Wide-field intraoperative Raman imaging technique to guide cytoreductive surgery for advanced stages of ovarian cancer (Conference Presentation)
Bibliographic record
Abstract
Ovarian cancer is the fifth most deadly cancer among women in North America. Because this type of cancer is often diagnosed late, cytoreductive surgery is often the first therapeutic step. Currently, visual inspection of the surgical cavity is the only technique used to detect residual tumors. Therefore, there is a need for the development of new imaging techniques that can detect cancer tissue with high specificity and sensitivity during cytoreductive procedures. To address this unmet clinical need, we developed an intraoperative wide-field Raman spectroscopy (RS) imaging system to be used alongside tissue classification models trained to recognize cancer tissue using artificial intelligence techniques. The system can sequentially acquire up to 5 Raman bands in imaging mode over a macroscopic tissue area of more than 1-centimeter diameter. Preliminary analyses are presented demonstrating the ability of the system to recover the main Raman tissue bands in synthetic and biologic tissue. Two types of tissues in a biological sample can also be differentiated by the system. Moreover, cancer detection models are produced using a single-point RS probe based on ex vivo human measurements collected from 20 ovarian cancer patients. Using supervised machine learning techniques, it is demonstrated the model can detect tissue containing epithelial cancer cells with an accuracy higher than 90%. Based on this dataset, multivariate statistical analyzes were performed demonstrating the 5 features contributing the most to the classification. These studies pave the way to the development of a new generation wide-field Raman spectroscopy techniques for macroscopic tissue characterization during surgery.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".