation program. SPECT reconstructions without and with resolution modeling were performed using the CASToR and STIR reconstruction software, respectively. The pairs of ground-truth activity distributions and simulated SPECT images were used for training various U-Nets. Quantitative analysis of the performance of these U-Nets was based on metrics such as the structural similarity index measure or normalized root-mean-square error, but also on volume activity accuracy, a new metric that describes the fraction of voxels in which the determined activity concentration deviates from the true activity concentration by less than a certain margin. On the basis of this analysis, the optimal parameters for normalization, input size, and network architecture were identified. Results: Our simulation-based analysis revealed that DL-PVC (0.95/7.8%/35.8% for structural similarity index measure/normalized root-mean-square error/volume activity accuracy) outperforms SPECT without PVC (0.89/10.4%/12.1%) and after iterative Yang PVC (0.94/8.6%/15.1%). Additionally, we validated DL-PVC on 177 Lu SPECT/CT measurements of 3-dimensionally printed phantoms of different geometries. Although DL-PVC showed activity recovery similar to that of the iterative Yang method, no segmentation was required. In addition, DL-PVC was able to correct other image artifacts such as Gibbs ringing, making it clearly superior at the voxel level. Conclusion: In this work, we demonstrate the added value of DL-PVC for quantitative 177 Lu SPECT/CT. Our analysis validates the functionality of DL-PVC and paves the way for future deployment on clinical image data., (© 2024 by the Society of Nuclear Medicine and Molecular Imaging.)

Background: Leishmaniasis, an illness caused by protozoa, accounts for a substantial number of human fatalities globally, thereby emerging as one of the most fatal parasitic diseases. The conventional methods employed for detecting the Leishmania parasite through microscopy are not only time-consuming but also susceptible to errors. Therefore, the main objective of this study is to develop a model based on deep learning, a subfield of artificial intelligence, that could facilitate automated diagnosis of leishmaniasis., Methods: In this research, we introduce LeishFuNet, a deep learning framework designed for detecting Leishmania parasites in microscopic images. To enhance the performance of our model through same-domain transfer learning, we initially train four distinct models: VGG19, ResNet50, MobileNetV2, and DenseNet 169 on a dataset related to another infectious disease, COVID-19. These trained models are then utilized as new pre-trained models and fine-tuned on a set of 292 self-collected high-resolution microscopic images, consisting of 138 positive cases and 154 negative cases. The final prediction is generated through the fusion of information analyzed by these pre-trained models. Grad-CAM, an explainable artificial intelligence technique, is implemented to demonstrate the model's interpretability., Results: The final results of utilizing our model for detecting amastigotes in microscopic images are as follows: accuracy of 98.95 1.4%, specificity of 98 2.67%, sensitivity of 100%, precision of 97.91 2.77%, F1-score of 98.92 1.43%, and Area Under Receiver Operating Characteristic Curve of 99 1.33., Conclusion: The newly devised system is precise, swift, user-friendly, and economical, thus indicating the potential of deep learning as a substitute for the prevailing leishmanial diagnostic techniques., (© 2024. The Author(s).)

Accurate prediction of the estrus period is crucial for optimizing insemination efficiency and reducing costs in animal husbandry, a vital sector for global food production. Precise estrus period determination is essential to avoid economic losses, such as milk production reductions, delayed calf births, and disqualification from government support. The proposed method integrates estrus period detection with cow identification using augmented reality (AR). It initiates deep learning-based mounting detection, followed by identifying the mounting region of interest (ROI) using YOLOv5. The ROI is then cropped with padding, and cow ID detection is executed using YOLOv5 on the cropped ROI. The system subsequently records the identified cow IDs. The proposed system accurately detects mounting behavior with 99% accuracy, identifies the ROI where mounting occurs with 98% accuracy, and detects the mounting couple with 94% accuracy. The high success of all operations with the proposed system demonstrates its potential contribution to AR and artificial intelligence applications in livestock farming.

Sign language recognition, an essential interface between the hearing and deaf-mute communities, faces challenges with high false positive rates and computational costs, even with the use of advanced deep learning techniques. Our proposed solution is a stacked encoded model, combining artificial intelligence (AI) with the Internet of Things (IoT), which refines feature extraction and classification to overcome these challenges. We leverage a lightweight backbone model for preliminary feature extraction and use stacked autoencoders to further refine these features. Our approach harnesses the scalability of big data, showing notable improvement in accuracy, precision, recall, F1-score, and complexity analysis. Our model's effectiveness is demonstrated through testing on the ArSL2018 benchmark dataset, showcasing superior performance compared to state-of-the-art approaches. Additional validation through an ablation study with pre-trained convolutional neural network (CNN) models affirms our model's efficacy across all evaluation metrics. Our work paves the way for the sustainable development of high-performing, IoT-based sign-language-recognition applications.

Fishing has provided mankind with a protein-rich source of food and labor, allowing for the development of an important industry, which has led to the overexploitation of most targeted fish species. The sustainable management of these natural resources requires effective control of fish landings and, therefore, an accurate calculation of fishing quotas. This work proposes a deep learning-based spatial-spectral method to classify five pelagic species of interest for the Chilean fishing industry, including the targeted Engraulis ringens, Merluccius gayi , and Strangomera bentincki and non-targeted Normanichthtys crockeri and Stromateus stellatus fish species. This proof-of-concept method is composed of two channels of a convolutional neural network (CNN) architecture that processes the Red-Green-Blue ( RGB ) images and the visible and near-infrared (VIS-NIR) reflectance spectra of each species. The classification results of the CNN model achieved over 94% in all performance metrics, outperforming other state-of-the-art techniques. These results support the potential use of the proposed method to automatically monitor fish landings and, therefore, ensure compliance with the established fishing quotas.

