Search

Background: The most recent advances in Computed Tomography (CT) image reconstruction technology are Deep learning image reconstruction (DLIR) algorithms. Due to drawbacks in Iterative reconstruction (IR) techniques such as negative image texture and nonlinear spatial resolutions, DLIRs are gradually replacing them. However, the potential use of DLIR in Head and Chest CT has to be examined further. Hence, the purpose of the study is to review the influence of DLIR on Radiation dose (RD), Image noise (IN), and outcomes of the studies compared with IR and FBP in Head and Chest CT examinations., Methods: We performed a detailed search in PubMed, Scopus, Web of Science, Cochrane Library, and Embase to find the articles reported using DLIR for Head and Chest CT examinations between 2017 to 2023. Data were retrieved from the short-listed studies using Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines., Results: Out of 196 articles searched, 15 articles were included. A total of 1292 sample size was included. 14 articles were rated as high and 1 article as moderate quality. All studies compared DLIR to IR techniques. 5 studies compared DLIR with IR and FBP. The review showed that DLIR improved IQ, and reduced RD and IN for CT Head and Chest examinations., Conclusions: DLIR algorithm have demonstrated a noted enhancement in IQ with reduced IN for CT Head and Chest examinations at lower dose compared with IR and FBP. DLIR showed potential for enhancing patient care by reducing radiation risks and increasing diagnostic accuracy., Competing Interests: No competing interests were disclosed., (Copyright: © 2024 Chandran M O et al.)

Traditional algorithms can achieve good results when registering homologous images, but it cannot reach satisfying results for registration between synthetic aperture radar (SAR) and optical images. The difficulty is that the image texture information and structures of different modalities is very different which leads to poor registration results. To solve this problem, we present a robust matching framework for registration between SAR and optical images. First, a novel deep learning network is utilized to generate high quality pseudo-optical images from SAR images. Next, feature points are detected and extracted using the multi-scale Harris algorithm. Then the feature points are constructed through the gradient position orientation histogram method. Finally, the actual position of the feature points will be reconstructed through a feedback mechanism for matching. Experimental results demonstrate its superior matching performance with respect to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As an important part of metal processing, welding is widely used in industrial manufacturing activities, and its application scenarios are very extensive. Due to technical limitations, the welding process always unavoidably leaves weld defects. Weld defects are extremely hazardous, and the work used must be guaranteed to be defect-free, regardless of the field. However, manual weld inspection has subjective factors such as inefficiency and easy missed detection, and although some automatic weld inspection methods have appeared, these traditional methods still do not meet actual demand in terms of detection time and detection accuracy. Therefore, there is a need for a higher quality weld image automatic detection method to replace the manual method and the traditional automatic detection method. In view of the above, this paper proposes a weld seam image recognition algorithm based on deep learning. The Adam adaptive moment estimation algorithm is chosen as the backpropagation optimization algorithm to accelerate the training of convolutional neural networks and design an independent adaptive learning rate. Through the simulation of the collected 4500 tube images, the adaptive threshold-based method is used for weld seam extraction. The algorithm proposed in this paper is compared with the weld seam recognition method based on image texture feature value distribution (ITFVD) and the SUSAN-based weld defect target detection method. The results show that the proposed method can identify weld defects in a short time on different sizes of weld images, and can further detect the type of weld defects. In addition, the method in this paper is better than the other two methods in the false detection rate, recall rate and overall recognition accuracy, which shows that the experimental results have achieved the expected results. [ABSTRACT FROM AUTHOR]

To ensure the timely detection of safety hazards in transmission lines and to enhance accurately the detection of insulator defects in complicated environments, this study proposes a 3D attention-focused pure convolutional target detection algorithm (CMYOLOv7) based on you only look once v7 (YOLOv7) for defect detection on insulators in complicated environments. Firstly, to address the incapacity of focusing on the target in the backbone feature extraction networks, this study proposes a focused pure convolutional feature extraction module (ConvSimCB) to enhance the extraction and focus capability on insulator defect features. Secondly, to solve the problem of loss of key detail feature information caused by maximum pooling in spatial pyramid pooling module (SPPCSPC), this study proposes a mixed spatial pyramid pooling module (MIXPCSPC) to retain abundant image texture detail information and increase accuracy in detection of tiny insulator defects. Finally, a lightweight generic upsampling operator (CARAFE) is introduced to enhance the feature map resolution to address image distortion caused by the Nearest Neighbor Method of upsampling. This study proposed CMYOLOv7 achieves 98.37% precision, 90.59% recall, 95.68% mean average precision (MAP), and 94% F1 score, higher than YOLOv7 by 0.61%, 8.64%, 5.41%, and 5%. [ABSTRACT FROM AUTHOR]

Considering the defect detection issues in electroluminescence (EL) of photovoltaic (PV) cell systems, lots of factors result in performance degradation, including defect diversity, data imbalance, scale difference, etc. Focal-EIoU loss, an effective defect detection solution for EL, is proposed based on the improved YOLOv5. Firstly, by analyzing the detection background and scale characteristics of EL defects, a binary classification is carried out in the system. Subsequently, a cascade detection network based on YOLOv5 is designed to further extract features from the binary-classified defects. The defect localization and classification are achieved in this way. To address the problem of imbalanced defect samples, a loss function is designed based on EIoU and Focal-F1 Loss. Experimental results are illustrated to show the effectiveness. Compared with the existing CNN-based deep learning approaches, the proposed focal loss calculation-based method can effectively improve the performance of handling sample imbalance. Moreover, in the detection of 12 types of defects, the Yolov5 algorithms can always obtain higher MAP (mean average precision) even with different parameter levels (Yolov5m: 0.791 vs. 0.857, Yolov5l: 0.798 vs. 0.862, Yolov5x: 0.802 vs. 0.867, Yolov5s: 0.793 vs. 0.865). [ABSTRACT FROM AUTHOR]

In order to solve the problems of poor region delineation and boundary artifacts in Chinese style migration of images, an improved Variational Autoencoder (VAE) method for dress style migration is proposed. Firstly, the Yolo v3 model is used to quickly identify the dress localization of the input image, then, the classical semantic segmentation algorithm (FCN) is used to finely delineate the desired dress style migration region twice, and finally, the trained VAE model is used to generate the migrated Chinese style image. The results show that, compared with the traditional style migration model, the improved VAE style migration model can obtain finer synthetic images for dress style migration and can adapt to different Chinese traditional styles to meet the application requirements of dress style migration scenarios. We evaluated several deep learning-based models and achieved a BLEU value of 0.6 on average. The transformer-based model outperformed the other models, achieving a BLEU value of up to 0.72. [ABSTRACT FROM AUTHOR]

