NLM DIR Seminar Schedule
UPCOMING SEMINARS
-
Nov. 16, 2026 Jeremy Miller, PhD
Open access neuroscience data and tools from the Allen Institute and collaborators -
Dec. 8, 2026 Francisco Salvà Serra
TBD -
Dec. 15, 2026 Di Huang
TBD -
Jan. 5, 2027 Vivek Anantharaman
TBD -
Jan. 12, 2027 Oleg Igorevich Obolensky
TBD
RECENT SEMINARS
-
Nov. 3, 2026 Joseph Thole
Using ProteinMPNN to Dissect RfaH CTD Refolding -
Oct. 27, 2026 Bayarbaatar Amgalan
Computational methods to study interactions between tumors and their micro and macro environments -
Oct. 20, 2026 Devlina Chakravarty
Toward Reliable Amyloid Assembly Prediction -
Oct. 13, 2026 Ryan Bell
Satellite Phage Integrated Defensive and Ecotypic Replicons (SPIDERs). -
Oct. 6, 2026 Roman Kogay
Beyond canonical architectures: exploring hidden variation of prokaryotic defense systems
Scheduled Seminars on June 7, 2022
Contact NLMDIRSeminarScheduling@mail.nih.gov with questions about this seminar.
Abstract:
The technique of deep learning, or artificial intelligence (AI) broadly, has been employed in a lot of medical informatics research driven by imaging data. Topics such as classification and object detection have been actively studied in the field. It is well known that deep learning is data hungry technique. However, a higher data quantity doesn’t always guarantee higher performance. Data quality is also important for training of a robust deep learning model. In our studies using medical imaging data, quality factors include image sharpness, resolution, image labeling, specular reflection, data noise, etc. In this talk, several deep learning techniques will be introduced for dataset filtering, data augmentation, data enhancement, etc. These techniques are used to recode our cervical cancer datasets to achieve higher data quality.