Search

In transportation, roads sometimes have cracks due to overloading and other reasons, which seriously affect driving safety, and it is crucial to identify and fill road cracks in time. Aiming at the defects of existing semantic segmentation models that have degraded the segmentation performance of road crack images and the standard convolution makes it challenging to capture the spatial and channel coupling relationship between pixels. It is difficult to differentiate crack pixels from background pixels in complex backgrounds; this paper proposes a semantic segmentation model for road cracks that combines channel-spatial convolution with the aggregation of frequency features. A new convolutional block is proposed to accurately identify cracked pixels by grouping spatial displacements and convolutional kernel weight dynamization while modeling pixel spatial relationships linked to channel features. To enhance the contrast of crack edges, a frequency domain feature aggregation module is proposed, which uses a simple windowing strategy to solve the problem of mismatch of frequency domain inputs and, at the same time, takes into account the effect of the frequency imaginary part on the features to model the deep frequency features effectively. Finally, a feature refinement module is designed to refine the semantic features to improve the segmentation accuracy. Many experiments have proved that the model proposed in this paper has better performance and more application potential than the current popular general model. [ABSTRACT FROM AUTHOR]

Bone segmentation is an important step to perform biomechanical failure load simulations on in-vivo CT data of patients with bone metastasis, as it is a mandatory operation to obtain meshes needed for numerical simulations. Segmentation can be a tedious and time consuming task when done manually, and expert segmentations are subject to intra- and inter-operator variability. Deep learning methods are increasingly employed to automatically carry out image segmentation tasks. These networks usually need to be trained on a large image dataset along with the manual segmentations to maximize generalization to new images, but it is not always possible to have access to a multitude of CT-scans with the associated ground truth. It then becomes necessary to use training techniques to make the best use of the limited available data. In this paper, we propose a dedicated pipeline of preprocessing, deep learning based segmentation method and post-processing for in-vivo human femurs and vertebrae segmentation from CT-scans volumes. We experimented with three U-Net architectures and showed that out-of-the-box models enable automatic and high-quality volume segmentation if carefully trained. We compared the failure load simulation results obtained on femurs and vertebrae using either automatic or manual segmentations and studied the sensitivity of the simulations on small variations of the automatic segmentation. The failure loads obtained using automatic segmentations were comparable to those obtained using manual expert segmentations for all the femurs and vertebrae tested, demonstrating the effectiveness of the automated segmentation approach for failure load simulations. [ABSTRACT FROM AUTHOR]

Blinding eye diseases are often related to changes in retinal structure, which can be detected by analysing retinal blood vessels in fundus images. However, existing techniques struggle to accurately segment these delicate vessels. Although deep learning has shown promise in medical image segmentation, its reliance on specific operations can limit its ability to capture crucial details such as the edges of the vessel. This paper introduces LMBiS-Net, a lightweight convolutional neural network designed for the segmentation of retinal vessels. LMBiS-Net achieves exceptional performance with a remarkably low number of learnable parameters (only 0.172 million). The network used multipath feature extraction blocks and incorporates bidirectional skip connections for the information flow between the encoder and decoder. In addition, we have optimised the efficiency of the model by carefully selecting the number of filters to avoid filter overlap. This optimisation significantly reduces training time and improves computational efficiency. To assess LMBiS-Net's robustness and ability to generalise to unseen data, we conducted comprehensive evaluations on four publicly available datasets: DRIVE, STARE, CHASE_DB1, and HRF The proposed LMBiS-Net achieves significant performance metrics in various datasets. It obtains sensitivity values of 83.60%, 84.37%, 86.05%, and 83.48%, specificity values of 98.83%, 98.77%, 98.96%, and 98.77%, accuracy (acc) scores of 97.08%, 97.69%, 97.75%, and 96.90%, and AUC values of 98.80%, 98.82%, 98.71%, and 88.77% on the DRIVE, STARE, CHEASE_DB, and HRF datasets, respectively. In addition, it records F1 scores of 83.43%, 84.44%, 83.54%, and 78.73% on the same datasets. Our evaluations demonstrate that LMBiS-Net achieves high segmentation accuracy (acc) while exhibiting both robustness and generalisability across various retinal image datasets. This combination of qualities makes LMBiS-Net a promising tool for various clinical applications. [ABSTRACT FROM AUTHOR]