In the petroleum and coal industries, digital image technology and acoustic emission technology are employed to study rock properties, but both exhibit flaws during data processing. Digital image technology is vulnerable to interference from fractures and scaling, leading to potential loss of image data; while acoustic emission technology is not hindered by these issues, noise from rock destruction can interfere with the electrical signals, causing errors. The monitoring errors of these techniques can undermine the effectiveness of rock damage analysis. To address this issue, this paper focuses on the restoration of image data acquired through digital image technology, leveraging deep learning techniques, and using soft and hard rocks made of similar materials as research subjects, an improved Incremental Transformer image algorithm is employed to repair distorted or missing strain nephograms during uniaxial compression experiments. The concrete implementation entails using a comprehensive training set of strain nephograms derived from digital image technology, fabricating masks for absent image segments, and predicting strain nephograms with full strain detail. Additionally, we adopt deep separable convolutional networks to optimize the algorithm's operational efficiency. Based on this, the analysis of rock damage is conducted using the repaired strain nephograms, achieving a closer correlation with the actual physical processes of rock damage compared to conventional digital image technology and acoustic emission techniques. The improved incremental Transformer algorithm presented in this paper will contribute to enhancing the efficiency of digital image technology in the realm of rock damage, saving time and money, and offering an innovative approach to traditional rock damage analysis. [ABSTRACT FROM AUTHOR]

Deep learning, which is a dominating technique in artificial intelligence, has completely changed image understanding over the past decade. As a consequence, the sea ice extraction (SIE) problem has reached a new era. We present a comprehensive review of four important aspects of SIE, including algorithms, datasets, applications and future trends. Our review focuses on research published from 2016 to the present, with a specific focus on deep-learning-based approaches in the last five years. We divided all related algorithms into three categories, including the conventional image classification approach, the machine learning-based approach and deep-learning-based methods. We reviewed the accessible ice datasets including SAR-based datasets, the optical-based datasets and others. The applications are presented in four aspects including climate research, navigation, geographic information systems (GIS) production and others. This paper also provides insightful observations and inspiring future research directions. [ABSTRACT FROM AUTHOR]

Many security detectors do not have the ability to output individual luggage package images and are not compatible with deep learning algorithms. In this paper, a luggage package extraction of X-ray images based on the ES-MBD (Edge Sensitive Multi-channel Background Difference Algorithm) method is proposed, which is aiming at the problem that background difference binarization is insensitive to texture features and edge detection binarization is insensitive to smooth areas. In this method, X-ray luggage package images from complex original video images are used as a key target, the RGB three-channel background difference is calculated from the original X-ray image, the edge detection of the grayscale map is performed using the Sobel operator optimized by local gradient enhancement, and the morphological expansion process is performed on the combined results to obtain the complete wrapping target. The Suzuki algorithm is used to detect the outline of the binarized package image, match the package frame area and determine the key target. The ES-MBD method solves the problem of information loss in the traditional binarization method, and retains the information of insensitive regions while reducing noise. Through experimental comparison, the accuracy of ES-MBD binarization method reaches 97.3%, the recall rate reaches 96.5%, and ES-MBD method has obvious advantages in key target extraction of X-ray images. [ABSTRACT FROM AUTHOR]

The purpose is to evaluate whether deep learning-based denoising (DLD) algorithm provides sufficient image quality for abdominal computed tomography (CT) with a 30% reduction in radiation dose, compared to standard-dose CT reconstructed with conventional hybrid iterative reconstruction (IR). The subjects consisted of 50 patients who underwent abdominal CT with standard dose and reconstructed with hybrid IR (ASiR-V50%) and another 50 patients who underwent abdominal CT with approximately 30% less dose and reconstructed with ASiR-V50% and DLD at low-, medium- and high-strength (DLD-L, DLD-M and DLD-H, respectively). The standard deviation of attenuation in liver parenchyma was measured as image noise. Contrast-to-noise ratio (CNR) for portal vein on portal venous phase was calculated. Lesion conspicuity in 23 abdominal solid mass on the reduced-dose CT was rated on a 5-point scale: 0 (best) to −4 (markedly inferior). Compared with hybrid IR of standard-dose CT, DLD-H of reduced-dose CT provided significantly lower image noise (portal phase: 9.0 (interquartile range, 8.7–9.4) HU vs 12.0 (11.4–12.7) HU, P < 0.0001) and significantly higher CNR (median, 5.8 (4.4–7.4) vs 4.3 (3.3–5.3), P = 0.0019). As for DLD-M of reduced-dose CT, no significant difference was found in image noise and CNR compared to hybrid IR of standard-dose CT (P > 0.99). Lesion conspicuity scores for DLD-H and DLD-M were significantly better than hybrid IR (P < 0.05). Dynamic contrast-enhanced abdominal CT acquired with approximately 30% lower radiation dose and generated with the DLD algorithm exhibit lower image noise and higher CNR compared to standard-dose CT with hybrid IR. [ABSTRACT FROM AUTHOR]

Computed tomography (CT) is an imaging technique extensively used in medical treatment, but too much radiation dose in a CT scan will cause harm to the human body. Decreasing the dose of radiation will result in increased noise and artifacts in the reconstructed image, blurring the internal tissue and edge details. To get high-quality CT images, we present a multi-scale feature fusion network (MSFLNet) for low-dose CT (LDCT) denoising. In our MSFLNet, we combined multiple feature extraction modules, effective noise reduction modules, and fusion modules constructed using the attention mechanism to construct a horizontally connected multi-scale structure as the overall architecture of the network, which is used to construct different levels of feature maps at all scales. We innovatively define a composite loss function composed of pixel-level loss based on MS-SSIM-L1 and edge-based edge loss for LDCT denoising. In short, our approach learns a rich set of features that combine contextual information from multiple scales while maintaining the spatial details of denoised CT images. Our laboratory results indicate that compared with the existing methods, the peak signal-to-noise ratio (PSNR) value of CT images of the AAPM dataset processed by the new model is 33.6490, and the structural similarity (SSIM) value is 0.9174, which also achieves good results on the Piglet dataset with different doses. The results also show that the method removes noise and artifacts while effectively preserving CT images' architecture and grain information. [ABSTRACT FROM AUTHOR]

