Objective：Due to inconsistent subjective assessment criteria and excessively long calculation responses，there is a high risk of mistakenly discarding suspected hemolytic plasma and inappropriately discarding suspected non - hemolytic plasma during plasma preparation，posing significant risks to patient safety and leading to waste. This study aims to resolue these problems. Methods： A thresholding method that integrates deep learning with color-changing ink concepts was developed. By employing an enhanced U-Net architecture for image segmentation，the study introduces an advanced attention mechanism，batch normalization，and a padding module to tackle issues such as mean estimation bias，computational inefficiencies，and limited receptive field sizes in spatial mapping relationships. The model was validated and compared using a self-collected sample dataset. Results：This study employed the color-changing ink boundary method for classification，enhancing the computational efficiency of plasma discrimination and reducing discrimination time，while ensuring the accuracy of plasma sample identification. The accuracy rate of the experimental results is 99.52%. Conclusion：The results indicate that the plasma discrimination accuracy of this model is superior to other discrimination models，and it is expected to be applied in clinical practice.