Skip to main content
main-content

25.05.2019 | Original Article | Ausgabe 11/2019

International Journal of Computer Assisted Radiology and Surgery 11/2019

Deep transfer learning methods for colon cancer classification in confocal laser microscopy images

Zeitschrift:
International Journal of Computer Assisted Radiology and Surgery > Ausgabe 11/2019
Autoren:
Nils Gessert, Marcel Bengs, Lukas Wittig, Daniel Drömann, Tobias Keck, Alexander Schlaefer, David B. Ellebrecht
Wichtige Hinweise
N. Gessert and M. Bengs have contributed equally to this work.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Abstract

Purpose

The gold standard for colorectal cancer metastases detection in the peritoneum is histological evaluation of a removed tissue sample. For feedback during interventions, real-time in vivo imaging with confocal laser microscopy has been proposed for differentiation of benign and malignant tissue by manual expert evaluation. Automatic image classification could improve the surgical workflow further by providing immediate feedback.

Methods

We analyze the feasibility of classifying tissue from confocal laser microscopy in the colon and peritoneum. For this purpose, we adopt both classical and state-of-the-art convolutional neural networks to directly learn from the images. As the available dataset is small, we investigate several transfer learning strategies including partial freezing variants and full fine-tuning. We address the distinction of different tissue types, as well as benign and malignant tissue.

Results

We present a thorough analysis of transfer learning strategies for colorectal cancer with confocal laser microscopy. In the peritoneum, metastases are classified with an AUC of 97.1, and in the colon the primarius is classified with an AUC of 73.1. In general, transfer learning substantially improves performance over training from scratch. We find that the optimal transfer learning strategy differs for models and classification tasks.

Conclusions

We demonstrate that convolutional neural networks and transfer learning can be used to identify cancer tissue with confocal laser microscopy. We show that there is no generally optimal transfer learning strategy and model as well as task-specific engineering is required. Given the high performance for the peritoneum, even with a small dataset, application for intraoperative decision support could be feasible.

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

★ PREMIUM-INHALT
e.Med Interdisziplinär

Mit e.Med Interdisziplinär erhalten Sie Zugang zu allen CME-Fortbildungen und Fachzeitschriften auf SpringerMedizin.de.

Jetzt e.Med zum Sonderpreis bestellen!

Sichern Sie sich jetzt Ihr e.Med-Abo und sparen Sie 50 %!

Weitere Produktempfehlungen anzeigen
Literatur
Über diesen Artikel

Weitere Artikel der Ausgabe 11/2019

International Journal of Computer Assisted Radiology and Surgery 11/2019 Zur Ausgabe
  1. Sie können e.Med Chirurgie 14 Tage kostenlos testen (keine Print-Zeitschrift enthalten). Der Test läuft automatisch und formlos aus. Es kann nur einmal getestet werden.

  2. Sie können e.Med Radiologie 14 Tage kostenlos testen (keine Print-Zeitschrift enthalten). Der Test läuft automatisch und formlos aus. Es kann nur einmal getestet werden.