S2DA-Net: Spatial and spectral-learning double-branch aggregation network for liver tumor segmentation in CT images.

Accurate liver tumor segmentation is crucial for aiding radiologists in hepatocellular carcinoma evaluation and surgical planning. While convolutional neural networks (CNNs) have been successful in medical image segmentation, they face challenges in capturing long-term dependencies among pixels. On the other hand, Transformer-based models demand a high number of parameters and involve significant computational costs. To address these issues, we propose the Spatial and Spectral-learning Double-branched Aggregation Network (S2DA-Net) for liver tumor segmentation. S2DA-Net consists of a double-branched encoder and a decoder with a Group Multi-Head Cross-Attention Aggregation (GMCA) module, Two branches in the encoder consist of a Fourier Spectral-learning Multi-scale Fusion (FSMF) branch and a Multi-axis Aggregation Hadamard Attention (MAHA) branch. The FSMF branch employs a Fourier-based network to learn amplitude and phase information, capturing richer features and detailed information without introducing an excessive number of parameters. The FSMF branch utilizes a Fourier-based network to capture amplitude and phase information, enriching features without introducing excessive parameters. The MAHA branch incorporates spatial information, enhancing discriminative features while minimizing computational costs. In the decoding path, a GMCA module extracts local information and establishes long-term dependencies, improving localization capabilities by amalgamating features from diverse branches. Experimental results on the public LiTS2017 liver tumor datasets show that the proposed segmentation model achieves significant improvements compared to the state-of-the-art methods, obtaining dice per case (DPC) 69.4 % and global dice (DG) 80.0 % for liver tumor segmentation on the LiTS2017 dataset. Meanwhile, the pre-trained model based on the LiTS2017 datasets obtain, DPC 73.4 % and an DG 82.2 % on the 3DIRCADb dataset.

BreastDM: A DCE-MRI dataset for breast tumor image segmentation and classification.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has shown high sensitivity to diagnose breast cancer. However, few computer-aided algorithms focus on employing DCE-MR images for breast cancer diagnosis due to the lack of publicly available DCE-MRI datasets. To address this issue, our work releases a new DCE-MRI dataset called BreastDM for breast tumor segmentation and classification. In particular, a dataset of 232 patients selected with DCE-MR images for benign and malignant cases is established. Each case consists of three types of sequences: pre-contrast, post-contrast, and subtraction sequences. To show the difficulty of breast DCE-MRI tumor image segmentation and classification tasks, benchmarks are achieved by state-of-the-art image segmentation and classification algorithms, including conventional hand-crafted based methods and recently-emerged deep learning-based methods. More importantly, a local-global cross attention fusion network (LG-CAFN) is proposed to further improve the performance of breast tumor images classification. Specifically, LG-CAFN achieved the highest accuracy (88.20%, 83.93%) and AUC value (0.9154,0.8826) in both groups of experiments. Extensive experiments are conducted to present strong baselines based on various typical image segmentation and classification algorithms. Experiment results also demonstrate the superiority of the proposed LG-CAFN to other breast tumor images classification methods. The related dataset and evaluation codes are publicly available at smallboy-code/Breast-cancer-dataset.

BAF-Net: Bidirectional attention fusion network via CNN and transformers for the pepper leaf segmentation.

The segmentation of pepper leaves from pepper images is of great significance for the accurate control of pepper leaf diseases. To address the issue, we propose a bidirectional attention fusion network combing the convolution neural network (CNN) and Swin Transformer, called BAF-Net, to segment the pepper leaf image. Specially, BAF-Net first uses a multi-scale fusion feature (MSFF) branch to extract the long-range dependencies by constructing the cascaded Swin Transformer-based and CNN-based block, which is based on the U-shape architecture. Then, it uses a full-scale feature fusion (FSFF) branch to enhance the boundary information and attain the detailed information. Finally, an adaptive bidirectional attention module is designed to bridge the relation of the MSFF and FSFF features. The results on four pepper leaf datasets demonstrated that our model obtains F1 scores of 96.75%, 91.10%, 97.34% and 94.42%, and IoU of 95.68%, 86.76%, 96.12% and 91.44%, respectively. Compared to the state-of-the-art models, the proposed model achieves better segmentation performance. The code will be available at the website: https://github.com/fangchj2002/BAF-Net.

