I2U-Net: A dual-path U-Net with rich information interaction for medical image segmentation.

Although the U-shape networks have achieved remarkable performances in many medical image segmentation tasks, they rarely model the sequential relationship of hierarchical layers. This weakness makes it difficult for the current layer to effectively utilize the historical information of the previous layer, leading to unsatisfactory segmentation results for lesions with blurred boundaries and irregular shapes. To solve this problem, we propose a novel dual-path U-Net, dubbed I2U-Net. The newly proposed network encourages historical information re-usage and re-exploration through rich information interaction among the dual paths, allowing deep layers to learn more comprehensive features that contain both low-level detail description and high-level semantic abstraction. Specifically, we introduce a multi-functional information interaction module (MFII), which can model cross-path, cross-layer, and cross-path-and-layer information interactions via a unified design, making the proposed I2U-Net behave similarly to an unfolded RNN and enjoying its advantage of modeling time sequence information. Besides, to further selectively and sensitively integrate the information extracted by the encoder of the dual paths, we propose a holistic information fusion and augmentation module (HIFA), which can efficiently bridge the encoder and the decoder. Extensive experiments on four challenging tasks, including skin lesion, polyp, brain tumor, and abdominal multi-organ segmentation, consistently show that the proposed I2U-Net has superior performance and generalization ability over other state-of-the-art methods. The code is available at https://github.com/duweidai/I2U-Net.

Improved genomic prediction using machine learning with Variational Bayesian sparsity.

BACKGROUND: Genomic prediction has become a powerful modelling tool for assessing line performance in plant and livestock breeding programmes. Among the genomic prediction modelling approaches, linear based models have proven to provide accurate predictions even when the number of genetic markers exceeds the number of data samples. However, breeding programmes are now compiling data from large numbers of lines and test environments for analyses, rendering these approaches computationally prohibitive. Machine learning (ML) now offers a solution to this problem through the construction of fully connected deep learning architectures and high parallelisation of the predictive task. However, the fully connected nature of these architectures immediately generates an over-parameterisation of the network that needs addressing for efficient and accurate predictions. RESULTS: In this research we explore the use of an ML architecture governed by variational Bayesian sparsity in its initial layers that we have called VBS-ML. The use of VBS-ML provides a mechanism for feature selection of important markers linked to the trait, immediately reducing the network over-parameterisation. Selected markers then propagate to the remaining fully connected feed-forward components of the ML network to form the final genomic prediction. We illustrated the approach with four large Australian wheat breeding data sets that range from 2665 lines to 10375 lines genotyped across a large set of markers. For all data sets, the use of the VBS-ML architecture improved genomic prediction accuracy over legacy linear based modelling approaches. CONCLUSIONS: An ML architecture governed under a variational Bayesian paradigm was shown to improve genomic prediction accuracy over legacy modelling approaches. This VBS-ML approach can be used to dramatically decrease the parameter burden on the network and provide a computationally feasible approach for improving genomic prediction conducted with large breeding population numbers and genetic markers.

Self-Supervised Interactive Embedding for One-Shot Organ Segmentation.

One-shot organ segmentation (OS2) aims at segmenting the desired organ regions from the input medical imaging data with only one pre-annotated example as the reference. By using the minimal annotation data to facilitate organ segmentation, OS2 receives great attention in the medical image analysis community due to its weak requirement on human annotation. In OS2, one core issue is to explore the mutual information between the support (reference slice) and the query (test slice). Existing methods rely heavily on the similarity between slices, and additional slice allocation mechanisms need to be designed to reduce the impact of the similarity between slices on the segmentation performance. To address this issue, we build a novel support-query interactive embedding (SQIE) module, which is equipped with the channel-wise co-attention, spatial-wise co-attention, and spatial bias transformation blocks to identify "what to look", "where to look", and "how to look" in the input test slice. By combining the three mechanisms, we can mine the interactive information of the intersection area and the disputed area between slices, and establish the feature connection between the target in slices with low similarity. We also propose a self-supervised contrastive learning framework, which transforms knowledge from the physical position to the embedding space to facilitate the self-supervised interactive embedding of the query and support slices. Comprehensive experiments on two large benchmarks demonstrate the superior capacity of the proposed approach when compared with the current alternatives and baseline models.

SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring.

The goal of dynamic scene deblurring is to remove the motion blur presented in a given image. To recover the details from the severe blurs, conventional convolutional neural networks (CNNs) based methods typically increase the number of convolution layers, kernel-size, or different scale images to enlarge the receptive field. However, these methods neglect the non-uniform nature of blurs, and cannot extract varied local and global information. Unlike the CNNs-based methods, we propose a Transformer-based model for image deblurring, named SharpFormer, that directly learns long-range dependencies via a novel Transformer module to overcome large blur variations. Transformer is good at learning global information but is poor at capturing local information. To overcome this issue, we design a novel Locality preserving Transformer (LTransformer) block to integrate sufficient local information into global features. In addition, to effectively apply LTransformer to the medium-resolution features, a hybrid block is introduced to capture intermediate mixed features. Furthermore, we use a dynamic convolution (DyConv) block, which aggregates multiple parallel convolution kernels to handle the non-uniform blur of inputs. We leverage a powerful two-stage attentive framework composed of the above blocks to learn the global, hybrid, and local features effectively. Extensive experiments on the GoPro and REDS datasets show that the proposed SharpFormer performs favourably against the state-of-the-art methods in blurred image restoration.

DHT-Net: Dynamic Hierarchical Transformer Network for Liver and Tumor Segmentation.

Automatic segmentation of liver tumors is crucial to assist radiologists in clinical diagnosis. While various deep learningbased algorithms have been proposed, such as U-Net and its variants, the inability to explicitly model long-range dependencies in CNN limits the extraction of complex tumor features. Some researchers have applied Transformer-based 3D networks to analyze medical images. However, the previous methods focus on modeling the local information (eg. edge) or global information (eg. morphology) with fixed network weights. To learn and extract complex tumor features of varied tumor size, location, and morphology for more accurate segmentation, we propose a Dynamic Hierarchical Transformer Network, named DHT-Net. The DHT-Net mainly contains a Dynamic Hierarchical Transformer (DHTrans) structure and an Edge Aggregation Block (EAB). The DHTrans first automatically senses the tumor location by Dynamic Adaptive Convolution, which employs hierarchical operations with the different receptive field sizes to learn the features of various tumors, thus enhancing the semantic representation ability of tumor features. Then, to adequately capture the irregular morphological features in the tumor region, DHTrans aggregates global and local texture information in a complementary manner. In addition, we introduce the EAB to extract detailed edge features in the shallow fine-grained details of the network, which provides sharp boundaries of liver and tumor regions. We evaluate DHT-Net on two challenging public datasets, LiTS and 3DIRCADb. The proposed method has shown superior liver and tumor segmentation performance compared to several state-of-the-art 2D, 3D, and 2.5D hybrid models.

Ms RED: A novel multi-scale residual encoding and decoding network for skin lesion segmentation.

