Skip to main content

Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations.

Publication ,  Conference
McManigle, JE; Bartz, RR; Carin, L
Published in: Annu Int Conf IEEE Eng Med Biol Soc
July 2020

Over the last decade, convolutional neural networks (CNNs) have emerged as the leading algorithms in image classification and segmentation. Recent publication of large medical imaging databases have accelerated their use in the biomedical arena. While training data for photograph classification benefits from aggressive geometric augmentation, medical diagnosis - especially in chest radiographs - depends more strongly on feature location. Diagnosis classification results may be artificially enhanced by reliance on radiographic annotations. This work introduces a general pre-processing step for chest x-ray input into machine learning algorithms. A modified Y-Net architecture based on the VGG11 encoder is used to simultaneously learn geometric orientation (similarity transform parameters) of the chest and segmentation of radiographic annotations. Chest x-rays were obtained from published databases. The algorithm was trained with 1000 manually labeled images with augmentation. Results were evaluated by expert clinicians, with acceptable geometry in 95.8% and annotation mask in 96.2% (n = 500), compared to 27.0% and 34.9% respectively in control images (n = 241). We hypothesize that this pre-processing step will improve robustness in future diagnostic algorithms.Clinical relevance-This work demonstrates a universal pre-processing step for chest radiographs - both normalizing geometry and masking radiographic annotations - for use prior to further analysis.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Annu Int Conf IEEE Eng Med Biol Soc

DOI

EISSN

2694-0604

Publication Date

July 2020

Volume

2020

Start / End Page

1266 / 1269

Location

United States

Related Subject Headings

  • X-Rays
  • Radiography
  • Neural Networks, Computer
  • Machine Learning
  • Algorithms
 

Citation

APA
Chicago
ICMJE
MLA
NLM
McManigle, J. E., Bartz, R. R., & Carin, L. (2020). Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations. In Annu Int Conf IEEE Eng Med Biol Soc (Vol. 2020, pp. 1266–1269). United States. https://doi.org/10.1109/EMBC44109.2020.9176334
McManigle, John E., Raquel R. Bartz, and Lawrence Carin. “Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations.” In Annu Int Conf IEEE Eng Med Biol Soc, 2020:1266–69, 2020. https://doi.org/10.1109/EMBC44109.2020.9176334.
McManigle JE, Bartz RR, Carin L. Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations. In: Annu Int Conf IEEE Eng Med Biol Soc. 2020. p. 1266–9.
McManigle, John E., et al. “Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations.Annu Int Conf IEEE Eng Med Biol Soc, vol. 2020, 2020, pp. 1266–69. Pubmed, doi:10.1109/EMBC44109.2020.9176334.
McManigle JE, Bartz RR, Carin L. Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations. Annu Int Conf IEEE Eng Med Biol Soc. 2020. p. 1266–1269.

Published In

Annu Int Conf IEEE Eng Med Biol Soc

DOI

EISSN

2694-0604

Publication Date

July 2020

Volume

2020

Start / End Page

1266 / 1269

Location

United States

Related Subject Headings

  • X-Rays
  • Radiography
  • Neural Networks, Computer
  • Machine Learning
  • Algorithms