Malaria parasite segmentation using U-Net: Comparative study of loss functions

Abstract

The convolutional neural network is commonly used for classification. However, convolutional networks can also be used for semantic segmentation using the fully convolutional network approach. U-Net is one example of a fully convolutional network architecture capable of producing accurate segmentation on biomedical images. This paper proposes to use U-Net for Plasmodium segmentation on thin blood smear images. The evaluation shows that U-Net can accurately perform Plasmodium segmentation on thin blood smear images, besides this study also compares the three loss functions, namely mean-squared error, binary cross-entropy, and Huber loss. The results show that Huber loss has the best testing metrics: 0.9297, 0.9715, 0.8957, 0.9096 for F1 score, positive predictive value (PPV), sensitivity (SE), and relative segmentation accuracy (RSA), respectively.

Advanced Image Analytics for Mobile Robot-Based Condition Monitoring in Hazardous Environments: A Comprehensive Thermal Defect Processing Framework

“…To compare this study with our previous work, different variations of the U-Net architecture, including base U-Net [ 18 ], attention U-Net [ 68 ], and attention residual (ARes) U-Net [ 69 ], were employed to be compared with the proposed CNN models in the performance of semantic segmentation tasks [ 17 ]. In this study, binary cross-entropy (BCE) was employed as a loss function to train the U-Net models [ 70 ]. Table 3 and Table 4 compare the performance metrics of the studied methods.…”