Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.15062 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918501789204480 |
|---|---|
| author | Yang, Chengshuai Xing, Lei Entin, Gregory Vemulapalli, Roopa Casey, Lisa Zaman, Raiyan Tripti |
| author_facet | Yang, Chengshuai Xing, Lei Entin, Gregory Vemulapalli, Roopa Casey, Lisa Zaman, Raiyan Tripti |
| contents | Background. RGB-trained capsule-endoscopy classifiers underperform on small-vessel vascular findings by
conflating hemoglobin contrast with bile and illumination falloff. Thus, here we test whether a Monte
Carlo-inspired analytic model can compute hemoglobin from RGB signal built upon extracted classifier.
Methods. On Kvasir-Capsule (47,238 frames, video-level 70/15/15 split, 11 evaluable classes) we evaluate two
software-only configurations against RGB-only EfficientNet-B0 across 6 seeds: (i) a prior P_blood =
sigma(alpha * (H_norm - 0.5)) * Phi(r) fused as 2 zero-init auxiliary channels; (ii) a distillation head
training a 3-channel RGB backbone to predict P_blood. Significance: paired DeLong, McNemar, bootstrap CIs
with Bonferroni correction.
Results. Across 6 seeds (n=6,423), the analytic prior provides a small but direction-consistent macro-AUC
improvement: RGB-only 0.760 +/- 0.027, input-fusion 0.783 +/- 0.024 (paired Delta = +0.023, sign-positive on
5/6 seeds), distillation 0.773 +/- 0.028. The largest robust per-class lift is on Lymphangiectasia, where AUC
rises from RGB 0.238 +/- 0.057 to input-fusion 0.337 +/- 0.019, sign-consistent across all 6 seeds. On rare
focal-vascular classes (Angiectasia, Blood - fresh) the prior's per-seed effects are bimodal: seed=42 reaches
Angiectasia AUC 0.528 -> 0.916, but the cross-seed mean is 0.646 -> 0.608 with sigma_PI = 0.23 - reported as
a high-variance per-seed exemplar.
Conclusion. A Monte Carlo-inspired analytic prior provides a small, direction-consistent macro-AUC
improvement on Kvasir-Capsule across 6 seeds with the largest robust per-class lift on Lymphangiectasia; the
distillation variant runs on plain 3-channel RGB and yields a free interpretability heatmap. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15062 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Computational Imaging Priors for Wireless Capsule Endoscopy: Monte Carlo-Guided Hemoglobin Mapping for Rare-Anomaly Detection Yang, Chengshuai Xing, Lei Entin, Gregory Vemulapalli, Roopa Casey, Lisa Zaman, Raiyan Tripti Computer Vision and Pattern Recognition 68T07, 68T45, 92C55 Background. RGB-trained capsule-endoscopy classifiers underperform on small-vessel vascular findings by conflating hemoglobin contrast with bile and illumination falloff. Thus, here we test whether a Monte Carlo-inspired analytic model can compute hemoglobin from RGB signal built upon extracted classifier. Methods. On Kvasir-Capsule (47,238 frames, video-level 70/15/15 split, 11 evaluable classes) we evaluate two software-only configurations against RGB-only EfficientNet-B0 across 6 seeds: (i) a prior P_blood = sigma(alpha * (H_norm - 0.5)) * Phi(r) fused as 2 zero-init auxiliary channels; (ii) a distillation head training a 3-channel RGB backbone to predict P_blood. Significance: paired DeLong, McNemar, bootstrap CIs with Bonferroni correction. Results. Across 6 seeds (n=6,423), the analytic prior provides a small but direction-consistent macro-AUC improvement: RGB-only 0.760 +/- 0.027, input-fusion 0.783 +/- 0.024 (paired Delta = +0.023, sign-positive on 5/6 seeds), distillation 0.773 +/- 0.028. The largest robust per-class lift is on Lymphangiectasia, where AUC rises from RGB 0.238 +/- 0.057 to input-fusion 0.337 +/- 0.019, sign-consistent across all 6 seeds. On rare focal-vascular classes (Angiectasia, Blood - fresh) the prior's per-seed effects are bimodal: seed=42 reaches Angiectasia AUC 0.528 -> 0.916, but the cross-seed mean is 0.646 -> 0.608 with sigma_PI = 0.23 - reported as a high-variance per-seed exemplar. Conclusion. A Monte Carlo-inspired analytic prior provides a small, direction-consistent macro-AUC improvement on Kvasir-Capsule across 6 seeds with the largest robust per-class lift on Lymphangiectasia; the distillation variant runs on plain 3-channel RGB and yields a free interpretability heatmap. |
| title | Computational Imaging Priors for Wireless Capsule Endoscopy: Monte Carlo-Guided Hemoglobin Mapping for Rare-Anomaly Detection |
| topic | Computer Vision and Pattern Recognition 68T07, 68T45, 92C55 |
| url | https://arxiv.org/abs/2605.15062 |