Infrared spectral histopathology for cancer diagnosis: a novel approach for automated pattern recognition of colon adenocarcinoma
Bibliographic record
Abstract
Histopathology remains the gold standard method for colon cancer diagnosis. Novel complementary approaches for molecular level diagnosis of the disease are need of the hour. Infrared (IR) imaging could be a promising candidate method as it probes the intrinsic chemical bonds present in a tissue, and provides a "spectral fingerprint" of the biochemical composition. To this end, IR spectral histopathology, which combines IR imaging and data processing techniques, was employed on seventy seven paraffinized colon tissue samples (48 tumoral and 29 non-tumoral) in the form of tissue arrays. To avoid chemical deparaffinization, a digital neutralization of the spectral interference of paraffin was implemented. Clustering analysis was used to partition the spectra and construct pseudo-colored images, for assigning spectral clusters to various tissue structures (normal epithelium, malignant epithelium, connective tissue etc.). Based on the clustering results, linear discriminant analysis was then used to construct a stringent prediction model which was applied on samples without a priori histopathological information. The predicted spectral images not only revealed common features representative of the colonic tissue biochemical make-up, but also highlighted additional features like tumor budding and tumor-stroma association in a label-free manner. This novel approach of IR spectral imaging on paraffinized tissues showed 100% sensitivity and allowed detection and differentiation of normal and malignant colonic features based purely on their intrinsic biochemical features. This non-destructive methodology combined with multivariate statistical image analysis appears as a promising tool for colon cancer diagnosis and opens up the way to the concept of numerical spectral histopathology.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".