Isthmic spondylolysis results in fracture of pars interarticularis of the lumbar spine, found in as many as half of adolescent athletes with persistent low back pain. While computed tomography (CT) is the gold standard for the diagnosis of spondylolysis, the use of ionizing radiation near reproductive organs in young subjects is undesirable. While magnetic resonance imaging (MRI) is preferable, it has lowered sensitivity for detecting the condition. Recently, it has been shown that ultrashort echo time (UTE) MRI can provide markedly improved bone contrast compared to conventional MRI. To take UTE MRI further, we developed supervised deep learning tools to generate (1) CT-like images and (2) saliency maps of fracture probability from UTE MRI, using ex vivo preparation of cadaveric spines. We further compared quantitative metrics of the contrast-to-noise ratio (CNR), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) between UTE MRI (inverted to make the appearance similar to CT) and CT and between CT-like images and CT. Qualitative results demonstrated the feasibility of successfully generating CT-like images from UTE MRI to provide easier interpretability for bone fractures thanks to improved image contrast and CNR. Quantitatively, the mean CNR of bone against defect-filled tissue was 35, 97, and 146 for UTE MRI, CT-like, and CT images, respectively, being significantly higher for CT-like than UTE MRI images. For the image similarity metrics using the CT image as the reference, CT-like images provided a significantly lower mean MSE (0.038 vs. 0.0528), higher mean PSNR (28.6 vs. 16.5), and higher SSIM (0.73 vs. 0.68) compared to UTE MRI images. Additionally, the saliency maps enabled quick detection of the location with probable pars fracture by providing visual cues to the reader. This proof-of-concept study is limited to the data from ex vivo samples, and additional work in human subjects with spondylolysis would be necessary to refine the models for clinical use. Nonetheless, this study shows that the utilization of UTE MRI and deep learning tools could be highly useful for the evaluation of isthmic spondylolysis.

The current outbreak of monkeypox (mpox) has become a major public health concern because of the quick spread of this disease across multiple countries. Early detection and diagnosis of mpox is crucial for effective treatment and management. Considering this, the purpose of this research was to detect and validate the best performing model for detecting mpox using deep learning approaches and classification models. To achieve this goal, we evaluated the performance of five common pretrained deep learning models (VGG19, VGG16, ResNet50, MobileNetV2, and EfficientNetB3) and compared their accuracy levels when detecting mpox. The performance of the models was assessed with metrics (i.e., the accuracy, recall, precision, and F1-score). Our experimental results demonstrate that the MobileNetV2 model had the best classification performance with an accuracy level of 98.16%, a recall of 0.96, a precision of 0.99, and an F1-score of 0.98. Additionally, validation of the model with different datasets showed that the highest accuracy of 0.94% was achieved using the MobileNetV2 model. Our findings indicate that the MobileNetV2 method outperforms previous models described in the literature in mpox image classification. These results are promising, as they show that machine learning techniques could be used for the early detection of mpox. Our algorithm was able to achieve a high level of accuracy in classifying mpox in both the training and test sets, making it a potentially valuable tool for quick and accurate diagnosis in clinical settings.

Background: Chest radiographs are routinely performed in intensive care unit (ICU) to confirm the correct position of an endotracheal tube (ETT) relative to the carina. However, their interpretation is often challenging and requires substantial time and expertise. The aim of this study was to propose an externally validated deep learning model with uncertainty quantification and image segmentation for the automated assessment of ETT placement on ICU chest radiographs., Methods: The CarinaNet model was constructed by applying transfer learning to the RetinaNet model using an internal dataset of ICU chest radiographs. The accuracy of the model in predicting the position of the ETT tip and carina was externally validated using a dataset of 200 images extracted from the MIMIC-CXR database. Uncertainty quantification was performed using the level of confidence in the ETT-carina distance prediction. Segmentation of the ETT was carried out using edge detection and pixel clustering., Results: The interrater agreement was 0.18 cm for the ETT tip position, 0.58 cm for the carina position, and 0.60 cm for the ETT-carina distance. The mean absolute error of the model on the external test set was 0.51 cm for the ETT tip position prediction, 0.61 cm for the carina position prediction, and 0.89 cm for the ETT-carina distance prediction. The assessment of ETT placement was improved by complementing the human interpretation of chest radiographs with the CarinaNet model., Conclusions: The CarinaNet model is an efficient and generalizable deep learning algorithm for the automated assessment of ETT placement on ICU chest radiographs. Uncertainty quantification can bring the attention of intensivists to chest radiographs that require an experienced human interpretation. Image segmentation provides intensivists with chest radiographs that are quickly interpretable and allows them to immediately assess the validity of model predictions. The CarinaNet model is ready to be evaluated in clinical studies., (© 2023. The Author(s).)

In this study, we used image recognition technology to explore different ways to improve the safety of construction workers. Three object recognition scenarios were designed for safety at a construction site, and a corresponding object recognition model was developed for each scenario. The first object recognition model checks whether there are construction workers at the site. The second object recognition model assesses the risk of falling (falling off a structure or falling down) when working at an elevated position. The third object recognition model determines whether the workers are appropriately wearing safety helmets and vests. These three models were newly created using the image data collected from the construction sites and synthetic image data collected from the virtual environment based on transfer learning. In particular, we verified an artificial intelligence model based on a virtual environment in this study. Thus, simulating and performing tests on worker falls and fall injuries, which are difficult to re-enact by humans, are efficient algorithm verification methods. The verification and synthesis data acquisition method based on a virtual environment is one of the main contributions of this study. This paper describes the overall application development approach, including the structure and method used to collect the construction site image data, structure of the training image dataset, image dataset augmentation method, and the artificial intelligence backbone model applied for transfer learning.

To evaluate the clinical performance of a deep learning-accelerated single-breath-hold half-Fourier acquisition single-shot turbo spin echo (HASTE DL )-sequence for T2-weighted fat-suppressed MRI of the abdomen at 1.5 T and 3 T in comparison to standard T2-weighted fat-suppressed multi-shot turbo spin echo-sequence. A total of 320 patients who underwent a clinically indicated liver MRI at 1.5 T and 3 T between August 2020 and February 2021 were enrolled in this single-center, retrospective study. HASTE DL and standard sequences were assessed regarding overall and organ-based image quality, noise, contrast, sharpness, artifacts, diagnostic confidence, as well as lesion detectability using a Likert scale ranging from 1 to 4 (4 = best). The number of visible lesions of each organ was counted and the largest diameter of the major lesion was measured. HASTE DL showed excellent image quality (median 4, interquartile range 3-4), although BLADE (median 4, interquartile range 4-4) was rated significantly higher for overall and organ-based image quality of the adrenal gland (P < .001), contrast (P < 0.001), sharpness (P < 0.001), artifacts (P < 0.001), as well as diagnostic confidence (P < .001). No significant differences were found concerning noise (P = 0.886), organ-based image quality of the liver, pancreas, spleen, and kidneys (P = 0.120-0.366), number and measured diameter of the detected lesions (ICC = 0.972-1.0). Reduction of the aquisition time (TA) was at least 89% for 1.5 T images and 86% for 3 T images. HASTE DL provided excellent image quality, good diagnostic confidence and lesion detection compared to a standard T2-sequences, allowing an eminent reduction of the acquisition time., (Copyright © 2022 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)

The segmentation of pulmonary lobes is important in clinical assessment, lesion location, and surgical planning. Automatic lobe segmentation is challenging, mainly due to the incomplete fissures or the morphological variation resulting from lung disease. In this work, we propose a learning-based approach that incorporates information from the local fissures, the whole lung, and priori pulmonary anatomy knowledge to separate the lobes robustly and accurately. The prior pulmonary atlas is registered to the test CT images with the aid of the detected fissures. The result of the lobe segmentation is obtained by mapping the deformation function on the lobes-annotated atlas. The proposed method is evaluated in a custom dataset with COPD. Twenty-four CT scans randomly selected from the custom dataset were segmented manually and are available to the public. The experiments showed that the average dice coefficients were 0.95, 0.90, 0.97, 0.97, and 0.97, respectively, for the right upper, right middle, right lower, left upper, and left lower lobes. Moreover, the comparison of the performance with a former learning-based segmentation approach suggests that the presented method could achieve comparable segmentation accuracy and behave more robustly in cases with morphological specificity.

