Open AccessDiscrimination of the Skin Microcirculatory Status Using Photoacoustic Technique and Long Short-term Memory Network
Author(s) -
Hui Ling Chua,
Audrey Huong
Publication year - 2022
Publication title -
international journal of online and biomedical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.184
H-Index - 8
ISSN - 2626-8493
DOI - 10.3991/ijoe.v18i01.27415
Subject(s) - computer science , standard deviation , artificial intelligence , pattern recognition (psychology) , task (project management) , set (abstract data type) , deep learning , test set , data set , photoacoustic imaging in biomedicine , sensitivity (control systems) , convolutional neural network , statistics , mathematics , engineering , physics , systems engineering , optics , programming language , electronic engineering
Measuring oxygen in blood with a standard imaging method is challenging. Most of the conventional imaging systems presented outcomes of microcirculatory change measurement as signals of complex forms. This leads to analytical insufficiency due to the complicated and visually unnoticeable features of the signals. For that reason, there is a great need to explore the use of photoacoustic (PA) method and deep learning technique for the task. This work presents the use of a deep network containing long short-term memory (LSTM) units for temporal features extraction and classification of skin microcirculatory status. The model was trained using a limited number of PA signals. One way ANOVA test was used to evaluate changes in the PA signals collected under different experiment condition. The results showed a strong statistical significance between the means of two groups (ρ < 0.05). The mean ± standard deviation (SD) final validation accuracies of the trained model is given by 95.60 ± 0.47 % with inclusion of augmented data, which showed better performance than the case without the augmentation method. The results of the testing set showed a considerably good classification accuracy, specificity, and sensitivity given by 97.6 %, 100 %, and 83.3%. The future of this work includes improvement of the network architecture to include more convolutional layers for searching patterns in the features extracted.