Multi-Scale Self-Guided Attention for Medical Image Segmentation

Learning to Segment From Scribbles Using Multi-Scale Adversarial Attention Gates

Large, fine-grained image segmentation datasets, annotated at pixel-level, are difficult to obtain, particularly in medical imaging, where annotations also require expert knowledge. Weakly-supervised learning can train models by relying on weaker forms of annotation, such as scribbles. Here, we learn to segment using scribble annotations in an adversarial game. With unpaired segmentation masks, we train a multi-scale GAN to generate realistic segmentation masks at multiple resolutions, while we use scribbles to learn their correct position in the image. Central to the model's success is a novel attention gating mechanism, which we condition with adversarial signals to act as a shape prior, resulting in better object localization at multiple scales. Subject to adversarial conditioning, the segmentor learns attention maps that are semantic, suppress the noisy activations outside the objects, and reduce the vanishing gradient problem in the deeper layers of the segmentor. We evaluated our model on several medical (ACDC, LVSC, CHAOS) and non-medical (PPSS) datasets, and we report performance levels matching those achieved by models trained with fully annotated segmentation masks. We also demonstrate extensions in a variety of settings: semi-supervised learning; combining multiple scribble sources (a crowdsourcing scenario) and multi-task learning (combining scribble and mask supervision). We release expert-made scribble annotations for the ACDC dataset, and the code used for the experiments, at https://vios-s.github.io/multiscale-adversarial-attention-gates.

LPAQR-Net: Efficient Vertebra Segmentation From Biplanar Whole-Spine Radiographs

Vertebra segmentation from biplanar whole-spine radiographs is highly demanded in the quantitative assessment of scoliosis and the resultant sagittal deformities. However, automatic vertebra segmentation from the radiographs is extremely challenging due to the low contrast, blended boundaries, and superimposition of many layers, especially in the sagittal plane. To alleviate these problems, we propose a lightweight pyramid attention quick refinement network (LPAQR-Net) for efficient and accurate vertebra segmentation. The LPAQR-Net consists of three components: (1) a lightweight backbone network (LB-Net) to prune network parameters and memory footprints to strike an optimal balance between speed and accuracy, (2) a series of global attention refinement (GAR) modules to selectively reuse low-level features to facilitate the feature refinement, and (3) an attention-based atrous spatial pyramid pooling (A-ASPP) module to extract weighted pyramid contexts to improve the segmentation of blurred vertebrae. Moreover, the multi-class training strategy is employed to alleviate the over-segmentation of adjacent vertebrae. Evaluation results on both frontal and lateral radiographs of 332 AIS patients show our method achieves accurate vertebra segmentation with significant reductions in inference time and computational demands compared to the state-of-the-art. Meanwhile, results on the public AASCE2019 dataset also demonstrate the good generalization ability of our model. It is the first attempt to explore the lightweight network for vertebra segmentation from biplanar whole-spine radiographs. It simulates radiologists gathering nearby contexts for accurate and robust vertebra boundary inference. The method can provide efficient and accurate vertebra segmentation for clinicians to perform a fast and reproducible spinal deformity evaluation.

APRNet: A 3D Anisotropic Pyramidal Reversible Network with Multi-modal Cross-Dimension Attention for Brain Tissue Segmentation in MR Images

Brain tissue segmentation in multi-modal magnetic resonance (MR) images is significant for the clinical diagnosis of brain diseases. Due to blurred boundaries, low contrast, and intricate anatomical relationships between brain tissue regions, automatic brain tissue segmentation without prior knowledge is still challenging. This paper presents a novel 3D fully convolutional network (FCN) for brain tissue segmentation, called APRNet. In this network, we first propose a 3D anisotropic pyramidal convolutional reversible residual sequence (3DAPC-RRS) module to integrate the intra-slice information with the inter-slice information without significant memory consumption; secondly, we design a multi-modal cross-dimension attention (MCDA) module to automatically capture the effective information in each dimension of multi-modal images; then, we apply 3DAPC-RRS modules and MCDA modules to a 3D FCN with multiple encoded streams and one decoded stream for constituting the overall architecture of APRNet. We evaluated APRNet on two benchmark challenges, namely MRBrainS13 and iSeg-2017. The experimental results show that APRNet yields state-of-the-art segmentation results on both benchmark challenge datasets and achieves the best segmentation performance on the cerebrospinal fluid region. Compared with other methods, our proposed approach exploits the complementary information of different modalities to segment brain tissue regions in both adult and infant MR images, and it achieves the average Dice coefficient of 87.22% and 93.03% on the MRBrainS13 and iSeg-2017 testing data, respectively. The proposed method is beneficial for quantitative brain analysis in the clinical study, and our code is made publicly available.

