Publications by authors named "Seiyon Lee"

2 Publications

  • Page 1 of 1

Higher levels of allograft injury in black patients early after heart transplantation.

J Heart Lung Transplant 2021 Dec 23. Epub 2021 Dec 23.

Genomic Research Alliance for Transplantation (GRAfT), Bethesda, Maryland; Laborarory of Applied Precision Omics (APO), Division of Intramural Research, National Heart, Lung and Blood Institute, National Institutes of Health, Bethesda, Maryland; Department of Medicine, Stanford University School of Medicine, Palo Alto, California. Electronic address:

Black patients suffer higher rates of antibody-mediated rejection and have worse long-term graft survival after heart transplantation. Donor-derived cell free DNA (ddcfDNA) is released into the blood following allograft injury. This study analyzed %ddcfDNA in 63 heart transplant recipients categorized by Black and non-Black race, during the first 200 days after transplant. Immediately after transplant, %ddcfDNA was higher for Black patients (mean [SE]: 8.3% [1.3%] vs 3.2% [1.2%], p = 0.001). In the first week post-transplant, the rate of decay in %ddcfDNA was similar (0.7% [0.68] vs 0.7% [0.11], p = 0.78), and values declined in both groups to a comparable plateau at 7 days post-transplant (0.46% [0.03] vs 0.45% [0.04], p = 0.78). The proportion of Black patients experiencing AMR was higher than non-Black patients (21% vs 9% [hazard ratio of 2.61 [95% confidence interval: 0.651-10.43], p = 0.18). Black patients were more likely to receive a race mismatched organ than non-Black patients (69% vs 35%, p = 0.01), which may explain the higher levels of early allograft injury.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.healun.2021.12.006DOI Listing
December 2021

Bi-Modal Transfer Learning for Classifying Breast Cancers via Combined B-Mode and Ultrasound Strain Imaging.

IEEE Trans Ultrason Ferroelectr Freq Control 2022 01 31;69(1):222-232. Epub 2021 Dec 31.

Although accurate detection of breast cancer still poses significant challenges, deep learning (DL) can support more accurate image interpretation. In this study, we develop a highly robust DL model based on combined B-mode ultrasound (B-mode) and strain elastography ultrasound (SE) images for classifying benign and malignant breast tumors. This study retrospectively included 85 patients, including 42 with benign lesions and 43 with malignancies, all confirmed by biopsy. Two deep neural network models, AlexNet and ResNet, were separately trained on combined 205 B-mode and 205 SE images (80% for training and 20% for validation) from 67 patients with benign and malignant lesions. These two models were then configured to work as an ensemble using both image-wise and layer-wise and tested on a dataset of 56 images from the remaining 18 patients. The ensemble model captures the diverse features present in the B-mode and SE images and also combines semantic features from AlexNet and ResNet models to classify the benign from the malignant tumors. The experimental results demonstrate that the accuracy of the proposed ensemble model is 90%, which is better than the individual models and the model trained using B-mode or SE images alone. Moreover, some patients that were misclassified by the traditional methods were correctly classified by the proposed ensemble method. The proposed ensemble DL model will enable radiologists to achieve superior detection efficiency owing to enhance classification accuracy for breast cancers in ultrasound (US) images.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TUFFC.2021.3119251DOI Listing
January 2022
-->