Automated Detection of Bleeding in Capsule Endoscopy Using On-Chip Multispectral Imaging Sensors
Bibliographic record
Abstract
Gastrointestinal (GI) bleeding is a common problem and may lead to fatal consequences. The detection of bleeding is currently determined through conventional examination of wireless capsule endoscopy (WCE) images. Image-based bleeding detection is performed using only color pixels; therefore, image and color distortion affect the accuracy of RGB-based methods adversely. On the other hand, imaging modalities like multispectral features contain several unique characteristics of the target material, and therefore are less error-prone. In this regard, an on-chip bleeding detection sensor based on blood's optical properties is developed in this article. For creating this sensor, an array of 12 optical sensors, six in visible and six in near-infrared range, is tested with blood samples (BS) in various concentrations and non-blood samples (NBS), such as food pigments and natural foods (digestible and nondigestible). Various feature selection and machine learning approaches have been used to select the optimal bandwidth for the best detection accuracy. A capsule prototype is designed that uses 450 nm, 610 nm, and 810 nm of wavelengths. The prototype is tested in two in vitro experiments using two porcine intestines to validate the proof of concept. The results indicate that the designed system can distinguish occult and acute bleeding from a distance of 1 cm with angles of 45 and 90 degrees. An F1-score of 99% is achieved using the bagged decision tree algorithm. The proposed solution for detecting GI bleeding will eliminate the need to use a camera module and large data transmission, and thereby consumes 1.48 times less power than conventional WCE systems.
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 | 0.000 | 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 | 0.001 |
| 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".