Listening Through the Noise: Cauchy-Driven Diffusion Bridges for Robust Gastrointestinal Auscultation and Clinical Benchmarking

Dian Ding, Liren Dong, Yu Lu, Juntao Zhou, Ran Wang, Peng Li, Zhenyi Jia, Guangtao Xue
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:24817-24842, 2026.

Abstract

Gastrointestinal (GI) motility assessment via bowel sounds (BS) offers a non-invasive alternative to resource-intensive clinical standards. However, the diagnostic utility of BS is often compromised by its spectral overlap with non-stationary speech interference. While generative models have advanced signal restoration, traditional Gaussian-based diffusion frameworks struggle with the impulsive, heavy-tailed nature of real-world clinical noise. In this paper, we propose a novel Cauchy-driven Diffusion Bridge framework to isolate high-fidelity bowel sounds from complex interference. Our contributions are three-fold: (1) We introduce ClinBS, a large-scale clinical dataset (over 25 hours) containing rare pathological transients verified by experts; (2) We mathematically formulate a Cauchy bridge driver, deriving closed-form expressions for the score and density to better model heavy-tailed perturbations; and (3) We implement an efficient sampling procedure via Gaussian scale-mixture reparameterization. Extensive experiments show our framework achieves state-of-the-art performance, outperforming baselines by 13.4%–49.8% across core metrics and elevating abnormal BS recognition accuracy to 88.01%. These results demonstrate the system’s potential for robust clinical GI monitoring and diagnosis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-ding26a, title = {Listening Through the Noise: Cauchy-Driven Diffusion Bridges for Robust Gastrointestinal Auscultation and Clinical Benchmarking}, author = {Ding, Dian and Dong, Liren and Lu, Yu and Zhou, Juntao and Wang, Ran and Li, Peng and Jia, Zhenyi and Xue, Guangtao}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {24817--24842}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/ding26a/ding26a.pdf}, url = {https://proceedings.mlr.press/v306/ding26a.html}, abstract = {Gastrointestinal (GI) motility assessment via bowel sounds (BS) offers a non-invasive alternative to resource-intensive clinical standards. However, the diagnostic utility of BS is often compromised by its spectral overlap with non-stationary speech interference. While generative models have advanced signal restoration, traditional Gaussian-based diffusion frameworks struggle with the impulsive, heavy-tailed nature of real-world clinical noise. In this paper, we propose a novel Cauchy-driven Diffusion Bridge framework to isolate high-fidelity bowel sounds from complex interference. Our contributions are three-fold: (1) We introduce ClinBS, a large-scale clinical dataset (over 25 hours) containing rare pathological transients verified by experts; (2) We mathematically formulate a Cauchy bridge driver, deriving closed-form expressions for the score and density to better model heavy-tailed perturbations; and (3) We implement an efficient sampling procedure via Gaussian scale-mixture reparameterization. Extensive experiments show our framework achieves state-of-the-art performance, outperforming baselines by 13.4%–49.8% across core metrics and elevating abnormal BS recognition accuracy to 88.01%. These results demonstrate the system’s potential for robust clinical GI monitoring and diagnosis.} }
Endnote
%0 Conference Paper %T Listening Through the Noise: Cauchy-Driven Diffusion Bridges for Robust Gastrointestinal Auscultation and Clinical Benchmarking %A Dian Ding %A Liren Dong %A Yu Lu %A Juntao Zhou %A Ran Wang %A Peng Li %A Zhenyi Jia %A Guangtao Xue %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-ding26a %I PMLR %P 24817--24842 %U https://proceedings.mlr.press/v306/ding26a.html %V 306 %X Gastrointestinal (GI) motility assessment via bowel sounds (BS) offers a non-invasive alternative to resource-intensive clinical standards. However, the diagnostic utility of BS is often compromised by its spectral overlap with non-stationary speech interference. While generative models have advanced signal restoration, traditional Gaussian-based diffusion frameworks struggle with the impulsive, heavy-tailed nature of real-world clinical noise. In this paper, we propose a novel Cauchy-driven Diffusion Bridge framework to isolate high-fidelity bowel sounds from complex interference. Our contributions are three-fold: (1) We introduce ClinBS, a large-scale clinical dataset (over 25 hours) containing rare pathological transients verified by experts; (2) We mathematically formulate a Cauchy bridge driver, deriving closed-form expressions for the score and density to better model heavy-tailed perturbations; and (3) We implement an efficient sampling procedure via Gaussian scale-mixture reparameterization. Extensive experiments show our framework achieves state-of-the-art performance, outperforming baselines by 13.4%–49.8% across core metrics and elevating abnormal BS recognition accuracy to 88.01%. These results demonstrate the system’s potential for robust clinical GI monitoring and diagnosis.
APA
Ding, D., Dong, L., Lu, Y., Zhou, J., Wang, R., Li, P., Jia, Z. & Xue, G.. (2026). Listening Through the Noise: Cauchy-Driven Diffusion Bridges for Robust Gastrointestinal Auscultation and Clinical Benchmarking. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:24817-24842 Available from https://proceedings.mlr.press/v306/ding26a.html.

Related Material