Abstract: Provided is a weakly supervised pathological image tissue segmentation method based on an online noise suppression strategy, including: acquiring a hematoxylin-eosin (H&E) stained graph, processing the H&E stained graph to obtain a data set, dividing the data set, training a classification network based on a divided data set, and generating a pseudo-label; suppressing a noise existing in the pseudo-label based on the online noise suppression strategy, and training a semantic segmentation network through the pseudo-label after noise suppression and a training set corresponding to the pseudo-label to obtain a prediction result of the semantic segmentation network after the training, and taking the prediction result as a final segmentation result.

Abstract: The present invention discloses a non-invasive blood glucose measurement method, applied to noninvasive blood glucose measuring instruments including measuring hosts and fingertip measuring probes, comprising pre-storing a random forest algorithm and a neural network prediction algorithm in the measuring host; measuring energy metabolism parameters of a fingertip of an individual to be measured and transmitting the parameters to the measuring host by the fingertip measuring probe; calling the random forest algorithm to predict the blood glucose type of the energy metabolism parameters of the fingertip of the individual to be measured and calling the corresponding neural network prediction algorithm to calculate the blood glucose value of the fingertip of the individual to be measured by the measuring host. The present invention also provides a fingertip-measuring probe.