OKEN: A Supervised Evolutionary Optimizable Dimensionality Reduction Framework for Whole Slide Image Classification

TL;DR

This paper introduces OKEN, a new framework for classifying lung cancer subtypes from digital tissue slides using an evolutionary algorithm to optimize feature encoding.

Contribution

The novelty lies in using an evolutionary algorithm to create an optimizable kernel for efficient and adjustable feature encoding in whole slide image classification.

Findings

OKEN outperforms Vim-S16 in accuracy and F1 score on internal lung cancer datasets at ×2.5 and ×10 magnifications.

The model achieves the highest accuracy (0.833) and F1 score (0.721) at ×2.5 magnification on the internal test set.

On the external test set, OKEN-DenseNet121 at ×2.5 achieves the best F1 score (0.772).

Abstract

Classification of lung cancer subtypes is a critical clinical step; however, relying solely on H&E-stained histopathology images can pose challenges, and additional immunohistochemical analysis is sometimes required for definitive subtyping. Digital pathology facilitates the use of artificial intelligence for automatic classification of digital tissue slides. Automatic classification of Whole Slide Images (WSIs) typically involves extracting features from patches obtained from them. The aim of this study was to develop a WSI classification framework utilizing an optimizable kernel to encode features from each patch from a WSI into a desirable and adjustable latent space using an evolutionary algorithm. The encoded data can then be used for classification and segmentation while being computationally more efficient. Our proposed framework is compared with a state-of-the-art model, Vim4Path, on an internal and external dataset of lung cancer WSIs. The proposed model outperforms Vim-S16 in accuracy and F1 score at both ×2.5 and ×10 magnification levels on the internal test set, with the highest accuracy (0.833) and F1 score (0.721) at ×2.5. On the external test set, Vim-S16 at ×10 achieves the highest accuracy (0.732), whereas OKEN-DenseNet121 at ×2.5 has the best F1 score (0.772). In future work, finding a dynamic way to tune the output dimensions of the evolutionary algorithm would be of value.

Figures