This study is aimed to evaluate effects of deep learning image reconstruction (DLIR) on image quality in single-energy CT (SECT) and dual-energy CT (DECT), in reference to adaptive statistical iterative reconstruction-V (ASIR-V). The Gammex 464 phantom was scanned in SECT and DECT modes at three dose levels (5, 10, and 20 mGy). Raw data were reconstructed using six algorithms: filtered back-projection (FBP), ASIR-V at 40% (AV-40) and 100% (AV-100) strength, and DLIR at low (DLIR-L), medium (DLIR-M), and high strength (DLIR-H), to generate SECT 120kVp images and DECT 120kVp-like images. Objective image quality metrics were computed, including noise power spectrum (NPS), task transfer function (TTF), and detectability index (d′). Subjective image quality evaluation, including image noise, texture, sharpness, overall quality, and low- and high-contrast detectability, was performed by six readers. DLIR-H reduced overall noise magnitudes from FBP by 55.2% in a more balanced way of low and high frequency ranges comparing to AV-40, and improved the TTF values at 50% for acrylic inserts by average percentages of 18.32%. Comparing to SECT 20 mGy AV-40 images, the DECT 10 mGy DLIR-H images showed 20.90% and 7.75% improvement in d′ for the small-object high-contrast and large-object low-contrast tasks, respectively. Subjective evaluation showed higher image quality and better detectability. At 50% of the radiation dose level, DECT with DLIR-H yields a gain in objective detectability index compared to full-dose AV-40 SECT images used in daily practice. [ABSTRACT FROM AUTHOR]

Simple Summary: Brain MRI scans often require different imaging sequences based on tissue types, posing a common challenge. In our research, we propose a method that utilizes Generative Adversarial Networks (GAN) to translate T2-weighted-Fluid-attenuated-Inversion-Recovery (FLAIR) MRI volumes into T2-Weighted (T2W) volumes, and vice versa. To evaluate the effectiveness of our approach, we introduce a novel evaluation schema that incorporates radiomic features. We train two distinct GAN-based architectures, namely Cycle GAN and Dual Cycle-Consistent Adversarial network (DC2Anet), using 510 pair-slices from 102 patients. Our findings indicate that the generative methods can produce results similar to the original sequence without significant changes in radiometric features. This method has the potential to assist clinicians in making informed decisions based on generated images when alternative sequences are unavailable, or time constraints prevent re-scanning MRI patients. One of the most common challenges in brain MRI scans is to perform different MRI sequences depending on the type and properties of tissues. In this paper, we propose a generative method to translate T2-Weighted (T2W) Magnetic Resonance Imaging (MRI) volume from T2-weight-Fluid-attenuated-Inversion-Recovery (FLAIR) and vice versa using Generative Adversarial Networks (GAN). To evaluate the proposed method, we propose a novel evaluation schema for generative and synthetic approaches based on radiomic features. For the evaluation purpose, we consider 510 pair-slices from 102 patients to train two different GAN-based architectures Cycle GAN and Dual Cycle-Consistent Adversarial network (DC2Anet). The results indicate that generative methods can produce similar results to the original sequence without significant change in the radiometric feature. Therefore, such a method can assist clinics to make decisions based on the generated image when different sequences are not available or there is not enough time to re-perform the MRI scans. [ABSTRACT FROM AUTHOR]

Merchant ships sometimes fail to detect small ships at night and in poor visibility, leading to urgent situations and even collisions. Infrared (IR) cameras have inherent advantages in small target detection and become essential environmental awareness equipment on unmanned ships. The existing target detection models are complex and difficult to deploy on small devices. Lightweight detection algorithms are needed with the increase in the number of shipborne cameras. Therefore, herein, a lightweight model for small IR ship detection was selected as the research object. IR videos were collected in the Bohai Strait, the image sampling interval was calculated, and an IR dataset of small ships was constructed. Based on the analysis of the characteristics of the IR ship images, gamma transform was used to preprocess the images, which increased the gray difference between the target and background. The backbone of YOLOv5 was replaced with that of Mobilev3 to improve the computing efficiency. Finally, the results showed that the parameters of the proposed model were reduced by 83% compared with those of the YOLOv5m model, while the detection performance was almost the same. [ABSTRACT FROM AUTHOR]

Simple Summary: A major prognosis factor for glioblastoma patients is the methylation status of the DNA repair enzyme MGMT. Obtaining this information using deep learning models trained on non-invasive MRI data is a major challenge with no scientific consensus to date. In this study, we provide a more rigorous and comprehensive answer to this question by using confidence metrics and relating them to the exact percentage of methylation obtained at biopsy. This systematic approach confirms that the deep learning algorithms developed until now are not suitable for clinical application. We also provide, to the best of our knowledge, the first fully reproducible source code and experiments on this issue. Glioblastoma is the most aggressive primary brain tumor, which almost systematically relapses despite surgery (when possible) followed by radio-chemotherapy temozolomide-based treatment. Upon relapse, one option for treatment is another chemotherapy, lomustine. The efficacy of these chemotherapy regimens depends on the methylation of a specific gene promoter known as MGMT, which is the main prognosis factor for glioblastoma. Knowing this biomarker is a key issue for the clinician to personalize and adapt treatment to the patient at primary diagnosis for elderly patients, in particular, and also upon relapse. The association between MRI-derived information and the prediction of MGMT promoter status has been discussed in many studies, and some, more recently, have proposed the use of deep learning algorithms on multimodal scans to extract this information, but they have failed to reach a consensus. Therefore, in this work, beyond the classical performance figures usually displayed, we seek to compute confidence scores to see if a clinical application of such methods can be seriously considered. The systematic approach carried out, using different input configurations and algorithms as well as the exact methylation percentage, led to the following conclusion: current deep learning methods are unable to determine MGMT promoter methylation from MRI data. [ABSTRACT FROM AUTHOR]

Background: To evaluate the image quality of lower extremity computed tomography angiography (CTA) with deep learning–based reconstruction (DLR) compared to model-based iterative reconstruction (MBIR), hybrid-iterative reconstruction (HIR), and filtered back projection (FBP). Methods: Fifty patients (38 males, average age 59.8 ± 19.2 years) who underwent lower extremity CTA between January and May 2021 were included. Images were reconstructed with DLR, MBIR, HIR, and FBP. The standard deviation (SD), contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), noise power spectrum (NPS) curves, and the blur effect, were calculated. The subjective image quality was independently evaluated by two radiologists. The diagnostic accuracy of DLR, MBIR, HIR, and FBP reconstruction algorithms was calculated. Results: The CNR and SNR were significantly higher in DLR images than in the other three reconstruction algorithms, and the SD was significantly lower in DLR images of the soft tissues. The noise magnitude was the lowest with DLR. The NPS average spatial frequency (fav) values were higher using DLR than HIR. For blur effect evaluation, DLR and FBP were similar for soft tissues and the popliteal artery, which was better than HIR and worse than MBIR. In the aorta and femoral arteries, the blur effect of DLR was worse than MBIR and FBP and better than HIR. The subjective image quality score of DLR was the highest. The sensitivity and specificity of the lower extremity CTA with DLR were the highest in the four reconstruction algorithms with 98.4% and 97.2%, respectively. Conclusions: Compared to the other three reconstruction algorithms, DLR showed better objective and subjective image quality. The blur effect of the DLR was better than that of the HIR. The diagnostic accuracy of lower extremity CTA with DLR was the best among the four reconstruction algorithms. [ABSTRACT FROM AUTHOR]

