BIBM 2019
147 papers
The 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) featured 174 papers, with a significant emphasis on causal inference and clinical data representation. Research themes focused on causal discovery, including structural optimization, uncertainty quantification, and the development of interventional metrics for evaluation. Another prominent area involved automated representation learning and semantic vector embeddings for structured medical sequences. Prolific contributors to this year's proceedings included Jianxin Wang, Eric P. Xing, and Haohan Wang.
The conference also highlighted advancements in medical imaging and natural language processing. Notable studies addressed 3D U-Net architectures for glioma segmentation, lymphoma detection in PET images using genetic algorithms, and pulmonary nodule characterization. In biomedical text mining, research explored distantly supervised named entity recognition and introduced the BioRel dataset for relation extraction. Additional work covered cellular electron cryo-tomograms classification and receptor-ligand binding pathways using motion planning. These contributions reflect a broad integration of machine learning techniques with computational biology and clinical informatics.
Top Research Directions
Research directions most represented by BIBM 2019 papers.
Top Authors
Impactful Papers
Papers from BIBM 2019 that shaped research clusters.
Influential
Boosting Local Causal Discovery in High-Dimensional Expression Data
influential
Inferring Causal Structure from Observat
Papers
« prev Page 3/3