Abstract
Recent innovations have made it possible to produce millions of distinct nanoparticles on a chip. These vast volumes of data are impossible to analyze manually, necessitating the development of automated tools. In previous work, we created a binary classification machine learning model to select quality nanoparticle images for downstream analysis. In this work, we show that adding a custom image preprocessing step before model training can produce significantly higher-performing models in a fraction of the time and make the model more robust to different image noise levels and microscope acquisition settings. The proposed image processing pipeline effectively cleans raw nanoparticle images, enhances key features, and allows us to use much lower resolution images and simpler neural network model architectures, resulting in higher performance and significant cost savings. Experiments demonstrate superior performance relative to our baseline, including a 15% improvement in recall and more than a 10% increase in accuracy. Given the high cost of downstream analysis, it is critical to minimize false positives in our application, and our best-performing model obtains a precision of 97.3% and weighted F-score of 95.9% on an unseen test set. Additionally, model training time is reduced from 15.5 hours to 32 seconds. We expect that adopting this pipeline for AI-driven automated nanoparticle characterization will offer a considerable speedup in the laboratory, allowing researchers to rapidly and accurately analyze much greater volumes of data and accelerate materials discovery.
Original language | English (US) |
---|---|
Title of host publication | CIKM 2024 - Proceedings of the 33rd ACM International Conference on Information and Knowledge Management |
Publisher | Association for Computing Machinery |
Pages | 4462-4469 |
Number of pages | 8 |
ISBN (Electronic) | 9798400704369 |
DOIs | |
State | Published - Oct 21 2024 |
Event | 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024 - Boise, United States Duration: Oct 21 2024 → Oct 25 2024 |
Publication series
Name | International Conference on Information and Knowledge Management, Proceedings |
---|---|
ISSN (Print) | 2155-0751 |
Conference
Conference | 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024 |
---|---|
Country/Territory | United States |
City | Boise |
Period | 10/21/24 → 10/25/24 |
Funding
This work is supported in part by the following: the Northwestern University Center for Nanocombinatorics and the International Institute for Nanotechnology; the National Science Foundation (NSF) Graduate Research Fellowship Program under grant DGE- 2234667; NSF awards OAC-2331329, CMMI-2053929, DMR-2308691 and ECCS-2025633; the National Institute of Standards and Technology award 70NANB19H005; U.S. Department of Energy award DE-SC0021399; the United States Department of Defense Army Research Office (ARO) under grant W911NF-23-1-0141; and the Sherman Fairchild Foundation and the Toyota Research Institute. This work made use of the EPIC facility of Northwestern University's NUANCE Center, which has received support from the Soft and Hybrid Nanotechnology Experimental (SHyNE) Resource (NSF ECCS-2025633); the MRSEC program (NSF DMR-2308691) at the Materials Research Center; the International Institute of Nanotechnology (IIN), the Keck Foundation; and the State of Illinois, through the IIN. We would also like to thank the following members of the Mirkin Group at Northwestern for their support: Dr. Chad A. Mirkin, Dr. Sarah H. Petrosko, Dr. Jenny K. Orbeck, Dr. Noel J. Leon, Corey Drennon and Pamela Watson.
Keywords
- computer vision
- machine learning
- materials characterization
ASJC Scopus subject areas
- General Business, Management and Accounting
- General Decision Sciences