Spatial-frequency 3D fluorescence for surgical guidance: margin thickness quantification
Bibliographic record
Abstract
Accurate assessment of 3D surgical margins remains a challenge after tumor resection. Fluorescence-guided surgery systems show promise to provide precise identification of residual tumor on the surface of resected tissue, but existing 2D fluorescence imaging systems lack the ability to quantify the 3D margin (i.e., thickness of healthy tissue surrounding the resected tumor). In oral cancer, a 5mm pathologic margin has been identified as the prognostic cutoff by several studies, indicating the clinical significance of assessing subsurface information in tissue. To quantify the 3D surgical margins in ex vivo surgical specimens, our group has been developing a deep learning (DL)-enabled 3D fluorescence spatial frequency domain imaging (SFDI) system. Here, we examine the utility of in silico training for margin thickness quantification. A set of 10,000 synthetic tumors were generated using composite spherical harmonics (CSH) and passed into a diffusion theory light propagation model to output fluorescence and reflectance images. Optical property maps were subsequently extracted using a lookup table. The fluorescence images and optical property maps were input into a custom Siamese attention U-net to predict fluorophore concentration and subsurface depth. DL performance was evaluated using in silico testing data of: i) CSH; and ii) patient-derived oral cancer tumor shapes. Analysis included the overall depth and concentration error as well as the classification metrics for determining margin status. Future studies are required to assess DL performance in phantom and animal experiments.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".