Anatomy-guided multimodal registration by learning segmentation without ground truth: Application to intraprocedural CBCT/MR liver segmentation and registration

Multimodal image registration has many applications in diagnostic medical imaging and image-guided interventions, such as Transcatheter Arterial Chemoembolization (TACE) of liver cancer guided by intraprocedural CBCT and pre-operative MR. The ability to register peri-procedurally acquired diagnostic images into the intraprocedural environment can potentially improve the intra-procedural tumor targeting, which will significantly improve therapeutic outcomes. However, the intra-procedural CBCT often suffers from suboptimal image quality due to lack of signal calibration for Hounsfield unit, limited FOV, and motion/metal artifacts. These non-ideal conditions make standard intensity-based multimodal registration methods infeasible to generate correct transformation across modalities. While registration based on anatomic structures, such as segmentation or landmarks, provides an efficient alternative, such anatomic structure information is not always available. One can train a deep learning-based anatomy extractor, but it requires large-scale manual annotations on specific modalities, which are often extremely time-consuming to obtain and require expert radiological readers. To tackle these issues, we leverage annotated datasets already existing in a source modality and propose an anatomy-preserving domain adaptation to segmentation network (APA2Seg-Net) for learning segmentation without target modality ground truth. The segmenters are then integrated into our anatomy-guided multimodal registration based on the robust point matching machine. Our experimental results on in-house TACE patient data demonstrated that our APA2Seg-Net can generate robust CBCT and MR liver segmentation, and the anatomy-guided registration framework with these segmenters can provide high-quality multimodal registrations.

A Comprehensive Study on Colorectal Polyp Segmentation With ResUNet++, Conditional Random Field and Test-Time Augmentation

Colonoscopy is considered the gold standard for detection of colorectal cancer and its precursors. Existing examination methods are, however, hampered by high overall miss-rate, and many abnormalities are left undetected. Computer-Aided Diagnosis systems based on advanced machine learning algorithms are touted as a game-changer that can identify regions in the colon overlooked by the physicians during endoscopic examinations, and help detect and characterize lesions. In previous work, we have proposed the ResUNet++ architecture and demonstrated that it produces more efficient results compared with its counterparts U-Net and ResUNet. In this paper, we demonstrate that further improvements to the overall prediction performance of the ResUNet++ architecture can be achieved by using Conditional Random Field (CRF) and Test-Time Augmentation (TTA). We have performed extensive evaluations and validated the improvements using six publicly available datasets: Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, ETIS-Larib Polyp DB, ASU-Mayo Clinic Colonoscopy Video Database, and CVC-VideoClinicDB. Moreover, we compare our proposed architecture and resulting model with other state-of-the-art methods. To explore the generalization capability of ResUNet++ on different publicly available polyp datasets, so that it could be used in a real-world setting, we performed an extensive cross-dataset evaluation. The experimental results show that applying CRF and TTA improves the performance on various polyp segmentation datasets both on the same dataset and cross-dataset. To check the model's performance on difficult to detect polyps, we selected, with the help of an expert gastroenterologist, 196 sessile or flat polyps that are less than ten millimeters in size. This additional data has been made available as a subset of Kvasir-SEG. Our approaches showed good results for flat or sessile and smaller polyps, which are known to be one of the major reasons for high polyp miss-rates. This is one of the significant strengths of our work and indicates that our methods should be investigated further for use in clinical practice.

Learning With Context Feedback Loop for Robust Medical Image Segmentation

Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead to less output pixel interdependence producing incomplete and unrealistic segmentation results. In this paper, we present a fully automatic deep learning method for robust medical image segmentation by formulating the segmentation problem as a recurrent framework using two systems. The first one is a forward system of an encoder-decoder CNN that predicts the segmentation result from the input image. The predicted probabilistic output of the forward system is then encoded by a fully convolutional network (FCN)-based context feedback system. The encoded feature space of the FCN is then integrated back into the forward system's feed-forward learning process. Using the FCN-based context feedback loop allows the forward system to learn and extract more high-level image features and fix previous mistakes, thereby improving prediction accuracy over time. Experimental results, performed on four different clinical datasets, demonstrate our method's potential application for single and multi-structure medical image segmentation by outperforming the state of the art methods. With the feedback loop, deep learning methods can now produce results that are both anatomically plausible and robust to low contrast images. Therefore, formulating image segmentation as a recurrent framework of two interconnected networks via context feedback loop can be a potential method for robust and efficient medical image analysis.