The performance of underwater target detection algorithms is affected by poor imaging quality in underwater environments. Due to the arithmetic power limitation of underwater devices, existing deep learning networks are unable to provide efficient detection processes with high detection accuracy. Lightweight CNN models have been actively applied for underwater environment detection, yet their lite feature fusion networks cannot provide effective fusion effects and reduce the detection accuracy. In this paper, a lightweight algorithm based on multi-scale feature fusion was proposed, with the model parameters greatly reduced, improving the target detection accuracy. The forward propagation memory overhead is reduced by using multi-scale shared convolutional kernels and pooling operations to co-construct the query matrix in the Tansformer encoding stage. Then, the feature fusion path is optimized in order to enhance the connection of multi-scale features. A multiscale feature adaptive fusion strategy is used to enhance the detection performance and reduce the dependence on the complex feature extraction network. The feature extraction network is also reparameterized to simplify the operation. Using the UPRC offshore dataset for validation, the study results have demonstrated that the statistical mAP metrics validate the detection accuracy. Compared with SSD, RetinaNet and YOLOv5-s improved by 13%, 8.6%, and 0.8%, while the number of parameters decreased by 76.09%, 89.74%, and 87.67%. In addition, compared with the YOLOv5-lite model algorithm with the same parameter volume, the mAP is improved by 3.8%, which verifies the accuracy and efficiency of the algorithm in this paper. [ABSTRACT FROM AUTHOR]

To solve the problems of over-fitting, poor convergence, and reduced recall and accuracy of traditional image recognition algorithms, a junk image recognition algorithm based on deep learning is proposed. Dropout is introduced to overcome over fitting, adagrad adaptive method is used to debug the parameters of deep neural network, and ReLU is adopted to solve the gradient dispersion of neural network training, realize the centralized processing of garbage image data, and extract the edge features, color features and texture features of garbage image in the data set, respectively, shape features. The modified probability density function is used for image classification. According to the different characteristics of garbage image, the image to be recognized is divided into different categories to complete garbage image recognition. The experimental results show that the designed algorithm has good convergence, high recall and accuracy, and short recognition time, indicating that the algorithm is feasible and practical. [ABSTRACT FROM AUTHOR]

Accurate and efficient extraction of cultivated land data is of great significance for agricultural resource monitoring and national food security. Deep-learning-based classification of remote-sensing images overcomes the two difficulties of traditional learning methods (e.g., support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF)) when extracting the cultivated land: (1) the limited performance when extracting the same land-cover type with the high intra-class spectral variation, such as cultivated land with both vegetation and non-vegetation cover, and (2) the limited generalization ability for handling a large dataset to apply the model to different locations. However, the "pooling" process in most deep convolutional networks, which attempts to enlarge the sensing field of the kernel by involving the upscale process, leads to significant detail loss in the output, including the edges, gradients, and image texture details. To solve this problem, in this study we proposed a new end-to-end extraction algorithm, a high-resolution U-Net (HRU-Net), to preserve the image details by improving the skip connection structure and the loss function of the original U-Net. The proposed HRU-Net was tested in Xinjiang Province, China to extract the cultivated land from Landsat Thematic Mapper (TM) images. The result showed that the HRU-Net achieved better performance (Acc: 92.81%; kappa: 0.81; F1-score: 0.90) than the U-Net++ (Acc: 91.74%; kappa: 0.79; F1-score: 0.89), the original U-Net (Acc: 89.83%; kappa: 0.74; F1-score: 0.86), and the Random Forest model (Acc: 76.13%; kappa: 0.48; F1-score: 0.69). The robustness of the proposed model for the intra-class spectral variation and the accuracy of the edge details were also compared, and this showed that the HRU-Net obtained more accurate edge details and had less influence from the intra-class spectral variation. The model proposed in this study can be further applied to other land cover types that have more spectral diversity and require more details of extraction. [ABSTRACT FROM AUTHOR]

Deep learning has achieved remarkable performance in semantically segmenting remotely sensed images. However, the high-frequency detail loss caused by continuous convolution and pooling operations and the uncertainty introduced when annotating low-contrast objects with weak boundaries induce blurred object boundaries. Therefore, a dual-stream network MAE-BG, consisting of an edge detection (ED) branch and a smooth branch with boundary guidance (BG), is proposed. The ED branch is designed to enhance the weak edges that need to be preserved, simultaneously suppressing false responses caused by local texture. This mechanism is achieved by introducing improved multiple-attention edge detection blocks (MAE). Furthermore, two specific ED branches with MAE are designed to combine with typical deep convolutional (DC) and Codec infrastructures and result in two configurations of MAE-A and MAE-B. Meanwhile, multiscale edge information extracted by MAE networks is fed into the backbone networks to complement the detail loss caused by convolution and pooling operations. This results in smooth networks with BG. After that, the segmentation results with improved boundaries are obtained by stacking the output of the ED and smooth branches. The proposed algorithms were evaluated on the ISPRS Potsdam and Inria Aerial Image Labelling datasets. Comprehensive experiments show that the proposed method can precisely locate object boundaries and improve segmentation performance. The MAE-A branch leads to an overall accuracy (OA) of 89.16%, a mean intersection over union (MIOU) of 80.25% for Potsdam, and an OA of 96.61% and MIOU of 86.63% for Inria. Compared with the results without the proposed edge optimization blocks, the OAs from the Potsdam and Inria datasets increase by 5.49% and 7.64%, respectively. [ABSTRACT FROM AUTHOR]

Rapid advancements and the escalating necessity of autonomous algorithms in medical imaging require efficient models to accomplish tasks such as segmentation and classification. However, there exists a significant dependency on the image quality of datasets when using these models. Appreciable improvements to enhance datasets for efficient image analysis have been noted in the past. In addition, deep learning and machine learning are vastly employed in this field. However, even after the advent of these advanced techniques, a significant space exists for new research. Recent research works indicate the vast applicability of preprocessing techniques in segmentation tasks. Contrast stretching is one of the preprocessing techniques used to enhance a region of interest. We propose a novel hybrid meta-heuristic preprocessor (DE-ABC), which optimises the decision variables used in the contrast-enhancement transformation function. We validated the efficiency of the preprocessor against some state-of-the-art segmentation algorithms. Publicly available skin-lesion datasets such as P H 2 , ISIC-2016, ISIC-2017, and ISIC-2018 were employed. We used Jaccard and the dice coefficient as performance matrices; at the maximum, the proposed model improved the dice coefficient from 93.56% to 94.09%. Cross-comparisons of segmentation results with the original datasets versus the contrast-stretched datasets validate that DE-ABC enhances the efficiency of segmentation algorithms. [ABSTRACT FROM AUTHOR]