In the wake of COVID-19, the digital fitness market combining health equipment and ICT technologies is experiencing unexpected high growth. A smart trampoline fitness system is a new representative home exercise equipment for muscle strengthening and rehabilitation exercises. Recognizing the motions of the user and evaluating user activity is critical for implementing its self-guided exercising system. This study aimed to estimate the three-dimensional positions of the user's foot using deep learning-based image processing algorithms for footprint shadow images acquired from the system. The proposed system comprises a jumping fitness trampoline; an upward-looking camera with a wide-angle and fish-eye lens; and an embedded board to process deep learning algorithms. Compared with our previous approach, which suffered from a geometric calibration process, a camera calibration method for highly distorted images, and algorithmic sensitivity to environmental changes such as illumination conditions, the proposed deep learning algorithm utilizes end-to-end learning without calibration. The network is configured with a modified Fast-RCNN based on ResNet-50, where the region proposal network is modified to process location regression different from box regression. To verify the effectiveness and accuracy of the proposed algorithm, a series of experiments are performed using a prototype system with a robotic manipulator to handle a foot mockup. The three root mean square errors corresponding to X, Y, and Z directions were revealed to be 8.32, 15.14, and 4.05 mm, respectively. Thus, the system can be utilized for motion recognition and performance evaluation of jumping exercises.

Deep learning (DL) enables the creation of computational models comprising multiple processing layers that learn data representations at multiple levels of abstraction. In the recent past, the use of deep learning has been proliferating, yielding promising results in applications across a growing number of fields, most notably in image processing, medical image analysis, data analysis, and bioinformatics. DL algorithms have also had a significant positive impact through yielding improvements in screening, recognition, segmentation, prediction, and classification applications across different domains of healthcare, such as those concerning the abdomen, cardiac, pathology, and retina. Given the extensive body of recent scientific contributions in this discipline, a comprehensive review of deep learning developments in the domain of diabetic retinopathy (DR) analysis, viz., screening, segmentation, prediction, classification, and validation, is presented here. A critical analysis of the relevant reported techniques is carried out, and the associated advantages and limitations highlighted, culminating in the identification of research gaps and future challenges that help to inform the research community to develop more efficient, robust, and accurate DL models for the various challenges in the monitoring and diagnosis of DR.

The automatic parking system based on vision is greatly affected by uneven lighting, which is difficult to make an accurate judgment on parking spaces in the case of complex image information. To solve this problem, this paper proposes a parking space visual detection and image processing method based on deep learning. Firstly, a 360-degree panoramic system was designed to photograph the vehicle environment. The image has been processed to obtain a panoramic aerial view, which was input as the original image of the parking space detection system. Secondly, the Faster R-CNN (Region-Convolutional Neural Network) parking detection model was established based on deep learning. It was aimed to detect and extract the parking space from the input image. Thirdly, the problems of uneven illumination and complex background were solved effectively by removing the background light from the image. Finally, a parking space extraction method based on the connected region has been designed, which further simplified the parking space extraction and image processing. The experiment results show that the mAP (mean Average Precision) value of the Faster R-CNN model using 101-Floor ResNet as the feature extraction network is 89.30%, which is 2.28% higher than that of the Faster R-CNN model using 50-Floor ResNet as the feature extraction network. The model built in this paper can detect most parking spaces well. The position of the output target box is accurate. In some test scenarios, the confidence of parking space recognition can even reach 100%. In summary, the proposed method can realize the effective identification and accurate positioning of parking spaces.

Deep learning models achieve high-quality results in image processing. However, to robustly optimize parameters of deep neural networks, large annotated datasets are needed. Image annotation is often performed manually by experts without a comprehensive tool for assistance which is time- consuming, burdensome, and not intuitive. Using the here presented modular Karlsruhe Image Data Annotation (KaIDA) tool, for the first time assisted annotation in various image processing tasks is possible to support users during this process. It aims to simplify annotation, increase user efficiency, enhance annotation quality, and provide additional useful annotation-related functionalities. KaIDA is available open-source at https://git.scc.kit.edu/sc1357/kaida., (© 2022 the author(s), published by De Gruyter, Berlin/Boston.)

One of the primary factors contributing to death across all age groups is cardiovascular disease. In the analysis of heart function, analyzing the left ventricle (LV) from 2D echocardiographic images is a common medical procedure for heart patients. Consistent and accurate segmentation of the LV exerts significant impact on the understanding of the normal anatomy of the heart, as well as the ability to distinguish the aberrant or diseased structure of the heart. Therefore, LV segmentation is an important and critical task in medical practice, and automated LV segmentation is a pressing need. The deep learning models have been utilized in research for automatic LV segmentation. In this work, three cutting-edge convolutional neural network architectures (SegNet, Fully Convolutional Network, and Mask R-CNN) are designed and implemented to segment the LV. In addition, an echocardiography image dataset is generated, and the amount of training data is gradually increased to measure segmentation performance using evaluation metrics. The pixel's accuracy, precision, recall, specificity, Jaccard index, and dice similarity coefficients are applied to evaluate the three models. The Mask R-CNN model outperformed the other two models in these evaluation metrics. As a result, the Mask R-CNN model is used in this study to examine the effect of training data. For 4,000 images, the network achieved 92.21% DSC value, 85.55% Jaccard index, 98.76% mean accuracy, 96.81% recall, 93.15% precision, and 96.58% specificity value. Relatively, the Mask R-CNN outperformed other architectures, and the performance achieves stability when the model is trained using more than 4,000 training images., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Shoaib, Lai, Chuah, Hum, Ali, Dhanalakshmi, Wang and Wu.)

