Joint Dense Residual and Recurrent Attention Network for DCE-MRI Breast Tumor Segmentation.
Ontology highlight
ABSTRACT:
SUBMITTER: Qin C
PROVIDER: S-EPMC9045980 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The optic disc(OD) and the optic cup(OC) segmentation is an key step in fundus medical image analysis. Previously, FCN-based methods have been proposed for medical image segmentation tasks. However, the consecutive convolution and pooling operations usually hinder dense prediction tasks which require detailed spatial information, such as image segmentation. In this paper, we propose a network called Recurrent Fully Convolution Network(RFC-Net) for automatic joint segmentation of the OD and the OC, which can captures more high-level information and subtle edge information. The RFC-Net can minimize the loss of spatial information. It is mainly composed of multi-scale input layer, recurrent fully convolutional network, multiple output layer and polar transformation. In RFC-Net, the multi-scale input layer constructs an image pyramid. We propose four recurrent units, which are respectively applied to RFC-Net. Recurrent convolution layer effectively ensures feature representation for OD and OC segmentation tasks through feature accumulation. For each multiple output image, the multiple output cross entropy loss function is applied. To better balance the cup ratio of the segmented image, the polar transformation is used to transform the fundus image from the cartesian coordinate system to the polar coordinate system. We evaluate the effectiveness and generalization of the proposed method on the DRISHTI-GS1 dataset. Compared with the original FCN method and other state-of-the-art methods, the proposed method achieves better segmentation performance.
| S-EPMC7505429 | biostudies-literature
Project description:BackgroundFast and accurate multiorgans segmentation from computed tomography (CT) scans is essential for radiation treatment planning. Self-attention(SA)-based deep learning methodologies provide higher accuracies than standard methods but require memory and computationally intensive calculations, which restricts their use to relatively shallow networks.PurposeOur goal was to develop and test a new computationally fast and memory-efficient bidirectional SA method called nested block self-attention (NBSA), which is applicable to shallow and deep multiorgan segmentation networks.MethodsA new multiorgan segmentation method combining a deep multiple resolution residual network with computationally efficient SA called nested block SA (MRRN-NBSA) was developed and evaluated to segment 18 different organs from head and neck (HN) and abdomen organs. MRRN-NBSA combines features from multiple image resolutions and feature levels with SA to extract organ-specific contextual features. Computational efficiency is achieved by using memory blocks of fixed spatial extent for SA calculation combined with bidirectional attention flow. Separate models were trained for HN (n = 238) and abdomen (n = 30) and tested on set aside open-source grand challenge data sets for HN (n = 10) using a public domain database of computational anatomy and blinded testing on 20 cases from Beyond the Cranial Vault data set with overall accuracy provided by the grand challenge website for abdominal organs. Robustness to two-rater segmentations was also evaluated for HN cases using the open-source data set. Statistical comparison of MRRN-NBSA against Unet, convolutional network-based SA using criss-cross attention (CCA), dual SA, and transformer-based (UNETR) methods was done by measuring the differences in the average Dice similarity coefficient (DSC) accuracy for all HN organs using the Kruskall-Wallis test, followed by individual method comparisons using paired, two-sided Wilcoxon-signed rank tests at 95% confidence level with Bonferroni correction used for multiple comparisons.ResultsMRRN-NBSA produced an average high DSC of 0.88 for HN and 0.86 for the abdomen that exceeded current methods. MRRN-NBSA was more accurate than the computationally most efficient CCA (average DSC of 0.845 for HN, 0.727 for abdomen). Kruskal-Wallis test showed significant difference between evaluated methods (p=0.00025). Pair-wise comparisons showed significant differences between MRRN-NBSA than Unet (p=0.0003), CCA (p=0.030), dual (p=0.038), and UNETR methods (p=0.012) after Bonferroni correction. MRRN-NBSA produced less variable segmentations for submandibular glands (0.82 ± 0.06) compared to two raters (0.75 ± 0.31).ConclusionsMRRN-NBSA produced more accurate multiorgan segmentations than current methods on two different public data sets. Testing on larger institutional cohorts is required to establish feasibility for clinical use.
