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

arXiv: https://arxiv.org/abs/2109.06547 · HTML: https://mlsanity.com/paper/2109.06547/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 7 of 7)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Multiple Instance Learning for Heterogeneous Images: Training a CNN for Histopathology](https://mlsanity.com/paper/1806.05083/) (2018)
- [Convolutional Neural Networks for Histopathology Image Classification: Training vs. Using Pre-Trained Networks](https://mlsanity.com/paper/1710.05726/) (2017)
- [Advanced Deep Convolutional Neural Network Approaches for Digital Pathology Image Analysis: a comprehensive evaluation with different use cases](https://mlsanity.com/paper/1904.09075/) (2019)
- [Medulloblastoma Tumor Classification using Deep Transfer Learning with Multi-Scale EfficientNets](https://mlsanity.com/paper/2109.05025/) (2021)

## Built on by (most cited first, 1 of 1)

- [Joint Stream: Malignant Region Learning for Breast Cancer Diagnosis](https://mlsanity.com/paper/2406.18212/) (2024)

## Abstract (arXiv)

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.