Investigation of melanoma tissue with nonlinear multimodal polarimetric microscopy using texture analysis and machine learning
Bibliographic record
Abstract
Development and metastasis of cancer are known to change the structure of extracellular matrix (ECM), which affect the tumor's further growth and spread. A substantial part of ECM is comprised of collagen, which is a noncentrosymmetric structure. As a result, it generates second harmonic signals, dependent on the polarization of incoming light. This property of collagen led to the applications of polarization-resolved second-harmonic generation (P-SHG) microscopy in investigating collagen ultrastructure changes in different cancers. In this work, multiphoton absorption fluorescence (MPF), third-harmonic generation (THG) and polarimetric second-harmonic generation (P-SHG) measurements were performed on various types and staging of human melanoma histological sections. Reduced polarimetry techniques, employing linear and circular polarization states, were used to obtain polarimetric SHG parameters of collagen in both normal and cancerous tissues. These parameters provide important information about the structural properties of collagen. The parameter distributions were analyzed using a grey-level co-occurrence matrix (GLCM), which allows to obtain statistical parameters, such as correlation, contrast, entropy, angular second moment and inverse difference moment. Statistical tests were performed on polarimetric and texture analysis data in order to determine whether parameter distribution differences in normal and cancerous tissues are statistically significant. Furthermore, a machine learning classifier algorithm was trained to distinguish normal tissues from cancerous using aforementioned polarimetric and texture parameters as predictors. Firstly, separate training and testing datasets were formed from each sample and classification was carried out for each of them individually and afterwards, a common training dataset was used for all samples. The results suggest that normal and cancerous skin tissues can be distinguished from each other with the help of multimodal nonlinear polarimetric microscopy. Also, depending on the type and stage of melanoma, the differences in some polarimetric and texture parameters are more pronounced, suggesting its possible application in melanoma diagnostics and differentiation.
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".