An attention-based deep convolutional neural network for classification and grading of interferents in serum specimens

Abstract

Accurate diagnosis depends on the provision of high-quality and efficient laboratory testing in which the serum test is one of the most important tools. However, for various reasons, interferents in serum specimens exist, which affect the accuracy of biochemical tests. Hemolysis, icterus, and lipemia (HIL) are the three most frequent interferents in serum samples. Determining their existence and degree of interference in serum samples before testing is essential to improve test quality. In this study, a deep learning model for classifying and grading HIL interferences is designed under the assumption that the serum color images contain information on the category and degree of interference. Because the major features of the classification and grading should be obtained from the liquid region of the serum, an auxiliary segmentation task was designed to assist the main classification task. The segmentation result provided the position information of the serum region for the main classification task as a spatial attention mechanism, which helped the network to focus on learning the significant features selectively with a channel attention mechanism. The method unified the two-stage task of 3-class classification and 5-degree grading of interferents into one model. The accuracy of the 15-class classification was 98.62%, and the degree grading accuracy of the three serum interferents (HIL) reached 98.74, 98.52, and 98.54%, respectively. This research provides a new approach to realize the automatic classification and grading of HIL interferents in serum specimens.