<i>In vivo</i> near‐infrared autofluorescence imaging of pigmented skin lesions: methods, technical improvements and preliminary clinical results
Bibliographic record
Abstract
BACKGROUND/PURPOSES: Fluorescence emission from in vivo cutaneous melanin was recently detected under near-infrared (NIR) excitation by our group. We then built a prototype NIR autofluorescence imaging system to observe and characterize the melanin distribution in human skin. In this article, we reported a new setup of NIR fluorescence imaging system and calibration methods to optimize the system for better clinical feasibility and clearer image. METHODS: The imaging system was designed to perform both fluorescence and reflectance imaging with a 785-nm fiber-coupled laser source. The illumination light was purified by a 785-nm bandpass filter for fluorescence excitation; while the spontaneous components were selected by a longpass filter for NIR reflectance imaging. A hand-controlled filter wheel was used to switch these two filters for different imaging modes. A dichroic filter was used to guide the illuminating light onto the skin surface for excitation. Reflectance and fluorescence signals were collected sequentially by a NIR optimized CCD camera. The captured images were calibrated by the reflectance images of a standard reflectance disk for non-uniform illuminations and light collection efficiencies. RESULTS: The clinical results demonstrated that NIR fluorescence intensities and distribution patterns vary among lesion types. It was also confirmed that pigmented skin lesions emitted higher NIR fluorescence than the surrounding normal skin due to the presentation of higher concentrations of cutaneous melanin within the lesions. CONCLUSION: NIR autofluorescence imaging system could be utilized as a powerful tool for visualizing melanin distribution in pigmented skin lesions and as a potential method for aiding melanoma detection.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".