EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial neural networks as a prognostic tool using hyperspectral imaging on pretherapeutic histopathological specimens of esophageal adenocarcinoma

Christel Teresa Trifone, Marianne Maktabi, Philipp Bischoff, Katrin Schierle, Stefan Niebisch, Yusef Moulla, Patrick Sven Plum, Boris Jansen-Winkeln, Ines Gockel, René Thieme

Journal of Cancer Research and Clinical Oncology · 2025

DOI: 10.1007/s00432-025-06340-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cancer Research and Clinical Oncology, 2025. Verfasst von Christel Teresa Trifone und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department for General and Abdominal Surgery, Hospital Chemnitz gGmbH, Chemnitz, Germany. Hauptthemen laut MEDLINE: Esophageal Neoplasms, Neural Networks, Computer, Adenocarcinoma, Hyperspectral Imaging. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universitätsklinikum Leipzig.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

The integration of artificial intelligence (AI) with hyperspectral imaging (HSI) offers a promising avenue for improving pre-therapeutic prognosis, a key factor in optimizing cancer treatment strategies. This study explores the potential of artificial neural networks (ANNs) to predict the effectiveness of preoperative chemo- or radiochemotherapy in esophageal adenocarcinoma (EAC), using HSI data derived from histopathological tissue samples.

Methods

HSI data were obtained from pre-therapeutic histopathological samples of 21 patients with EAC. Following annotation and spectral extraction, the data underwent pre-processing steps including normalization, shuffling, and batch organization. Three artificial neural network (ANN) models—2D convolutional neural networks (2D-CNNs), 3D convolutional neural networks (3D-CNNs), and Hybrid-Spectral Networks (Hybrid-SN)—were trained to predict treatment response. Model performance was assessed using sensitivity, specificity, accuracy, and F1-score, offering insights into their clinical utility Results The 3D-CNN model achieved the highest accuracy (0.68 ± 0.09) and F1-score (0.66 ± 0.08), highlighting its strength in capturing both spatial and spectral information. The Hybrid-SN model demonstrated the highest sensitivity (0.79 ± 0.19), indicating strong performance in identifying responders to neoadjuvant therapy. In contrast, the 2D-CNN model achieved the highest specificity (0.73 ± 0.15), reflecting its effectiveness in correctly identifying non-responders.

Conclusion

This study demonstrates the potential of combining HSI with ANNs to predict treatment response in EAC. Among the models evaluated, the 3D-CNN showed the most balanced performance, effectively leveraging spatial and spectral features, while the Hybrid-SN and 2D-CNN models excelled in sensitivity and specificity, respectively. These findings underline the feasibility of using AI-driven analysis of histopathological HSI data to support personalized treatment planning in EAC, paving the way for more accurate and tailored therapeutic strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Esophageal NeoplasmsNeural Networks, ComputerAdenocarcinomaHyperspectral ImagingHumansPrognosisFemaleMaleMiddle AgedAged

Stichwörter der Autor:innen

Digital pathologyEsophageal adenocarcinomaHyperspectral imaging (HSI)Personalized treatmentTherapy prediction

Autor:innen und Institutionen

  • Department for General and Abdominal Surgery, Hospital Chemnitz gGmbH, Chemnitz, Germany.
  • Department of Visceral, Transplant, Thorax and Vascular Surgery, University Hospital of Leipzig, Leipzig, Germany.
  • Innovation Center Computer Assisted Surgery (ICCAS), University of Leipzig, LeipzigLeipzig, Germany.
  • Department of Electrical, Mechanical and Industrial Engineering Köthen, University of Applied Science Anhalt, Bernburg, Germany.
  • Institute of Pathology, SLK-Kliniken Heilbronn, Heilbronn, Germany.
  • Department of General, Visceral, Thoracic and Vascular Surgery, St. George's Hospital Leipzig, Leipzig, Germany.

Förderung

  • Universitätsklinikum Leipzig

Zitieren

APA

Trifone, C. T., Maktabi, M., Bischoff, P., Schierle, K., Niebisch, S., Moulla, Y., Plum, P. S., Jansen-Winkeln, B., Gockel, I., & Thieme, R. (2025). Artificial neural networks as a prognostic tool using hyperspectral imaging on pretherapeutic histopathological specimens of esophageal adenocarcinoma. Journal of Cancer Research and Clinical Oncology. https://doi.org/10.1007/s00432-025-06340-5

Vancouver

Trifone CT, Maktabi M, Bischoff P, Schierle K, Niebisch S, Moulla Y, et al. Artificial neural networks as a prognostic tool using hyperspectral imaging on pretherapeutic histopathological specimens of esophageal adenocarcinoma. Journal of Cancer Research and Clinical Oncology. 2025. doi:10.1007/s00432-025-06340-5

BibTeX
@article{Trifone2025,
  author = {Trifone, Christel Teresa and Maktabi, Marianne and Bischoff, Philipp and Schierle, Katrin and Niebisch, Stefan and Moulla, Yusef and Plum, Patrick Sven and Jansen-Winkeln, Boris and Gockel, Ines and Thieme, René},
  title = {Artificial neural networks as a prognostic tool using hyperspectral imaging on pretherapeutic histopathological specimens of esophageal adenocarcinoma},
  journal = {Journal of Cancer Research and Clinical Oncology},
  year = {2025},
  doi = {10.1007/s00432-025-06340-5}
}
Kostenlos starten →