Yi Xin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yi Xin has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Maurizio Cereda
Department of Anesthesiology, Mass General Brigham, Boston, MA
3 shared publications - Marcus Victor
Aeronautics Institute of Technology
2 shared publications - Timothy Glen Gaulton
Department of Anesthesiology, Mass General Brigham, Boston, MA
2 shared publications - Alice Nova
Mass General Brigham and Harvard Medical School
1 shared publication - Arthur S. Ribeiro
Electronics Engineering Division, Aeronautics Institute of Technology, Sao Paulo, Brazil
1 shared publication - Eduardo Leite Vieira Costa
Pulmonary Division, Instituto do Coração, Hospital das Clínicas, Faculdade de Medicina, Universidade de São Paulo - São Paulo (SP), Brazil
1 shared publication
Latest Publications
- 13 June 2025
- Published by IOP Publishing in Biomedical Physics & Engineering Express
- Vol. 11 (4) , 045013
Supervised and unsupervised learning for lung perfusion data segmentation in electrical impedance tomography
Objective: Effective lung gas exchange relies on the balance between alveolar ventilation and perfusion, which can be disrupted in mechanically ventilated patients. Lung perfusion assessment using electrical impedance tomography (EIT) typically involves a sudden injection of a hypertonic saline solution. The large field of view provided by EIT often results in ambivalent behavior of many voxel waveforms following an indicator injection, where some exhibit indicator kinetics solely through the lungs (pulmonary), while others show passage through both the heart and lungs (hybrid). Consequently, a segmentation algorithm is essential for accurate perfusion evaluation. Approach: Sixteen pigs (29–35 kg) were mechanically ventilated and received a 10 ml bolus of 7.5% NaCl solution to assess lung perfusion during a healthy stage and, later, in an injured stage after receiving 3.5 ml kg−1 of HCl to induce acute lung injury. Supervised (Bagged Trees, Neural Networks, and Support Vector Machine) and unsupervised (K-means, Hierarchical, and Principal Component Analysis) learning methods were employed using 115 saline injections comprising voxel waveforms to label voxels as either hybrid or pulmonary. All segmentation methods were compared to a ground-truth mask manually drawn. A training dataset (81 injections) was used to train and cross-validate (five-fold) the supervised methods using previously extracted features. The test dataset (34 injections) was used to test both supervised and unsupervised learning algorithms. Main Results: A Principal Component Analysis (unsupervised learning) method exhibited the best overall performance, achieving 83% sensitivity, 92% specificity, 89% accuracy, and 84% dice similarity coefficient. No significant difference in performance was observed between healthy and injured subsets. Unsupervised methods consistently yielded more physiologically plausible and less scattered regions of interest. Significance: Accurate voxel labeling is crucial for lung perfusion assessment, as it enables discrimination of the indicator passage through the heart and lungs, thereby improving the estimation of regional pulmonary blood flow.
- 13 June 2025
- Published by IOP Publishing in Biomedical Physics & Engineering Express
- Vol. 11 (4) , 045013
Supervised and unsupervised learning for lung perfusion data segmentation in electrical impedance tomography
Objective: Effective lung gas exchange relies on the balance between alveolar ventilation and perfusion, which can be disrupted in mechanically ventilated patients. Lung perfusion assessment using electrical impedance tomography (EIT) typically involves a sudden injection of a hypertonic saline solution. The large field of view provided by EIT often results in ambivalent behavior of many voxel waveforms following an indicator injection, where some exhibit indicator kinetics solely through the lungs (pulmonary), while others show passage through both the heart and lungs (hybrid). Consequently, a segmentation algorithm is essential for accurate perfusion evaluation. Approach: Sixteen pigs (29–35 kg) were mechanically ventilated and received a 10 ml bolus of 7.5% NaCl solution to assess lung perfusion during a healthy stage and, later, in an injured stage after receiving 3.5 ml kg−1 of HCl to induce acute lung injury. Supervised (Bagged Trees, Neural Networks, and Support Vector Machine) and unsupervised (K-means, Hierarchical, and Principal Component Analysis) learning methods were employed using 115 saline injections comprising voxel waveforms to label voxels as either hybrid or pulmonary. All segmentation methods were compared to a ground-truth mask manually drawn. A training dataset (81 injections) was used to train and cross-validate (five-fold) the supervised methods using previously extracted features. The test dataset (34 injections) was used to test both supervised and unsupervised learning algorithms. Main Results: A Principal Component Analysis (unsupervised learning) method exhibited the best overall performance, achieving 83% sensitivity, 92% specificity, 89% accuracy, and 84% dice similarity coefficient. No significant difference in performance was observed between healthy and injured subsets. Unsupervised methods consistently yielded more physiologically plausible and less scattered regions of interest. Significance: Accurate voxel labeling is crucial for lung perfusion assessment, as it enables discrimination of the indicator passage through the heart and lungs, thereby improving the estimation of regional pulmonary blood flow.
