Tissue-border detection in volumetric laser endomicroscopy using bi-directional gated recurrent neural networks

Computer-aided detection (CAD) approaches have shown promising results for early esophageal cancer detection using Volumetric Laser Endoscopy (VLE) imagery. However, the relatively slow and computationally costly tissue segmentation employed in these approaches hamper their clinical applicability. In this paper, we propose to reframe the 2D tissue segmentation problem into a 1D tissue boundary detection problem. Instead of using an encoder-decoder architecture, we propose to follow the tissue boundary using a Recurrent Neural Network (RNN), exploiting the spatio-temporal relations within VLE frames. We demonstrate a near state-of-the-art performance using 18 times less floating point operations, enabling real-time execution in clinical practice.

[1]  Joost van der Putten,et al.  Tissue segmentation in volumetric laser endomicroscopy data using FusionNet and a domain-specific loss function , 2019, Medical Imaging: Image Processing.

[2]  Jiliu Zhou,et al.  FusionNet: A Parallel Interactive Neural Network for Compressed Sensing MRI Reconstruction , 2019, 1910.10392.

[3]  M. Solaymani-Dodaran,et al.  Risk of oesophageal cancer in Barrett’s oesophagus and gastro-oesophageal reflux , 2004, Gut.

[4]  E. Schoon,et al.  Computer-aided detection of early Barrett's neoplasia using volumetric laser endomicroscopy. , 2017, Gastrointestinal endoscopy.

[5]  Sven Loncaric,et al.  Retinal Vessel Segmentation using Deep Neural Networks , 2015, VISAPP.

[6]  Ma Haiqing,et al.  Incidence and Survival Changes in Patients with Esophageal Adenocarcinoma during 1984–2013 , 2019, BioMed research international.

[7]  L. Miller,et al.  Incremental yield of dysplasia detection in Barrett's esophagus using volumetric laser endomicroscopy with and without laser marking compared with a standardized random biopsy protocol. , 2018, Gastrointestinal endoscopy.

[8]  Anne-Fré Swager,et al.  Identification of volumetric laser endomicroscopy features predictive for early neoplasia in Barrett's esophagus using high-quality histological correlation. , 2017, Gastrointestinal endoscopy.

[9]  David Alonso-Caneiro,et al.  Automatic segmentation of OCT retinal boundaries using recurrent neural networks and graph search. , 2018, Biomedical optics express.

[10]  P. Fockens,et al.  Surveillance history of endoscopically treated patients with early Barrett's neoplasia: nonadherence to the Seattle biopsy protocol leads to sampling error. , 2008, Diseases of the esophagus : official journal of the International Society for Diseases of the Esophagus.

[11]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[12]  Wei Zhao,et al.  Impact of endoscopic surveillance on mortality from Barrett's esophagus-associated esophageal adenocarcinomas. , 2013, Gastroenterology.

[13]  Daniel Rueckert,et al.  Recurrent neural networks for aortic image sequence segmentation with sparse annotations , 2018, MICCAI.

[14]  Fons van der Sommen,et al.  Predictive features for early cancer detection in Barrett's esophagus using Volumetric Laser Endomicroscopy , 2018, Comput. Medical Imaging Graph..

[15]  Won-Ki Jeong,et al.  FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics , 2016, Frontiers in Computer Science.

[16]  Michael B. Wallace,et al.  Volumetric laser endomicroscopy in Barrett's esophagus: interobserver agreement for interpretation of Barrett's esophagus and associated neoplasia among high-frequency users. , 2017, Gastrointestinal endoscopy.

[17]  Shu Liao,et al.  Representation Learning: A Unified Deep Learning Framework for Automatic Prostate MR Segmentation , 2013, MICCAI.

[18]  Nicholas J Shaheen,et al.  ACG Clinical Guideline: Diagnosis and Management of Barrett’s Esophagus , 2016, The American Journal of Gastroenterology.