Most LLIE algorithms focus solely on enhancing the brightness of the image and ignore the extraction of image details, leading to losing much of the information that reflects the semantics of the image, losing the edges, textures, and shape features, resulting in image distortion. In this paper, the DELLIE algorithm is proposed, an algorithmic framework with deep learning as the central premise that focuses on the extraction and fusion of image detail features. Unlike existing methods, basic enhancement preprocessing is performed first, and then the detail enhancement components are obtained by using the proposed detail component prediction model. Then, the V-channel is decomposed into a reflectance map and an illumination map by proposed decomposition network, where the enhancement component is used to enhance the reflectance map. Then, the S and H channels are nonlinearly constrained using an improved adaptive loss function, while the attention mechanism is introduced into the algorithm proposed in this paper. Finally, the three channels are fused to obtain the final enhancement effect. The experimental results show that, compared with the current mainstream LLIE algorithm, the DELLIE algorithm proposed in this paper can extract and recover the image detail information well while improving the luminance, and the PSNR, SSIM, and NIQE are optimized by 1.85%, 4.00%, and 2.43% on average on recognized datasets. [ABSTRACT FROM AUTHOR]

Road detection is defined as one of the core technology of Advanced Driving Assistance System (ADAS), and this problem is important for improving the recognition accuracy and speed. Though much work has been done concerning road detection, the related questions about non-road areas are not thoroughly considered. Understanding the question is of primary importance in ADAS, we proposed an improved algorithm based on deep learning network for road image redundancy removal. Compared with the most typical road recognition methods, the experimental results show that the proposed method improves the speed of road recognition greatly, while ensuring the accuracy of road recognition to high level. [ABSTRACT FROM AUTHOR]

With the development of image restoration technology based on deep learning, more complex problems are being solved, especially in image semantic inpainting based on context. Nowadays, image semantic inpainting techniques are becoming more mature. However, due to the limitations of memory, the instability of training, and the lack of sample diversity, the results of image restoration are still encountering difficult problems, such as repairing the content of glitches which cannot be well integrated with the original image. Therefore, we propose an image inpainting network based on Wasserstein generative adversarial network (WGAN) distance. With the corresponding technology having been adjusted and improved, we attempted to use the Adam algorithm to replace the traditional stochastic gradient descent, and another algorithm to optimize the training used in recent years. We evaluated our algorithm on the ImageNet dataset. We obtained high-quality restoration results, indicating that our algorithm improves the clarity and consistency of the image. [ABSTRACT FROM AUTHOR]

As an active microwave device, synthetic aperture radar (SAR) uses the backscatter of objects for imaging. SAR image ship targets are characterized by unclear contour information, a complex background and strong scattering. Existing deep learning detection algorithms derived from anchor-based methods mostly rely on expert experience to set a series of hyperparameters, and it is difficult to characterize the unique characteristics of SAR image ship targets, which greatly limits detection accuracy and speed. Therefore, this paper proposes a new lightweight position-enhanced anchor-free SAR ship detection algorithm called LPEDet. First, to resolve unclear SAR target contours and multiscale performance problems, we used YOLOX as the benchmark framework and redesigned the lightweight multiscale backbone, called NLCNet, which balances detection speed and accuracy. Second, for the strong scattering characteristics of the SAR target, we designed a new position-enhanced attention strategy, which suppresses background clutter by adding position information to the channel attention that highlights the target information to more accurately identify and locate the target. The experimental results for two large-scale SAR target detection datasets, SSDD and HRSID, show that our method achieves a higher detection accuracy and a faster detection speed than state-of-the-art SAR target detection methods. [ABSTRACT FROM AUTHOR]

In recent years, touch-screen mobile phones have been loved by more and more users, and the word user experience has been mentioned more and more, and interface design has undoubtedly become an important method of interactive design of touch-screen mobile phones. With the progress of technology and market demand, the importance of rational design of smart phone interactive interface is particularly prominent, and user-centered experience design has been paid more and more attention. The traditional style migration is only used on computers, and its target audience is relatively small, with low efficiency and poor effect. At present, the application of interactive art design is becoming more and more homogeneous, without too much change in essential functions, and with no outstanding features in mature applications, some applications have failed to meet users' expectations in terms of functions and operation modes, resulting in polarization of application use and difficulty for new applications to survive. Mobile phone theme design, as a new field of interface interaction design, meets the personalized needs of users and attracts more and more designers' attention. With the rise of artificial intelligence technology, especially the rapid development of deep learning and convolutional neural network, a large number of advanced theories and algorithms have emerged in the field of computer vision. As an important direction of vision research, target detection and style transfer have become the research hotspot of many researchers. How to reasonably formulate the interaction mode, determine the user interface style, layout structure, and information display mode and how to organically combine the mobile phone theme interface design and user interaction experience are problems worthy of discussion and research at present. By studying the process of smart phone theme interface interaction design, sorting out the methods of mobile phone interface interaction design style, this paper deeply analyzes the popular flat and quasi-materialized style and discusses the skills of application. [ABSTRACT FROM AUTHOR]

Texture fusion is the process of applying the style of one style image to another content image. It is an artistic creation and image editing technology. In recent years, the rapid development of deep learning has injected new power into the field of computer vision, and a large number of image style transfer algorithms based on deep learning have been proposed. At the same time, some current character conversion algorithms based on unsupervised learning also face the loss of the content and structure of the generated characters, and at the same time, they have not learned a good face deformation effect, resulting in poor image generation effects. This paper studies the relevant research background and research significance of image style transfer methods and summarizes them in the time sequence of their development; summarizes the style transfer algorithms based on deep learning, and analyzes the advantages and disadvantages of each type of algorithm. Based on the fast style transfer algorithm, this method adds a saliency detection network and designs a saliency loss function. In the training process, the difference between the saliency map of the generated image and the content image is additionally calculated, and the saliency loss is used as a part of the total loss for iterative training. Experiments show that the stylized image generated by this algorithm can better retain the salient area of the content image and has a good visual effect. Compared with the original network, the amount of parameters of the attention mechanism is very small, and there is almost no additional burden. [ABSTRACT FROM AUTHOR]

