Shannon Tucker Kahn
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shannon Tucker Kahn has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Harold I. Saavedra
Department of Radiation Oncology, Winship Cancer Institute, Emory University School of Medicine, C3084, 1365C Clifton Road NE, Atlanta, GA 30322, USA
1 shared publication - Hui-Kuo George Shu
Department of Radiation Oncology, Emory University, Atlanta, GA 30322, USA
1 shared publication - Jing Wang
Emory University, Department of Radiation Oncology and Winship Cancer Institute, Atlanta, Georgia, United States
1 shared publication - Justin Roper
Emory University, Winship Cancer Institute, Department of Radiation Oncology, Atlanta, Georgia, United States
1 shared publication - Kailin Yang
Department of Radiation Oncology, Taussig Cancer Center, Cleveland Clinic, Cleveland, USA
1 shared publication - Katie R. Hagen
Integrated Research Facility, Division of Clinical Research, National Institute of Allergy and Infectious Diseases, National Institutes of Health, 8200 Research Plaza, Fort Detrick, Frederick, MD 21702, USA
1 shared publication
Latest Publications
- 1 January 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (01) , 014503-17
MGMT promoter methylation prediction based on multiparametric MRI via vision graph neural network
PurposeGlioblastoma (GBM) is aggressive and malignant. The methylation status of the O6‐methylguanine‐DNA methyltransferase (MGMT) promoter in GBM tissue is considered an important biomarker for developing the most effective treatment plan. Although the standard method for assessing the MGMT promoter methylation status is via bisulfite modification and deoxyribonucleic acid (DNA) sequencing of biopsy or surgical specimens, a secondary automated method based on medical imaging may improve the efficiency and accuracy of those tests.ApproachWe propose a deep vision graph neural network (ViG) using multiparametric magnetic resonance imaging (MRI) to predict the MGMT promoter methylation status noninvasively. Our model was compared to the RSNA radiogenomic classification winners. The dataset includes 583 usable patient cases. Combinations of MRI sequences were compared. Our multi-sequence fusion strategy was compared with those using single MR sequences.ResultsOur best model [Fluid Attenuated Inversion Recovery (FLAIR), T1-weighted pre-contrast (T1w), T2-weighted (T2)] outperformed the winning models with a test area under the curve (AUC) of 0.628, an accuracy of 0.632, a precision of 0.646, a recall of 0.677, a specificity of 0.581, and an F1 score of 0.661. Compared to the winning models with single MR sequences, our ViG utilizing fused-MRI showed a significant improvement statistically in AUC scores, which are FLAIR (p=0.042), T1w (p=0.017), T1wCE (p=0.001), and T2 (p=0.018).ConclusionsOur model is superior to challenge champions. A graph representation of the medical images enabled good handling of complexity and irregularity. Our work provides an automatic secondary check pipeline to ensure the correctness of MGMT methylation status prediction.
- 1 January 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (01) , 014503-17
MGMT promoter methylation prediction based on multiparametric MRI via vision graph neural network
PurposeGlioblastoma (GBM) is aggressive and malignant. The methylation status of the O6‐methylguanine‐DNA methyltransferase (MGMT) promoter in GBM tissue is considered an important biomarker for developing the most effective treatment plan. Although the standard method for assessing the MGMT promoter methylation status is via bisulfite modification and deoxyribonucleic acid (DNA) sequencing of biopsy or surgical specimens, a secondary automated method based on medical imaging may improve the efficiency and accuracy of those tests.ApproachWe propose a deep vision graph neural network (ViG) using multiparametric magnetic resonance imaging (MRI) to predict the MGMT promoter methylation status noninvasively. Our model was compared to the RSNA radiogenomic classification winners. The dataset includes 583 usable patient cases. Combinations of MRI sequences were compared. Our multi-sequence fusion strategy was compared with those using single MR sequences.ResultsOur best model [Fluid Attenuated Inversion Recovery (FLAIR), T1-weighted pre-contrast (T1w), T2-weighted (T2)] outperformed the winning models with a test area under the curve (AUC) of 0.628, an accuracy of 0.632, a precision of 0.646, a recall of 0.677, a specificity of 0.581, and an F1 score of 0.661. Compared to the winning models with single MR sequences, our ViG utilizing fused-MRI showed a significant improvement statistically in AUC scores, which are FLAIR (p=0.042), T1w (p=0.017), T1wCE (p=0.001), and T2 (p=0.018).ConclusionsOur model is superior to challenge champions. A graph representation of the medical images enabled good handling of complexity and irregularity. Our work provides an automatic secondary check pipeline to ensure the correctness of MGMT methylation status prediction.
