Fast tissue detection in volumetric laser endomicroscopy using convolutional neural networks: an object-detection approach

Endi Selmanaj; Fons van der Sommen; Sanne E. Okel; Joost van der Putten; Maarten R. Struyvenberg; Jacques J. G. H. M. Bergman; Peter H. N. de With

doi:10.1117/12.2579573

15 February 2021 Fast tissue detection in volumetric laser endomicroscopy using convolutional neural networks: an object-detection approach

Endi Selmanaj, Fons van der Sommen, Sanne E. Okel, Joost van der Putten, Maarten R. Struyvenberg, Jacques J. G. H. M. Bergman, Peter H. N. de With

Author Affiliations +

Proceedings Volume 11596, Medical Imaging 2021: Image Processing; 1159635 (2021) https://doi.org/10.1117/12.2579573
Event: SPIE Medical Imaging, 2021, Online Only

Conference Poster

Abstract

Barrett's Esophagus is a precursor of esophageal adenocarcinoma, one of the most lethal forms of cancer. Volumetric laser endomicroscopy (VLE) is a relatively new technology used for early detection of abnormal cells in BE by imaging the inner tissue layers of the esophagus. Computer-Aided Detection (CAD) shows great promise in analyzing the VLE frames due to the advances in deep learning. However, a full VLE scan produces 1,200 scans of 4,096 x 2,048 pixels, making automated pre-processing for the tissue of interest extraction necessary. This paper explores an object detection for tissue detection in VLE scans. We show that this can be achieved in real time with very low inference time, using single-stage object detection like YOLO. Our best performing model achieves a value of 98.23% for the mean average precision of bounding boxes correctly predicting the tissue of interest. Additionally, we have found that the tiny YOLO with Partial Residual Networks architecture further reduces the inference speed with a factor of 10, while only sacrificing less than 1% of accuracy. This proposed method does not only segment the tissue of interest in real time without any latency, but it can also achieve this efficiently using limited GPU resources, rendering it attractive for embedded applications. Our paper is the first to introduce object detection as a new approach for VLE-data tissue segmentation and paves the way for real-time VLE-based detection of early cancer in BE.

Conference Presentation

Citation Download Citation

Endi Selmanaj, Fons van der Sommen, Sanne E. Okel, Joost van der Putten, Maarten R. Struyvenberg, Jacques J. G. H. M. Bergman, and Peter H. N. de With "Fast tissue detection in volumetric laser endomicroscopy using convolutional neural networks: an object-detection approach", Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 1159635 (15 February 2021); https://doi.org/10.1117/12.2579573

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available