Infrared Thermal Images Classification for Pressure Injury Prevention Incorporating the Convolutional Neural Networks

被引:11
作者
Wang, Yu [1 ]
Jiang, Xiaoqiong [2 ]
Yu, Kangyuan [3 ]
Shi, Fuqian [4 ]
Qin, Longjiang [1 ]
Zhou, Hui [1 ]
Cai, Fuman [2 ]
机构
[1] Wenzhou Med Univ, Affiliated Hosp 1, Wenzhou 325025, Peoples R China
[2] Wenzhou Med Univ, Coll Nursing, Wenzhou 325025, Peoples R China
[3] Wenzhou Med Univ, Coll Optometry & Biomed Engn, Wenzhou 325025, Peoples R China
[4] Rutgers Canc Inst New Jersey, New Brunswick, NJ 08903 USA
关键词
Convolutional neural networks; thermal image; pressure injury; THERMOGRAPHY; DAMAGE; RISK;
D O I
10.1109/ACCESS.2021.3051095
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Hospital-acquired pressure injury is difficult to identify in the early stage, accompanied with increased morbidity but considered to be preventable. For helping the nurses to monitor the status of the patients' skin, the infrared thermal imaging and the convolutional neural networks were integrated to identify and prevent pressure injury. In the first stage, infrared thermal images were shoot and labelled with the normal group and the pressure injury group by the clinical nurses. In the second stage, the convolutional neural networks and two machine learning algorithms, the random forest and the support vector machine, were applied to classify these two classes of the collected images. The classification model was trained on 164 images and was tested on the special image dataset consisted of 82 infrared thermal images of 1 day before pressure injury. Gray level co-occurrence matrix was utilized to extract the texture features of the infrared thermal images and we chose the pearson correlation coefficient and the Chi square test as the feature selection methods. The classification accuracy of the proposed convolutional neural networks model was 95.2% and the area under curve was 0.98. Moreover, the classification results from the test dataset were conformed to the experience of the experts. After feature selection, variance and entropy were proved to the best distinguishable features. Finally, we concluded that combining the infrared thermal imaging and convolutional neural networks could contribute to the prevention of pressure injury. This measure should be performed in high-risk populations to reduce the incidence of pressure injury.
引用
收藏
页码:15181 / 15190
页数:10
相关论文
共 50 条
[41]   Glomerulus Classification with Convolutional Neural Networks [J].
Pedraza, Anibal ;
Gallego, Jaime ;
Lopez, Samuel ;
Gonzalez, Lucia ;
Laurinavicius, Arvydas ;
Bueno, Gloria .
MEDICAL IMAGE UNDERSTANDING AND ANALYSIS (MIUA 2017), 2017, 723 :839-849
[42]   Convolutional Neural Networks for Font Classification [J].
Tensmeyer, Chris ;
Saunders, Daniel ;
Martinez, Tony .
2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, :985-990
[43]   Affine registration of thermal images of plantar feet using convolutional neural networks [J].
Aferhane, Asma ;
Bouallal, Doha ;
Douzi, Hassan ;
Harba, Rachid ;
Vilcahuaman, Luis ;
Arbanil, Hugo .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 95
[44]   Ship detection in spaceborne infrared images based on Convolutional Neural Networks and synthetic targets [J].
Jiang, Bitao ;
Ma, Xiaofeng ;
Lu, Yao ;
Li, Yang ;
Feng, Li ;
Shi, Zhenwei .
INFRARED PHYSICS & TECHNOLOGY, 2019, 97 :229-234
[45]   Polyp Classification and Clustering from Endoscopic Images using Competitive and Convolutional Neural Networks [J].
Kabra, Avish ;
Iwahori, Yuji ;
Usami, Hiroyasu ;
Bhuyan, M. K. ;
Ogasawara, Naotaka ;
Kasugai, Kunio .
ICPRAM: PROCEEDINGS OF THE 8TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION APPLICATIONS AND METHODS, 2019, :446-452
[46]   Automated lithology classification from drill core images using convolutional neural networks [J].
Alzubaidi, Fatimah ;
Mostaghimi, Peyman ;
Swietojanski, Pawel ;
Clark, Stuart R. ;
Armstrong, Ryan T. .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2021, 197
[47]   Classification for Dermoscopy Images Using Convolutional Neural Networks Based on Region Average Pooling [J].
Yang, Jiawen ;
Xie, Fengying ;
Fan, Haidi ;
Jiang, Zhiguo ;
Liu, Jie .
IEEE ACCESS, 2018, 6 :65130-65138
[48]   CLASSIFICATION OF MULTITEMPORAL SAR IMAGES USING CONVOLUTIONAL NEURAL NETWORKS AND MARKOV RANDOM FIELDS [J].
Danilla, Carolyne ;
Persello, Claudio ;
Tolpekin, Valentyn ;
Bergado, John Ray .
2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2017, :2231-2234
[49]   Underwater Targets Radiated Noise Classification Based on Enhanced Images and Convolutional Neural Networks [J].
Lei, Zhufeng ;
Luo, Jiachao ;
Qin, Qiwei ;
Lei, Xiaofang ;
Zhou, Chuanghui ;
Zhang, Qian .
IEEE ACCESS, 2024, 12 :105968-105973
[50]   Very high resolution images classification by fine tuning deep convolutional neural networks [J].
Iftene, M. ;
Liu, Q. ;
Wang, Y. .
EIGHTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2016), 2016, 10033