EUVIMEDEUVIMED entdecken
Crossref

Unsupervised detection of potentially necrotic intestinal segments using autoencoder residuals and multispectral imaging

Yi Xie, DanFei Huang, JiaXuan Yan, LiBin Zhu, TianCi Weng, Shujat Ali, Zhonghao Xie, Guangzao Huang, XiaoJing Chen

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-08 · 356 · 127751

DOI: 10.1016/j.saa.2026.127751 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-08. Verfasst von Yi Xie und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun 130000, China; Zhongshan Research Institute, Changch…. Hauptthemen laut MEDLINE: Intestine, Small, Image Processing, Computer-Assisted, Intestines, Spectrum Analysis. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: The Education Department of Jilin Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and timely identification of potentially necrotic intestinal segments during surgery is critical for surgical decision-making. However, existing classification methods heavily rely on labeled data or struggle to capture early subtle abnormal features, thereby limiting their accuracy and generalizability in clinical applications. This study aims to achieve sensitive detection of potentially necrotic intestinal segments through an unsupervised one-class classification method based on autoencoder (AE) residuals. The AE was trained using readily available multispectral data from the normal small intestine to construct residuals that amplify abnormal spectral differences. The residual features were used as input for three unsupervised one-class classification algorithms, namely Local Outlier Factor, Isolation Forest and Minimum Covariance Determinant (MCD) for detection. Validation data were collected from rabbit models under different occlusion durations. The construction of residuals significantly improved the performance of all classifiers. In the potentially necrotic phase at 10 min of occlusion, the overall accuracy of the algorithms was steadily improved at about 80%, especially the sensitivity of MCD jumped from 26.5% to 80.7%, ensuring high detection rates from the outset. When the occlusion duration was extended, the sensitivity of all algorithms showed a positive correlation, consistent with the object physiological patterns. Final visualization results confirmed that residual features improved classification performance and preserved spatial continuity. This approach shows promise for early anomaly detection in other medical imaging applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Intestine, SmallImage Processing, Computer-AssistedIntestinesSpectrum AnalysisAnimalsAutoencoderRabbitsNecrosisAlgorithmsClassification Algorithms

Stichwörter der Autor:innen

Autoencoder residualsMultispectral imagingPotentially necrotic intestinal segmentsUnsupervised one-class classification

Autor:innen und Institutionen

  • College of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun 130000, China; Zhongshan Research Institute, Changchun University of Science and Technology, Zhongshan 528400, China.
  • College of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun 130000, China; Zhongshan Research Institute, Changchun University of Science and Technology, Zhongshan 528400, China. Elec…
  • Pediatric General Surgery, The Second Hospital of Wenzhou Medical University, Wenzhou 325000, China.
  • College of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325000, China.
  • College of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun 130000, China; College of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325000, China; Zhejiang Key L…

Förderung

  • The Education Department of Jilin Province
  • National Natural Science Foundation of China

Zitieren

APA

Xie, Y., Huang, D., Yan, J., Zhu, L., Weng, T., Ali, S., Xie, Z., Huang, G., & Chen, X. (2026). Unsupervised detection of potentially necrotic intestinal segments using autoencoder residuals and multispectral imaging. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 356, 127751. https://doi.org/10.1016/j.saa.2026.127751

Vancouver

Xie Y, Huang D, Yan J, Zhu L, Weng T, Ali S, et al. Unsupervised detection of potentially necrotic intestinal segments using autoencoder residuals and multispectral imaging. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;356:127751. doi:10.1016/j.saa.2026.127751

BibTeX
@article{Xie2026,
  author = {Xie, Yi and Huang, DanFei and Yan, JiaXuan and Zhu, LiBin and Weng, TianCi and Ali, Shujat and Xie, Zhonghao and Huang, Guangzao and Chen, XiaoJing},
  title = {Unsupervised detection of potentially necrotic intestinal segments using autoencoder residuals and multispectral imaging},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  volume = {356},
  pages = {127751},
  doi = {10.1016/j.saa.2026.127751}
}
Kostenlos starten →