Automated texture-based segmentation of hair follicles in volumetric optical coherence tomography images of dermatologic burn wounds
Bibliographic record
Abstract
Adnexal structures in skin, such as sweat glands and hair follicles, harbor stem cells that are indispensable for wound healing following acute injuries such as burns of various degrees [1]. Developing a method to identify and visualize these structures in the dermal layer of tissue would greatly supplement imaging studies probing burn injury depth-extent, to assess whether intact adnexal structures will contribute to wound healing and provide invaluable prognostic information in the clinic. Two methods were recently attempted for this purpose in literature but held limitations of resolution and lack of proper filtering [2, 3], thus here we present an automated segmentation algorithm for volumetrically delineating such adnexal structures as hair follicles from surrounding skin tissue by performing texture-based analysis of optical coherence tomography (OCT) images of burn wounds. OCT, a label-free imaging modality, has been previously used for burn wound examination and is ideally suited for dermatological studies demanding high resolution, real-time, and noncontact evaluation to avoid infliction of further injury and patient discomfort [4]. The proposed method is based on Gamma distribution fits of OCT speckle pattern histograms [5], with demonstrated sensitivity of the fitting parameters to follicle locations, the boundary detection of which is confirmed with histology. Our technique demonstrates high accuracy in hair follicle delineation and strong applicability to subsequent studies to assess skin regeneration potential based on follicle location in measured depth-extent of burn injury, enabling future clinical translation not only to burn wounds, but other types of skin injuries.
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 | 0.001 | 0.006 |
| 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".