NLM DIR Seminar Schedule
UPCOMING SEMINARS
-
July 3, 2025 Matthew Diller
Using Ontologies to Make Knowledge Computable -
July 15, 2025 Noam Rotenberg
Cell phenotypes in the biomedical literature: a systematic analysis and the NLM CellLink text mining corpus
RECENT SEMINARS
-
July 3, 2025 Matthew Diller
Using Ontologies to Make Knowledge Computable -
July 1, 2025 Yoshitaka Inoue
Graph-Aware Interpretable Drug Response Prediction and LLM-Driven Multi-Agent Drug-Target Interaction Prediction -
June 10, 2025 Aleksandra Foerster
Interactions at pre-bonding distances and bond formation for open p-shell atoms: a step toward biomolecular interaction modeling using electrostatics -
June 3, 2025 MG Hirsch
Interactions among subclones and immunity controls melanoma progression -
May 29, 2025 Harutyun Sahakyan
In silico evolution of globular protein folds from random sequences
Scheduled Seminars on Oct. 15, 2024
Contact NLMDIRSeminarScheduling@mail.nih.gov with questions about this seminar.
Abstract:
Artificial Intelligence (AI) has emerged as a powerful tool in medical image analysis, offering significant potential for diagnosing health conditions and predicting disease progression. Providing accurate diagnostic and prognostic information from medical images is crucial for clinical decision-making, yet challenges such as the high dimensionality of data and limited data availability can hinder progress. This presentation highlights three key research papers that showcase applications of AI and deep learning (DL) in medical imaging. The first introduces EfficientSwin, a hybrid model that combines the strengths of EfficientNet and Swin Transformer for hematologic (blood) cell classification. It significantly improved the potential identification of hematological disorders, including in contexts where medical imaging data may be limited. Next, will be work on an adaptive discriminator augmentation (ADA) mechanism to enhance StyleSwin, a transformer-based generative model for medical image synthesis, which is particularly useful in data-limited environments. The third part of this talk will explore the influence of facial expressions on DL-based diagnostic accuracy for genetic conditions such as Williams and Angelman syndromes (selected due to association with certain facial expressions. Leveraging GAN-based techniques to modify facial expressions, we examined how human experts’ diagnostic performance is impacted, underscoring the need to mitigate confounding factors such as facial expression in clinical AI applications.