Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning
Standard
Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning. / Bengs, M.; Pant, S.; Bockmayr, M.; Schüller, U.; Schlaefer, A.
in: Current Directions in Biomedical Engineering, Jahrgang 7, Nr. 1, 20211115, 01.08.2021.Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning
AU - Bengs, M.
AU - Pant, S.
AU - Bockmayr, M.
AU - Schüller, U.
AU - Schlaefer, A.
N1 - Publisher Copyright: © 2021 by Walter de Gruyter Berlin/Boston.
PY - 2021/8/1
Y1 - 2021/8/1
N2 - 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.
AB - 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.
KW - convolutional neural networks
KW - digital pathology
KW - histopathology
KW - medulloblastoma
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85114439798&partnerID=8YFLogxK
U2 - 10.1515/cdbme-2021-1014
DO - 10.1515/cdbme-2021-1014
M3 - SCORING: Journal article
AN - SCOPUS:85114439798
VL - 7
JO - Current Directions in Biomedical Engineering
JF - Current Directions in Biomedical Engineering
SN - 2364-5504
IS - 1
M1 - 20211115
ER -