Automating the extraction of meaningful temporal information from sequences of microscopy images represents a major challenge to characterize dynamical biological processes. So far, strong limitations in the ability to quantitatively analyze single-cell trajectories have prevented large-scale investigations to assess the dynamics of entry into replicative senescence in yeast. Here, we have developed DetecDiv, a microfluidic-based image acquisition platform combined with deep learning-based software for high-throughput single-cell division tracking. We show that DetecDiv can automatically reconstruct cellular replicative lifespans with high accuracy and performs similarly with various imaging platforms and geometries of microfluidic traps. In addition, this methodology provides comprehensive temporal cellular metrics using time-series classification and image semantic segmentation. Last, we show that this method can be further applied to automatically quantify the dynamics of cellular adaptation and real-time cell survival upon exposure to environmental stress. Hence, this methodology provides an all-in-one toolbox for high-throughput phenotyping for cell cycle, stress response, and replicative lifespan assays., Competing Interests: TA, DH, GC No competing interests declared, (© 2022, Aspert et al.)

Background: Refractive error detection is a significant factor in preventing the development of myopia. To improve the efficiency and accuracy of refractive error detection, a refractive error detection network (REDNet) is proposed that combines the advantages of a convolutional neural network (CNN) and a recurrent neural network (RNN). It not only extracts the features of each image, but also fully utilizes the sequential relationship between images. In this article, we develop a system to predict the spherical power, cylindrical power, and spherical equivalent in multiple eccentric photorefraction images. Approach First, images of the pupil area are extracted from multiple eccentric photorefraction images; then, the features of each pupil image are extracted using the REDNet convolution layers. Finally, the features are fused by the recurrent layers in REDNet to predict the spherical power, cylindrical power, and spherical equivalent., Results: The results show that the mean absolute error (MAE) values of the spherical power, cylindrical power, and spherical equivalent can reach 0.1740 D (diopters), 0.0702 D, and 0.1835 D, respectively., Significance: This method demonstrates a much higher accuracy than those of current state-of-the-art deep-learning methods. Moreover, it is effective and practical., (© 2022. The Author(s).)

With the SARS-CoV-2's exponential growth, intelligent and constructive practice is required to diagnose the COVID-19. The rapid spread of the virus and the shortage of reliable testing models are considered major issues in detecting COVID-19. This problem remains the peak burden for clinicians. With the advent of artificial intelligence (AI) in image processing, the burden of diagnosing the COVID-19 cases has been reduced to acceptable thresholds. But traditional AI techniques often require centralized data storage and training for the predictive model development which increases the computational complexity. The real-world challenge is to exchange data globally across hospitals while also taking into account of the organizations' privacy concerns. Collaborative model development and privacy protection are critical considerations while training a global deep learning model. To address these challenges, this paper proposes a novel framework based on blockchain and the federated learning model. The federated learning model takes care of reduced complexity, and blockchain helps in distributed data with privacy maintained. More precisely, the proposed federated learning ensembled deep five learning blockchain model (FLED-Block) framework collects the data from the different medical healthcare centers, develops the model with the hybrid capsule learning network, and performs the prediction accurately, while preserving the privacy and shares among authorized persons. Extensive experimentation has been carried out using the lung CT images and compared the performance of the proposed model with the existing VGG-16 and 19, Alexnets, Resnets-50 and 100, Inception V3, Densenets-121, 119, and 150, Mobilenets, SegCaps in terms of accuracy (98.2%), precision (97.3%), recall (96.5%), specificity (33.5%), and F1-score (97%) in predicting the COVID-19 with effectively preserving the privacy of the data among the heterogeneous users., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Durga and Poovammal.)

The performance of a neural network depends on the availability of datasets, and most deep learning techniques lack accuracy and generalization when they are trained using limited datasets. Using synthesized training data is one of the effective ways to overcome the above limitation. Besides, the previous corroded bolt detection method has focused on classifying only two classes, clean and fully rusted bolts, and its performance for detecting partially rusted bolts is still questionable. This study presents a deep learning method to identify corroded bolts in steel structures using a mask region-based convolutional neural network (Mask-RCNN) trained on synthesized data. The Resnet50 integrated with a feature pyramid network is used as the backbone for feature extraction in the Mask-RCNN-based corroded bolt detector. A four-step data synthesis procedure is proposed to autonomously generate the training datasets of corroded bolts with different severities. Afterwards, the proposed detector is trained by the synthesized datasets, and its robustness is demonstrated by detecting corroded bolts in a lab-scale steel structure under varying capturing distances and perspectives. The results show that the proposed method has detected corroded bolts well and identified their corrosion levels with the most desired overall accuracy rate = 96.3% for a 1.0 m capturing distance and 97.5% for a 15° perspective angle.

In this paper, deep learning and image processing technologies are combined, and an automatic sampling robot is proposed that can completely replace the manual method in the three-dimensional space when used for the autonomous location of sampling points. It can also achieve good localization accuracy, which solves the problems of the high labor intensity, low efficiency, and poor scientific accuracy of the manual sampling of mineral powder. To improve localization accuracy and eliminate non-linear image distortion due to wide-angle lenses, distortion correction was applied to the captured images. We solved the problem of low detection accuracy in some scenes of Single Shot MultiBox Detector (SSD) through data augmentation. A visual localization model has been established, and the image coordinates of the sampling point have been determined through color screening, image segmentation, and connected body feature screening, while coordinate conversion has been performed to complete the spatial localization of the sampling point, guiding the robot in performing accurate sampling. Field experiments were conducted to validate the intelligent sampling robot, which showed that the maximum visual positioning error of the robot is 36 mm in the x-direction and 24 mm in the y-direction, both of which meet the error range of less than or equal to 50 mm, and could meet the technical standards and requirements of industrial sampling localization accuracy.

In this paper, a new algorithm for extracting the laser fringe center is proposed. Based on a deep learning skeleton extraction network, the laser stripe center can be extracted quickly and accurately. Skeleton extraction is the process of reducing the shape image to its approximate central axis representation while maintaining the image's topological and geometric shape. Skeleton extraction is an important step in topological and geometric shape analysis. According to the characteristics of the wheelset laser curve dataset, a new skeleton extraction network, a hierarchical skeleton network (LuoNet), is proposed. The proposed architecture has three levels of the encoder-decoder network, and YE Module interconnection is designed between each level of the encoder and decoder network. In the wheelset laser curve dataset, the F1&#95;score can reach 0.714. Compared with the traditional laser curve center extraction algorithm, the proposed LuoNet algorithm has the advantages of short running time, high accuracy, and stable extraction results.

