Jinghui Chu’s research while affiliated with Tianjin University and other places

Colorectal cancer is a multifaceted disease, but it can be effectively prevented through colonoscopy for the detection of polyps. In clinical practice, the development of automatic polyp segmentation techniques for colonoscopy images can significantly enhance the efficiency and accuracy of polyp detection, and help clinicians to precisely localize the polyps. However, existing segmentation methods have several obvious limitations: (1) inadequate utilization of multi-level features extracted by feature encoders, (2) ineffective aggregation of high-level and low-level features, and (3) unclear delineation of polyp boundaries. To address these challenges while enhancing the clarity of polyp boundaries in segmentation, we propose a novel Multi-layer Information Fusion and Optimization Network (MIFONet) consisting of the following components: (1) Contextual and Fine Feature Processing (CFFP) module, employed to effectively extract both local and global contextual information, (2) Hierarchical Feature Integration Module (HFIM), added to facilitate efficient aggregation of processed high-level and low-level features and strengthen the association between contextual features, (3) Multi-Scale Contextual Attention (MSCA) module, used to deeply integrate aggregated high-level features with low-level features, and (4) a novel refinement module composed of an Adaptive Channel Attention Pyramid (ACAP) part and a Skip-Reverse Attention (SRA) part, with the ability of capturing fine-grained information and refining feature representation. We conducted extensive experiments and comparative analysis of our proposed model with 19 popular or state-of-the-art (SOTA) methods on five renowned polyp benchmark datasets. To further validate the model’s generalization performance, we also designed three cross-dataset experiments. Experimental results demonstrate that MIFONet consistently achieves excellent segmentation performance across most datasets. Especially, we achieve 94.6% mean Dice on CVC-ClinicDB dataset which obtains the superior performance compared with SOTA methods.

Early detection of colonic polyps is crucial for the prevention and diagnosis of colorectal cancer. Currently, deep learning-based polyp segmentation methods have become mainstream and achieved remarkable results. Acquiring a large number of labeled data is time-consuming and labor-intensive, and meanwhile the presence of numerous similar wrinkles in polyp images also hampers model prediction performance. In this paper, we propose a novel approach called Phase- wise Feature Pyramid with Retention Network (PFPRNet), which leverages a pre-trained Transformer-based Encoder to obtain multi-scale feature maps. A Phase- wise Feature Pyramid with Retention Decoder is designed to gradually integrate global features into local features and guide the model's attention towards key regions. Additionally, our custom Enhance Perception module enables capturing image information from a broader perspective. Finally, we introduce an innovative Low-layer Retention module as an alternative to Transformer for more efficient global attention modeling. Evaluation results on several widely-used polyp segmentation datasets demonstrate that our proposed method has strong learning ability and generalization capability, and outperforms the state-of-the-art approaches.

Semi-supervised learning aims to train a high-performance model with a minority of labeled data and a majority of unlabeled data. Existing methods mostly adopt the mechanism of prediction task to obtain precise segmentation maps with the constraints of consistency or pseudo-labels, whereas the mechanism usually fails to overcome confirmation bias. To address this issue, in this paper, we propose a novel Confidence-Guided Mask Learning (CGML) for semi-supervised medical image segmentation. Specifically, on the basis of the prediction task, we further introduce an auxiliary generation task with mask learning, which intends to reconstruct the masked images for extremely facilitating the model capability of learning feature representations. Moreover, a confidence-guided masking strategy is developed to enhance model discrimination in uncertain regions. Besides, we introduce a triple-consistency loss to enforce a consistent prediction of the masked unlabeled image, original unlabeled image and reconstructed unlabeled image for generating more reliable results. Extensive experiments on two datasets demonstrate that our proposed method achieves remarkable performance.

Automatic polyp segmentation is critical for early prevention and diagnosis of colorectal cancer. However, diverse foreground appearance and complicated background interference severely degrade the performance of pixel-level prediction. The excessive computational overheads further hinder the practical clinical applications of existing methods. In this paper, we propose a novel Lesion-Aware Contextual Interaction Network (LACINet), which aims to explore the long-range dependencies and global contexts with friendly computing resource consumption for polyp segmentation. Specifically, we present a Lesion-aware Pyramid Mechanism (LPM) to weaken the influence of background noise and refine lesion-related features. We also develop a robust Representation Enhancement Decoder (RED) to learn global feature representations and aggregate the multi-level contexts. In RED, we first build a Non-local Contextual Lesion Interaction Module (NCLIM) to integrate the cross-level contextual information for obtaining the intrinsic feature representations, and then design a Tri-branching Multi-scale Perceptual Self-attention Module (TMPSM) to sufficiently excavate the global features. Notably, we introduce an asymmetric multi-branch strategy to alleviate the computational burden. The experimental results on several widely-used benchmark datasets demonstrate the superior performance of our proposed LACINet in comparison with state-of-the-art methods.

High-quality and high-resolution medical images can help doctors make more accurate diagnoses, but the resolution of medical images is often limited by a variety of factors such as device, operation and compression rate. To deal with this issue, in this paper, we propose a novel densely connected network for super-resolution reconstruction of 3D medical images. In order to obtain multiscale information, we first adopt 3D dilated convolution with different dilation rates to extract shallow features. To better handle these hierarchical features, we combine local residual learning with densely connected layers, which apply 3D asymmetric convolution to improve performance without increasing inference time. Meanwhile, an improved attention module, which considers both channel-wise and spatial information, is applied to enhance attention of the channels and regions with more high-frequency details. Finally, a feature fusion module which contains three parallel dilated convolution is applied to fuse hierarchical features. Compared with the state-of-the-art methods, such as SRCNN, FSRCNN, SRResnet, DCSRN, ReCNN and DCED, our experimental results show that the proposed method has better performance in both objective metrics and visual effect.

Single-image super-resolution (SISR) has been an important topic due to the demand for high-quality virtual images in the field of visual artificial intelligence. Methods based on deep learning have achieved great success based on the excellent capability of grasping complicated features of deep convolutional networks. The performance can be improved slightly but not obviously by simply widening or deepening the network. In this paper, we propose a merged convolutional network for super-resolution, which extracts more adequate details to restore high-resolution images. We used dense blocks for feature extraction to concatenate deep features with shallow features in depth. We also designed two sub-nets with distinct convolution kernels as different branches of the network, which can widen the network and improve the performance of the system. Finally, we employed sub-pixel layers to avoid feature distortion for up-sampling at the very end. Our method was evaluated using several standard benchmark datasets. The results demonstrate superior performance and good robustness compared with state-of-the-art methods.

Arrhythmia classification is useful during heart disease diagnosis. Although well-established for intra-patient diagnoses, inter-patient arrhythmia classification remains difficult. Most previous work has focused on the intra-patient condition and has not followed the Association for the Advancement of Medical Instrumentation (AAMI) standards. Here, we propose a novel system for arrhythmia classification based on multi-lead electrocardiogram (ECG) signals. The core of the design is that we fuse two types of deep learning features with some common traditional features and select discriminating features using a binary particle swarm optimization algorithm (BPSO). Then, the feature vector is classified using a weighted support vector machine (SVM) classifier. For a better generalization of the model and to draw fair comparisons, we carried out inter-patient experiments and followed the AAMI standards. We found that, when using common metrics aimed at multi-classification either macro- or micro-averaging, our system outperforms most other state-of-the-art methods.

With the rapid development of the wireless sensor network and the continuous improvement of its key technologies, the concept of Internet of Things (IoT) has been encouraged and extended due to its wide applications in scenarios such as smart homes and healthcare. Under the background, human activity recognition (HAR) has drawn great attention in recent years. In this paper, we present a discriminant approach to recognize daily human activities recorded through accelerometer sensor. In the proposed approach, we first use S transform (ST) to extract features, and then introduce a supervised regularization-based robust subspace (SRRS) learning method to learn low-dimensional intrinsic feature representation from the original feature subspace. Particularly, ST has been described as a joint time-frequency representation (TFR), which is insensitive to noise. SRRS can learn more robust and discriminative features to reinforce the descriptions of samples while removing noise and redundancy. Experiments are conducted on three publicly available datasets i.e., WISDM, SCUT-NAA and mHealth demonstrating the superior performance of our proposed scheme compared with state-of-the-art methods.