Hyperspectral microscopy-based label-free semi-automatic segmentation of eye tissues
Bibliographic record
Abstract
Fluorescence microscopic imaging of tissues is widely used for pathological diagnosis of diseases and biomedical research purposes. In addition to the exogenous fluorescent signal that is targeted for analysis, some molecules within biological tissues exhibit intrinsic fluorescence referred to as autofluorescence. This tissue optical property interferes with the detection and quantification of the fluorescent signal used to detect and assess biological tissues. To overcome this, hyperspectral imagers with increased spectral and spatial resolution have the capacity to provide greater structural and molecular information. Algorithm-based analysis platforms capable of analyzing large biomedical hyperspectral datasets are unmet needs and can extract useful spectral-spatial information from complex tissues. We present an open-source data analysis approach to exploit the potential of hyperspectral autofluorescence imaging and to extract unbiased and useful spectral-spatial information from the eye. Using an Image Mapping Spectrometer (from 528 nm to 836 nm); mounted on a fluorescence microscope, a non-destructive and label-free approach to evaluate the retina, choroid, and scleral tissues in eye sections is presented. The segmentation of the tissues is based on their respective autofluorescence spectral profiles and are compared using Analysis of Variance (ANOVA) and functional ANOVA. We demonstrate distinctly different autofluorescence spectra for individual eye tissue types. Furthermore, the systematic segmentation method is used to classify tissue types based on their divergent autofluorescence spectra. This study provides the metrics for further construction of spectral profile signatures in eye conditions and diseases. Furthermore, this hyperspectral-based semi-automatic segmentation approach can be expanded for application to other tissues in health and disease.
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 | 0.001 |
| 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 | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".