Directed Fine Tuning Using Feature Clustering for Instance Segmentation of Toxoplasmosis Fundus Images

Dilanga Abeyrathna, Mahadevan Subramaniam, Parvathi Chundi, Murat Hasanreisoglu, Muhammad Sohail Halim, Pinar Cakar Ozdal, Quan Dong Nguyen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Medical image segmentation is a challenging problem for computer vision approaches where deep learning networks have achieved impressive successes in recent years. In this paper, we propose a directed, fine tuning approach for instance segmentation networks by using feature clustering of predictions along with labeled training instances to improve network performance. The approach directs and limits analyses of predicted instances by experts to similar training instances only and reduces manual overheads by managing the number of instances that need to be examined. Sub-optimal network predictions are handled either by retraining the networks on data augmented with the relevant training instances, correcting training labels, and/or by readjusting network inference parameters. We first develop a state-of-the-art Mask R-CNN based network for instance segmentation of fundus images with retinal lesions and scars caused by Ocular Toxoplasmosis. Then, we show how the proposed approach can be applied to fine tune this network in a directed manner using feature clustering using a pre-trained CNN network. We demonstrate the robustness of our proposed approach with the evaluation results - mask average IoU increased by 7% and mAP under 0.5 IoU threshold increased by 20%. Our experiments also show that fine tuning by analyzing 66% of the predicted instances achieves the same improvement as that obtained by all of the predicted instances, a significant reduction of the manual overheads for fine tuning.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE 20th International Conference on Bioinformatics and Bioengineering, BIBE 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages767-772
Number of pages6
ISBN (Electronic)9781728195742
DOIs
StatePublished - Oct 2020
Event20th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2020 - Virtual, Cincinnati, United States
Duration: Oct 26 2020Oct 28 2020

Publication series

NameProceedings - IEEE 20th International Conference on Bioinformatics and Bioengineering, BIBE 2020

Conference

Conference20th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2020
Country/TerritoryUnited States
CityVirtual, Cincinnati
Period10/26/2010/28/20

Keywords

  • Instance segmentation
  • Mask R-CNN
  • Medical Imaging
  • Ocular Toxoplasmosis

ASJC Scopus subject areas

  • Biotechnology
  • Genetics
  • Molecular Biology
  • Artificial Intelligence
  • Computer Science Applications
  • Biomedical Engineering
  • Modeling and Simulation
  • Health Informatics

Fingerprint

Dive into the research topics of 'Directed Fine Tuning Using Feature Clustering for Instance Segmentation of Toxoplasmosis Fundus Images'. Together they form a unique fingerprint.

Cite this