Queens College Health-Care Informatics Lab

Our research lab primarily focuses on biomedical imaging informatics, which involves development of algorithms for understanding of image contents, fusion of information extracted across multiple images, and identification of clinical features with diagnostic or prognostic values to advance medical treatments. It spans the areas of computer vision, image processing, and machine learning. Not limited to just images, we also leverage other information modalities to include structural information in ensemble learning. We actively seek collaborations with experts in nature science to explore applications of big data in medicine and health care. Our research should generate greater scientific insights into hypotheses, not answered by traditional small data studies, while improving state-of-the-art machine learning models. Our graduate students work actively with collaborators from problem formulation to publication.

Below are ongoing projects with selected publications. For a complete list of my publications, please visit my Google Scholar.

Biomedical Image Analysis

Development of algorithms for understanding of image contents, fusion of information extracted across multiple image modalities, and large-scale analysis of such information. Ongoing projects include diagnosis and localization of Polypoidal Choroidal Vasculopathy in Fluorescein Angiography (FA) and weakly supervised segmentation of Optical Coherence Tomography (OCT) imaging biomarkers for diabetic retinopathy.

Collaborators:

Dr. Shih-Jen Chen Taipei Veterans General Hospital, Taiwan
Dr. Wei-Yang Lin, National Chung Cheng University, Taiwan
Dr. Nitish Mehta, NYU Langone Eye Center, USA
Dr. Chao Chen, Stony Brook University, USA
Dr. Wei-Chi Wu, Chang Gung Memorial Hospital, Taiwan

Selected publications

J. Yang, N. Mehta, G. M. Demirci, X. Hu, M. S. Ramakrishnan, M. Naguib, C. Chen and C.-L. Tsai. “Anomaly-Guided Weakly Supervised Lesion Segmentation on Retinal OCT Images”, Medical Image Analysis, 2024
T.-H. Yang, Y.-Y. Su, C.-L Tsai, K.-H. Lin, W.-Y. Lin and S.-F. Sung. “Magnetic resonance imaging-based deep learning imaging biomarker for predicting functional outcomes after acute ischemic stroke”, European Journal of Radiology, 2024
Y.-Y. Tsai, W.-Y. Lin, S.-J. Chen, P. Ruamviboonsuk, C.-Ho. King, and C.-L. Tsai. “Early diagnosis of Polypoidal Choroidal Vasculopathy from Fluorescein Angiography Using Deep Learning”, Translational Vision Science & Technology, February, 2022
J. Yang, X. Hu, C. Chen, and C.-L. Tsai. “A Topological-Attention ConvLSTM Network and Its Application to EM Images”, Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021, September
J. Yang, X. Hu, C. Chen, and C.-L. Tsai. “3D Topology-Preserving Segmentation with Compound Multi-Slice Representation”, International Symposium on Biomedical Imaging (ISBI), 2021, April

Machine Learning in Healthcare

Longitudinal studies on neurobehavioral development of infants. Ongoing projects include study of neurobehavioral phenotypes and brain structural alterations associated with impact of in-utero exposure to natural disasters, and prediction of developmental delay in pre-term infants.

Collaborators:

Dr. Yoko Numura, Psychology, Queens College CUNY, USA
Dr. Duke Shereen, Psychology, CUNY Advanced Science Research Center, USA
Infant Development Research Program, NYS Institute for Basic Research in Developmental Disabilities, USA

Selected publications

G. M. Demirci, P. Kittler, M.J. Flory, H.T. Phan, A. Gordon, S. Parab, and C.-L. Tsai. "Predicting mental and psychomotor delay in very pre-term infants using machine learning", Pediatr Res, 2023.
G. M. Demirci, D. Delngeniis, W. M. Wong, D. Sheeren, Y. Nomura and C.-L. Tsai. "Superstorm Sandy exposure in utero is associated with neurobehavioral phenotypes and brain structure alterations in childhood: A machine learning approach", Frontiers in Neuroscience, 2023.
G. M. Demirci, C.-L. Tsai, M.J. Flory, H.T. Phan, A. Gordon, S. Parab, and P. Kittler. “Predicting Developmental Delay in Very Pre-Term Infants Using Machine Learning”, Association for Psychological Science (APS) Annual Convention, 2022, May

Data Science in Literacy Education

Application of machine learning techniques on mapping of the assessment outcomes to teaching strategies for effective Response-to-Intervention. Ongoing projects include the development of a recommender system for reading comprehension. The system is developed with a collection of fourth grade New York English Language Arts (ELA) assessments.

Collaborators:

Dr. Marlene Zakierski, Sage Colleges, USA
Dr. Wei-Yang Lin, National Chung Cheng University, Taiwan

Selected publications

M.-C. Liu, and W.-Y. Lin and C.-L. Tsai. “Computer-Aided Response-to-Intervention for Reading Comprehension Based on Recommender System”, International Conference on Artificial Intelligence in Education, 2022, July
C.-L. Tsai, Y.-G. Lin, and M.-C. Liu, and W.-Y. Lin. “Computer-Aided Grouping of Students with Reading Disabilities for Effective Response-to-Intervention”, 16th International Conference on Intelligent Tutoring Systems, 2020, June.
C.-L. Tsai, Y.-G. Lin, W.-Y. Lin, and M. Zakierski. “Computer-Aided Intervention for Reading Comprehension Disabilities”, 15th International Conference on Intelligent Tutoring Systems, 2019, June.