- 15 May 2024
- Published by Oxford University Press (OUP) in American Journal of Respiratory and Critical Care Medicine
- Vol. 209 (10) , 1263-1265
First-Pass Kinetics Model to Estimate Pulmonary Perfusion by Electrical Impedance Tomography During Uninterrupted Breathing
- 15 May 2024
- Published by Oxford University Press (OUP) in American Journal of Respiratory and Critical Care Medicine
- Vol. 209 (10) , 1263-1265
First-Pass Kinetics Model to Estimate Pulmonary Perfusion by Electrical Impedance Tomography During Uninterrupted Breathing
- 1 June 2022
- Published by American Physiological Society in American Journal of Physiology-Lung Cellular and Molecular Physiology
- Vol. 322 (6) , L866-L872
Imatinib alleviates lung injury and prolongs survival in ventilated rats
Imatinib, a tyrosine kinase inhibitor, attenuates pulmonary edema and inflammation in lung injury. However, the physiological effects of this drug and their impact on outcomes are poorly characterized. Using serial computed tomography (CT), we tested the hypothesis that imatinib reduces injury severity and improves survival in ventilated rats. Hydrochloric acid (HCl) was instilled in the trachea (pH 1.5, 2.5 mL/kg) of anesthetized, intubated supine rats. Animals were randomized ( n = 17 each group) to receive intraperitoneal imatinib or vehicle immediately prior to HCl. All rats then received mechanical ventilation. CT was performed hourly for 4 h. Images were quantitatively analyzed to assess the progression of radiological abnormalities. Injury severity was confirmed via hourly blood gases, serum biomarkers, bronchoalveolar lavage (BAL), and histopathology. Serial blood drug levels were measured in a subset of rats. Imatinib reduced mortality while delaying functional and radiological injury progression: out of 17 rats per condition, 2 control vs. 8 imatinib-treated rats survived until the end of the experiment ( P = 0.02). Imatinib attenuated edema after lung injury ( P < 0.05), and survival time in both groups was negatively correlated with increased lung mass ( R2 = 0.70) as well as other physiological and CT parameters. Capillary leak (BAL protein concentration) was significantly lower in the treated group ( P = 0.04). Peak drug concentration was reached after 70 min, and the drug half-life was 150 min. Imatinib decreased both mortality and lung injury severity in mechanically ventilated rats. Pharmacological inhibition of edema could be used during mechanical ventilation to improve the severity and outcome of lung injury.
- 1 June 2022
- Published by American Physiological Society in American Journal of Physiology-Lung Cellular and Molecular Physiology
- Vol. 322 (6) , L866-L872
Imatinib alleviates lung injury and prolongs survival in ventilated rats
Imatinib, a tyrosine kinase inhibitor, attenuates pulmonary edema and inflammation in lung injury. However, the physiological effects of this drug and their impact on outcomes are poorly characterized. Using serial computed tomography (CT), we tested the hypothesis that imatinib reduces injury severity and improves survival in ventilated rats. Hydrochloric acid (HCl) was instilled in the trachea (pH 1.5, 2.5 mL/kg) of anesthetized, intubated supine rats. Animals were randomized ( n = 17 each group) to receive intraperitoneal imatinib or vehicle immediately prior to HCl. All rats then received mechanical ventilation. CT was performed hourly for 4 h. Images were quantitatively analyzed to assess the progression of radiological abnormalities. Injury severity was confirmed via hourly blood gases, serum biomarkers, bronchoalveolar lavage (BAL), and histopathology. Serial blood drug levels were measured in a subset of rats. Imatinib reduced mortality while delaying functional and radiological injury progression: out of 17 rats per condition, 2 control vs. 8 imatinib-treated rats survived until the end of the experiment ( P = 0.02). Imatinib attenuated edema after lung injury ( P < 0.05), and survival time in both groups was negatively correlated with increased lung mass ( R2 = 0.70) as well as other physiological and CT parameters. Capillary leak (BAL protein concentration) was significantly lower in the treated group ( P = 0.04). Peak drug concentration was reached after 70 min, and the drug half-life was 150 min. Imatinib decreased both mortality and lung injury severity in mechanically ventilated rats. Pharmacological inhibition of edema could be used during mechanical ventilation to improve the severity and outcome of lung injury.