Tujia brocades are important carriers of Chinese Tujia national culture and art. It records the most detailed and real cultural history of Tujia nationality and is one of the National Intangible Cultural Heritage. Classic graphic elements are separated from Tujia brocade patterns to establish the Tujia brocade graphic element database, which is used for the protection and inheritance of traditional national culture. Tujia brocade dataset collected a total of more than 200 clear Tujia brocade patterns and was divided into seven categories, according to traditional meanings. The weave texture of a Tujia brocade is coarse, and the textural features of the background are obvious, so classical segmentation algorithms cannot achieve good segmentation effects. At the same time, deep learning technology cannot be used because there is no standard Tujia brocade dataset. Based on the above problems, this study proposes a method based on an unsupervised clustering algorithm for the segmentation of Tujia brocades. First, the cluster number K is calculated by fusing local binary patterns (LBP) and gray-level co-occurrence matrix (GLCM) characteristic values. Second, clustering and segmentation are conducted on each input Tujia brocade image by adopting a Gaussian mixture model (GMM) to obtain a preliminary segmentation image, wherein the image yielded after preliminary segmentation is rough. Then, a method based on voting optimization and dense conditional random field (DenseCRF) (CRF denotes conditional random filtering) is adopted to optimize the image after preliminary segmentation and obtain the image segmentation results. Finally, the desired graphic element contour is extracted through interactive cutting. The contributions of this study include: (1) a calculation method for the cluster number K wherein the experimental results show that the effect of the clustering number K chosen in this paper is ideal; (2) an optimization method for the noise points of Tujia brocade patterns based on voting, which can effectively eliminate isolated noise points from brocade patterns. [ABSTRACT FROM AUTHOR]

A face-based authentication system has become an important topic in various fields of IoT applications such as identity validation for social care, crime detection, ATM access, computer security, etc. However, these authentication systems are vulnerable to different attacks. Presentation attacks have become a clear threat for facial biometric-based authentication and security applications. To address this issue, we proposed a deep learning approach for face spoofing detection systems in IoT cloud-based environment. The deep learning approach extracted features from multicolor space to obtain more information from the input face image regarding luminance and chrominance data. These features are combined and selected by the Minimum Redundancy Maximum Relevance (mRMR) algorithm to provide an efficient and discriminate feature set. Finally, the extracted deep color-based features of the face image are used for face spoofing detection in a cloud environment. The proposed method achieves stable results with less training data compared to conventional deep learning methods. This advantage of the proposed approach reduces the time of processing in the training phase and optimizes resource management in storing training data on the cloud. The proposed system was tested and evaluated based on two challenging public access face spoofing databases, namely, Replay-Attack and ROSE-Youtu. The experimental results based on these databases showed that the proposed method achieved satisfactory results compared to the state-of-the-art methods based on an equal error rate (EER) of 0.2% and 3.8%, respectively, for the Replay-Attack and ROSE-Youtu databases. [ABSTRACT FROM AUTHOR]

It is difficult to recognize a target object from foggy images. Aiming at solving this problem, a new algorithm is thereby proposed. Fog concentration estimation is the prerequisite for image defogging. Due to the uncertainty of fog distribution, a fog concentration estimation model is accordingly proposed. Establish the brightness and gradient model in the spatial domain, and establish the FFT model in the frequency domain. Also, a multiple branch network framework is established to realize the qualitative estimation of the fog concentration in images based on comprehensive analysis from spatial and frequency domain levels. In the aspect of foggy image target recognition, a residual network is introduced based on Fast RCNN network structure. The fog concentration information is added into the target recognition function to realize accurate recognition of target from foggy images. Experimental results show that the accuracy of AOM is higher than 81 under different fog concentration indoors and outdoors. [ABSTRACT FROM AUTHOR]

Background: To evaluate the performance of a Deep Learning Image Reconstruction (DLIR) algorithm in pediatric head CT for improving image quality and lesion detection with 0.625 mm thin-slice images. Methods: Low-dose axial head CT scans of 50 children with 120 kV, 0.8 s rotation and age-dependent 150–220 mA tube current were selected. Images were reconstructed at 5 mm and 0.625 mm slice thickness using Filtered back projection (FBP), Adaptive statistical iterative reconstruction-v at 50% strength (50%ASIR-V) (as reference standard), 100%ASIR-V and DLIR-high (DL-H). The CT attenuation and standard deviation values of the gray and white matters in the basal ganglia were measured. The clarity of sulci/cisterns, boundary between white and gray matters, and overall image quality was subjectively evaluated. The number of lesions in each reconstruction group was counted. Results: The 5 mm FBP, 50%ASIR-V, 100%ASIR-V and DL-H images had a subjective score of 2.25 ± 0.44, 3.05 ± 0.23, 2.87 ± 0.39 and 3.64 ± 0.49 in a 5-point scale, respectively with DL-H having the lowest image noise of white matter at 2.00 ± 0.34 HU; For the 0.625 mm images, only DL-H images met the diagnostic requirement. The 0.625 mm DL-H images had similar image noise (3.11 ± 0.58 HU) of the white matter and overall image quality score (3.04 ± 0.33) as the 5 mm 50% ASIR-V images (3.16 ± 0.60 HU and 3.05 ± 0.23). Sixty-five lesions were recognized in 5 mm 50%ASIR-V images and 69 were detected in 0.625 mm DL-H images. Conclusion: DL-H improves the head CT image quality for children compared with ASIR-V images. The 0.625 mm DL-H images improve lesion detection and produce similar image noise as the 5 mm 50%ASIR-V images, indicating a potential 85% dose reduction if current image quality and slice thickness are desired. [ABSTRACT FROM AUTHOR]

Removing motion blur has been an important issue in computer vision literature. Motion blur is caused by the relative motion between the camera and the photographed object. However, in recent years, some achievements have been made in the research of image deblurring by using deep learning algorithms. In this paper, an enhanced adversarial network model is proposed. The proposed model can use the weight of feature channel to generate sharp image and eliminate draughtboard artefacts. In addition, the mixed loss function enables the network to output high-quality image. The proposed approach is tested using GOPRO datasets and Lai datasets. In the GOPRO datasets, the peak signal-to-noise ratio of the proposed approach is up to 28.674, and DeblurGAN is 27.454. And the structural similarity measure can be achieved up to 0.969, and DeblurGAN is 0.939. Furthermore, the images were obtained from China's Chang'e 3 Lander to test the new algorithm. Due to the elimination of the chessboard effect, the deblurred image has a better visual appearance. The proposed method achieved higher performance and efficiency in qualitative and quantitative aspects using the benchmark dataset experiments. The results also provided various insights into the design and development of the camera pointing system, which was mounted on the Lander for capturing images of the moon and rover for Chang'e space mission. [ABSTRACT FROM AUTHOR]

