Communications in Science and Technology
Vol 4 No 2 (2019)

MALARIA PARASITE SEGMENTATION USING U-NET: COMPARATIVE STUDY OF LOSS FUNCTIONS

Abraham, Julisa Bana (Unknown)



Article Info

Publish Date
30 Dec 2019

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.

Copyrights © 2019






Journal Info

Abbrev

cst

Publisher

Subject

Engineering

Description

Communication in Science and Technology [p-ISSN 2502-9258 | e-ISSN 2502-9266] is an international open access journal devoted to various disciplines including social science, natural science, medicine, technology and engineering. CST publishes research articles, reviews and letters in all areas of ...