Lili Xia

Nuclei segmentation and classification in Hematoxylin and Eosin (H&E) stained histology images play a vital role in cancer diagnosis, treatment planning, and research. However, accurate segmentation can be hindered by factors like irregular cell shapes, unclear boundaries, and class imbalance. To address these challenges, we propose the Adaptive Gated Attention Fusion Network (AGAFNet), which integrates three innovative attention-based blocks into a U-shaped architecture complemented by dedicated decoders for both segmentation and classification tasks. These blocks comprise the Channel-wise and Spatial Attention Integration Block (CSAIB) for enhanced feature representation and selective focus on informative regions; the Adaptive Gated Convolutional Block (AGCB) for robust feature selection throughout the network; and the Fusion Attention Refinement Block (FARB) for effective information fusion. AGAFNet leverages these elements to provide a robust solution for precise nuclei segmentation and classification in H&E stained histology images. We evaluate the performance of AGAFNet on three large-scale multi-tissue datasets: PanNuke, CoNSeP, and Lizard. The experimental results demonstrate our proposed AGAFNet achieves comparable performance to state-of-the-art methods.

Electroencephalography (EEG) signals play a vital role in brain science research and clinical diagnostics. However, these signals are often contaminated by physiological artifacts such as electromyography (EMG), electrooculography (EOG), electrocardiography (ECG), and nonphysiological noise like white Gaussian noise (WGN), which substantially reduce the accuracy of analysis and decoding. In recent years, deep learning (DL) techniques have shown significant promise in EEG denoising tasks. However, existing methods struggle to capture the complex, nonlinear relationships inherent in EEG signals, particularly in multiscale feature extraction and time-frequency representation. To address these limitations, we propose WNOTNet, a novel model that integrates the Wavelet Neural Operator (WNO) and Transformer architecture. The WNO enables multiscale analysis and captures intricate time-frequency features, while the Transformer effectively models long-range dependencies and global context. This integration significantly improves both denoising performance and generalization capabilities. Extensive experiments conducted on the publicly available EEGdenoiseNet dataset show that WNOTNet outperforms existing methods across multiple evaluation metrics, including time-relative root mean square error (T-RRMSE), spectral-relative root mean square error (S-RRMSE), correlation coefficient (CC), signal-to-noise ratio (SNR), and others. In real-world applications, WNOT-Net was evaluated on practical EEG classification tasks, including sleep stage classification (MIT-BIH Polysomnographic dataset), driver fatigue detection, and emotion recognition. Notably, after denoising with WNOTNet, classification accuracy improved by 2.53% for sleep staging, 7.88% for driver fatigue detection, and 11.82% for emotion recognition. These experimental results demonstrate that WNOTNet can effectively enhance EEG signal quality and improve downstream classification accuracy. These findings indicate that WNOTNet provides robust and reliable denoising performance with strong generalization potential, making it suitable for practical EEG-based applications.

Epilepsy is a recurrent neurological disorder, and nearly 30% of epilepsy patients continue to experience symptoms despite taking anti-epileptic drugs. Predicting epileptic seizures enables patients to proactively take preventive measures against potential harm. Higher accuracy of seizure prediction would lead to a reduced incidence rate and decreased labor and resource consumption. In this study, we propose a hybrid LSTM-Transformer model for predicting epileptic seizures using scalp electroencephalogram (EEG) data. Time-frequency features are extracted through the short-time Fourier transform (STFT) applied to EEG signals, which are then inputted into the model to distinguish the interictal state and the preictal state. Our approach combines the long-distance dependence capability of Transformer with the advantages of LSTM in processing variable-length information, resulting in more robust and informative feature extraction. We evaluate our proposed method on the CHB-MIT dataset and conduct quantitative comparisons with recent methods. The results demonstrate that our method achieves the sensitivity of 99.75%, the false prediction rate (FPR) of 0, and the area under curve (AUC) of 99.39%. This novel approach provides valuable insights for epilepsy prediction.

Gas-liquid two-phase flow is vital in industrial production. The transient and unstable nature of two-phase flow makes it a challenging task to accurately measure and analyze the flow parameters. In this paper, we first design a dynamic experiment of gas-liquid two-phase flow and use the designed four-sector sensor to obtain the dynamic experimental data. Then, we construct the joint recurrence network from the collected data and calculate the average node degree for characterizing the evolution of gas-liquid two-phase flow. Finally, we propose a recurrence network-based densely connection neural network for flow parameter measurements in two-phase flow, and in the end, the accuracy of flow pattern identification is 95.17%, and the mean absolute percentage error (MAPE) of our model is less than 2.8% and the mean squared error (MSE) is less than 0.0023. At the same time, our method also offers a novel approach for industrial soft measurement models.

Brain tumor segmentation is a key step in brain cancer diagnosis. Segmentation of brain tumor sub-regions, including necrotic, enhancing, and edematous regions, can provide more detailed guidance for clinical diagnosis. Weakly supervised brain tumor segmentation methods have received much attention because they do not require time-consuming pixel-level annotations. However, existing weakly supervised methods focus on the segmentation of the entire tumor region while ignoring the challenging task of multi-label segmentation for the tumor sub-regions. In this paper, we propose a weakly supervised approach to solve the multi-label brain tumor segmentation problem. To the best of our knowledge, it's the first end-to-end multi-label weakly supervised segmentation model applied to brain tumor segmentation. With well-designed loss functions and a contrastive learning pre-training process, our proposed Transformer-based segmentation method (WS-MTST) has the ability to perform segmentation of brain tumor sub-regions. We conduct comprehensive experiments and demonstrate that our method reaches the state-of-the-art on the popular brain tumor dataset BraTS (from 2018 to 2020).

Nuclei segmentation is an essential step in the automatic analysis of histopathology images. This segmentation task requires much work to manually generate accurate pixel-level annotations for fully supervised training. To overcome such expensive and hard-to-get pixel-level annotations, in this paper we propose a weakly supervised method for nuclei segmentation only using point annotations based on convolutional neural network. The proposed method effectively combines a weakly supervised segmentation task and an auxiliary colorization task. The dual input with boundaries and color information maximizes the inherent features of the image. Two types of coarse labels generated from point annotations are applied to provide constraint information for the segmentation task. As an auxiliary task, colorization is incorporated to guide the network to extract effective features and improve the segmentation performance of the network. We evaluate our proposed method on two public nuclei segmentation datasets. The experimental results indicate that our method is superior to other state-of-the-art methods.