| S-EPMC9908007 | biostudies-literature
Project description:PurposeAccurate segmentation of liver and liver tumors is critical for radiotherapy. Liver tumor segmentation, however, remains a difficult and relevant problem in the field of medical image processing because of the various factors like complex and variable location, size, and shape of liver tumors, low contrast between tumors and normal tissues, and blurred or difficult-to-define lesion boundaries. In this paper, we proposed a neural network (S-Net) that can incorporate attention mechanisms to end-to-end segmentation of liver tumors from CT images.MethodsFirst, this study adopted a classical coding-decoding structure to realize end-to-end segmentation. Next, we introduced an attention mechanism between the contraction path and the expansion path so that the network could encode a longer range of semantic information in the local features and find the corresponding relationship between different channels. Then, we introduced long-hop connections between the layers of the contraction path and the expansion path, so that the semantic information extracted in both paths could be fused. Finally, the application of closed operation was used to dissipate the narrow interruptions and long, thin divide. This eliminated small cavities and produced a noise reduction effect.ResultsIn this paper, we used the MICCAI 2017 liver tumor segmentation (LiTS) challenge dataset, 3DIRCADb dataset and doctors' manual contours of Hubei Cancer Hospital dataset to test the network architecture. We calculated the Dice Global (DG) score, Dice per Case (DC) score, volumetric overlap error (VOE), average symmetric surface distance (ASSD), and root mean square error (RMSE) to evaluate the accuracy of the architecture for liver tumor segmentation. The segmentation DG for tumor was found to be 0.7555, DC was 0.613, VOE was 0.413, ASSD was 1.186 and RMSE was 1.804. For a small tumor, DG was 0.3246 and DC was 0.3082. For a large tumor, DG was 0.7819 and DC was 0.7632.ConclusionS-Net obtained more semantic information with the introduction of an attention mechanism and long jump connection. Experimental results showed that this method effectively improved the effect of tumor recognition in CT images and could be applied to assist doctors in clinical treatment.
| S-EPMC8381250 | biostudies-literature
Project description:Defining myocardial contours is often the most time-consuming portion of dynamic cardiac MRI image analysis. Displacement encoding with stimulated echoes (DENSE) is a quantitative MRI technique that encodes tissue displacement into the phase of the complex MRI images. Cine DENSE provides a time series of these images, thus facilitating the non-invasive study of myocardial kinematics. Epicardial and endocardial contours need to be defined at each frame on cine DENSE images for the quantification of regional displacement and strain as a function of time. This work presents a reliable and effective two-dimensional semi-automated segmentation technique that uses the encoded motion to project a manually-defined region of interest through time. Contours can then easily be extracted for each cardiac phase. This method boasts several advantages, including, (1) parameters are based on practical physiological limits, (2) contours are calculated for the first few cardiac phases, where it is difficult to visually distinguish blood from myocardium, and (3) the method is independent of the shape of the tissue delineated and can be applied to short- or long-axis views, and on arbitrary regions of interest. Motion-guided contours were compared to manual contours for six conventional and six slice-followed mid-ventricular short-axis cine DENSE datasets. Using an area measure of segmentation error, the accuracy of the segmentation algorithm was shown to be similar to inter-observer variability. In addition, a radial segmentation error metric was introduced for short-axis data. The average radial epicardial segmentation error was 0.36+/-0.08 and 0.40+/-0.10 pixels for slice-followed and conventional cine DENSE, respectively, and the average radial endocardial segmentation error was 0.46+/-0.12 and 0.46+/-0.16 pixels for slice following and conventional cine DENSE, respectively. Motion-guided segmentation employs the displacement-encoded phase shifts intrinsic to DENSE MRI to accurately propagate a single set of pre-defined contours throughout the remaining cardiac phases.
| S-EPMC2614556 | biostudies-literature
Project description:Accurate and robust segmentation of anatomical structures from magnetic resonance images is valuable in many computer-aided clinical tasks. Traditional codec networks are not satisfactory because of their low accuracy of edge segmentation, the low recognition rate of the target, and loss of detailed information. To address these problems, this study proposes a series of improved models for semantic segmentation and progressively optimizes them from the three aspects of convolution module, codec unit, and feature fusion. Instead of the standard convolution structure, we apply a new type of convolution module for the feature extraction. The networks integrate a multi-path method to obtain richer-detail edge information. Finally, a dense network is utilized to strengthen the ability of the feature fusion and integrate more different-level information. The evaluation of the Accuracy, Dice coefficient, and Jaccard index led to values of 0.9855, 0.9185, and 0.8507, respectively. These metrics of the best network increased by 1.0%, 4.0%, and 6.1%, respectively. Boundary F1-Score reached 0.9124 indicating that the proposed networks can segment smaller targets to obtain smoother edges. Our methods obtain more key information than traditional methods and achieve superiority in segmentation performance.
| S-EPMC7954354 | biostudies-literature
Project description:BackgroundThe segmentation of breast ultrasound (US) images has been a challenging task, mainly due to limited data and the inherent image characteristics involved, such as low contrast and speckle noise. Although convolutional neural network-based (CNN-based) methods have made significant progress over the past decade, they lack the ability to model long-range interactions. Recently, the transformer method has been successfully applied to the tasks of computer vision. It has a strong ability to capture distant interactions. However, most transformer-based methods with excellent performance rely on pre-training on large datasets, making it infeasible to directly apply them to medical images analysis, especially that of breast US images with limited high-quality labels. Therefore, it is of great significance to find a robust and efficient transformer-based method for use on small breast US image datasets.MethodsWe developed a dilated transformer (DT) method which mainly uses the proposed residual axial attention layers to build encoder blocks and the introduced dilation module (DM) to further increase the receptive field. We evaluated the proposed method on 2 breast US image datasets using the 5-fold cross-validation method. Dataset A was a public dataset with 562 images, while dataset B was a private dataset with 878 images. Ground truth (GT) was delineated by 2 radiologists with more than 5 years of experience. The evaluation was followed by related ablation experiments.ResultsThe DT was found to be comparable with the state-of-the-art (SOTA) CNN-based method and outperformed the related transformer-based method, medical transformer (MT), on both datasets. Especially on dataset B, the DT outperformed the MT on metrics of Jaccard index (JI) and Dice similarity coefficient (DSC) by 2.67% and 4.68%, respectively. Meanwhile, when compared with Unet, the DT improved JI and DSC by 4.89% and 4.66%, respectively. Moreover, the results of the ablation experiments showed that each add-on part of the DT is important and contributes to the segmentation accuracy.ConclusionsThe proposed transformer-based method could achieve advanced segmentation performance on different small breast US image datasets without pretraining.
| S-EPMC9403584 | biostudies-literature
Project description:We propose a novel multi-level dilated residual neural network, an extension of the classical U-Net architecture, for biomedical image segmentation. U-Net is the most popular deep neural architecture for biomedical image segmentation, however, despite being state-of-the-art, the model has a few limitations. In this study, we suggest replacing convolutional blocks of the classical U-Net with multi-level dilated residual blocks, resulting in enhanced learning capability. We also propose to incorporate a non-linear multi-level residual blocks into skip connections to reduce the semantic gap and to restore the information lost when concatenating features from encoder to decoder units. We evaluate the proposed approach on five publicly available biomedical datasets with different imaging modalities, including electron microscopy, magnetic resonance imaging, histopathology, and dermoscopy, each with its own segmentation challenges. The proposed approach consistently outperforms the classical U-Net by 2%, 3%, 6%, 8%, and 14% relative improvements in dice coefficient, respectively for magnetic resonance imaging, dermoscopy, histopathology, cell nuclei microscopy, and electron microscopy modalities. The visual assessments of the segmentation results further show that the proposed approach is robust against outliers and preserves better continuity in boundaries compared to the classical U-Net and its variant, MultiResUNet.