Due to its increasing incidence, skin cancer, and especially melanoma, is a serious health disease today. The high mortality rate associated with melanoma makes it necessary to detect the early stages to be treated urgently and properly. This is the reason why many researchers in this domain wanted to obtain accurate computer-aided diagnosis systems to assist in the early detection and diagnosis of such diseases. The paper presents a systematic review of recent advances in an area of increased interest for cancer prediction, with a focus on a comparative perspective of melanoma detection using artificial intelligence, especially neural network-based systems. Such structures can be considered intelligent support systems for dermatologists. Theoretical and applied contributions were investigated in the new development trends of multiple neural network architecture, based on decision fusion. The most representative articles covering the area of melanoma detection based on neural networks, published in journals and impact conferences, were investigated between 2015 and 2021, focusing on the interval 2018-2021 as new trends. Additionally presented are the main databases and trends in their use in teaching neural networks to detect melanomas. Finally, a research agenda was highlighted to advance the field towards the new trends.

The aim of this study was to develop a deep learning-based algorithm for fully automated spleen segmentation using CT images and to evaluate the performance in conditions directly or indirectly affecting the spleen (e.g., splenomegaly, ascites). For this, a 3D U-Net was trained on an in-house dataset (n = 61) including diseases with and without splenic involvement (in-house U-Net), and an open-source dataset from the Medical Segmentation Decathlon (open dataset, n = 61) without splenic abnormalities (open U-Net). Both datasets were split into a training (n = 32.52%), a validation (n = 9.15%) and a testing dataset (n = 20.33%). The segmentation performances of the two models were measured using four established metrics, including the Dice Similarity Coefficient (DSC). On the open test dataset, the in-house and open U-Net achieved a mean DSC of 0.906 and 0.897 respectively ( p = 0.526). On the in-house test dataset, the in-house U-Net achieved a mean DSC of 0.941, whereas the open U-Net obtained a mean DSC of 0.648 ( p < 0.001), showing very poor segmentation results in patients with abnormalities in or surrounding the spleen. Thus, for reliable, fully automated spleen segmentation in clinical routine, the training dataset of a deep learning-based algorithm should include conditions that directly or indirectly affect the spleen.

With the rapid growth and development of cities, Intelligent Traffic Management and Control (ITMC) is becoming a fundamental component to address the challenges of modern urban traffic management, where a wide range of daily problems need to be addressed in a prompt and expedited manner. Issues such as unpredictable traffic dynamics, resource constraints, and abnormal events pose difficulties to city managers. ITMC aims to increase the efficiency of traffic management by minimizing the odds of traffic problems, by providing real-time traffic state forecasts to better schedule the intersection signal controls. Reliable implementations of ITMC improve the safety of inhabitants and the quality of life, leading to economic growth. In recent years, researchers have proposed different solutions to address specific problems concerning traffic management, ranging from image-processing and deep-learning techniques to forecasting the traffic state and deriving policies to control intersection signals. This review article studies the primary public datasets helpful in developing models to address the identified problems, complemented with a deep analysis of the works related to traffic state forecast and intersection-signal-control models. Our analysis found that deep-learning-based approaches for short-term traffic state forecast and multi-intersection signal control showed reasonable results, but lacked robustness for unusual scenarios, particularly during oversaturated situations, which can be resolved by explicitly addressing these cases, potentially leading to significant improvements of the systems overall. However, there is arguably a long path until these models can be used safely and effectively in real-world scenarios.

Generalizability of deep-learning (DL) model performance is not well understood and uses anecdotal assumptions for increasing training data to improve segmentation of medical images. We report statistical methods for visual interpretation of DL models trained using ImageNet initialization with natural-world ( T II ) and supervised learning with medical images ( L MI ) for binary segmentation of skin cancer, prostate tumors, and kidneys. An algorithm for computation of Dice scores from union and intersections of individual output masks was developed for synergistic segmentation by T II and L MI models. Stress testing with non-Gaussian distributions of infrequent clinical labels and images showed that sparsity of natural-world and domain medical images can counterintuitively reduce type I and type II errors of DL models. A toolkit of 30 T II and L MI models, code, and visual outputs of 59,967 images is shared to identify the target and non-target medical image pixels and clinical labels to explain the performance of DL models., Competing Interests: The authors declare no competing interests., (© 2021 The Authors.)

Background: Abdominal aortic atherosclerotic plaque burden may have clinical significance but manual measurement is time-consuming and impractical., Purpose: To perform external validation on an automated atherosclerotic plaque detector for noncontrast and postcontrast abdominal CT., Materials and Methods: The training data consisted of 114 noncontrast CT scans and 23 postcontrast CT urography scans. The testing data set consisted of 922 CT colonography (CTC) scans, and 1207 paired noncontrast and postcontrast CT scans from renal donors from a second institution. Reference standard data included manual plaque segmentations in the 137 training scans and manual plaque burden measurements in the 922 CTC scans. The total Agatston score and group (0-3) was determined using fully-automated deep learning software. Performance was assessed by measures of agreement, linear regression, and paired evaluations., Results: On CTC scans, automated Agatston scoring correlated highly with manual assessment (R 2  = 0.94). On paired renal donor CT scans, automated Agatston scoring on postcontrast CT correlated highly with noncontrast CT (R 2  = 0.95). When plaque burden was expressed as a group score, there was excellent agreement for both the CTC (weighted kappa 0.80 ± 0.01 [95% confidence interval: 0.78-0.83]) and renal donor (0.83 ± 0.02 [0.79-0.86]) assessments., Conclusion: Fully automated detection, segmentation, and scoring of abdominal aortic atherosclerotic plaques on both pre- and post-contrast CT was validated and may have application for population-based studies., (Published by Elsevier Inc.)

Purpose: The purpose of this study was to develop a fast and automatic algorithm to detect and segment lymphadenopathy from head and neck computed tomography (CT) examination., Materials and Methods: An ensemble of three convolutional neural networks (CNNs) based on a U-Net architecture were trained to segment the lymphadenopathies in a fully supervised framework. The resulting predictions were assessed using the Dice similarity coefficient (DSC) on examinations presenting one or more adenopathies. On examinations without adenopathies, the score was given by the formula M/(M+A) where M was the mean adenopathy volume per patient and A the volume segmented by the algorithm. The networks were trained on 117 annotated CT acquisitions., Results: The test set included 150 additional CT acquisitions unseen during the training. The performance on the test set yielded a mean score of 0.63., Conclusion: Despite limited available data and partial annotations, our CNN based approach achieved promising results in the task of cervical lymphadenopathy segmentation. It has the potential to bring precise quantification to the clinical workflow and to assist the clinician in the detection task., (Copyright © 2021 Société française de radiologie. Published by Elsevier Masson SAS. All rights reserved.)

