Utilizing Mask R-CNN for Automated Evaluation of Diabetic Foot Ulcer Healing Trajectories: A Novel Approach
Bibliographic record
Abstract
The healing trajectory of diabetic foot ulcers (DFUs) is commonly determined through manual inspection, a method which is often subjective and prone to errors.In an effort to address these limitations, this study explores an artificial intelligence-based, computer-aided assessment technique as an alternative.This approach leverages the power of a Hue, Saturation, and Value (HSV)-based image fusion technique, integrating thermal and visual data to deliver precise wound characterizations.Further, through the deployment of an instance segmentation-based Mask Region-based Convolutional Neural Network (Mask-RCNN), the area of the wound is estimated.This randomized, prospective, single-blind study was conducted over a 12-week period, focusing on neuropathic DFUs (Wagner grade 2) located on the plantar aspect of the foot.Forty-two patients were enrolled, with an average age of 54.28 ±7.45 years and an average ulcer duration of 5.86±2.22years.The healing trajectory of eight patients, observed weekly, was further analyzed.The absolute temperature difference (ATD) between contralateral ulcer regions was found to be 2.63± 1.99℃, with the respective z-score values of ATD providing a significant p-value of 0.000040412 (i.e., p<0.05).The correlation between the ground truth (ulcer area estimation by clinicians using Woundly software) and the proposed method was found to be at an average of 92.50%.The study ultimately concludes that the Mask-RCNN technique, when applied to fused images, can facilitate automated and user-independent assessments of DFUs.This method has the potential to aid in the accurate characterization of healing trajectories, thereby enhancing the overall understanding of wound progression in diabetic patients.
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 | 0.002 | 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".