Computer-aided diagnosis (CAD) technology can assist clinicians in evaluating liver lesions and intervening with treatment in time. Although CAD technology has advanced in recent years, the application scope of existing datasets remains relatively limited, typically supporting only single tasks, which has somewhat constrained the development of CAD technology. To address the above limitation, in this paper, we construct a multi-task liver dataset (LiMT) used for liver and tumor segmentation, multi-label lesion classification, and lesion detection based on arterial phase-enhanced computed tomography (CT), potentially providing an exploratory solution that is able to explore the correlation between tasks and does not need to worry about the heterogeneity between task-specific datasets during training. The dataset includes CT volumes from 150 different cases, comprising four types of liver diseases as well as normal cases. Each volume has been carefully annotated and calibrated by experienced clinicians. This public multi-task dataset may become a valuable resource for the medical imaging research community in the future. In addition, this paper not only provides relevant baseline experimental results but also reviews existing datasets and methods related to liver-related tasks.

Medical Visual Question Answering (Med-VQA) models often suffer from language bias, which relies on linguistic cues to predict answers instead of understanding image content, limiting model performance. To address this, we propose DeCI, a novel causally-inspired intervention scheme to mitigate language bias in Med-VQA tasks. Specifically, DeCI incorporates two debiasing modules: a keyword-based fine-grained debiasing module to eliminate spurious correlations between clinical terms and answers, and a keyword-guided visual enhancement module to focus on key regions without requiring manual annotations. Experimental results on two public datasets and their bias-sensitive variants demonstrate that DeCI outperforms existing state-of-the-art Med-VQA models, achieving significant improvements in accuracy.

The success of deep learning in 3D medical image segmentation hinges on training with a large dataset of fully annotated 3D volumes, which are difficult and time-consuming to acquire. Although recent foundation models (e.g., segment anything model, SAM) can utilize sparse annotations to reduce annotation costs, segmentation tasks involving organs and tissues with blurred boundaries remain challenging. To address this issue, we propose a region uncertainty estimation framework for Computed Tomography (CT) image segmentation using noisy labels. Specifically, we propose a sample-stratified training strategy that stratifies samples according to their varying quality labels, prioritizing confident and fine-grained information at each training stage. This sample-to-voxel level processing enables more reliable supervision information to propagate to noisy label data, thus effectively mitigating the impact of noisy annotations. Moreover, we further design a boundary-guided regional uncertainty estimation module that adapts sample hierarchical training to assist in evaluating sample confidence. Experiments conducted across multiple CT datasets demonstrate the superiority of our proposed method over several competitive approaches under various noise conditions. Our proposed reliable label propagation strategy not only significantly reduces the cost of medical image annotation and robust model training but also improves the segmentation performance in scenarios with imperfect annotations, thus paving the way towards the application of medical segmentation foundation models under low-resource and remote scenarios. Code will be available at https://github.com/KHan-UJS/NoisyLabel.

Accurate segmentation of organs and tumors is crucial for clinical diagnosis. Deep learning methods have been widely applied to various medical image segmentation tasks. However, these methods often suffer from the foreground and background class imbalance challenge when dealing with small regions of interest. To address this limitation, we propose a Wavelet Transform-based Distribution Discrepancy Maximization (WT-DDM) framework for medical image segmentation. Specifically, we first introduce a Distribution Discrepancy Maximization (DDM) module that makes the model on the foreground region from abundant irrelevant background. Then, the Wavelet Transform-based Feature Enhancement (WTFE) module was applied to mine the texture details of the foreground object. Experiments on multiple popular medical image segmentation datasets demonstrate that our framework yields highly competitive segmentation results.