Computer-Aided Diagnosis (CAD) for dermatological diseases offers one of the most notable showcases where deep learning technologies display their impressive performance in acquiring and surpassing human experts. In such the CAD process, a critical step is concerned with segmenting skin lesions from dermoscopic images. Despite remarkable successes attained by recent deep learning efforts, much improvement is still anticipated to tackle challenging cases, e.g., segmenting lesions that are irregularly shaped, bearing low contrast, or possessing blurry boundaries. To address such inadequacies, this study proposes a novel Multi-scale Residual Encoding and Decoding network (Ms RED) for skin lesion segmentation, which is able to accurately and reliably segment a variety of lesions with efficiency. Specifically, a multi-scale residual encoding fusion module (MsR-EFM) is employed in an encoder, and a multi-scale residual decoding fusion module (MsR-DFM) is applied in a decoder to fuse multi-scale features adaptively. In addition, to enhance the representation learning capability of the newly proposed pipeline, we propose a novel multi-resolution, multi-channel feature fusion module (M2F2), which replaces conventional convolutional layers in encoder and decoder networks. Furthermore, we introduce a novel pooling module (Soft-pool) to medical image segmentation for the first time, retaining more helpful information when down-sampling and getting better segmentation performance. To validate the effectiveness and advantages of the proposed network, we compare it with several state-of-the-art methods on ISIC 2016, 2017, 2018, and PH2. Experimental results consistently demonstrate that the proposed Ms RED attains significantly superior segmentation performance across five popularly used evaluation criteria. Last but not least, the new model utilizes much fewer model parameters than its peer approaches, leading to a greatly reduced number of labeled samples required for model training, which in turn produces a substantially faster converging training process than its peers. The source code is available at https://github.com/duweidai/Ms-RED.

AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system.

The sudden outbreak of novel coronavirus 2019 (COVID-19) increased the diagnostic burden of radiologists. In the time of an epidemic crisis, we hope artificial intelligence (AI) to reduce physician workload in regions with the outbreak, and improve the diagnosis accuracy for physicians before they could acquire enough experience with the new disease. In this paper, we present our experience in building and deploying an AI system that automatically analyzes CT images and provides the probability of infection to rapidly detect COVID-19 pneumonia. The proposed system which consists of classification and segmentation will save about 30%-40% of the detection time for physicians and promote the performance of COVID-19 detection. Specifically, working in an interdisciplinary team of over 30 people with medical and/or AI background, geographically distributed in Beijing and Wuhan, we are able to overcome a series of challenges (e.g. data discrepancy, testing time-effectiveness of model, data security, etc.) in this particular situation and deploy the system in four weeks. In addition, since the proposed AI system provides the priority of each CT image with probability of infection, the physicians can confirm and segregate the infected patients in time. Using 1,136 training cases (723 positives for COVID-19) from five hospitals, we are able to achieve a sensitivity of 0.974 and specificity of 0.922 on the test dataset, which included a variety of pulmonary diseases.

COVID-19 Chest CT Image Segmentation Network by Multi-Scale Fusion and Enhancement Operations.

A novel coronavirus disease 2019 (COVID-19) was detected and has spread rapidly across various countries around the world since the end of the year 2019. Computed Tomography (CT) images have been used as a crucial alternative to the time-consuming RT-PCR test. However, pure manual segmentation of CT images faces a serious challenge with the increase of suspected cases, resulting in urgent requirements for accurate and automatic segmentation of COVID-19 infections. Unfortunately, since the imaging characteristics of the COVID-19 infection are diverse and similar to the backgrounds, existing medical image segmentation methods cannot achieve satisfactory performance. In this article, we try to establish a new deep convolutional neural network tailored for segmenting the chest CT images with COVID-19 infections. We first maintain a large and new chest CT image dataset consisting of 165,667 annotated chest CT images from 861 patients with confirmed COVID-19. Inspired by the observation that the boundary of the infected lung can be enhanced by adjusting the global intensity, in the proposed deep CNN, we introduce a feature variation block which adaptively adjusts the global properties of the features for segmenting COVID-19 infection. The proposed FV block can enhance the capability of feature representation effectively and adaptively for diverse cases. We fuse features at different scales by proposing Progressive Atrous Spatial Pyramid Pooling to handle the sophisticated infection areas with diverse appearance and shapes. The proposed method achieves state-of-the-art performance. Dice similarity coefficients are 0.987 and 0.726 for lung and COVID-19 segmentation, respectively. We conducted experiments on the data collected in China and Germany and show that the proposed deep CNN can produce impressive performance effectively. The proposed network enhances the segmentation ability of the COVID-19 infection, makes the connection with other techniques and contributes to the development of remedying COVID-19 infection.