In developed countries, colorectal cancer is the second cause of cancer-related mortality. Chemotherapy is considered a standard treatment for colorectal liver metastases (CLM). Among patients who develop CLM, the assessment of patient response to chemotherapy is often required to determine the need for second-line chemotherapy and eligibility for surgery. However, while FOLFOX-based regimens are typically used for CLM treatment, the identification of responsive patients remains elusive. Computer-aided diagnosis systems may provide insight in the classification of liver metastases identified on diagnostic images. In this paper, we propose a fully automated framework based on deep convolutional neural networks (DCNN) which first differentiates treated and untreated lesions to identify new lesions appearing on CT scans, followed by a fully connected neural networks to predict from untreated lesions in pre-treatment computed tomography (CT) for patients with CLM undergoing chemotherapy, their response to a FOLFOX with Bevacizumab regimen as first-line of treatment. The ground truth for assessment of treatment response was histopathology-determined tumor regression grade. Our DCNN approach trained on 444 lesions from 202 patients achieved accuracies of 91% for differentiating treated and untreated lesions, and 78% for predicting the response to FOLFOX-based chemotherapy regimen. Experimental results showed that our method outperformed traditional machine learning algorithms and may allow for the early detection of non-responsive patients. [ABSTRACT FROM AUTHOR]

Due to the fact that coverless information hiding can effectively resist the detection of steganalysis tools, it has attracted more attention in the field of information hiding. At present, most coverless information hiding schemes select text and image as transmission carriers, while there are few studies on emerging popular media such as video, which has more abundant contents. Taking the natural video as the carrier is more secure and can avoid the attention of attackers. In this paper, we propose a coverless video steganography algorithm based on semantic segmentation. Specifically, to establish the mapping relationship between secret information and video files effectively, this paper introduces the deep learning based on semantic segmentation network to calculate the statistical histogram of semantic information. To quickly index the sender's secret message to the corresponding video frame, we build a three-digit index structure. The receiver can extract the valid video frame from the three-digit index information and restore the secret information. On the one hand, the neural network is trained through the original image and the noisy image in this scheme; therefore, it can not only effectively resist the interference of noises, but also accurately extract the robust deep features of the image. The frames of video generate the robust mapping to the secret information after the semantic information statistics. On the other hand, semantic segmentation belongs to pixel-level segmentation, which has high requirements for network parameters, so it is difficult for attackers to decrypt and recover secret information. Since this scheme does not modify the primitiveness of video data, it can effectively resist steganalysis tools. The experimental results and analysis show that the video coverless information hiding scheme has a large capacity and a certain resistance to noise attack. [ABSTRACT FROM AUTHOR]

This paper compares a series of traditional and deep learning methodologies for the segmentation of textures. Six well-known texture composites first published by Randen and Husøy were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a deep-learning approach based on the U-Net architecture. For the latter, the effects of depth of the network, number of epochs and different optimisation algorithms were investigated. Overall, the best results were provided by the deep-learning approach. However, the best results were distributed within the parameters, and many configurations provided results well below the traditional techniques. [ABSTRACT FROM AUTHOR]

Deep-learning algorithms typically fall within the domain of supervised artificial intelligence and are designed to "learn" from annotated data. Deep-learning models require large, diverse training datasets for optimal model convergence. The effort to curate these datasets is widely regarded as a barrier to the development of deep-learning systems. We developed RIL-Contour to accelerate medical image annotation for and with deep-learning. A major goal driving the development of the software was to create an environment which enables clinically oriented users to utilize deep-learning models to rapidly annotate medical imaging. RIL-Contour supports using fully automated deep-learning methods, semi-automated methods, and manual methods to annotate medical imaging with voxel and/or text annotations. To reduce annotation error, RIL-Contour promotes the standardization of image annotations across a dataset. RIL-Contour accelerates medical imaging annotation through the process of annotation by iterative deep learning (AID). The underlying concept of AID is to iteratively annotate, train, and utilize deep-learning models during the process of dataset annotation and model development. To enable this, RIL-Contour supports workflows in which multiple-image analysts annotate medical images, radiologists approve the annotations, and data scientists utilize these annotations to train deep-learning models. To automate the feedback loop between data scientists and image analysts, RIL-Contour provides mechanisms to enable data scientists to push deep newly trained deep-learning models to other users of the software. RIL-Contour and the AID methodology accelerate dataset annotation and model development by facilitating rapid collaboration between analysts, radiologists, and engineers. [ABSTRACT FROM AUTHOR]

With success of Deep Belief Networks (DBNs) in computer vision, DBN has attracted great attention in hyperspectral classification. Many deep learning based algorithms have been focused on deep feature extraction for classification improvement. Multi-features, such as texture feature, are widely utilized in classification process to enhance classification accuracy greatly. In this paper, a novel hyperspectral classification framework based on an optimal DBN and a novel texture feature enhancement (TFE) is proposed. Through band grouping, sample band selection and guided filtering, the texture features of hyperspectral data are improved. After TFE, the optimal DBN is employed on the hyperspectral reconstructed data for feature extraction and classification. Experimental results demonstrate that the proposed classification framework outperforms some state-of-the-art classification algorithms, and it can achieve outstanding hyperspectral classification performance. Furthermore, our proposed TFE method can play a significant role in improving classification accuracy. [ABSTRACT FROM AUTHOR]

Regional landslide identification is important for the risk management of landslide hazards. The traditional methods of regional landslide identification were mainly conducted by a human being. In previous studies, automatic landslide recognition mainly focused on new landslides distinct from the environment induced by rainfall or earthquake, using the image classification method and semantic segmentation method of deep learning. However, there is a lack of research on the automatic recognition of old loess landslides, which are difficult to distinguish from the environment. Therefore, this study uses the object detection method of deep learning to identify old loess landslides with Google Earth images. At first, a database of loess historical landslide samples was established for deep learning based on Google Earth images. A total of 6111 landslides were interpreted in three landslide areas in Gansu Province, China. Second, three object detection algorithms including the one-stage algorithm RetinaNet and YOLO v3 and the two-stage algorithm Mask R-CNN, were chosen for automatic landslide identification. Mask R-CNN achieved the greatest accuracy, with an AP of 18.9% and F1-score of 55.31%. Among the three landslide areas, the order of identification accuracy from high to low was Site 1, Site 2, and Site 3, with the F1-scores of 62.05%, 61.04% and 50.88%, respectively, which were positively related to their recognition difficulty. The research results proved that the object detection method can be employed for the automatic identification of loess landslides based on Google Earth images. [ABSTRACT FROM AUTHOR]

