Accelerating Domain-Aware Electron Microscopy Analysis Using Deep Learning Models with Synthetic Data and Image-Wide Confidence Scoring
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911135177900032 |
|---|---|
| author | Lynch, Matthew J. Jacobs, Ryan Bruno, Gabriella Patki, Priyam Morgan, Dane Field, Kevin G. |
| author_facet | Lynch, Matthew J. Jacobs, Ryan Bruno, Gabriella Patki, Priyam Morgan, Dane Field, Kevin G. |
| contents | The integration of machine learning (ML) models enhances the efficiency, affordability, and reliability of feature detection in microscopy, yet their development and applicability are hindered by the dependency on scarce and often flawed manually labeled datasets and a lack of domain awareness. We addressed these challenges by creating a physics-based synthetic image and data generator, resulting in a machine learning model that achieves comparable precision (0.86), recall (0.63), F1 scores (0.71), and engineering property predictions (R2=0.82) to a model trained on human-labeled data. We enhanced both models by using feature prediction confidence scores to derive an image-wide confidence metric, enabling simple thresholding to eliminate ambiguous and out-of-domain images resulting in performance boosts of 5-30% with a filtering-out rate of 25%. Our study demonstrates that synthetic data can eliminate human reliance in ML and provides a means for domain awareness in cases where many feature detections per image are needed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01558 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Accelerating Domain-Aware Electron Microscopy Analysis Using Deep Learning Models with Synthetic Data and Image-Wide Confidence Scoring Lynch, Matthew J. Jacobs, Ryan Bruno, Gabriella Patki, Priyam Morgan, Dane Field, Kevin G. Computer Vision and Pattern Recognition Materials Science The integration of machine learning (ML) models enhances the efficiency, affordability, and reliability of feature detection in microscopy, yet their development and applicability are hindered by the dependency on scarce and often flawed manually labeled datasets and a lack of domain awareness. We addressed these challenges by creating a physics-based synthetic image and data generator, resulting in a machine learning model that achieves comparable precision (0.86), recall (0.63), F1 scores (0.71), and engineering property predictions (R2=0.82) to a model trained on human-labeled data. We enhanced both models by using feature prediction confidence scores to derive an image-wide confidence metric, enabling simple thresholding to eliminate ambiguous and out-of-domain images resulting in performance boosts of 5-30% with a filtering-out rate of 25%. Our study demonstrates that synthetic data can eliminate human reliance in ML and provides a means for domain awareness in cases where many feature detections per image are needed. |
| title | Accelerating Domain-Aware Electron Microscopy Analysis Using Deep Learning Models with Synthetic Data and Image-Wide Confidence Scoring |
| topic | Computer Vision and Pattern Recognition Materials Science |
| url | https://arxiv.org/abs/2408.01558 |