Attention-Guided Deep Neural Network With Multi-Scale Feature Fusion for Liver Vessel Segmentation.

Liver vessel segmentation is fast becoming a key instrument in the diagnosis and surgical planning of liver diseases. In clinical practice, liver vessels are normally manual annotated by clinicians on each slice of CT images, which is extremely laborious. Several deep learning methods exist for liver vessel segmentation, however, promoting the performance of segmentation remains a major challenge due to the large variations and complex structure of liver vessels. Previous methods mainly using existing UNet architecture, but not all features of the encoder are useful for segmentation and some even cause interferences. To overcome this problem, we propose a novel deep neural network for liver vessel segmentation, called LVSNet, which employs special designs to obtain the accurate structure of the liver vessel. Specifically, we design Attention-Guided Concatenation (AGC) module to adaptively select the useful context features from low-level features guided by high-level features. The proposed AGC module focuses on capturing rich complemented information to obtain more details. In addition, we introduce an innovative multi-scale fusion block by constructing hierarchical residual-like connections within one single residual block, which is of great importance for effectively linking the local blood vessel fragments together. Furthermore, we construct a new dataset containing 40 thin thickness cases (0.625 mm) which consist of CT volumes and annotated vessels. To evaluate the effectiveness of the method with minor vessels, we also propose an automatic stratification method to split major and minor liver vessels. Extensive experimental results demonstrate that the proposed LVSNet outperforms previous methods on liver vessel segmentation datasets. Additionally, we conduct a series of ablation studies that comprehensively support the superiority of the underlying concepts.

Deep HDR Imaging via A Non-local Network.

One of the most challenging problems in reconstructing a high dynamic range (HDR) image from multiple low dynamic range (LDR) inputs is the ghosting artifacts caused by the object motion across different inputs. When the object motion is slight, most existing methods can well suppress the ghosting artifacts through aligning LDR inputs based on optical flow or detecting anomalies among them. However, they often fail to produce satisfactory results in practice, since the real object motion can be very large. In this study, we present a novel deep framework, termed NHDRRnet, which adopts an alternative direction and attempts to remove ghosting artifacts by exploiting the non-local correlation in inputs. In NHDRRnet, we first adopt an Unet architecture to fuse all inputs and map the fusion results into a low-dimensional deep feature space. Then, we feed the resultant features into a novel global non-local module which reconstructs each pixel by weighted averaging all the other pixels using the weights determined by their correspondences. By doing this, the proposed NHDRRnet is able to adaptively select the useful information (e.g., which are not corrupted by large motions or adverse lighting conditions) in the whole deep feature space to accurately reconstruct each pixel. In addition, we also incorporate a triple-pass residual module to capture more powerful local features, which proves to be effective in further boosting the performance. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed NDHRnet in terms of suppressing the ghosting artifacts in HDR reconstruction, especially when the objects have large motions.

Two-Stream Convolutional Networks for Blind Image Quality Assessment.

Traditional image quality assessment (IQA) methods do not perform robustly due to the shallow hand-designed features. It has been demonstrated that deep neural network can learn more effective features than ever. In this paper, we describe a new deep neural network to predict the image quality accurately without relying on the reference image. To learn more effective feature representations for non-reference IQA, we propose a two-stream convolution network that includes two subcomponents for image and gradient image. The motivation for this design is using a two-stream scheme to capture different-level information of inputs and easing the difficulty of extracting features from one steam. The gradient stream focuses on extracting structure features in details, and the image stream pays more attention to the information in intensity. In addition, to consider the locally non-uniform distribution of distortion in images, we add a region-based fully convolutional layer for using the information around the center of the input image patch. The final score of the overall image is calculated by averaging of the patch scores. The proposed network performs in an end-to-end manner in both the training and testing phases. The experimental results on a series of benchmark datasets, e.g., LIVE, CISQ, IVC, TID2013, and Waterloo Exploration Database, show that the proposed algorithm outperforms the state-of-the-art methods, which verifies the effectiveness of our network architecture.