- Open Access
- 25 July 2013
- Published by Springer Nature in Cell Division
- Vol. 8 (1) , 10
Silencing CDK4 radiosensitizes breast cancer cells by promoting apoptosis
Background: The discovery of molecular markers associated with various breast cancer subtypes has greatly improved the treatment and outcome of breast cancer patients. Unfortunately, breast cancer cells acquire resistance to various therapies. Mounting evidence suggests that resistance is rooted in the deregulation of the G1 phase regulatory machinery.Methods: To address whether deregulation of the G1 phase regulatory machinery contributes to radiotherapy resistance, the MCF10A immortalized human mammary epithelial cell line, ER-PR-Her2+ and ER-PR-Her2- breast cancer cell lines were irradiated. Colony formation assays measured radioresistance, while immunocytochemistry, Western blots, and flow cytometry measured the cell cycle, DNA replication, mitosis, apoptosis, and DNA breaks.Results: Molecular markers common to all cell lines were overexpressed, including cyclin A1 and cyclin D1, which impinge on CDK2 and CDK4 activities, respectively. We addressed their potential role in radioresistance by generating cell lines stably expressing small hairpin RNAs (shRNA) against CDK2 and CDK4. None of the cell lines knocked down for CDK2 displayed radiosensitization. In contrast, all cell lines knocked down for CDK4 were significantly radiosensitized, and a CDK4/CDK6 inhibitor sensitized MDA-MB-468 to radiation induced apoptosis. Our data showed that silencing CDK4 significantly increases radiation induced cell apoptosis in cell lines without significantly altering cell cycle progression, or DNA repair after irradiation. Our results indicate lower levels of phospho-Bad at ser136 upon CDK4 silencing and ionizing radiation, which has been shown to signal apoptosis.Conclusion: Based on our data we conclude that knockdown of CDK4 activity sensitizes breast cancer cells to radiation by activating apoptosis pathways.
- 25 July 2013
- Published by Springer Nature in Cell Division
- Vol. 8 (1) , 10
Open AccessSilencing CDK4 radiosensitizes breast cancer cells by promoting apoptosis
Background: The discovery of molecular markers associated with various breast cancer subtypes has greatly improved the treatment and outcome of breast cancer patients. Unfortunately, breast cancer cells acquire resistance to various therapies. Mounting evidence suggests that resistance is rooted in the deregulation of the G1 phase regulatory machinery.Methods: To address whether deregulation of the G1 phase regulatory machinery contributes to radiotherapy resistance, the MCF10A immortalized human mammary epithelial cell line, ER-PR-Her2+ and ER-PR-Her2- breast cancer cell lines were irradiated. Colony formation assays measured radioresistance, while immunocytochemistry, Western blots, and flow cytometry measured the cell cycle, DNA replication, mitosis, apoptosis, and DNA breaks.Results: Molecular markers common to all cell lines were overexpressed, including cyclin A1 and cyclin D1, which impinge on CDK2 and CDK4 activities, respectively. We addressed their potential role in radioresistance by generating cell lines stably expressing small hairpin RNAs (shRNA) against CDK2 and CDK4. None of the cell lines knocked down for CDK2 displayed radiosensitization. In contrast, all cell lines knocked down for CDK4 were significantly radiosensitized, and a CDK4/CDK6 inhibitor sensitized MDA-MB-468 to radiation induced apoptosis. Our data showed that silencing CDK4 significantly increases radiation induced cell apoptosis in cell lines without significantly altering cell cycle progression, or DNA repair after irradiation. Our results indicate lower levels of phospho-Bad at ser136 upon CDK4 silencing and ionizing radiation, which has been shown to signal apoptosis.Conclusion: Based on our data we conclude that knockdown of CDK4 activity sensitizes breast cancer cells to radiation by activating apoptosis pathways.