Vehicle identification systems are vital components that enable many aspects of contemporary life, such as safety, trade, transit, and law enforcement. They improve community and individual well-being by increasing vehicle management, security, and transparency. These tasks entail locating and extracting license plates from images or video frames using computer vision and machine learning techniques, followed by recognizing the letters or digits on the plates. This paper proposes a new license plate detection and recognition method based on the deep learning YOLO v8 method, image processing techniques, and the OCR technique for text recognition. For this, the first step was the dataset creation, when gathering 270 images from the internet. Afterward, CVAT (Computer Vision Annotation Tool) was used to annotate the dataset, which is an open-source software platform made to make computer vision tasks easier to annotate and label images and videos. Subsequently, the newly released Yolo version, the Yolo v8, has been employed to detect the number plate area in the input image. Subsequently, after extracting the plate the k-means clustering algorithm, the thresholding techniques, and the opening morphological operation were used to enhance the image and make the characters in the license plate clearer before using OCR. The next step in this process is using the OCR technique to extract the characters. Eventually, a text file containing only the character reflecting the vehicle's country is generated. To ameliorate the efficiency of the proposed approach, several metrics were employed, namely precision, recall, F1-Score, and CLA. In addition, a comparison of the proposed method with existing techniques in the literature has been given. The suggested method obtained convincing results in both detection as well as recognition by obtaining an accuracy of 99% in detection and 98% in character recognition. [ABSTRACT FROM AUTHOR]

Polyp detection is a challenging task in the diagnosis of Colorectal Cancer (CRC), and it demands clinical expertise due to the diverse nature of polyps. The recent years have witnessed the development of automated polyp detection systems to assist the experts in early diagnosis, considerably reducing the time consumption and diagnostic errors. In automated CRC diagnosis, polyp segmentation is an important step which is carried out with deep learning segmentation models. Recently, Vision Transformers (ViT) are slowly replacing these models due to their ability to capture long range dependencies among image patches. However, the existing ViTs for polyp do not harness the inherent self-attention abilities and incorporate complex attention mechanisms. This paper presents Polyp-Vision Transformer (Polyp-ViT), a novel Transformer model based on the conventional Transformer architecture, which is enhanced with adaptive mechanisms for feature extraction and positional embedding. Polyp-ViT is tested on the Kvasir-seg and CVC-Clinic DB Datasets achieving segmentation accuracies of 0.9891 ± 0.01 and 0.9875 ± 0.71 respectively, outperforming state-of-the-art models. Polyp-ViT is a prospective tool for polyp segmentation which can be adapted to other medical image segmentation tasks as well due to its ability to generalize well. [ABSTRACT FROM AUTHOR]

Given that defect detection in weld X-ray images is a critical aspect of pressure vessel manufacturing and inspection, accurate differentiation of the type, distribution, number, and area of defects in the images serves as the foundation for judging weld quality, and the segmentation method of defects in digital X-ray images is the core technology for differentiating defects. Based on the publicly available weld seam dataset GDX-ray, this paper proposes a complete technique for fault segmentation in X-ray pictures of pressure vessel welds. The key works are as follows: (1) To address the problem of a lack of defect samples and imbalanced distribution inside GDX-ray, a DA-DCGAN based on a two-channel attention mechanism is devised to increase sample data. (2) A convolutional block attention mechanism is incorporated into the coding layer to boost the accuracy of small-scale defect identification. The proposed MAU-Net defect semantic segmentation network uses multi-scale even convolution to enhance large-scale features. The proposed method can mask electrostatic interference and non-defect-class parts in the actual weld X-ray images, achieve an average segmentation accuracy of 84.75% for the GDX-ray dataset, segment and accurately rate the valid defects with a correct rating rate of 95%, and thus realize practical value in engineering. [ABSTRACT FROM AUTHOR]

Semantic segmentation of remote sensing imagery (RSI) is critical in many domains due to the diverse landscapes and different sizes of geo-objects that RSI contains, making semantic segmentation challenging. In this paper, a convolutional network, named Adaptive Feature Fusion UNet (AFF-UNet), is proposed to optimize the semantic segmentation performance. The model has three key aspects: (1) dense skip connections architecture and an adaptive feature fusion module that adaptively weighs different levels of feature maps to achieve adaptive feature fusion, (2) a channel attention convolution block that obtains the relationship between different channels using a tailored configuration, and (3) a spatial attention module that obtains the relationship between different positions. AFF-UNet was evaluated on two public RSI datasets and was quantitatively and qualitatively compared with other models. Results from the Potsdam dataset showed that the proposed model achieved an increase of 1.09% over DeepLabv3 + in terms of the average F1 score and a 0.99% improvement in overall accuracy. The visual qualitative results also demonstrated a reduction in confusion of object classes, better performance in segmenting different sizes of object classes, and better object integrity. Therefore, the proposed AFF-UNet model optimizes the accuracy of RSI semantic segmentation. [ABSTRACT FROM AUTHOR]

