Convolutional neural Network-based detection of deep vein thrombosis in a low limb with light reflection rheography. (15th February 2022)

• Record Type: Journal Article
• Authors: Liu, Shing-Hong; Chen, Wenxi; Su, Chun-Hung; Pan, Kuo-Li
• Is Part Of: Measurement. Volume 189(2022)
• Publication Date: 2022-02-15
• Subjects: Vein thrombosis -- Light reflection rheography -- Convolutional neural network -- Homecare; DVT deep vein thrombosis -- LRR light reflection rheography -- 2D CNN two-dimension convolutional neural network -- APP application program -- VGG-19 19 layers CNN proposed by Visual Geometry Group -- DL deep learning -- ECG electrocardiogram -- EEG electroencephalogram -- ML machine learning -- LSTM long short-term memory -- PPG photoplethysmography -- ROC receiver operating characteristic -- LED light-emitting diode -- PD photoelectric diode -- FIR finite impulse response -- TP true positive -- FP false positive -- TN true negative -- FN false negative -- VP1 the change of venous pump volume between the ending point of LRR and resting baseline -- VP2 the change of venous pump volume between the ending point of LRR and refilling baseline -- m10 the slope of the emptying curve from the ending point of LRR to start point of LRR -- m40 the slope of the refilling curve from the ending point of LRR to the point at 40 s -- m50 the slope of the refilling curve from the ending point of LRR to the point at 50 s -- m60 the slope of the refilling curve from the ending point of LRR to the point at 60 s -- N-DVT Non DVT -- L-DVT Slight DVT -- S-DVT Serious DVT -- AUC areas under curves; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.110457
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: The light reflection rheography (LRR) are used to examine the deep vein thrombosis. 2D CNN is used to evaluate the signal quality and classify the DVT. The image pattern is combining the LRR with signal of accelerometer. Abstract: Artificial intelligence has been widely used in the biomedical engineering field, which can assist the clinicians in disease diagnoses, help the engineers in physiological signal processing, or serve the people with chronic diseases in the homecare management. Blood clots in the deep veins of human body is called the deep vein thromboses (DVT). If the embolus passes through the lung, patient will have a life-threatening risk. Therefore, how to use the artificial intelligence to serve daily monitoring of the DVT condition is a valuable exploration. The light reflection rheography (LRR) has been used to detect the DVT of low limbs. In the previous study, the wearable device using LRR technique has been developed. But, this examination system could not be used by non-physician because the signal-quality evaluation of LRR and the classification of positive or negative DVT using the LRR signal all need the manual process. The goal of this study is to use a two-dimension convolutional neural network (2D CNN) to evaluate the qualities of LRR signals and classify the positive or negative DVT from the LRR signal with high reliability. The LRR signal and the smoothed signal were combined together to form a 450x450 image as the input pattern. In this study, twenty subjects were recruited to perform four-time experiments. A cuff pressured to 100 mmHg and 150 mmHg occluded the veins of low limbs to simulate the slight and serious DVT scenarios, and which was placed at the top and bottom of the knee of left leg to simulate the distal and proximal embolization. In the signal-quality evaluation, there were 700 samples including 476 high qualities and 224 low qualities, which were marked by the experts according to the vein emptying phenomenon. In the DVT classification, there were 476 samples including 167 negative samples, 158 slight positive samples, and 151 serious positive samples. A 19-layer CNN model proposed by Visual Geometry Group (VGG-19) was used in the two experiments. We performed the inter-group and intra-group analysis. Both results were better than the previous study. The accuracies of signal-quality evaluation and DVT classification were 0.92 and 0.75, respectively. Thus, the proposed method could support people with the high risk for DVT examination at non-medical settings.