Accurate segmentation of liver images is an essential step in liver disease diagnosis, treatment planning, and prognosis. In recent years, although liver segmentation methods based on 2D convolutional neural networks have achieved good results, there is still a lack of interlayer information that causes severe loss of segmentation accuracy to a certain extent. Meanwhile, making the best of high-level and low-level features more effectively in a 2D segmentation network is a challenging problem. Therefore, we designed and implemented a 2.5-dimensional convolutional neural network, VNet_WGAN, to improve the accuracy of liver segmentation. First, we chose three adjacent layers of a liver model as the input of our network and adopted two convolution kernels in series connection, which can integrate cross-sectional spatial information and interlayer information of liver models. Second, a chain residual pooling module is added to fuse multilevel feature information to optimize the skip connection. Finally, the boundary loss function in the generator is employed to compensate for the lack of marginal pixel accuracy in the Dice loss function. The effectiveness of the proposed method is verified on two datasets, LiTS and CHAOS. The Dice coefficients are 92% and 90%, respectively, which are better than those of the compared segmentation networks. In addition, the experimental results also show that the proposed method can reduce computational consumption while retaining higher segmentation accuracy, which is significant for liver segmentation in practice and provides a favorable reference for clinicians in liver segmentation.
25 November 2025 in Computers and Electronics in Agriculture
In recent years, U-Net and its extended variants have made remarkable progress in the realm of liver and liver tumor segmentation. However, the limitations of single-path convolutional operations have hindered the full exploitation of valuable features and restricted their mobility within networks. Moreover, the semantic gap between shallow and deep features proves that a simplistic shortcut is not enough. To address these issues and realize automatic liver and tumor area segmentation in CT images, we introduced the multi-scale feature fusion with dense connections and an attention mechanism segmentation method (MDAU-Net). This network leverages the multi-head attention (MHA) mechanism and multi-scale feature fusion. First, we introduced a double-flow linear pooling enhancement unit to optimize the fusion of deep and shallow features while mitigating the semantic gap between them. Subsequently, we proposed a cascaded adaptive feature extraction unit, combining attention mechanisms with a series of dense connections to capture valuable information and encourage feature reuse. Additionally, we designed a cross-level information interaction mechanism utilizing bidirectional residual connections to address the issue of forgetting a priori knowledge during training. Finally, we assessed MDAU-Net’s performance on the LiTS and SLiver07 datasets. The experimental results demonstrated that MDAU-Net is well-suited for liver and tumor segmentation tasks, outperforming existing widely used methods in terms of robustness and accuracy.
Generating food images aims to convert textual food ingredients into corresponding images for the visualization of color and shape adjustments, dietary guidance, and the creation of new dishes. It has a wide range of applications, including food recommendation, recipe development, and health management. However, existing food image generation models, predominantly based on GANs (Generative Adversarial Networks), face challenges in maintaining semantic consistency between image and text, as well as achieving visual realism in the generated images. These limitations are attributed to the constrained representational capacity of sparse ingredient embedding and the lack of diversity in GAN-based food image generation models. To alleviate this problem, this paper proposes a food image generation network, named MLA-Diff, in which ingredient and image features are learned and integrated as ingredient-image pairs to generate initial images, and then image details are refined by using an attention fusion module. The main contributions are as follows: (1) The enhanced CLIP (Contrastive Language-Image Pre-Training) module is constructed by transforming sparse ingredient embedding into compact embedding and capturing multi-scale image features, providing an effective solution to alleviate semantic consistency issues. (2) The Memory module is proposed by embedding a pre-trained diffusion model to generate initial images with diversity and reality. (3) The attention fusion module is proposed by integrating features from diverse modalities to enhance the comprehension between ingredient and image features. Extensive experiments on the Mini-food dataset demonstrate the superiority of the MLA-Diff in terms of semantic consistency and visual realism, generating high-quality food images.
1 September 2014 in Computational and Mathematical Methods in Medicine
In this paper we propose a novel visual method for protein model classification and retrieval. Different from the conventional methods, the key idea of the proposed method is to extract image features of proteins and measure the visual similarity between proteins. Firstly, the multiview images are captured by vertices and planes of a given octahedron surrounding the protein. Secondly, the local features are extracted from each image of the different views by the SURF algorithm and are vector quantized into visual words using a visual codebook. Finally, KLD is employed to calculate the similarity distance between two feature vectors. Experimental results show that the proposed method has encouraging performances for protein retrieval and categorization as shown in the comparison with other methods.
1 January 2021 in Computational Intelligence and Neuroscience
Text‐based multitype question answering is one of the research hotspots in the field of reading comprehension models. Multitype reading comprehension models have the characteristics of shorter time to propose, complex components of relevant corpus, and greater difficulty in model construction. There are relatively few research works in this field. Therefore, it is urgent to improve the model performance. In this paper, a text‐based multitype question and answer reading comprehension model (MTQA) is proposed. The model is based on a multilayer transformer encoding and decoding structure. In the decoding structure, the headers of the answer type prediction decoding, fragment decoding, arithmetic decoding, counting decoding, and negation are added for the characteristics of multiple types of corpora. Meanwhile, high‐performance ELECTRA checkpoints are employed, and secondary pretraining based on these checkpoints and an absolute loss function are designed to improve the model performance. The experimental results show that the performance of the proposed model on the DROP and QUOREF corpora is better than the best results of the current existing models, which proves that the proposed MTQA model has high feature extraction and relatively strong generalization capabilities.