Monitoring of adherent live cells morphology using the undecimated wavelet transform multivariate image analysis (UWT‐MIA)
Bibliographic record
Abstract
Cell morphology is an important macroscopic indicator of cellular physiology and is increasingly used as a mean of probing culture state in vitro. Phase contrast microscopy (PCM) is a valuable tool for observing live cells morphology over long periods of time with minimal culture artifact. Two general approaches are commonly used to analyze images: individual object segmentation and characterization by pattern recognition. Single-cell segmentation is difficult to achieve in PCM images of adherent cells since their contour is often irregular and blurry, and the cells bundle together when the culture reaches confluence. Alternatively, pattern recognition approaches such as the undecimated wavelet transform multivariate image analysis (UWT-MIA), allow extracting textural features from PCM images that are correlated with cellular morphology. A partial least squares (PLS) regression model built using textural features from a set of 200 ground truth images was shown to predict the distribution of cellular morphological features (major and minor axes length, orientation, and roundness) with good accuracy for most images. The PLS models were then applied on a large dataset of 631,136 images collected from live myoblast cell cultures acquired under different conditions and grown in two different culture media. The method was found sensitive to morphological changes due to cell growth (culture time) and those introduced by the use of different culture media, and was able to distinguish both sources of variations. The proposed approach is promising for application on large datasets of PCM live-cell images to assess cellular morphology and growth kinetics in real-time which could be beneficial for high-throughput screening as well as automated cell culture kinetics assessment and control applications. Biotechnol. Bioeng. 2017;114: 141-153. © 2016 Wiley Periodicals, Inc.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".