Timely diagnosis of type 2 diabetes and early intervention and treatment of it are important for controlling metabolic disorders, delaying and reducing complications, reducing mortality, and improving quality of life. Type 2 diabetes was diagnosed by Fourier transform mid-infrared (FTIR) attenuated total reflection (ATR) spectroscopy in combination with extreme gradient boosting (XGBoost). Whole blood FTIR-ATR spectra of 51 clinically diagnosed type 2 diabetes and 55 healthy volunteers were collected. For the complex composition of whole blood and much spectral noise, Savitzky–Golay smoothing was first applied to the FTIR-ATR spectrum. Then PCA was used to eliminate redundant data and got the best number of principle components. Finally, the XGBoost algorithm was used to discriminate the type 2 diabetes from healthy volunteers and the grid search algorithm was used to optimize the relevant parameters of the XGBoost model to improve the robustness and generalization ability of the model. The sensitivity of the optimal XGBoost model was 95.23% (20/21), the specificity was 96.00% (24/25), and the accuracy was 95.65% (44/46). The experimental results show that FTIR-ATR spectroscopy combined with XGBoost algorithm can diagnose type 2 diabetes quickly and accurately without reagents.
Leukemia diagnosis based on bone marrow cell morphology primarily relies on the manual microscopy of bone marrow smears. However, this method is greatly affected by subjective factors and tends to lead to misdiagnosis. This study proposes using bone marrow cell microscopy images and employs convolutional neural network (CNN) combined with transfer learning to establish an objective, rapid, and accurate method for classification and diagnosis of LKA (AML, ALL, and CML). We collected cell microscopy images of 104 bone marrow smears (including 18 healthy subjects, 53 AML patients, 23 ALL patients, and 18 CML patients). The perfect reflection algorithm and a self-adaptive filter algorithm were first used for preprocessing of bone marrow cell images collected from experiments. Subsequently, 3 CNN frameworks (Inception-V3, ResNet50, and DenseNet121) were used to construct classification models for the raw dataset and preprocessed dataset. Transfer learning was used to improve the prediction accuracy of the model. Results showed that the DenseNet121 model based on the preprocessed dataset provided the best classification results, with a prediction accuracy of 74.8%. The prediction accuracy of the DenseNet121 model that was obtained by transfer learning optimization was 95.3%, which was increased by 20.5%. In this model, the prediction accuracies of the normal groups, AML, ALL, and CML were 90%, 99%, 97%, and 95%, respectively. The results showed that the leukemic cell morphology classification and diagnosis based on CNN combined with transfer learning is feasible. Compared with conventional manual microscopy, this method is more rapid, accurate, and objective.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.