Image Analysis for In-line Measurement of Multidimensional Size, Shape, and Polymorphic Transformation of <scp>l</scp>-Glutamic Acid Using Deep Learning-Based Image Segmentation and Classification
Bibliographic record
Abstract
In situ tracking of the crystallization process through image segmentation has been developed and has encountered many challenges including improvement of in situ image quality, optimization of algorithms, and increased computation efficiency. In this study, a new method based on computer vision was proposed using the state-of-the-art deep learning technology to track crystal individuals. For the model compound l -glutamic acid, two polymorphic forms with different morphologies were segmented and classified during a seeded polymorphic transformation process. Information such as counts, size, surface area, crystal size distribution, and morphology of α- and β-form crystals was extracted for the individual crystals during the process. A comparative analysis was conducted with traditional process analytical technologies such as in situ Raman and focus beam reflection measurement. Results show a high accuracy of segmentation and classification technique and a reliable tracking of crystals evolution. The image processing speed of up to 10 frames per second makes the proposed approach suitable for in situ tracking and control of crystallization and particulate processes. Our work in this study attempts to bridge the gap between the advanced imaging analysis technology that is available today and the specific needs of solution crystallization, to track, count, and measure the individual crystals.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".