Munich Personal RePEc Archive

Glioblastoma Multiforme Classification On High Resolution Histology Image Using Deep Spatial Fusion Network

Sumi, P. Sobana and Delhibabu, Radhakrishnan (2019): Glioblastoma Multiforme Classification On High Resolution Histology Image Using Deep Spatial Fusion Network. Published in: CEUR Workshop Proceedings , Vol. 2479, (26 September 2019): pp. 109-120.

[img]
Preview
PDF
project4.pdf

Download (1MB) | Preview

Abstract

Brain tumor is a growth of abnormal cells in brain, which canbe cancerous or non-cancerous. The Brain tumor have scarce symptomsso it is very difficult to classify. Diagnosing brain tumor with histologyimages will efficiently helps us to classify brain tumor types. Sometimes,histology based image analysis is not accepted due to its variations inmorphological features. Deep learning CNN models helps to overcomethis problem by feature extraction and classification. Here proposed amethod to classify high resolution histology image. InceptionResNetV2is an CNN model, which is adopted to extract hierarchical features with-out any loss of data. Next generated deep spatial fusion network to ex-tract spatial features found in between patches and to predict correct fea-tures from unpredictable discriminative features. 10-fold cross-validationis performed on the histology image. This achieves 95.6 percent accu-racy on 4-class classification (benign, malignant, Glioblastoma, Oligo-dendroglioma). Also obtained 99.1 percent accuracy and 99.6 percentAUC on 2-way classification (necrosis and non-necrosis).

UB_LMU-Logo
MPRA is a RePEc service hosted by
the Munich University Library in Germany.