Strong evidence from studies on primates and rodents shows that changes in pupil diameter may reflect neural activity in the locus coeruleus (LC). Pupillometry is the only available non-invasive technique that could be used as a reliable and easily accessible real-time biomarker of changes in the in vivo activity of the LC. However, the application of pupillometry to preclinical research in rodents is not yet fully standardized. A lack of consensus on the technical specifications of some of the components used for image recording or positioning of the animal and cameras have been recorded in recent scientific literature. In this study, a novel pupillometry system to indirectly assess, in real-time, the function of the LC in anesthetized rodents is presented. The system comprises a deep learning SOLOv2 instance-based fast segmentation framework and a platform designed to place the experimental subject, the video cameras for data acquisition, and the light source. The performance of the proposed setup was assessed and compared to other baseline methods using a validation and an external test set. In the latter, the calculated intersection over the union was 0.93 and the mean absolute percentage error was 1.89% for the selected method. The Bland-Altman analysis depicted an excellent agreement. The results confirmed a high accuracy that makes the system suitable for real-time pupil size tracking, regardless of the pupil's size, light intensity, or any features typical of the recording process in sedated mice. The framework could be used in any neurophysiological study with sedated or fixed-head animals.

A deep learning (DL) method for accelerated magnetic resonance (MR) imaging is presented that incorporates domain knowledge of parallel MR imaging to augment the DL networks for accurate and stable image reconstruction. The proposed DL method employs a novel loss function consisting of a combination of mean absolute error, structural similarity, and sobel edge loss. The DL model takes both original measurements and images reconstructed by the parallel imaging method as inputs to the network. The accuracy of the proposed method was evaluated using two anatomical regions and six MRI contrasts and was compared with state-of-the-art parallel imaging and deep learning methods. The proposed method significantly outperformed the other methods for all the six different contrasts in terms of structural similarity, peak signal to noise ratio, and normalized mean squared error. The out-of-sample performance of the proposed method was assessed for a truly "unseen" case in a volunteer scan. The method produced images without any artificial features, often occurring in the DL image reconstruction methods. A stability analysis was performed by adding perturbations to the input, which demonstrated that the proposed method is robust and stable with respect to small structural changes, and different undersampling ratios. Comprehensive validation on large datasets demonstrated that incorporation of domain knowledge sufficiently regularizes the DL based image reconstruction and produces accurate and stable image enhancement., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

Advancements in volume electron microscopy mean it is now possible to generate thousands of serial images at nanometre resolution overnight, yet the gold standard approach for data analysis remains manual segmentation by an expert microscopist, resulting in a critical research bottleneck. Although some machine learning approaches exist in this domain, we remain far from realizing the aspiration of a highly accurate, yet generic, automated analysis approach, with a major obstacle being lack of sufficient high-quality ground-truth data. To address this, we developed a novel citizen science project, Etch a Cell, to enable volunteers to manually segment the nuclear envelope (NE) of HeLa cells imaged with serial blockface scanning electron microscopy. We present our approach for aggregating multiple volunteer annotations to generate a high-quality consensus segmentation and demonstrate that data produced exclusively by volunteers can be used to train a highly accurate machine learning algorithm for automatic segmentation of the NE, which we share here, in addition to our archived benchmark data., (© 2021 The Authors. Traffic published by John Wiley & Sons Ltd.)

Artificial intelligence (AI)-based image analysis has increased drastically in recent years. However, all applications use individual solutions, highly specialized for a particular task. Here, an easy-to-use, adaptable, and open source software, called AIDeveloper (AID) to train neural nets (NN) for image classification without the need for programming is presented. AID provides a variety of NN-architectures, allowing to apply trained models on new data, obtain performance metrics, and export final models to different formats. AID is benchmarked on large image datasets (CIFAR-10 and Fashion-MNIST). Furthermore, models are trained to distinguish areas of differentiated stem cells in images of cell culture. A conventional blood cell count and a blood count obtained using an NN are compared, trained on >1.2 million images, and demonstrated how AID can be used for label-free classification of B- and T-cells. All models are generated by non-programmers on generic computers, allowing for an interdisciplinary use., (© 2021 The Authors. Advanced Science published by Wiley-VCH GmbH.)

The quantification of blood flow velocity in the human conjunctiva is clinically essential for assessing microvascular hemodynamics. Since the conjunctival microvessel is imaged in several seconds, eye motion during image acquisition causes motion artifacts limiting the accuracy of image segmentation performance and measurement of the blood flow velocity. In this paper, we introduce a novel customized optical imaging system for human conjunctiva with deep learning-based segmentation and motion correction. The image segmentation process is performed by the Attention-UNet structure to achieve high-performance segmentation results in conjunctiva images with motion blur. Motion correction processes with two steps-registration and template matching-are used to correct for large displacements and fine movements. The image displacement values decrease to 4-7 μm during registration (first step) and less than 1 μm during template matching (second step). With the corrected images, the blood flow velocity is calculated for selected vessels considering temporal signal variances and vessel lengths. These methods for resolving motion artifacts contribute insights into studies quantifying the hemodynamics of the conjunctiva, as well as other tissues.

The use of deep learning models to identify lesions on cotton leaves on the basis of images of the crop in the field is proposed in this article. Cultivated in most of the world, cotton is one of the economically most important agricultural crops. Its cultivation in tropical regions has made it the target of a wide spectrum of agricultural pests and diseases, and efficient solutions are required. Moreover, the symptoms of the main pests and diseases cannot be differentiated in the initial stages, and the correct identification of a lesion can be difficult for the producer. To help resolve the problem, the present research provides a solution based on deep learning in the screening of cotton leaves which makes it possible to monitor the health of the cotton crop and make better decisions for its management. With the learning models GoogleNet and Resnet50 using convolutional neural networks, a precision of 86.6% and 89.2%, respectively, was obtained. Compared with traditional approaches for the processing of images such as support vector machines (SVM), Closest k-neighbors (KNN), artificial neural networks (ANN) and neuro-fuzzy (NFC), the convolutional neural networks proved to be up to 25% more precise, suggesting that this method can contribute to a more rapid and reliable inspection of the plants growing in the field.

