Mr. Thomas Z. Li Profile

Thomas Z. Li

SPIE Involvement:

Author

Thomas is an MD/Ph.D. candidate at Vanderbilt University in the Medical-image Analysis and Statistical Interpretation Lab. He studied computer science at Duke University and has held software engineering roles in industry. His research is centered around combining AI with longitudinal and multi-modal medical data to advance the management of pulmonary nodules and lung cancer.

SPIE Journal Paper | 5 November 2024 Open Access

Data-driven nucleus subclassification on colon hematoxylin and eosin using style-transferred digital pathology

Lucas Remedios, Shunxing Bao, Samuel Remedios, Ho Hin Lee, Leon Cai, Thomas Li, Ruining Deng, Nancy Newlin, Adam Saunders, Can Cui, Jia Li, Qi Liu, Ken S. Lau, Joseph Roland, Mary Washington, Lori Coburn, Keith Wilson, Yuankai Huo, Bennett Landman

JMI, Vol. 11, Issue 06, 067501, (November 2024) https://doi.org/10.1117/12.10.1117/1.JMI.11.6.067501

KEYWORDS: Education and training, Tissues, Colon, Data modeling, Diseases and disorders, Virtual colonoscopy, Image segmentation, Performance modeling, Pathology, Cross validation

Read Abstract +

PurposeCells are building blocks for human physiology; consequently, understanding the way cells communicate, co-locate, and interrelate is essential to furthering our understanding of how the body functions in both health and disease. Hematoxylin and eosin (H&E) is the standard stain used in histological analysis of tissues in both clinical and research settings. Although H&E is ubiquitous and reveals tissue microanatomy, the classification and mapping of cell subtypes often require the use of specialized stains. The recent CoNIC Challenge focused on artificial intelligence classification of six types of cells on colon H&E but was unable to classify epithelial subtypes (progenitor, enteroendocrine, goblet), lymphocyte subtypes (B, helper T, cytotoxic T), and connective subtypes (fibroblasts). We propose to use inter-modality learning to label previously un-labelable cell types on H&E.ApproachWe took advantage of the cell classification information inherent in multiplexed immunofluorescence (MxIF) histology to create cell-level annotations for 14 subclasses. Then, we performed style transfer on the MxIF to synthesize realistic virtual H&E. We assessed the efficacy of a supervised learning scheme using the virtual H&E and 14 subclass labels. We evaluated our model on virtual H&E and real H&E.ResultsOn virtual H&E, we were able to classify helper T cells and epithelial progenitors with positive predictive values of 0.34±0.15 (prevalence 0.03±0.01) and 0.47±0.1 (prevalence 0.07±0.02), respectively, when using ground truth centroid information. On real H&E, we needed to compute bounded metrics instead of direct metrics because our fine-grained virtual H&E predicted classes had to be matched to the closest available parent classes in the coarser labels from the real H&E dataset. For the real H&E, we could classify bounded metrics for the helper T cells and epithelial progenitors with upper bound positive predictive values of 0.43±0.03 (parent class prevalence 0.21) and 0.94±0.02 (parent class prevalence 0.49) when using ground truth centroid information.ConclusionsThis is the first work to provide cell type classification for helper T and epithelial progenitor nuclei on H&E.

DOWNLOAD PAPER

Proceedings Article | 3 April 2024 Presentation + Paper

Nucleus subtype classification using inter-modality learning

Lucas Remedios, Shunxing Bao, Samuel Remedios, Ho Hin Lee, Leon Cai, Thomas Li, Ruining Deng, Can Cui, Jia Li, Qi Liu, Ken Lau, Joseph Roland, Mary Washington, Lori Coburn, Keith Wilson, Yuankai Huo, Bennett Landman

Proceedings Volume 12933, 129330F (2024) https://doi.org/10.1117/12.3006237

KEYWORDS: Machine learning, Colon, Pathology, Multiplexing, Human physiology, Clinical research, Biological imaging, Artificial intelligence

Read Abstract +

Proceedings Article | 2 April 2024 Presentation + Paper

Inter-vendor harmonization of CT reconstruction kernels using unpaired image translation

Aravind Krishnan, Kaiwen Xu, Thomas Li, Chenyu Gao, Lucas Remedios, Praitayini Kanakaraj, Ho Hin Lee, Shunxing Bao, Kim Sandler, Fabien Maldonado, Ivana Išgum, Bennett Landman

Proceedings Volume 12926, 129261D (2024) https://doi.org/10.1117/12.3006608

KEYWORDS: Emphysema, Bone, CT reconstruction, Computed tomography, Data modeling, Lung, Image analysis, Medical image reconstruction

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Learning site-invariant features of connectomes to harmonize complex network measures

Nancy Newlin, Praitayini Kanakaraj, Thomas Li, Kimberly Pechman, Derek Archer, Angela Jefferson, Bennett Landman, Daniel Moyer

Proceedings Volume 12930, 129302E (2024) https://doi.org/10.1117/12.3009645

KEYWORDS: Education and training, Brain, Scanners, Diffusion, Alzheimer disease, Diffusion magnetic resonance imaging, Data modeling, Biological imaging, Matrices, Magnetic resonance imaging

Read Abstract +

SPIE Journal Paper | 18 July 2023 Open Access

Quantifying emphysema in lung screening computed tomography with robust automated lobe segmentation

Thomas Z. Li, Ho Hin Lee, Kaiwen Xu, Riqiang Gao, Benoit M. Dawant, Fabien Maldonado, Kim L. Sandler, Bennett A. Landman

JMI, Vol. 10, Issue 04, 044002, (July 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.4.044002

KEYWORDS: Emphysema, Lung, Lung cancer, Computed tomography, Chronic obstructive pulmonary disease, Algorithm development, Image segmentation, Education and training, 3D modeling, Data modeling

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 11 April 2023 Presentation + Paper

Stratification of lung cancer risk with thoracic imaging phenotypes

Kaiwen Xu, Mirza Khan, Thomas Li, Riqiang Gao, Sanja Antic, Yuankai Huo, Kim Sandler, Fabien Maldonado, Bennett Landman

Proceedings Volume 12464, 1246407 (2023) https://doi.org/10.1117/12.2654018

KEYWORDS: Body composition, Computed tomography

Read Abstract +

Proceedings Article | 10 April 2023 Presentation

Characterizing browser-based medical imaging AI with serverless edge computing: towards addressing clinical data security constraints

Chenxi Dong, Thomas Li, Kaiwen Xu, Zekun Wang, Fabien Maldonado, Kim Sandler, Bennett Landman, Yuankai Huo

Proceedings Volume 12469, 1246907 (2023) https://doi.org/10.1117/12.2653626

KEYWORDS: Artificial intelligence, Medical imaging, Computer security, 3D modeling, Computed tomography, Systems modeling, Data modeling, Clouds, Visualization, Tumor growth modeling

Read Abstract +

Proceedings Article | 3 April 2023 Presentation + Paper

Time-distance vision transformers in lung cancer diagnosis from longitudinal computed tomography

Thomas Li, Kaiwen Xu, Riqiang Gao, Yucheng Tang, Thomas Lasko, Fabien Maldonado, Kim Sandler, Bennett Landman

Proceedings Volume 12464, 1246412 (2023) https://doi.org/10.1117/12.2653911

KEYWORDS: Transformers, Lung cancer, Tumors, Lung, Chest, Medical imaging, Computed tomography, Cancer

Read Abstract +

Showing 5 of 8 publications

Keywords/Phrases

Search In:

Publication Years