Transfer learning for endoscopy disease detection and segmentation with MASk-RCNN benchmark architecture

Shahadate Rezvy, Tahmina Zebin, Barbara Braden, Wei Pang, Stephen Taylor, Xiaohong W. Gao

Research output: Contribution to journalConference article

5 Downloads (Pure)

Abstract

We proposed and implemented a disease detection and semantic segmentation pipeline using a modified mask-RCNN infrastructure model on the EDD2020 dataset1. On the images provided for the phase-I test dataset, for'BE', we achieved an average precision of 51.14%, for'HGD' and'polyp' it is 50%. However, the detection score for'suspicious' and'cancer' were low. For phase-I, we achieved a dice coefficient of 0.4562 and an F2 score of 0.4508. We noticed the missed and mis-classification was due to the imbalance between classes. Hence, we applied a selective and balanced augmentation stage in our architecture to provide more accurate detection and segmentation. We observed an increase in detection score to 0.29 on phase -II images after balancing the dataset from our phase-I detection score of 0.24. We achieved an improved semantic segmentation score of 0.62 from our phase-I score of 0.52.

Original languageEnglish
Pages (from-to)68-72
Number of pages5
JournalCEUR Workshop Proceedings
Volume2595
Publication statusPublished - 23 Apr 2020
Event2nd International Workshop and Challenge on Computer Vision in Endoscopy 2020 - Iowa City, United States
Duration: 3 Apr 20203 Apr 2020

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Transfer learning for endoscopy disease detection and segmentation with MASk-RCNN benchmark architecture'. Together they form a unique fingerprint.

  • Cite this