Yubo Tao

Background : The pathological response to neoadjuvant chemotherapy (NAC) is an established predictor of long-term outcomes in breast cancer. However, conventional binary assessment based solely on pathological complete response (pCR) fails to capture prognostic heterogeneity across molecular subtypes. This study aimed to develop an interpretable deep learning model that integrates multiple clinical and pathological variables to predict both recurrence and metastasis development following NAC treatment. Methods: We conducted a retrospective analysis of 832 breast cancer patients who received NAC between 2013 and 2022. The analysis incorporated five key variables: tumor size changes, nodal status, Ki-67 index, Miller–Payne grade, and molecular subtype. A Multi-Layer Perceptron (MLP) model was implemented on the PyTorch platform and systematically benchmarked against SVM, Random Forest, and XGBoost models using five-fold cross-validation. Model performance was assessed by calculating the area under the curve (AUC), accuracy, precision, recall, and F1-score, and by analyzing confusion matrices. Results: The MLP model achieved AUC values of 0.86 (95% CI: 0.82–0.93) for HER2-positive cases, 0.82 (95% CI: 0.70–0.92) for triple-negative cases, and 0.76 (95% CI: 0.66–0.82) for HR+/HER2-negative cases. SHAP analysis identified post-NAC tumor size, Ki-67 index, and Miller–Payne grade as the most influential predictors. Notably, patients who achieved pCR still had a 12% risk of developing recurrence, highlighting the necessity for ongoing risk assessment beyond binary response evaluation. Conclusions: The proposed deep learning system provides precise and interpretable risk assessment for NAC patients, facilitating individualized treatment approaches and post-treatment monitoring plans.

Sentiment analysis methods for interactive services such as Danmu in online videos are challenged by their colloquial style and diverse sentiment expressions. For instance, the existing methods cannot easily distinguish between similar sentiments. To address these limitations, this paper proposes a dual-channel model integrated with attention mechanisms for multi-dimensional sentiment analysis of Danmu. First, we replace word embeddings with character embeddings to better capture the colloquial nature of Danmu text. Second, the dual-channel multi-dimensional sentiment encoder extracts both the high-level semantic and raw contextual information. Channel I of the encoder learns the sentiment features from different perspectives through a mixed model that combines the benefits of self-Attention and Dilated CNN (ADCMix) and performs contextual modeling through bidirectional long short-term memory (BiLSTM) with attention mechanisms. Channel II mitigates potential biases and omissions in the sentiment features. The model combines the two channels to erase the fuzzy boundaries between similar sentiments. Third, a multi-dimensional sentiment decoder is designed to handle the diversity in sentiment expressions. The superior performance of the proposed model is experimentally demonstrated on two datasets. Our model outperformed the state-of-the-art methods on both datasets, with improvements of at least 2.05% in accuracy and 3.28% in F1-score.

An efficient and precise diagnosis of retinal diseases is a fundamental goal for auxiliary diagnostic systems in ophthalmology. Inspired by the importance of scattered subtle lesions in manual retinal disease diagnosis, recent research has achieved state-of-the-art performance by mining information related to subtle lesions, including their texture and shape. However, the spatial distribution patterns of subtle lesion areas, which are also crucial in manual diagnosis, have been overlooked in existing research. Neglecting these spatial distribution patterns (e.g., the ring distribution of microaneurysms in diabetic macular edema) may negatively impact the diagnostic process. In this paper, we introduce the Saliency-Image-Graph (SIGraph) network to capture the spatial distribution patterns of lesion areas. We first employ saliency-based perception to identify latent lesion pixels. Subsequently, we propose a novel image-graph block to efficiently capture the global distribution of abundant lesion pixels with minimal information loss. By leveraging additional distribution patterns, SIGraph achieves state-of-the-art performance with at least a 1.5% performance gain across three datasets. Furthermore, ablation studies demonstrate that our image-graph block can be integrated into other visual backbones and effectively boost performance.

Recently, deep learning-based tooth segmentation methods have been limited by the expensive and time-consuming processes of data collection and labeling. Achieving high-precision segmentation with limited datasets is critical. A viable solution to this entails fine-tuning pre-trained multiview-based models, thereby enhancing performance with limited data. However, relying solely on two-dimensional (2D) images for three-dimensional (3D) tooth segmentation can produce suboptimal outcomes because of occlusion and deformation, i.e., incomplete and distorted shape perception. To improve this fine-tuning-based solution, this paper advocates 2D-3D joint perception. The fundamental challenge in employing 2D-3D joint perception with limited data is that the 3D-related inputs and modules must follow a lightweight policy instead of using huge 3D data and parameter-rich modules that require extensive training data. Following this lightweight policy, this paper selects skeletons as the 3D inputs and introduces MSFormer, a novel method for tooth segmentation. MSFormer incorporates two lightweight modules into existing multiview-based models: a 3D-skeleton perception module to extract 3D perception from skeletons and a skeleton-image contrastive learning module to obtain the 2D-3D joint perception by fusing both multiview and skeleton perceptions. The experimental results reveal that MSFormer paired with large pre-trained multiview models achieves state-of-the-art performance, requiring only 100 training meshes. Furthermore, the segmentation accuracy is improved by 2.4%-5.5% with the increasing volume of training data.