Advertisement

Adverse Effects of Image Tiling on Convolutional Neural Networks

  • G. Anthony ReinaEmail author
  • Ravi Panchumarthy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11383)

Abstract

Convolutional neural network models perform state of the art accuracy on image classification, localization, and segmentation tasks. A fully convolutional topology, such as U-Net, may be trained on images of one size and perform inference on images of another size. This feature allows researchers to work with images too large to fit into memory by simply dividing the image into small tiles, making predictions on these tiles, and stitching these tiles back together as the prediction of the whole image.

We compare how a tiled prediction of a U-Net model compares to a prediction that is based on the whole image. Our results show that using tiling to perform inference results in a significant increase in both false positive and false negative predictions when compared to using the whole image for inference. We are able to modestly improve the predictions by increasing both tile size and amount of tile overlap, but this comes at a greater computational cost and still produces inferior results to using the whole image.

Although tiling has been used to produce acceptable segmentation results in the past, we recommend performing inference on the whole image to achieve the best results and increase the state of the art accuracy for CNNs.

References

  1. 1.
    Greenspan, H., Van Ginneken, B., Summers, R.M.: Deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans. Med. Imaging 35(5), 1153–1159 (2016)CrossRefGoogle Scholar
  2. 2.
    Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115–118 (2017).  https://doi.org/10.1038/nature21056CrossRefGoogle Scholar
  3. 3.
    Tianqi, C., Bing, X., Chiyuan, Z., Guestrin, C.: Training deep nets with sublinear memory cost. arXiv:1604.06174v2 [cs.LG] 22 April 2016
  4. 4.
    Pinckaers, J.H.F.M., Litjens, G.J.S.: Training convolutional neural networks with megapixel images. arXiv:1804.05712v1 [cs.CV] 16 April 2018
  5. 5.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation, 18 May 2015. https://arxiv.org/abs/1505.04597
  6. 6.
    Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015).  https://doi.org/10.1109/TMI.2014.2377694CrossRefGoogle Scholar
  7. 7.
    Bakas, S., et al.: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Nature Sci. Data 4, 170117 (2017).  https://doi.org/10.1038/sdata.2017.117CrossRefGoogle Scholar
  8. 8.
    Bakas, S., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-GBM collection. The Cancer Imaging Archive (2017).  https://doi.org/10.7937/K9/TCIA.2017.KLXWJJ1Q
  9. 9.
    Bakas, S., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-LGG collection. The Cancer Imaging Archive (2017).  https://doi.org/10.7937/K9/TCIA.2017.GJQ7R0EF

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Artificial Intelligence Products GroupIntel CorporationHillsboroUSA

Personalised recommendations