Background: Multimodal wearable technologies have brought forward wide possibilities in human activity recognition, and more specifically personalized monitoring of eating habits. The emerging challenge now is the selection of most discriminative information from high-dimensional data collected from multiple sources. The available fusion algorithms with their complex structure are poorly adopted to the computationally constrained environment which requires integrating information directly at the source. As a result, more simple low-level fusion methods are needed., Objective: In the absence of a data combining process, the cost of directly applying high-dimensional raw data to a deep classifier would be computationally expensive with regard to the response time, energy consumption, and memory requirement. Taking this into account, we aimed to develop a data fusion technique in a computationally efficient way to achieve a more comprehensive insight of human activity dynamics in a lower dimension. The major objective was considering statistical dependency of multisensory data and exploring intermodality correlation patterns for different activities., Methods: In this technique, the information in time (regardless of the number of sources) is transformed into a 2D space that facilitates classification of eating episodes from others. This is based on a hypothesis that data captured by various sensors are statistically associated with each other and the covariance matrix of all these signals has a unique distribution correlated with each activity which can be encoded on a contour representation. These representations are then used as input of a deep model to learn specific patterns associated with specific activity., Results: In order to show the generalizability of the proposed fusion algorithm, 2 different scenarios were taken into account. These scenarios were different in terms of temporal segment size, type of activity, wearable device, subjects, and deep learning architecture. The first scenario used a data set in which a single participant performed a limited number of activities while wearing the Empatica E4 wristband. In the second scenario, a data set related to the activities of daily living was used where 10 different participants wore inertial measurement units while performing a more complex set of activities. The precision metric obtained from leave-one-subject-out cross-validation for the second scenario reached 0.803. The impact of missing data on performance degradation was also evaluated., Conclusions: To conclude, the proposed fusion technique provides the possibility of embedding joint variability information over different modalities in just a single 2D representation which results in obtaining a more global view of different aspects of daily human activities at hand, and yet preserving the desired performance level in activity recognition., (©Nooshin Bahador, Denzil Ferreira, Satu Tamminen, Jukka Kortelainen. Originally published in JMIR mHealth and uHealth (http://mhealth.jmir.org), 28.01.2021.)

This generation faces existential threats because of the global assault of the novel Corona virus 2019 (i.e., COVID-19). With more than thirteen million infected and nearly 600000 fatalities in 188 countries/regions, COVID-19 is the worst calamity since the World War II. These misfortunes are traced to various reasons, including late detection of latent or asymptomatic carriers, migration, and inadequate isolation of infected people. This makes detection, containment, and mitigation global priorities to contain exposure via quarantine, lockdowns, work/stay at home, and social distancing that are focused on "flattening the curve". While medical and healthcare givers are at the frontline in the battle against COVID-19, it is a crusade for all of humanity. Meanwhile, machine and deep learning models have been revolutionary across numerous domains and applications whose potency have been exploited to birth numerous state-of-the-art technologies utilised in disease detection, diagnoses, and treatment. Despite these potentials, machine and, particularly, deep learning models are data sensitive, because their effectiveness depends on availability and reliability of data. The unavailability of such data hinders efforts of engineers and computer scientists to fully contribute to the ongoing assault against COVID-19. Faced with a calamity on one side and absence of reliable data on the other, this study presents two data-augmentation models to enhance learnability of the Convolutional Neural Network (CNN) and the Convolutional Long Short-Term Memory (ConvLSTM)-based deep learning models (DADLMs) and, by doing so, boost the accuracy of COVID-19 detection. Experimental results reveal improvement in terms of accuracy of detection, logarithmic loss, and testing time relative to DLMs devoid of such data augmentation. Furthermore, average increases of 4% to 11% in COVID-19 detection accuracy are reported in favour of the proposed data-augmented deep learning models relative to the machine learning techniques. Therefore, the proposed algorithm is effective in performing a rapid and consistent Corona virus diagnosis that is primarily aimed at assisting clinicians in making accurate identification of the virus.

The emergence of deep-learning methods in different computer vision tasks has proved to offer increased detection, recognition or segmentation accuracy when large annotated image datasets are available. In the case of medical image processing and computer-aided diagnosis within ultrasound images, where the amount of available annotated data is smaller, a natural question arises: are deep-learning methods better than conventional machine-learning methods? How do the conventional machine-learning methods behave in comparison with deep-learning methods on the same dataset? Based on the study of various deep-learning architectures, a lightweight multi-resolution Convolutional Neural Network (CNN) architecture is proposed. It is suitable for differentiating, within ultrasound images, between the Hepatocellular Carcinoma (HCC), respectively the cirrhotic parenchyma (PAR) on which HCC had evolved. The proposed deep-learning model is compared with other CNN architectures that have been adapted by transfer learning for the ultrasound binary classification task, but also with conventional machine-learning (ML) solutions trained on textural features. The achieved results show that the deep-learning approach overcomes classical machine-learning solutions, by providing a higher classification performance.

The main purpose of the study was to develop a high accuracy system able to diagnose skin lesions using deep learning-based methods. We propose a new decision system based on multiple classifiers like neural networks and feature-based methods. Each classifier (method) gives the final decision system a certain weight, depending on the calculated accuracy, helping the system make a better decision. First, we created a neural network (NN) that can differentiate melanoma from benign nevus. The NN architecture is analyzed by evaluating it during the training process. Some biostatistic parameters, such as accuracy, specificity, sensitivity, and Dice coefficient are calculated. Then, we developed three other methods based on convolutional neural networks (CNNs). The CNNs were pre-trained using large ImageNet and Places365 databases. GoogleNet, ResNet-101, and NasNet-Large, were used in the enumeration order. CNN architectures were fine-tuned in order to distinguish the different types of skin lesions using transfer learning. The accuracies of the classifications were determined. The last proposed method uses the classical method of image object detection, more precisely, the one in which some features are extracted from the images, followed by the classification step. In this case, the classification was done by using a support vector machine. Just as in the first method, the sensitivity, specificity, Dice similarity coefficient and accuracy are determined. A comparison of the obtained results from all the methods is then done. As mentioned above, the novelty of this paper is the integration of these methods in a global fusion-based decision system that uses the results obtained by each individual method to establish the fusion weights. The results obtained by carrying out the experiments on two different free databases shows that the proposed system offers higher accuracy results.