Metallographic images or often called the microstructures contain important information about metals, such as strength, toughness, ductility, corrosion resistance, which are used to choose the proper materials for various engineering applications. Thus by understanding the microstructures, one can determine the behaviour of a component made of a particular metal, and can predict the failure of that component in certain conditions. Image segmentation is a powerful technique for determination of morphological features of the microstructure like volume fraction, inclusion morphology, void, and crystal orientations. These are some key factors for determining the physical properties of metal. Therefore, automatic micro-structure characterization using image processing is useful for industrial applications which currently adopts deep learning-based segmentation models. In this paper, we propose a metallographic image segmentation method using an ensemble of modified U-Nets. Three U-Net models having the same architecture are separately fed with color transformed imaged (RGB, HSV and YUV). We improvise the U-Net with dilated convolutions and attention mechanisms to get finer grained features. Then we apply the sum-rule-based ensemble method on the outcomes of U-Net models to get the final prediction mask. We achieve the mean intersection over union (IoU) score of 0.677 on a publicly available standard dataset, namely MetalDAM. We also show that the proposed method obtains results comparable to state-of-the-art methods with fewer number of model parameters. The source code of the proposed work can be found at https://github.com/mb16biswas/attention-unet. [ABSTRACT FROM AUTHOR]

Tongue cracks refer to fissures with different depth and shapes on the tongue's surface, which can characterize the pathological characteristics of spleen and stomach. Tongue cracks are of great significance to the objective study of tongue diagnosis. However, tongue cracks are small and complex, existing methods are difficult to extract them effectively. In order to achieve more accurate extraction and identification of tongue crack, this paper proposes to apply a deep learning network based on image segmentation (Segmentation-Based Deep-Learning, SBDL) to extract and identify tongue crack. In addition, we have studied the quantitative description of tongue crack features. Firstly, the pre-processed tongue crack samples were amplified by using adding salt and pepper noise, changing the contrast and horizontal mirroring; secondly, the annotation tool Crack-Tongue was used to label tongue crack; thirdly, the tongue crack extraction model was trained by using SBDL; fourthly, the cracks on the tongue surface were detected and located by the segmentation network, and then the output and features of the segmentation network were put into the decision network for the classification of crack tongue images; finally, the tongue crack segmentation and identification results were quantitatively evaluated. The experimental results showed that the tongue crack extraction and recognition results based on SBDL were better than Mask Region-based Convolutional Neural Network (Mask R-CNN), DeeplabV3+, U-Net, UNet++ and Semantic Segmentation with Adversarial Learning (SegAN). This method effectively solved the inaccurate tongue crack extraction caused by the tongue crack's color being close to the surrounding tongue coating's color. This method can achieve better tongue crack extraction and recognition results on a small tongue crack data set and provides a new idea for tongue crack recognition, which is of practical value for tongue diagnosis objectification. [ABSTRACT FROM AUTHOR]

Deep learning methods have enabled a fast, accurate and automated approach for retinal layer segmentation in posterior segment OCT images. Due to the success of semantic segmentation methods adopting the U-Net, a wide range of variants and improvements have been developed and applied to OCT segmentation. Unfortunately, the relative performance of these methods is difficult to ascertain for OCT retinal layer segmentation due to a lack of comprehensive comparative studies, and a lack of proper matching between networks in previous comparisons, as well as the use of different OCT datasets between studies. In this paper, a detailed and unbiased comparison is performed between eight U-Net architecture variants across four different OCT datasets from a range of different populations, ocular pathologies, acquisition parameters, instruments and segmentation tasks. The U-Net architecture variants evaluated include some which have not been previously explored for OCT segmentation. Using the Dice coefficient to evaluate segmentation performance, minimal differences were noted between most of the tested architectures across the four datasets. Using an extra convolutional layer per pooling block gave a small improvement in segmentation performance for all architectures across all four datasets. This finding highlights the importance of careful architecture comparison (e.g. ensuring networks are matched using an equivalent number of layers) to obtain a true and unbiased performance assessment of fully semantic models. Overall, this study demonstrates that the vanilla U-Net is sufficient for OCT retinal layer segmentation and that state-of-the-art methods and other architectural changes are potentially unnecessary for this particular task, especially given the associated increased complexity and slower speed for the marginal performance gains observed. Given the U-Net model and its variants represent one of the most commonly applied image segmentation methods, the consistent findings across several datasets here are likely to translate to many other OCT datasets and studies. This will provide significant value by saving time and cost in experimentation and model development as well as reduced inference time in practice by selecting simpler models. [ABSTRACT FROM AUTHOR]

