Deep Learning Assisted Imaging Methods to Facilitate Access to Ophthalmic Telepathology

Andrew W Browne; Geunwoo Kim; Anderson N Vu; Josiah K To; Don S Minckler; Maria Del Valle Estopinal; Narsing A Rao; Christine A Curcio; Pierre F Baldi

doi:10.1016/j.xops.2023.100450

Deep Learning Assisted Imaging Methods to Facilitate Access to Ophthalmic Telepathology

Ophthalmol Sci. 2023 Dec 12;4(3):100450. doi: 10.1016/j.xops.2023.100450. eCollection 2024 May-Jun.

Authors

Andrew W Browne^{1

2

3}, Geunwoo Kim⁴, Anderson N Vu², Josiah K To², Don S Minckler^{1

5}, Maria Del Valle Estopinal^{1

5}, Narsing A Rao⁶, Christine A Curcio⁷, Pierre F Baldi^{3

4}

Affiliations

¹ Department of Ophthalmology, Gavin Herbert Eye Institute, University of California, Irvine, California.
² Center for Translational Vision Research, University of California, Irvine, California.
³ Department of Biomedical Engineering, University of California, Irvine, California.
⁴ School of Information and Computer Sciences, University of California, Irvine, California.
⁵ Department of Pathology, University of California, Irvine, California.
⁶ Department of Ophthalmology, University of Southern California, Los Angeles, California.
⁷ Department of Ophthalmology and Visual Sciences, University of Alabama at Birmingham Heersink School of Medicine, Birmingham, Alabama.

Abstract

Purpose: To investigate the use of super-resolution imaging techniques to enable telepathology using low-cost commercial cameras.

Design: Experimental study.

Participants: A total of 139 ophthalmic pathology slides obtained from the Ophthalmic Pathology service at the University of California, Irvine.

Methods: Denoising Diffusion Probabilistic Model (DDPM) was developed to predict super-resolution pathology slide images from low-resolution inputs. The model was pretrained using 150 000 images randomly sampled from the ImageNet dataset. Patch aggregation was used to generate large images with DDPM. The performance of DDPM was evaluated against that of generative adversarial networks (GANs) and Robust UNet, which were also trained on the same dataset.

Main outcome measures: The performance of models trained to generate super-resolution output images from low-resolution input images can be evaluated by using the mean squared error (MSE) and Structural Similarity Index Measure (SSIM), as well as subjective grades provided by expert pathologist graders.

Results: In total, our study included 110 training images, 9 validation images, and 20 testing images. The objective performance scores were averaged over patches generated from 20 test images. The DDPM-based approach with pretraining produced the best results, with an MSE score of 1.35e-5 and an SSIM score of 0.8987. A qualitative analysis of super-resolution images was conducted by expert 3 pathologists and 1 expert ophthalmic microscopist, and the average accuracy of identifying the correct ground truth images ranged from 25% to 70% (with an average accuracy of 46.5%) for widefield images and 25% to 60% (with an average accuracy of 38.25%) for individual patches.

Conclusions: The DDPM-based approach with pretraining is assessed to be effective at super-resolution prediction for ophthalmic pathology slides both in terms of objective and subjective measures. The proposed methodology is expected to decrease the reliance on costly slide scanners for acquiring high-quality pathology slide images, while also streamlining clinical workflow and expanding the scope of ophthalmic telepathology.

Financial disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Keywords: Artificial intelligence; Deep learning; Diffusion model; Telepathology.

Grants and funding

UL1 TR001414/TR/NCATS NIH HHS/United States