Archive (2016–2006)

Investigating Recurrent Neural Networks for OCT A-scan Based Tissue Analysis

Journal: Methods of Information in Medicine
Subtitle: A journal stressing, for more than 50 years, the methodology and scientific fundamentals of organizing, representing and analyzing data, information and knowledge in biomedicine and health care
ISSN: 0026-1270

Focus Theme
Biosignal Interpretation I – Advanced Methods for Studying Cardiovascular and Respiratory Systems
Guest Editors: K. Yana, S. Cerutti, L. Mainardi, Y. Yamamoto

Issue: 2014 (Vol. 53): Issue 4 2014
Pages: 245-249

Investigating Recurrent Neural Networks for OCT A-scan Based Tissue Analysis

Original Article

C. Otte (1), S. Otte (2), L. Wittig (3), G. Hüttmann (4), C. Kugler (5), D. Drömann (3), A. Zell (2), A. Schlaefer (1)

(1) Institute of Medical Technology, Hamburg University of Technology, Hamburg, Germany; (2) Cognitive Systems Group, Computer Science Department, University of Tuebingen, Tuebingen, Germany; (3) Medical Clinic III, University Hospital Schleswig Holstein, Luebeck, Germany; (4) Institute of Biomedical Optics, University of Luebeck, Luebeck, Germany; (5) Medical Clinic III, Department of Thoracic Surgery, LungenClinic Grosshansdorf, Grosshansdorf, Germany


optical coherence tomography, biopsy guidance, optical soft tissue classification, identification of pulmonary nodules, Long Short Term Memory, recurrent eural nets


Objectives: Optical Coherence Tomography (OCT) has been proposed as a high resolution image modality to guide transbronchial biopsies. In this study we address the question, whether individual A-scans obtained in needle direction can contribute to the identification of pulmonary nodules.

Methods: OCT A-scans from freshly resected human lung tissue specimen were recorded through a customized needle with an embedded optical fiber. Bidirectional Long Short Term Memory networks (BLSTMs) were trained on randomly distributed training and test sets of the acquired A-scans. Patient specific training and different pre-processing steps were evaluated.

Results: Classification rates from 67.5% up to 76% were archived for different training scenarios. Sensitivity and specificity were highest for a patient specific training with 0.87 and 0.85. Low pass filtering decreased the accuracy from 73.2% on a reference distribution to 62.2% for higher cutoff frequencies and to 56% for lower cutoff frequencies.

Conclusion: The results indicate that a grey value based classification is feasible and may provide additional information for diagnosis and navigation. Furthermore, the experiments show patient specific signal properties and indicate that the lower and upper parts of the frequency spectrum contribute to the classification.

You may also be interested in...


M. Wölbert (1), A. U. Brandt (2), F. Paul (2), S. Schippling (1)

Nervenheilkunde 2011 30 7: 493-497