Diabetes mellitus is a global public health problem, and the epidemic situation in China is particularly serious. The prevalence of the disease has been increasing in recent years, and the number of patients is the highest in the world. Diabetes has become another chronic non-communicable disease that seriously endangers the health of our people after cardiovascular and cerebrovascular diseases and tumors. In this study, urine sample data were collected from 37 diabetic patients and 37 healthy volunteers using Raman spectroscopy. The collected data were preprocessed using an adaptive iterative reweighted penalized least squares (airPLS) algorithm and a polynomial Savitzky-Golay smoothing algorithm. After extracting features using principal component analysis (PCA) dimensionality reduction algorithm, ResNet, support vector machine (SVM) and linear discriminant analysis (LDA) classification models were selected to classify and identify diabetic patients and healthy controls. The results show that ResNet has the best discrimination effect, and the average accuracy, recall and F1-score can reach 84.28%, 86.20% and 84.02% respectively after five cross-validations, and the area under the subject working characteristic (ROC) curve is 0.93. The experimental results show that the model established in this paper is simple to operate, highly accurate and has good reference value for rapid screening of diabetes.

Histopathological image analysis is the gold standard for pathologists to grade colorectal cancers of different differentiation types. However, the diagnosis by pathologists is highly subjective and prone to misdiagnosis. In this study, we constructed a new attention mechanism named MCCBAM based on channel attention mechanism and spatial attention mechanism, and developed a computer-aided diagnosis (CAD) method based on CNN and MCCBAM, called HCCANet. In this study, 630 histopathology images processed with Gaussian filtering denoising were included and gradient-weighted class activation map (Grad-CAM) was used to visualize regions of interest in HCCANet to improve its interpretability. The experimental results show that the proposed HCCANet model outperforms four advanced deep learning (ResNet50, MobileNetV2, Xception, and DenseNet121) and four classical machine learning (KNN, NB, RF, and SVM) techniques, achieved 90.2%, 85%, and 86.7% classification accuracy for colorectal cancers with high, medium, and low differentiation levels, respectively, with an overall accuracy of 87.3% and an average AUC value of 0.9.In addition, the MCCBAM constructed in this study outperforms several commonly used attention mechanisms SAM, SENet, SKNet, Non_Local, CBAM, and BAM on the backbone network. In conclusion, the HCCANet model proposed in this study is feasible for postoperative adjuvant diagnosis and grading of colorectal cancer.