Investigating the potential of untrained convolutional layers and pruning in computational pathology

T. Rai; I. Papanikolaou; N. Dave; A. Morisi; B. Bacci; S. A. Thomas; R. La Ragione; K. Wells

doi:10.1117/12.2655252

6 April 2023 Investigating the potential of untrained convolutional layers and pruning in computational pathology

T. Rai, I. Papanikolaou, N. Dave, A. Morisi, B. Bacci, S. A. Thomas, R. La Ragione, K. Wells

Proceedings Volume 12471, Medical Imaging 2023: Digital and Computational Pathology; 1247119 (2023) https://doi.org/10.1117/12.2655252
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Abstract

The effectiveness of untrained convolutional layers for feature extraction in a computational pathology task using real-world data from a necrosis detection dataset is investigated. The study aims to determine whether ImageNet pretrained layers from deep CNNs combined with frozen untrained weights are sufficient for effective necrosis detection in canine Perivascular Wall Tumour (cPWT) whole slide images. Additionally, the authors investigate the impact of pruning CNNs, and whether it can be effective for necrosis detection as this technique can contribute towards reducing memory requirements and improve inference speed in diagnostic settings. The study found that fine-tuning the last (deepest) layers of a pretrained ImageNet model for necrosis detection in cPWT produces the highest test F1-score (0.715) when compared to alternative set ups. This score is further improved to 0.754 when the results are optimised using an optimal threshold predetermined on maximising the validation set F1-score. Resetting weights (untrained) and freezing the last few convolutional layers in the last dense block also demonstrated some capability in necrosis detection with an optimised F1-score of 0.747, still outperforming models trained from scratch as well as an ImageNet pretrained feature extraction model. Pruning the fine-tuned model using lower thresholds also showed the potential to improve performance, however thresholds higher than 0.40 negatively impacted performance.

Conference Presentation

Citation Download Citation

T. Rai, I. Papanikolaou, N. Dave, A. Morisi, B. Bacci, S. A. Thomas, R. La Ragione, and K. Wells "Investigating the potential of untrained convolutional layers and pruning in computational pathology", Proc. SPIE 12471, Medical Imaging 2023: Digital and Computational Pathology, 1247119 (6 April 2023); https://doi.org/10.1117/12.2655252

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available