Tuberculosis bacteria detection and counting in fluorescence microscopy images using a multi-stage deep learning pipeline

Marios Zachariou*, Ognjen Arandjelović*, Wilber Sabiiti, Bariki Mtafya, Derek Sloan*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Downloads (Pure)

Abstract

The manual observation of sputum smears by fluorescence microscopy for the diagnosis and treatment monitoring of patients with tuberculosis (TB) is a laborious and subjective task. In this work, we introduce an automatic pipeline which employs a novel deep learning-based approach to rapidly detect Mycobacterium tuberculosis (Mtb) organisms in sputum samples and thus quantify the burden of the disease. Fluorescence microscopy images are used as input in a series of networks, which ultimately produces a final count of present bacteria more quickly and consistently than manual analysis by healthcare workers. The pipeline consists of four stages: annotation by cycle-consistent generative adversarial networks (GANs), extraction of salient image patches, classification of the extracted patches, and finally, regression to yield the final bacteria count. We empirically evaluate the individual stages of the pipeline as well as perform a unified evaluation on previously unseen data that were given ground-truth labels by an experienced microscopist. We show that with no human intervention, the pipeline can provide the bacterial count for a sample of images with an error of less than 5%.
Original languageEnglish
Article number96
Number of pages16
JournalInformation
Volume13
Issue number2
DOIs
Publication statusPublished - 18 Feb 2022

Keywords

  • Cycle GANs
  • Semantic segmentation
  • Patch extraction
  • Saliency
  • Classification
  • Regression

Fingerprint

Dive into the research topics of 'Tuberculosis bacteria detection and counting in fluorescence microscopy images using a multi-stage deep learning pipeline'. Together they form a unique fingerprint.

Cite this