A Saliency-Based Unsupervised Method for Angioectasia Detection in Capsule Endoscopic Images
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch. The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map. In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.
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.
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 | 0.000 | 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) | 0.000 | 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 it