Please use this identifier to cite or link to this item:
Publisher DOI: 10.1515/cdbme-2021-1014
Title: Multi-scale input strategies for medulloblastoma tumor classification using deep transfer learning
Language: English
Authors: Bengs, Marcel 
Pant, Satish 
Bockmayr, Michael 
Schüller, Ulrich 
Schlaefer, Alexander 
Keywords: convolutional neural networks;digital pathology;histopathology;medulloblastoma;Transfer learning
Issue Date: 1-Aug-2021
Publisher: De Gruyter
Source: Current Directions in Biomedical Engineering 7 (1): 20211115, 63-66 (2021-08-01)
Journal: Current directions in biomedical engineering 
Abstract (english): 
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 timeconsuming 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 Desmoplastic/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.
DOI: 10.15480/882.3822
ISSN: 2364-5504
Institute: Medizintechnische und Intelligente Systeme E-1 
Document Type: Article
More Funding information: This work was partially supported by the Hamburg University of Technology i3 initiative.
License: CC BY 4.0 (Attribution) CC BY 4.0 (Attribution)
Appears in Collections:Publications with fulltext

Files in This Item:
File Description SizeFormat
10.1515_cdbme-2021-1014.pdfVerlags-PDF566,18 kBAdobe PDFView/Open
Show full item record

Page view(s)

checked on Oct 18, 2021


checked on Oct 18, 2021

Google ScholarTM


Note about this record

Cite this record


This item is licensed under a Creative Commons License Creative Commons