GCHA-Net: Global context and hybrid attention network for automatic liver segmentation.

Liver segmentation is a critical step in liver cancer diagnosis and surgical planning. The U-Net's architecture is one of the most efficient deep networks for medical image segmentation. However, the continuous downsampling operators in U-Net causes the loss of spatial information. To solve these problems, we propose a global context and hybrid attention network, called GCHA-Net, to adaptive capture the structural and detailed features. To capture the global features, a global attention module (GAM) is designed to model the channel and positional dimensions of the interdependencies. To capture the local features, a feature aggregation module (FAM) is designed, where a local attention module (LAM) is proposed to capture the spatial information. LAM can make our model focus on the local liver regions and suppress irrelevant information. The experimental results on the dataset LiTS2017 show that the dice per case (DPC) value and dice global (DG) value of liver were 96.5% and 96.9%, respectively. Compared with the state-of-the-art models, our model has superior performance in liver segmentation. Meanwhile, we test the experiment results on the 3Dircadb dataset, and it shows our model can obtain the highest accuracy compared with the closely related models. From these results, it can been seen that the proposed model can effectively capture the global context information and build the correlation between different convolutional layers. The code is available at the website: https://github.com/HuaxiangLiu/GCAU-Net.

Inner wall temperature distribution measurement of the ladle based on cavity effective emissivity correction.

Inner wall temperature of ladle is closely related to the quality of steelmaking and control of steel-making tapping temperature. This article adopts a rotating platform to drive an infrared temperature sensor and a laser sensor to scan the temperature field distribution of the ladle inner wall at the hot repair station, where the scanning laser sensor obtains coordinates of each measured point. Because of measuring errors of infrared thermal radiation caused by emissivity uncertainty of the ladle inner wall surface, this article proposes a method for temperature measurement based on Monte Carlo model for effective emissivity correction of each measured point. In the model, we consider the ladle and fire baffle as a cavity. By calculation of the model, the effect of distance from the fire baffle to the ladle and the material surface emissivity of the ladle inner wall on the effective emissivity of the cavity are obtained. After that, the effective emissivity of each measured point is determined. Then the scanning temperature of each measured point is corrected to real temperature. By field measuring test and verification contrast, the results show that: the maximum absolute error of the method in this article is 4.7 °C, the minimum error is 0.6 °C, and the average error is less than 2.8 °C. The method in this article achieves high measurement accuracy and contributes to the control of metallurgical process based on temperature information.

Localized Patch-Based Fuzzy Active Contours for Image Segmentation.

This paper presents a novel fuzzy region-based active contour model for image segmentation. By incorporating local patch-energy functional along each pixel of the evolving curve into the fuzziness of the energy, we construct a patch-based energy function without the regurgitation term. Its purpose is not only to make the active contour evolve very stably without the periodical initialization during the evolution but also to reduce the effect of noise. In particular, in order to reject local minimal of the energy functional, we utilize a direct method to calculate the energy alterations instead of solving the Euler-Lagrange equation of the underlying problem. Compared with other fuzzy active contour models, experimental results on synthetic and real images show the advantages of the proposed method in terms of computational efficiency and accuracy.

[Narrow band multi-region level set method for remote sensing image].

Massive redundant contours happen when the classical Chan-Vese (C-V) model is used to segment remote sensing images, which have interlaced edges. What's more, this model can't segment homogeneous objects with multiple regions. In order to overcome this limitation of C-V model, narrow band multiple level set method is proposed. The use of N-1 curves is required for the segmentation of N regions and each curve represents one region. First, the level set model to establish an independent multi-region region can eliminate the redundant contours and avoids the problems of vacuum and overlap. Then, narrow band approach to level set method can reduce the computational cost. Experimental results of remote image verify that our model is efficient and accurate.