MRI and CT bladder segmentation from classical to deep learning based approaches: Current limitations and lessons

Precise determination and assessment of bladder cancer (BC) extent of muscle invasion involvement guides proper risk stratification and personalized therapy selection. In this context, segmentation of both bladder walls and cancer are of pivotal importance, as it provides invaluable information to stage the primary tumor. Hence, multiregion segmentation on patients presenting with symptoms of bladder tumors using deep learning heralds a new level of staging accuracy and prediction of the biologic behavior of the tumor. Nevertheless, despite the success of these models in other medical problems, progress in multiregion bladder segmentation, particularly in MRI and CT modalities, is still at a nascent stage, with just a handful of works tackling a multiregion scenario. Furthermore, most existing approaches systematically follow prior literature in other clinical problems, without casting a doubt on the validity of these methods on bladder segmentation, which may present different challenges. Inspired by this, we provide an in-depth look at bladder cancer segmentation using deep learning models. The critical determinants for accurate differentiation of muscle invasive disease, current status of deep learning based bladder segmentation, lessons and limitations of prior work are highlighted.

Multi-Scale Squeeze U-SegNet with Multi Global Attention for Brain MRI Segmentation

In this paper, we propose a multi-scale feature extraction with novel attention-based convolutional learning using the U-SegNet architecture to achieve segmentation of brain tissue from a magnetic resonance image (MRI). Although convolutional neural networks (CNNs) show enormous growth in medical image segmentation, there are some drawbacks with the conventional CNN models. In particular, the conventional use of encoder-decoder approaches leads to the extraction of similar low-level features multiple times, causing redundant use of information. Moreover, due to inefficient modeling of long-range dependencies, each semantic class is likely to be associated with non-accurate discriminative feature representations, resulting in low accuracy of segmentation. The proposed global attention module refines the feature extraction and improves the representational power of the convolutional neural network. Moreover, the attention-based multi-scale fusion strategy can integrate local features with their corresponding global dependencies. The integration of fire modules in both the encoder and decoder paths can significantly reduce the computational complexity owing to fewer model parameters. The proposed method was evaluated on publicly accessible datasets for brain tissue segmentation. The experimental results show that our proposed model achieves segmentation accuracies of 94.81% for cerebrospinal fluid (CSF), 95.54% for gray matter (GM), and 96.33% for white matter (WM) with a noticeably reduced number of learnable parameters. Our study shows better segmentation performance, improving the prediction accuracy by 2.5% in terms of dice similarity index while achieving a 4.5 times reduction in the number of learnable parameters compared to previously developed U-SegNet based segmentation approaches. This demonstrates that the proposed approach can achieve reliable and precise automatic segmentation of brain MRI images.

Unsupervised Domain Adaption for High-Resolution Coastal Land Cover Mapping with Category-Space Constrained Adversarial Network

Coastal land cover mapping (CLCM) across image domains presents a fundamental and challenging segmentation task. Although adversaries-based domain adaptation methods have been proposed to address this issue, they always implement distribution alignment via a global discriminator while ignoring the data structure. Additionally, the low inter-class variances and intricate spatial details of coastal objects may entail poor presentation. Therefore, this paper proposes a category-space constrained adversarial method to execute category-level adaptive CLCM. Focusing on the underlying category information, we introduce a category-level adversarial framework to align semantic features. We summarize two diverse strategies to extract category-wise domain labels for source and target domains, where the latter is driven by self-supervised learning. Meanwhile, we generalize the lightweight adaptation module to multiple levels across a robust baseline, aiming to fine-tune the features at different spatial scales. Furthermore, the self-supervised learning approach is also leveraged as an improvement strategy to optimize the result within segmented training. We examine our method on two converse adaptation tasks and compare them with other state-of-the-art models. The overall visualization results and evaluation metrics demonstrate that the proposed method achieves excellent performance in the domain adaptation CLCM with high-resolution remotely sensed images.

