June 2020
Volume 61, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2020
Improving OCT B-scan of interest inference performance using TensorRT based neural network optimization
Author Affiliations & Notes
  • Hugang Ren
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Niranchana Manivannan
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Gary C Lee
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Sophia Yu
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Patty Sha
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Thais Conti
    Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Alline Melo
    Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Tyler Greenlee
    Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Eric Chen
    School of Medicine, Case Western Reserve University, Cleveland, Ohio, United States
  • Katherine Talcott
    Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Rishi P Singh
    Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Mary K Durbin
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Neil D'Souza
    Carl Zeiss Meditec, Inc., Dublin, California, United States
  • Footnotes
    Commercial Relationships   Hugang Ren, Carl Zeiss Meditec, Inc. (E); Niranchana Manivannan, Carl Zeiss Meditec, Inc. (E); Gary Lee, Carl Zeiss Meditec, Inc. (E); Sophia Yu, Carl Zeiss Meditec, Inc. (E); Patty Sha, Carl Zeiss Meditec, Inc. (E); Thais Conti, Carl Zeiss Meditec, Inc. (F); Alline Melo, Carl Zeiss Meditec, Inc. (F); Tyler Greenlee, Carl Zeiss Meditec, Inc. (F); Eric Chen, Carl Zeiss Meditec, Inc. (F); Katherine Talcott, Carl Zeiss Meditec, Inc. (F); Rishi Singh, Alcon (C), Apellis (F), Carl Zeiss Meditec, Inc. (C), Genentech (C), Graybug (F), Novartis (C), Regeneron (C); Mary Durbin, Carl Zeiss Meditec, Inc. (E); Neil D'Souza, Carl Zeiss Meditec, Inc. (E)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 1635. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Hugang Ren, Niranchana Manivannan, Gary C Lee, Sophia Yu, Patty Sha, Thais Conti, Alline Melo, Tyler Greenlee, Eric Chen, Katherine Talcott, Rishi P Singh, Mary K Durbin, Neil D'Souza; Improving OCT B-scan of interest inference performance using TensorRT based neural network optimization. Invest. Ophthalmol. Vis. Sci. 2020;61(7):1635.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : OCT B-scan of interest detection is a newly developed deep learning algorithm that aims to improve the workflow efficiency for CIRRUS™ HD-OCT during OCT data review. However, the inference time of the neural network can be long for 3D scans that have a large number of B-scans. In this study, we propose a method that can improve the inference performance of OCT B-scan of interest algorithm by optimizing the neural network using TensorRT.

Methods : 76,544 OCT B-scans from 598 macular cubes acquired from 598 subjects using CIRRUS HD-OCT 5000 (ZEISS, Dublin, CA) were used as the training and development sets. 148 B-scans were ungradable and were excluded. A 3-channel ResNet-50 neural network was trained using 61,058 B-scans from the training set and fine-tuned using 15,338 B-scans from the development set. The trained neural network was then frozen and saved as a protocol buffers (pb) file.
The frozen model was loaded into memory using TensorFlow 1.13.1 and optimized with TensorRT 5.0.2. A maximum batch size of 128 was specified when the TensorRT engine optimized the neural network.
To test the speed difference between the frozen model and the optimized model, 12,800 inferences were performed and the average inference time for each B-scan was measured. To test the accuracy of the optimized model, 25,600 B-scans acquired from 200 subjects at 3 different clinical sites were used. Both the B-scan of interest binary predication result and probability were compared between the original frozen model and the optimized model.

Results : For model complexity, the number of nodes of the network was reduced from 881 to 3 after optimization. For inference speed, each B-scan inference took 12.6 milliseconds before optimization and 6.9 milliseconds after optimization. The inference time for a macular cube scan was 1.61 seconds before optimization and 0.88 second after optimization. The optimized model ran about 1.8 times the speed of the original model. For accuracy, the sensitivity, specificity and AUC on the test set before and after optimization were the same: 92.6%, 95.1% and 0.98. The mean probability difference between the frozen model and the optimized model was negligible (-4.3e-8 ±5.0e-7).

Conclusions : In this study, we demonstrated a method that improves the inference speed for OCT B-scan of interest detection algorithm with the same accuracy maintained.

This is a 2020 ARVO Annual Meeting abstract.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×