The Application of Deep Convolutional Neural Networks to Brain Cancer Images: A Survey

Abstract

In recent years, improved deep learning techniques have been applied to biomedical image processing for the classification and segmentation of different tumors based on magnetic resonance imaging (MRI) and histopathological imaging (H&E) clinical information. Deep Convolutional Neural Networks (DCNNs) architectures include tens to hundreds of processing layers that can extract multiple levels of features in image-based data, which would be otherwise very difficult and time-consuming to be recognized and extracted by experts for classification of tumors into different tumor types, as well as segmentation of tumor images. This article summarizes the latest studies of deep learning techniques applied to three different kinds of brain cancer medical images (histology, magnetic resonance, and computed tomography) and highlights current challenges in the field for the broader applicability of DCNN in personalized brain cancer care by focusing on two main applications of DCNNs: classification and segmentation of brain cancer tumors images.

A deep convolutional neural network for segmentation of whole-slide pathology images identifies novel tumour cell-perivascular niche interactions that are associated with poor survival in glioblastoma

“…We have previously shown that DCNN models can be trained and applied to TCGA H&E histopathological images to predict brain cancer patient survival 46 (see also review in ref. 47 ). To analyse the relationship between segmentation results and patient survival, we next performed Pearson correlation analysis between the area of different brain tumour regions and patient survival across (i) all TCGA glioblastomas, and (ii) brain tumours harbouring the 13 most frequent mutations (PTEN, TP53, EGFR, NF1, PIK3CA, PI3KR1, TRAPP, ATRX, PDGFRA, KMT2C, PB1, GRIN2A, IDH1; see Supplementary Fig.…”

A Database for Learning Numbers by Visual Finger Recognition in Developmental Neuro-Robotics

“…A complete image classification model is a combination of convolutional and non-linearity layers, followed by several fully connected layers. With this architecture a number of models have been proposed, such as AlexNet (2012), ZF Net (2013), GoogLeNet (2014), VGGNet (2014), ResNet (2015), DenseNet (2016) (Khan et al, 2020 ).…”

Multi-Classification of Brain Tumor MRI Images Using Deep Convolutional Neural Network with Fully Optimized Framework

“…Researchers and readers who are interested in further papers on brain tumor classification using CNN can examine the following review articles (Litjens et al 2017 ; Lotan et al 2019 ; Muhammad et al 2021 ; Shaver et al 2019 ; Shirazi et al 2020 ; Tandel et al 2019 ; Tiwari et al 2020 ), which are very rich resources on this topic.…”