Non-Local Feature Search Network for Building and Road Segmentation of Remote Sensing Image

Building and road extraction from remote sensing images is of great significance to urban planning. At present, most of building and road extraction models adopt deep learning semantic segmentation method. However, the existing semantic segmentation methods did not pay enough attention to the feature information between hidden layers, which led to the neglect of the category of context pixels in pixel classification, resulting in these two problems of large-scale misjudgment of buildings and disconnection of road extraction. In order to solve these problem, this paper proposes a Non-Local Feature Search Network (NFSNet) that can improve the segmentation accuracy of remote sensing images of buildings and roads, and to help achieve accurate urban planning. By strengthening the exploration of hidden layer feature information, it can effectively reduce the large area misclassification of buildings and road disconnection in the process of segmentation. Firstly, a Self-Attention Feature Transfer (SAFT) module is proposed, which searches the importance of hidden layer on channel dimension, it can obtain the correlation between channels. Secondly, the Global Feature Refinement (GFR) module is introduced to integrate the features extracted from the backbone network and SAFT module, it enhances the semantic information of the feature map and obtains more detailed segmentation output. The comparative experiments demonstrate that the proposed method outperforms state-of-the-art methods, and the model complexity is the lowest.

ASCU-Net: Attention Gate, Spatial and Channel Attention U-Net for Skin Lesion Segmentation

Segmentation of skin lesions is a challenging task because of the wide range of skin lesion shapes, sizes, colors, and texture types. In the past few years, deep learning networks such as U-Net have been successfully applied to medical image segmentation and exhibited faster and more accurate performance. In this paper, we propose an extended version of U-Net for the segmentation of skin lesions using the concept of the triple attention mechanism. We first selected regions using attention coefficients computed by the attention gate and contextual information. Second, a dual attention decoding module consisting of spatial attention and channel attention was used to capture the spatial correlation between features and improve segmentation performance. The combination of the three attentional mechanisms helped the network to focus on a more relevant field of view of the target. The proposed model was evaluated using three datasets, ISIC-2016, ISIC-2017, and PH2. The experimental results demonstrated the effectiveness of our method with strong robustness to the presence of irregular borders, lesion and skin smooth transitions, noise, and artifacts.

Coastal Land Cover Classification of High-Resolution Remote Sensing Images Using Attention-Driven Context Encoding Network

Low inter-class variance and complex spatial details exist in ground objects of the coastal zone, which leads to a challenging task for coastal land cover classification (CLCC) from high-resolution remote sensing images. Recently, fully convolutional neural networks have been widely used in CLCC. However, the inherent structure of the convolutional operator limits the receptive field, resulting in capturing the local context. Additionally, complex decoders bring additional information redundancy and computational burden. Therefore, this paper proposes a novel attention-driven context encoding network to solve these problems. Among them, lightweight global feature attention modules are employed to aggregate multi-scale spatial details in the decoding stage. Meanwhile, position and channel attention modules with long-range dependencies are embedded to enhance feature representations of specific categories by capturing the multi-dimensional global context. Additionally, multiple objective functions are introduced to supervise and optimize feature information at specific scales. We apply the proposed method in CLCC tasks of two study areas and compare it with other state-of-the-art approaches. Experimental results indicate that the proposed method achieves the optimal performances in encoding long-range context and recognizing spatial details and obtains the optimum representations in evaluation indexes.

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease

Introduction: Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Non-invasive neuroimaging techniques, such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods: BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from three different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high- and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD); and via visual qualitative rating. Results: The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165, and 95HD = 29.153. The BRAVE-NET model was also the most resistant toward false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion: We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease and an external set of healthy volunteers. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.

FAU-Net: Fixup Initialization Channel Attention Neural Network for Complex Blood Vessel Segmentation

Medical image segmentation based on deep learning is a central research issue in the field of computer vision. Many existing segmentation networks can achieve accurate segmentation using fewer data sets. However, they have disadvantages such as poor network flexibility and do not adequately consider the interdependence between feature channels. In response to these problems, this paper proposes a new de-normalized channel attention network, which uses an improved de-normalized residual block structure and a new channel attention module in the network for the segmentation of sophisticated vessels. The de-normalized network sends the extracted rough features to the channel attention network. The channel attention module can explicitly model the interdependence between channels and pay attention to the correlation with crucial information in multiple feature channels. It can focus on the channels with the most association with vital information among multiple feature channels, and get more detailed feature results. Experimental results show that the network proposed in this paper is feasible, is robust, can accurately segment blood vessels, and is particularly suitable for complex blood vessel structures. Finally, we compared and verified the network proposed in this paper with the state-of-the-art network and obtained better experimental results.