The semantic segmentation of omnidirectional urban driving images is a research topic that has increasingly attracted the attention of researchers, because the use of such images in driving scenes is highly relevant. However, the case of motorized two-wheelers has not been treated yet. Since the dynamics of these vehicles are very different from those of cars, we focus our study on images acquired using a motorcycle. This paper provides a thorough comparative study to show how different deep learning approaches handle omnidirectional images with different representations, including perspective, equirectangular, spherical, and fisheye, and presents the best solution to segment road scene omnidirectional images. We use in this study real perspective images, and synthetic perspective, fisheye and equirectangular images, simulated fisheye images, as well as a test set of real fisheye images. By analyzing both qualitative and quantitative results, the conclusions of this study are multiple, as it helps understand how the networks learn to deal with omnidirectional distortions. Our main findings are that models with planar convolutions give better results than the ones with spherical convolutions, and that models trained on omnidirectional representations transfer better to standard perspective images than vice versa. [ABSTRACT FROM AUTHOR]

Fully automated and volumetric segmentation of critical tumors may play a crucial role in diagnosis and surgical planning. One of the most challenging tumor segmentation tasks is localization of pancreatic ductal adenocarcinoma (PDAC). Exclusive application of conventional methods does not appear promising. Deep learning approaches has achieved great success in the computer aided diagnosis, especially in biomedical image segmentation. This paper introduces a framework based on convolutional neural network (CNN) for segmentation of PDAC mass and surrounding vessels in CT images by incorporating powerful classic features, as well. First, a 3D-CNN architecture is used to localize the pancreas region from the whole CT volume using 3D Local Binary Pattern (LBP) map of the original image. Segmentation of PDAC mass is subsequently performed using 2D attention U-Net and Texture Attention U-Net (TAU-Net). TAU-Net is introduced by fusion of dense Scale-Invariant Feature Transform (SIFT) and LBP descriptors into the attention U-Net. An ensemble model is then used to cumulate the advantages of both networks using a 3D-CNN. In addition, to reduce the effects of imbalanced data, a multi-objective loss function is proposed as a weighted combination of three classic losses including Generalized Dice Loss (GDL), Weighted Pixel-Wise Cross Entropy loss (WPCE) and boundary loss. Due to insufficient sample size for vessel segmentation, we used the above-mentioned pre-trained networks and fine-tuned them. Experimental results show that the proposed method improves the Dice score for PDAC mass segmentation in portal-venous phase by 7.52% compared to state-of-the-art methods in term of DSC. Besides, three dimensional visualization of the tumor and surrounding vessels can facilitate the evaluation of PDAC treatment response. [ABSTRACT FROM AUTHOR]

Liver cancer is one of the leading causes of cancer deaths in Asia and Africa. It is caused by the Hepatocellular carcinoma (HCC) in almost 90% of all cases. HCC is a malignant tumor and the most common histological type of the primary liver cancers. The detection and evaluation of viable tumor regions in HCC present an important clinical significance since it is a key step to assess response of chemoradiotherapy and tumor cell proportion in genetic tests. Recent advances in computer vision, digital pathology and microscopy imaging enable automatic histopathology image analysis for cancer diagnosis. In this paper, we present a multi-resolution deep learning model HistoCAE for viable tumor segmentation in whole-slide liver histopathology images. We propose convolutional autoencoder (CAE) based framework with a customized reconstruction loss function for image reconstruction, followed by a classification module to classify each image patch as tumor versus non-tumor. The resulting patch-based prediction results are spatially combined to generate the final segmentation result for each WSI. Additionally, the spatially organized encoded feature map derived from small image patches is used to compress the gigapixel whole-slide images. Our proposed model presents superior performance to other benchmark models with extensive experiments, suggesting its efficacy for viable tumor area segmentation with liver whole-slide images. [ABSTRACT FROM AUTHOR]

Machine learning has considerably improved medical image analysis in the past years. Although data-driven approaches are intrinsically adaptive and thus, generic, they often do not perform the same way on data from different imaging modalities. In particular computed tomography (CT) data poses many challenges to medical image segmentation based on convolutional neural networks (CNNs), mostly due to the broad dynamic range of intensities and the varying number of recorded slices of CT volumes. In this paper, we address these issues with a framework that adds domain-specific data preprocessing and augmentation to state-of-the-art CNN architectures. Our major focus is to stabilise the prediction performance over samples as a mandatory requirement for use in automated and semi-automated workflows in the clinical environment. To validate the architecture-independent effects of our approach we compare a neural architecture based on dilated convolutions for parallel multi-scale processing (a modified Mixed-Scale Dense Network: MS-D Net) to traditional scaling operations (a modified U-Net). Finally, we show that an ensemble model combines the strengths across different individual methods. Our framework is simple to implement into existing deep learning pipelines for CT analysis. It performs well on a range of tasks such as liver and kidney segmentation, without significant differences in prediction performance on strongly differing volume sizes and varying slice thickness. Thus our framework is an essential step towards performing robust segmentation of unknown real-world samples. [ABSTRACT FROM AUTHOR]

An amendment to this paper has been published and can be accessed via a link at the top of the paper. [ABSTRACT FROM AUTHOR]