The electrocardiogram (ECG) is a non-invasive, inexpensive, and effective tool for myocardial infarction (MI) diagnosis. Conventional detection algorithms require solid domain expertise and rely heavily on handcrafted features. Although previous works have studied deep learning methods for extracting features, these methods still neglect the relationships between different leads and the temporal characteristics of ECG signals. To handle the issues, a novel multi-lead attention (MLA) mechanism integrated with convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU) framework (MLA-CNN-BiGRU) is therefore proposed to detect and locate MI via 12-lead ECG records. Specifically, the MLA mechanism automatically measures and assigns the weights to different leads according to their contribution. The two-dimensional CNN module exploits the interrelated characteristics between leads and extracts discriminative spatial features. Moreover, the BiGRU module extracts essential temporal features inside each lead. The spatial and temporal features from these two modules are fused together as global features for classification. In experiments, MI location and detection were performed under both intra-patient scheme and inter-patient scheme to test the robustness of the proposed framework. Experimental results indicate that our intelligent framework achieved satisfactory performance and demonstrated vital clinical significance.
The electronic nose (e-nose) system is a newly developing detection technology for its advantages of non-invasiveness, simple operation, and low cost. However, lung cancer screening through e-nose requires effective pattern recognition frameworks. Existing frameworks rely heavily on hand-crafted features and have relatively low diagnostic sensitivity. To handle these problems, gated recurrent unit based autoencoder (GRU-AE) is adopted to automatically extract features from temporal and high-dimensional e-nose data. Moreover, we propose a novel margin and sensitivity based ordering ensemble pruning (MSEP) model for effective classification. The proposed heuristic model aims to reduce missed diagnosis rate of lung cancer patients while maintaining a high rate of overall identification. In the experiments, five state-of-the-art classification models and two popular dimensionality reduction methods were involved for comparison to demonstrate the validity of the proposed GRU-AE-MSEP framework, through 214 collected breath samples measured by e-nose. Experimental results indicated that the proposed intelligent framework achieved high sensitivity of 94.22%, accuracy of 93.55%, and specificity of 92.80%, thereby providing a new practical means for wide disease screening by e-nose in medical scenarios.
Colorectal cancer continues to be a major health issue even though screening methods have facilitated early detection. Despite the high sensitivity of white-light colonoscopy, it frequently overlooks invasive flat or depressed lesions, which can lead to the development of larger, advanced tumors. Fluorescence molecular imaging offers a promising approach for early tumor detection by targeting specific molecular characteristics of lesions. CD24 is upregulated during the adenoma-to-colorectal cancer transition, providing a potential target for fluorescence molecular imaging. In this study, we developed a second near-infrared window (NIR-II) fluorescent probe with a high affinity for CD24 and evaluated its efficacy and targeting ability in cellular models, murine models, and clinical samples of colorectal cancer. CD24 expression was elevated in 76% of adenomas and 80% of colorectal cancers. In a colitis-associated cancer mouse model, NIR-II imaging with the CD24-targeted probe achieved a significantly higher tumor-to-background ratio compared with conventional NIR-I imaging. The probe demonstrated exceptional sensitivity (92%) and specificity (92%) for detecting colorectal cancer, including small lesions less than 1 mm in size. This led to the identification of precancerous lesions missed by white-light detection and lesions missed by NIR-I imaging. Moreover, ex vivo human tissue incubation with the probe supported the potential for intraprocedural lesion identification via topical probe application during colonoscopy. In conclusion, this study successfully demonstrates the potential of CD24-targeted NIR-II imaging for identifying colorectal neoplasia, highlighting its significance for early colorectal cancer detection in the gastrointestinal tract. Significance: Overexpression of CD24 in colorectal dysplasia provides the opportunity to use an NIR-II fluorescent probe targeting CD24 to detect colorectal neoplasms, including invisible lesions that are missed by white-light colonoscopy.
21 December 2025 in Expert Systems with Applications