Algorithms for Smartphone and Tablet Image Analysis for Healthcare Applications
Bibliographic record
Abstract
Smartphones and tablets are finding their way into healthcare delivery to the extent that mobile health (mHealth) has become an identifiable field within eHealth. In prior work, a mobile app to document chronic wounds and wound care, specifically pressure ulcers (bedsores) was developed for Android smartphones and tablets. One feature of the mobile app allowed users to take images of the wound using the smartphone or tablet's integrated camera. In a user trial with nurses at a personal care home, this feature emerged as a key benefit of the mobile app. This paper developed image analysis algorithms that facilitate noncontact measurements of irregularly shaped images (e.g., wounds), where the image is taken with a sole smartphone or tablet camera. The image analysis relies on the sensors integrated in the smartphone or tablet with no auxiliary or add-on instrumentation on the device. Three approaches to image analysis were developed and evaluated: 1) computing depth using autofocus data; 2) a custom sensor fusion of inertial sensors and feature tracking in a video stream; and 3) a custom pinch/zoom approach. The pinch/zoom approach demonstrated the strongest potential and thus developed into a fully functional prototype complete with a measurement mechanism. While image analysis is a very well developed field, this paper contributes to image analysis applications and implementation in mHealth, specifically for wound care.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.020 | 0.013 |
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".