Unsupervised anomaly detection in time series is essential in industrial applications, as it significantly reduces the need for manual intervention. Multivariate time series pose a complex challenge due to their feature and temporal dimensions. Traditional methods use Graph Neural Networks (GNNs) or Transformers to analyze spatial while RNNs to model temporal dependencies. These methods focus narrowly on one dimension or engage in coarse-grained feature extraction, which can be inadequate for large datasets characterized by intricate relationships and dynamic changes. This paper introduces a novel temporal model built on an enhanced Graph Attention Network (GAT) for multivariate time series anomaly detection called TopoGDN. Our model analyzes both time and feature dimensions from a fine-grained perspective. First, we introduce a multi-scale temporal convolution module to extract detailed temporal features. Additionally, we present an augmented GAT to manage complex inter-feature dependencies, which incorporates graph topology into node features across multiple scales, a versatile, plug-and-play enhancement that significantly boosts the performance of GAT. Our experimental results confirm that our approach surpasses the baseline models on four datasets, demonstrating its potential for widespread application in fields requiring robust anomaly detection. The code is available at https://github.com/ljj-cyber/TopoGDN.

Knowledge distillation transfers knowledge from the teacher model to the student one, significantly enhancing the capabilities of the student network. However, alleviating the information gap between the corresponding stages of the student and teacher during the distillation process poses a challenge. This challenge is particularly noticeable at deeper levels, where the limited capability of the student may result in capturing less information, thus leading to poor learning performance. To overcome this limitation, we introduce a novel multi-stage local feature distillation method, which leverages fused multiple feature maps named tutor to bridge the gap. Additionally, we have designed the Value Attention-Based Fusion module (Value-ABF) to enhance feature fusion reasonably. Compared with other distillation methods, our approach achieves comparable or even superior results and demonstrates better training efficiency on CIFAR-100 and COCO2017 datasets for tasks such as image classification, object detection, and instance segmentation.

Automated and accurate segmentation of medical images is important for facilitating clinical diagnosis and treatment. Currently, state-of-the-art(SOTA) diffusion based medical image segmentation methods are hampered by inherent randomness when generating diffusion model outcomes. Multiple generations are required to mitigate this randomness, which present a challenge for diffusion models. Due to the extended inference time required by diffusion models for multistep iterations, the process of obtaining final segmentation results by multiple generations is prolonged. As a result, this hampers the application of diffusion models in the medical field and limits the research potential of these models. In this paper, we present a medical image segmentation framework that concurrently predicts labels and noise. By leveraging label constraints within the diffusion model, we effectively suppress randomness, enabling the generation of segmentation maps with reduced errors in the initial stages and thereby suppress randomness. The performance of the proposed method is assessed using the ISIC2016 and Brats2018 datasets. Our approach necessitates just a single generation to produce effective segmentation results without the need for multiple steps to mitigate randomness and outperforms compared SOTA methods.

In the field of medical image processing, accurate segmentation is of great importance to assist doctors in diagnosis. However, existing machine learning methods are hardly effective for medical image segmentation in the absence of large and accurate datasets. Existing methods of learning with noisy labels rarely try to explore the correlation between noisy and clean labels. We found that some error corrections are learnable in the process of noisy labels corrected by medical experts. In this work, we propose a novel method to improve the performance of medical image segmentation. The method consists of two main networks: segmentation network segments the image and label correction network records and learns the denoising process of noisy labels, denoises the noisy labels. In addition, we introduce a feature fusion branch between the two networks. We compare with several state-of-the-art methods which learning with noisy label on the gastric wall dataset and notice that our method has strong competitiveness.

Despite the substantial progress made by deep networks in the field of medical image segmentation, they generally require sufficient pixel-level annotated data for training. The scale of training data remains to be the main bottleneck to obtain a better deep segmentation model. Semi-supervised learning is an effective approach that alleviates the dependence on labeled data. However, most existing semi-supervised image segmentation methods usually do not generate high-quality pseudo labels to expand training dataset. In this paper, we propose a deep semi-supervised approach for liver CT image segmentation by expanding pseudo-labeling algorithm under the very low annotated-data paradigm. Specifically, the output features of labeled images from the pretrained network combine with corresponding pixel-level annotations to produce class representations according to the mean operation. Then pseudo labels of unlabeled images are generated by calculating the distances between unlabeled feature vectors and each class representation. To further improve the quality of pseudo labels, we adopt a series of operations to optimize pseudo labels. A more accurate segmentation network is obtained by expanding the training dataset and adjusting the contributions between supervised and unsupervised loss. Besides, the novel random patch based on prior locations is introduced for unlabeled images in the training procedure. Extensive experiments show our method has achieved more competitive results compared with other semi-supervised methods when fewer labeled slices of LiTS dataset are available.

The U-Net is the well-known architecture for semantic segmentation and has achieved remarkable successes in many medical image segmentation applications. However, the features learned by standard convolution layers are not distinctive. To address this problem, we propose a novel architecture, called densely connected deep U-Net(DC U-Net). Specifically, the HU values in CT slices were first windowed in a range to exclude irrelevant organs, and then put it into DC U-Net for training. The DC U-Net consists of three blocks with dense connections, selective deconvlution layers with upsample and transconvlution filling function. To further improve the accuracy of small regin of interest segmentation with limited dataset, we proposed a novel loss function. With respect to the ground truth, average Dice overlap ratios for the liver and spleen are 94.9% and 92.1% respectively. The results demonstrated its potential in clinical usage with high effectiveness, robustness and efficiency.

The number of training data is the key bottleneck in achieving good results for medical image analysis and especially in deep learning. Due to small medical training data, deep learning models often fail to mine useful features and have serious over-fitting problems. In this paper, we propose a clean and effective feature fusion adversarial learning network to mine useful features and relieve over-fitting problems. Firstly, we train a fully convolution autoencoder network with unsupervised learning to mine useful feature maps from our liver lesion data. Secondly, these feature maps will be transferred to our adversarial SENet network for liver lesion classification. Our experiments on liver lesion classification in CT show an average accuracy as 85.47% compared with the baseline training scheme, which demonstrate our proposed method can mime useful features and relieve over-fitting problem. It can assist physicians in the early detection and treatment of liver lesions.

Segmentation methods only work for a single imaging modality usually suffer from the low spatial resolution in positron emission tomography (PET) or low contrast in computed tomography (CT) when the tumor region is inhomogeneous or not obvious. To address this problem, we develop a segmentation method combining the advantages and disadvantages of PET and CT. Firstly, the initial contours are obtained by the presegmentation of PET images using region growing and mathematical morphology. The initial contours can be used to automatically obtain the seed points required for random walk on PET and CT images, at the same time, they can be also used as a constraint in the random walk on CT images to solve the shortcoming that the tumor areas are not obvious if the CT images have not been enhanced. For the reason that CT provides essential details on anatomic structures, the anatomic structures of CT can be used to improve the weight of random walk on PET images. Finally, the similarity matrices obtained by random walk on PET and CT images are weighted to obtain identical results on PET and CT images. Our methods achieve an average DSC of 0.8456 ± 0.0703 on 14 patients with lung cancer. Our method has much better performance when the tumors are inhomogeneous on PET images and not obvious on CT images.

Existing studies have shown that neuronal functional networks (NFNs) exhibit small-world properties. However, the issue of whether NFNs have any other complex network topology properties remains unresolved. In this paper, we introduced a new hierarchical clustering-based method that can clearly indicate the hierarchical modular organization of NFNs. Based on the modularity function Q proposed by Newman, we can divide the NFNs into suitable sub-modules. We proposed a new measure function to calculate the correlations between pairs of spike trains without requiring binning of the spike trains through small time windows. This method can be used to analyze the level of synchronization between spike trains and functional connectivity relationships between neurons. We analyzed NFNs constructed from multi-electrode recordings in rat brain cerebral cortexes in vivo. These rats had been trained to perform different working memory cognitive tasks. The results show that NFNs exhibit a clear hierarchical modular organization in rat brains. These results provided evidence confirming that the brain networks are complex. This can also be used as a means of studying the relationship between neuronal functional organization and cognitive behavioral tasks.