The High Efficiency Video Coding Standard (HEVC) is one of the most advanced coding schemes at present, and its excellent coding performance is highly suitable for application in the navigation field with limited bandwidth. In recent years, the development of emerging technologies such as screen sharing and remote control has promoted the process of realizing the virtual driving of unmanned ships. In order to improve the transmission and coding efficiency during screen sharing, HEVC proposes a new extension scheme for screen content coding (HEVC-SCC), which is based on the original coding framework. SCC has improved the performance of compressing computer graphics content and video by adding new coding tools, but the complexity of the algorithm has also increased. At present, there is no delay in the compression optimization method designed for radar digital video in the field of navigation. Therefore, our paper starts from the perspective of increasing the speed of encoded radar video, and takes reducing the computational complexity of the rate distortion cost (RD-cost) as the goal of optimization. By analyzing the characteristics of shipborne radar digital video, a fast encoding algorithm for shipborne radar digital video based on deep learning is proposed. Firstly, a coding tree unit (CTU) division depth interval dataset of shipborne radar images was established. Secondly, in order to avoid erroneously skipping of the intra block copy (IBC)/palette mode (PLT) in the coding unit (CU) division search process, we designed a method to divide the depth interval by predicting the CTU in advance and limiting the CU rate distortion cost to be outside the traversal calculation depth interval, which effectively reduced the compression time. The effect of radar transmission and display shows that, within the acceptable range of Bjøntegaard Delta Bit Rate (BD-BR) and Bjøntegaard Delta Peak Signal to Noise Rate (BD-PSNR) attenuation, the algorithm proposed in this paper reduces the coding time by about 39.84%, on average, compared to SCM8.7. [ABSTRACT FROM AUTHOR]

The existing methods for thermal barrier coating (TBC) life prediction rely mainly on experience and formula derivation and are inefficient and inaccurate. By introducing deep learning into TBC life analyses, a convolutional neural network (CNN) is used to extract the TBC interface morphology and analyze its life information, which can achieve a high-efficiency accurate judgment of the TBC life. In this thesis, an Adap–Alex algorithm is proposed to overcome the problems related to the large training time, over-fitting, and low accuracy in the existing CNN training of TBC images with complex tissue morphologies. The method adjusts the receptive field size, stride length, and other parameter settings and combines training epochs with a sigmoid function to realize adaptive pooling. TBC data are obtained by thermal vibration experiments, a TBC dataset is constructed, and then the Adap–Alex algorithm is used to analyze the generated TBC dataset. The average training time of the Adap–Alex method is significantly smaller than those of VGG-Net and Alex-Net by 125 and 685 s, respectively. For a fixed number of thermal vibrations, the test accuracy of the Adap–Alex algorithm is higher than those of Alex-Net and VGG-Net, which facilitates the TBC identification. When the number of thermal vibrations is 300, the accuracy reaches 93%, and the performance is highest. [ABSTRACT FROM AUTHOR]

Phenotypic characteristics of fruit particles, such as projection area, can reflect the growth status and physiological changes of grapes. However, complex backgrounds and overlaps always constrain accurate grape border recognition and detection of fruit particles. Therefore, this paper proposes a two-step phenotypic parameter measurement to calculate areas of overlapped grape particles. These two steps contain particle edge detection and contour fitting. For particle edge detection, an improved HED network is introduced. It makes full use of outputs of each convolutional layer, introduces Dice coefficients to original weighted cross-entropy loss function, and applies image pyramids to achieve multi-scale image edge detection. For contour fitting, an iterative least squares ellipse fitting and region growth algorithm is proposed to calculate the area of grapes. Experiments showed that in the edge detection step, compared with current prevalent methods including Canny, HED, and DeepEdge, the improved HED was able to extract the edges of detected fruit particles more clearly, accurately, and efficiently. It could also detect overlapping grape contours more completely. In the shape-fitting step, our method achieved an average error of 1.5% in grape area estimation. Therefore, this study provides convenient means and measures for extraction of grape phenotype characteristics and the grape growth law. [ABSTRACT FROM AUTHOR]

Simple Summary: Artificial intelligence (AI) is gaining more and more attention in radiology. The efficiency of AI-based algorithms to solve specific problems is, in some cases, far superior compared to human-driven approaches. This is particularly evident in some repetitive tasks, such as segmentation, where AI usually outperforms manual approaches. AI may be also used in quantification where it can provide, for example, fast and efficient longitudinal follow up in liver tumour burden. AI, thanks to the association with radiomic and big data, may also suggest a diagnosis. Finally, AI algorithms can also reduce scan time, increase image quality and, in the case of computed tomography, reduce patient dose. Artificial intelligence (AI) is one of the most promising fields of research in medical imaging so far. By means of specific algorithms, it can be used to help radiologists in their routine workflow. There are several papers that describe AI approaches to solve different problems in liver and pancreatic imaging. These problems may be summarized in four different categories: segmentation, quantification, characterization and image quality improvement. Segmentation is usually the first step of successive elaborations. If done manually, it is a time-consuming process. Therefore, the semi-automatic and automatic creation of a liver or a pancreatic mask may save time for other evaluations, such as quantification of various parameters, from organs volume to their textural features. The alterations of normal liver and pancreas structure may give a clue to the presence of a diffuse or focal pathology. AI can be trained to recognize these alterations and propose a diagnosis, which may then be confirmed or not by radiologists. Finally, AI may be applied in medical image reconstruction in order to increase image quality, decrease dose administration (referring to computed tomography) and reduce scan times. In this article, we report the state of the art of AI applications in these four main categories. [ABSTRACT FROM AUTHOR]

The demand for location-based services (LBS) in large indoor spaces, such as airports, shopping malls, museums and libraries, has been increasing in recent years. However, there is still no fully applicable solution for indoor positioning and navigation like Global Navigation Satellite System (GNSS) solutions in outdoor environments. Positioning in indoor scenes by using smartphone cameras has its own advantages: no additional needed infrastructure, low cost and a large potential market due to the popularity of smartphones, etc. However, existing methods or systems based on smartphone cameras and visual algorithms have their own limitations when implemented in relatively large indoor spaces. To deal with this problem, we designed an indoor positioning system to locate users in large indoor scenes. The system uses common static objects as references, e.g., doors and windows, to locate users. By using smartphone cameras, our proposed system is able to detect static objects in large indoor spaces and then calculate the smartphones’ position to locate users. The system integrates algorithms of deep learning and computer vision. Its cost is low because it does not require additional infrastructure. Experiments in an art museum with a complicated visual environment suggest that this method is able to achieve positioning accuracy within 1 m. [ABSTRACT FROM AUTHOR]