TY - JOUR
T1 - Inhalation Injury Grading Using Transfer Learning Based on Bronchoscopy Images and Mechanical Ventilation Period
AU - Li, Yifan
AU - Pang, Alan W.
AU - Zeitouni, Jad
AU - Zeitouni, Ferris
AU - Mateja, Kirby
AU - Griswold, John A.
AU - Chong, Jo Woon
N1 - Publisher Copyright:
© 2022 by the authors.
PY - 2022/12
Y1 - 2022/12
N2 - The abbreviated injury score (AIS) is commonly used as a grading system for inhalation injuries. While inhalation injury grades have inconsistently been shown to correlate positively with the time mechanical ventilation is needed, grading is subjective and relies heavily on the clinicians’ experience and expertise. Additionally, no correlation has been shown between these patients’ inhalation injury grades and outcomes. In this paper, we propose a novel inhalation injury grading method which uses deep learning algorithms in bronchoscopy images to determine the injury grade from the carbonaceous deposits, blistering, and fibrin casts in the bronchoscopy images. The proposed method adopts transfer learning and data augmentation concepts to enhance the accuracy performance to avoid overfitting. We tested our proposed model on the bronchoscopy images acquired from eighteen patients who had suffered inhalation injuries, with the degree of severity 1, 2, 3, 4, 5, or 6. As performance metrics, we consider accuracy, sensitivity, specificity, F-1 score, and precision. Experimental results show that our proposed method, with both transfer learning and data augmentation components, provides an overall 86.11% accuracy. Moreover, the experimental results also show that the performance of the proposed method outperforms the method without transfer learning or data augmentation.
AB - The abbreviated injury score (AIS) is commonly used as a grading system for inhalation injuries. While inhalation injury grades have inconsistently been shown to correlate positively with the time mechanical ventilation is needed, grading is subjective and relies heavily on the clinicians’ experience and expertise. Additionally, no correlation has been shown between these patients’ inhalation injury grades and outcomes. In this paper, we propose a novel inhalation injury grading method which uses deep learning algorithms in bronchoscopy images to determine the injury grade from the carbonaceous deposits, blistering, and fibrin casts in the bronchoscopy images. The proposed method adopts transfer learning and data augmentation concepts to enhance the accuracy performance to avoid overfitting. We tested our proposed model on the bronchoscopy images acquired from eighteen patients who had suffered inhalation injuries, with the degree of severity 1, 2, 3, 4, 5, or 6. As performance metrics, we consider accuracy, sensitivity, specificity, F-1 score, and precision. Experimental results show that our proposed method, with both transfer learning and data augmentation components, provides an overall 86.11% accuracy. Moreover, the experimental results also show that the performance of the proposed method outperforms the method without transfer learning or data augmentation.
KW - convolutional neural networks (cnn)
KW - deep learning
KW - inhalation injury
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85143530993&partnerID=8YFLogxK
U2 - 10.3390/s22239430
DO - 10.3390/s22239430
M3 - Article
C2 - 36502127
AN - SCOPUS:85143530993
SN - 1424-8220
VL - 22
JO - Sensors (Switzerland)
JF - Sensors (Switzerland)
IS - 23
M1 - 9430
ER -