Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning

TL;DR

This paper investigates how different input strategies and tile sizes in deep transfer learning affect the classification accuracy of medulloblastoma subtypes in histopathological images, demonstrating that larger input tiles with downsampling improve performance.

Contribution

It systematically evaluates the impact of tile size and input strategy on CNN-based medulloblastoma classification, introducing an optimized approach for better accuracy.

Findings

Larger input tiles with downsampling outperform smaller tiles.

The best method achieves an AUC-ROC of 90.90%.

Systematic evaluation improves classification performance.

Abstract

Medulloblastoma (MB) is a primary central nervous system tumor and the most common malignant brain cancer among children. Neuropathologists perform microscopic inspection of histopathological tissue slides under a microscope to assess the severity of the tumor. This is a time-consuming task and often infused with observer variability. Recently, pre-trained convolutional neural networks (CNN) have shown promising results for MB subtype classification. Typically, high-resolution images are divided into smaller tiles for classification, while the size of the tiles has not been systematically evaluated. We study the impact of tile size and input strategy and classify the two major histopathological subtypes-Classic and Demoplastic/Nodular. To this end, we use recently proposed EfficientNets and evaluate tiles with increasing size combined with various downsampling scales. Our results demonstrate using large input tiles pixels followed by intermediate downsampling and patch cropping significantly improves MB classification performance. Our top-performing method achieves the AUC-ROC value of 90.90\% compared to 84.53\% using the previous approach with smaller input tiles.