A functional artificial neural network for noninvasive pretreatment evaluation of glioblastoma patients

Abstract

Background Pretreatment assessments for glioblastoma (GBM) patients, especially elderly or frail patients, are critical for treatment planning. However, genetic profiling with intracranial biopsy carries a significant risk of permanent morbidity. We previously demonstrated that the CUL2 gene, encoding the scaffold cullin2 protein in the cullin2-RING E3 ligase (CRL2), can predict GBM radiosensitivity and prognosis. CUL2 expression levels are closely regulated with its copy number variations (CNVs). This study aims to develop artificial neural networks (ANNs) for pretreatment evaluation of GBM patients with inputs obtainable without intracranial surgical biopsies. Methods Public datasets including Ivy-GAP, The Cancer Genome Atlas Glioblastoma (TCGA-GBM), the Chinese Glioma Genome Atlas (CGGA) were used for training and testing of the ANNs. T1 images from corresponding cases were studied using automated segmentation for features of heterogeneity and tumor edge contouring. A ratio comparing the surface area of tumor borders vs. the total volume (SvV) was derived from the DICOM-SEG conversions of segmented tumors. The edges of these borders were detected using the canny edge detector. Packages including Keras, Pytorch, and TensorFlow were tested to build the ANNs. A 4-layered ANN (8-8-8-2) with a binary output was built with optimal performance after extensive testing. Results The 4-layered deep learning ANN can identify a GBM patient’s overall survival (OS) cohort with 80-85% accuracy. The ANN requires 4 inputs, including CUL2 copy number, patients’ age at GBM diagnosis, Karnofsky Performance Scale (KPS), and SvV ratio. Conclusion Quantifiable image features can significantly improve the ability of ANNs to identify a GBM patients’ survival cohort. Features such as clinical measures, genetic data, and image data, can be integrated into a single ANN for GBM pretreatment evaluation.

A review of the current status and progress in difficult airway assessment research

“…The ultimate goal of deep learning is to enable robots to have analytical learning capabilities like humans, capable of recognizing data such as text, images and sounds, and the main pathways can be divided into convolutional neural network, fully convolutional network, recurrent neural network and generative adversarial network [ 57 , 58 ]. Its algorithms can be further divided into Keras, Tensorflow, Pytorch, Caffe and Theano [ 59 ].…”

Advancements in Image-Based Models for High-Grade Gliomas Might Be Accelerated

“…The expression levels of CUL2 are tightly regulated with its copy number variations (CNVs). Zander and colleagues developed artificial neural networks (ANNs) for the noninvasive pretreatment evaluation of HGG patients integrating clinical measurements, genetic data, and image data [127].…”

“…artificial neural networks (ANNs) for the noninvasive pretreatment evaluation of HGG patients integrating clinical measurements, genetic data, and image data [127].…”

Radiation Therapy in Older Adults With Cancer: A Critical Modality in Geriatric Oncology

“…Deep learning techniques can also be used to incorporate multiple data points such as clinical information, genetic/molecular data, and imaging to create models to better assess outcomes and help physicians select the appropriate therapy for patients. 43,44 Furthermore, older adults are under-represented in both prospective and retrospective studies analyzing genomic sequencing, which may affect future predictive tools using molecular pathways. 45 Genomic and molecular analyses of older adults specifically will likely be another important avenue of research to better understand correlations between genomic mutations, aging, and RT-related treatment outcomes and toxicities.…”