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

Shahadate Rezvy, Tahmina Zebin, Barbara Braden, Wei Pang, Stephen Taylor, Xiahong Gao

Research output: Contribution to conferencePaperpeer-review

8 Citations (Scopus)
20 Downloads (Pure)


We proposed and implemented a disease detection and semantic segmentation pipeline using a modified mask-RCNN infrastructure model on the EDD2020 dataset. 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
Number of pages5
Publication statusPublished - 2020
Event2020 IEEE 17th International Symposium on Biomedical Imaging: EndoCV2020 workshop - Iowa City, Iowa, United States
Duration: 3 Apr 20207 Apr 2020
Conference number: 17


Conference2020 IEEE 17th International Symposium on Biomedical Imaging
Abbreviated titleIEEE ISBI
Country/TerritoryUnited States
Internet address


  • Deep learning
  • Computer Vision
  • Endoscopy, Gastrointestinal

Cite this