| S-EPMC8266898 | biostudies-literature
Project description:Brain tumor localization and segmentation from magnetic resonance imaging (MRI) are hard and important tasks for several applications in the field of medical analysis. As each brain imaging modality gives unique and key details related to each part of the tumor, many recent approaches used four modalities T1, T1c, T2, and FLAIR. Although many of them obtained a promising segmentation result on the BRATS 2018 dataset, they suffer from a complex structure that needs more time to train and test. So, in this paper, to obtain a flexible and effective brain tumor segmentation system, first, we propose a preprocessing approach to work only on a small part of the image rather than the whole part of the image. This method leads to a decrease in computing time and overcomes the overfitting problems in a Cascade Deep Learning model. In the second step, as we are dealing with a smaller part of brain images in each slice, a simple and efficient Cascade Convolutional Neural Network (C-ConvNet/C-CNN) is proposed. This C-CNN model mines both local and global features in two different routes. Also, to improve the brain tumor segmentation accuracy compared with the state-of-the-art models, a novel Distance-Wise Attention (DWA) mechanism is introduced. The DWA mechanism considers the effect of the center location of the tumor and the brain inside the model. Comprehensive experiments are conducted on the BRATS 2018 dataset and show that the proposed model obtains competitive results: the proposed method achieves a mean whole tumor, enhancing tumor, and tumor core dice scores of 0.9203, 0.9113 and 0.8726 respectively. Other quantitative and qualitative assessments are presented and discussed.
| S-EPMC8149837 | biostudies-literature
Project description:Biologists who use electron microscopy (EM) images to build nanoscale 3D models of whole cells and their organelles have historically been limited to small numbers of cells and cellular features due to constraints in imaging and analysis. This has been a major factor limiting insight into the complex variability of cellular environments. Modern EM can produce gigavoxel image volumes containing large numbers of cells, but accurate manual segmentation of image features is slow and limits the creation of cell models. Segmentation algorithms based on convolutional neural networks can process large volumes quickly, but achieving EM task accuracy goals often challenges current techniques. Here, we define dense cellular segmentation as a multiclass semantic segmentation task for modeling cells and large numbers of their organelles, and give an example in human blood platelets. We present an algorithm using novel hybrid 2D-3D segmentation networks to produce dense cellular segmentations with accuracy levels that outperform baseline methods and approach those of human annotators. To our knowledge, this work represents the first published approach to automating the creation of cell models with this level of structural detail.
| S-EPMC7844272 | biostudies-literature
Project description:Previous work has shown that combining dynamic contrast-enhanced (DCE)-MRI and oxygen-enhanced (OE)-MRI binary enhancement maps can identify tumor hypoxia. The current work proposes a novel, data-driven method for mapping tissue oxygenation and perfusion heterogeneity, based on clustering DCE/OE-MRI data.DCE-MRI and OE-MRI were performed on nine U87 (glioblastoma) and seven Calu6 (non-small cell lung cancer) murine xenograft tumors. Area under the curve and principal component analysis features were calculated and clustered separately using Gaussian mixture modelling. Evaluation metrics were calculated to determine the optimum feature set and cluster number. Outputs were quantitatively compared with a previous non data-driven approach.The optimum method located six robustly identifiable clusters in the data, yielding tumor region maps with spatially contiguous regions in a rim-core structure, suggesting a biological basis. Mean within-cluster enhancement curves showed physiologically distinct, intuitive kinetics of enhancement. Regions of DCE/OE-MRI enhancement mismatch were located, and voxel categorization agreed well with the previous non data-driven approach (Cohen's kappa?=?0.61, proportional agreement?=?0.75).The proposed method locates similar regions to the previous published method of binarization of DCE/OE-MRI enhancement, but renders a finer segmentation of intra-tumoral oxygenation and perfusion. This could aid in understanding the tumor microenvironment and its heterogeneity. Magn Reson Med 79:2236-2245, 2018. © 2017 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
| S-EPMC5836865 | biostudies-other