Infrared thermal imaging presents a promising avenue for detecting physiological phenomena such as hot flushes in animals, presenting a non-invasive and efficient approach for monitoring health and behavior. However, thermal images often suffer from various types of noise, which can impede the accuracy of analysis. In this study, the efficacy of different noise filtering algorithms is investigated utilizing filtering algorithms as preprocessing steps to enhance U-Net convolutional neural network (CNN) performance in processing animal skin infrared image sets for hot flush recognition. This study compares the performance of four commonly used filtering methods: mean, median, Gaussian, and bilateral filters. The impact of each filtering technique on noise reduction and preservation of features critical for hot flush detection is evaluated in a machine learning hot flush detection algorithm. The optimal filtering for skin thermal imaging was a median filter which significantly improved the U-Net CNN's ability to accurately identify hot flush patterns, achieving an Intersection over Union score of 92.6% compared to 90.4% without filters. This research contributes to the advancement of thermal image processing methodologies for animal health monitoring applications, providing valuable insights for researchers and practitioners in the field of veterinary medicine and animal behavior studies utilizing autonomous thermal image segmentation. [ABSTRACT FROM AUTHOR]

This research paper introduces a novel approach in the realm of digital preservation and inheritance of Intangible Cultural Heritage (ICH) through a Customized 3D Convolutional Neural Network (CNN). The core of this study lies in the development of an advanced image processing algorithm tailored to accurately recognize, categorize, and archive diverse forms of ICH, which include traditional performances, ceremonies, oral traditions, and crafts. Utilizing a volumetric 3D CNN, this paper demonstrates how complex ICH elements can be effectively captured and analyzed, overcoming the limitations of traditional 2D image processing methods. The network is trained on a comprehensive dataset of ICH imagery, ensuring sensitivity to the subtle nuances and dynamic nature of these cultural expressions. This paper highlights the algorithm's capability in not only safeguarding the visual aspects of ICH but also in providing an interactive, digital medium for education and cultural dissemination. The proposed method shows significant promise in aiding the efforts of cultural preservationists and educators, offering a technologically advanced pathway for the protection and inheritance of the world's rich, yet vulnerable, cultural heritage. This study sets a precedent in the interdisciplinary field of cultural heritage conservation, digital technology, and artificial intelligence, providing a scalable and effective solution for global ICH preservation initiatives. [ABSTRACT FROM AUTHOR]

In this work we introduce GrapheNet, a deep learning framework based on an Inception-Resnet architecture using image-like encoding of structural features for the prediction of the properties of nanographenes. The model is validated on datasets of computed structure/property data on graphene oxide and defected graphene nanoflakes. By exploiting the planarity of quasi-bidimensional systems and through encoding structures into images, and leveraging the flexibility and power of deep learning in image processing, Graphenet achieves significant accuracy in predicting the physicochemical properties of nanographenes. This approach is able to efficiently encode structures composed of hundreds of atoms, scaling efficiently with the size of the model and enabling the prediction of the properties of large systems, which contrasts with the limitations of current atomistic-level representations for deep learning applications. The approach proposed based on image encoding exhibit a significant numerical accuracy and outperforms the computational efficiency of current representations of materials at the atomistic level, with significant advantages especially in the representation of nanostructures and large planar systems. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) single molecule localization microscopy (SMLM) plays an important role in biomedical applications, but its data processing is very complicated. Deep learning is a potential tool to solve this problem. As the state of art 3D super-resolution localization algorithm based on deep learning, FD-DeepLoc algorithm reported recently still has a gap with the expected goal of online image processing, even though it has greatly improved the data processing throughput. In this paper, a new algorithm Lite-FD-DeepLoc is developed on the basis of FD-DeepLoc algorithm to meet the online image processing requirements of 3D SMLM. This new algorithm uses the feature compression method to reduce the parameters of the model, and combines it with pipeline programming to accelerate the inference process of the deep learning model. The simulated data processing results show that the image processing speed of Lite-FD-DeepLoc is about twice as fast as that of FD-DeepLoc with a slight decrease in localization accuracy, which can realize real-time processing of 256×256 pixels size images. The results of biological experimental data processing imply that Lite-FD-DeepLoc can successfully analyze the data based on astigmatism and saddle point engineering, and the global resolution of the reconstructed image is equivalent to or even better than FD-DeepLoc algorithm. [ABSTRACT FROM AUTHOR]

In large-scale astronomical surveys, traditional supernova detection pipelines rely on complex and relatively inefficient image differencing techniques. This paper proposes an end-to-end deep-learning supernova detection network, the Real-Time SuperNova DEtection TRansformer (RT-SNDETR). This network partially replaces traditional pipelines by integrating image differencing, source detection, and Real-bogus classification, achieving a speed 51.49 times that of the fastest image differencing method, SFFT. Additionally, it remains competitive with methods like YOLO v8, offering a well-balanced trade-off between speed and accuracy. Experimental results highlight RT-SNDETR's superior performance, with an average precision(AP) of 96.30 per cent on synthetic samples and 76.60 per cent on real supernova samples. It significantly outperforms other detection networks, including RT-DETR (+5.6 per cent AP on synthetic/+5.1 per cent AP on real samples) and Cascade R-CNN (+8.9 per cent AP on synthetic/ +28.6 per cent AP on real samples). The incorporation of CycleGAN-based data generation methods plays a significant role in enhancing RT-SNDETR's performance. These methods simulate realistic PSF variations, enabling the object detection network to learn more robust features and improving its generalization to real supernovae data. Additionally, by integrating unsupervised domain adaptation techniques, RT-SNDETR achieves an AP of 81.70 per cent on real SDSS supernova survey samples. This study demonstrates RT-SNDETR's potential to significantly enhance both the speed and accuracy of supernova detection, making it a highly effective solution for large-scale astronomical surveys. [ABSTRACT FROM AUTHOR]

The recently developed high-throughput system for cell spheroid generation (SpheroWell) is a promising technology for cost- and time-efficient in vitro analysis of, for example, chondrogenic differentiation. It is a compartmental growth surface where spheroids develop from a cell monolayer by self-assembling and aggregation. In order to automatize the analysis of spheroids, we aimed to develop imaging software and improve the localization of cell compartments and fully formed spheroids. Our workflow provides automated detection and localization of spheroids in different formation stages within Petri dishes based on images created with a low-budget camera imaging setup. This automated detection enables a fast and inexpensive analysis workflow by processing a stack of images within a short period of time, which is essential for the extraction of early readout parameters. Our workflow combines image processing algorithms and deep learning-based image localization/segmentation methods like Mask R-CNN and Unet++. These methods are refined by an evolution strategy for automated grid detection, which is able to improve the overall segmentation and classification quality. Besides the already pre-trained neural networks and predefined image processing parameters, our evolution-based post-processing provides the required adaptability for our workflow to deliver a consistent and reproducible quality. This is especially important due to the use of a low-budget imaging setup with various light conditions. The to-be-detected objects of the three different stages show improved results using our evolutionary post-processing for monolayer and starting aggregation with Dice coefficients of 0.7301 and 0.8562, respectively, compared with the raw scores of 0.2879 and 0.8187. The Dice coefficient of the fully formed spheroids in both cases is 0.8829. With our algorithm, we provide automated analyses of cell spheroid by self-assembling in SpheroWell dishes, even if the images are created using a low-budget camera setup. [ABSTRACT FROM AUTHOR]