Detecting small polyps using a Dynamic SSD-GAN

Endoscopic examinations are used to inspect the throat, stomach and bowel for polyps which could develop into cancer. Machine learning systems can be trained to process colonoscopy images and detect polyps. However, these systems tend to perform poorly on objects which appear visually small in the images. It is shown here that combining the single-shot detector as a region proposal network with an adversarially-trained generator to upsample small region proposals can significantly improve the detection of visually-small polyps. The Dynamic SSD-GAN pipeline introduced in this paper achieved a 12% increase in sensitivity on visually-small polyps compared to a conventional FCN baseline.

[1]  Ilangko Balasingham,et al.  Improving Automatic Polyp Detection Using CNN by Exploiting Temporal Dependency in Colonoscopy Video , 2020, IEEE Journal of Biomedical and Health Informatics.

[2]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[3]  Muhammad F Dawwas,et al.  Adenoma detection rate and risk of colorectal cancer and death. , 2014, The New England journal of medicine.

[4]  Faisal Mahmood,et al.  Deep learning and conditional random fields‐based depth estimation and topographical reconstruction from conventional endoscopy , 2017, Medical Image Anal..

[5]  Sun Young Park,et al.  Colonoscopic polyp detection using convolutional neural networks , 2016, SPIE Medical Imaging.

[6]  Paolo Dario,et al.  Fully convolutional neural networks for polyp segmentation in colonoscopy , 2017, Medical Imaging.

[7]  P. Siersema,et al.  Multicenter, randomized, tandem evaluation of EndoRings colonoscopy – results of the CLEVER study , 2015, Endoscopy.

[8]  Bernard Ghanem,et al.  Finding Tiny Faces in the Wild with Generative Adversarial Network , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[10]  Duy-Dinh Le,et al.  Evaluation of Deep Models for Real-Time Small Object Detection , 2017, ICONIP.

[11]  R. Kiesslich,et al.  G-EYE colonoscopy is superior to standard colonoscopy for increasing adenoma detection rate: an international randomized controlled trial (with videos). , 2019, Gastrointestinal endoscopy.

[12]  Nima Tajbakhsh,et al.  A Comprehensive Computer-Aided Polyp Detection System for Colonoscopy Videos , 2015, IPMI.

[13]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[14]  P. Hewett,et al.  Endocuff Vision‐assisted colonoscopy: a randomized controlled trial , 2019, ANZ journal of surgery.

[15]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Subhas Banerjee,et al.  Adenoma miss rates associated with a 3-minute versus 6-minute colonoscopy withdrawal time: a prospective, randomized trial. , 2017, Gastrointestinal endoscopy.

[17]  Nima Tajbakhsh,et al.  Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[18]  Michael Riegler,et al.  KVASIR: A Multi-Class Image Dataset for Computer Aided Gastrointestinal Disease Detection , 2017, MMSys.