Singapore Institute of Technology
Browse
journal.pone.0274291.pdf (1.49 MB)

To pretrain or not? A systematic analysis of the benefits of pretraining in diabetic retinopathy.

Download (1.49 MB)
journal contribution
posted on 2023-09-28, 09:23 authored by Vignesh Srinivasan, Nils StrodthoffNils Strodthoff, Jackie Ma, Alexander Binder, Klaus-Robert Müller, Wojciech Samek

There is an increasing number of medical use cases where classification algorithms based on deep neural networks reach performance levels that are competitive with human medical experts. To alleviate the challenges of small dataset sizes, these systems often rely on pretraining. In this work, we aim to assess the broader implications of these approaches in order to better understand what type of pretraining works reliably (with respect to performance, robustness, learned representation etc.) in practice and what type of pretraining dataset is best suited to achieve good performance in small target dataset size scenarios. Considering diabetic retinopathy grading as an exemplary use case, we compare the impact of different training procedures including recently established self-supervised pretraining methods based on contrastive learning. To this end, we investigate different aspects such as quantitative performance, statistics of the learned feature representations, interpretability and robustness to image distortions. Our results indicate that models initialized from ImageNet pretraining report a significant increase in performance, generalization and robustness to image distortions. In particular, self-supervised models show further benefits to supervised models. Self-supervised models with initialization from ImageNet pretraining not only report higher performance, they also reduce overfitting to large lesions along with improvements in taking into account minute lesions indicative of the progression of the disease. Understanding the effects of pretraining in a broader sense that goes beyond simple performance comparisons is of crucial importance for the broader medical imaging community beyond the use case considered in this work.

History

Journal/Conference/Book title

PLoS ONE

Publication date

2022-10-18

Version

  • Published

Sub-Item type

  • Magazine article

Usage metrics

    Categories

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC