Comparison of Intraoperative Ultrasound B-Mode and Strain Elastography for the Differentiation of Glioblastomas From Solitary Brain Metastases. An Automated Deep Learning Approach for Image Analysis

Abstract

BackgroundThe differential diagnosis of glioblastomas (GBM) from solitary brain metastases (SBM) is essential because the surgical strategy varies according to the histopathological diagnosis. Intraoperative ultrasound elastography (IOUS-E) is a relatively novel technique implemented in the surgical management of brain tumors that provides additional information about the elasticity of tissues. This study compares the discriminative capacity of intraoperative ultrasound B-mode and strain elastography to differentiate GBM from SBM.MethodsWe performed a retrospective analysis of patients who underwent craniotomy between March 2018 to June 2020 with glioblastoma (GBM) and solitary brain metastases (SBM) diagnoses. Cases with an intraoperative ultrasound study were included. Images were acquired before dural opening, first in B-mode, and then using the strain elastography module. After image pre-processing, an analysis based on deep learning was conducted using the open-source software Orange. We have trained an existing neural network to classify tumors into GBM and SBM via the transfer learning method using Inception V3. Then, logistic regression (LR) with LASSO (least absolute shrinkage and selection operator) regularization, support vector machine (SVM), random forest (RF), neural network (NN), and k-nearest neighbor (kNN) were used as classification algorithms. After the models’ training, ten-fold stratified cross-validation was performed. The models were evaluated using the area under the curve (AUC), classification accuracy, and precision.ResultsA total of 36 patients were included in the analysis, 26 GBM and 10 SBM. Models were built using a total of 812 ultrasound images, 435 of B-mode, 265 (60.92%) corresponded to GBM and 170 (39.8%) to metastases. In addition, 377 elastograms, 232 (61.54%) GBM and 145 (38.46%) metastases were analyzed. For B-mode, AUC and accuracy values of the classification algorithms ranged from 0.790 to 0.943 and from 72 to 89%, respectively. For elastography, AUC and accuracy values ranged from 0.847 to 0.985 and from 79% to 95%, respectively.ConclusionAutomated processing of ultrasound images through deep learning can generate high-precision classification algorithms that differentiate glioblastomas from metastases using intraoperative ultrasound. The best performance regarding AUC was achieved by the elastography-based model supporting the additional diagnostic value that this technique provides.

Intraoperative tissue classification methods in orthopedic and neurological surgeries: A systematic review

“…Within the reviewed articles, three studies ( 12 , 34 , 35 ) unveiled the potential of ultrasound imaging for tissue classification ( Table 4 ). Carson et al ( 12 ) tackled the problem of nerve localization and identification in lateral lumbar interbody fusion surgery with a trans-psoas approach, where the disc space is accessed through the psoas muscle.…”

“…Carson et al ( 12 ) tackled the problem of nerve localization and identification in lateral lumbar interbody fusion surgery with a trans-psoas approach, where the disc space is accessed through the psoas muscle. Cepeda et al ( 34 ) and Ritschel et al ( 35 ) used ultrasound sensing in detecting brain tumor regions for tumor resection. Cepeda et al ( 34 ) compared B-mode and elastography ultrasound techniques in detecting the brain tumor region.…”

Multiparametric Intraoperative Ultrasound in Oncological Neurosurgery: A Pictorial Essay

“…Xflow and MicroV Doppler can explore the micro-vasculature, which in LGGs is usually scarce ( Figure 5 ). For this reason, in the case of LGGs, usually CEUS is much more informative than Doppler techniques ( Ng and Swanevelder, 2011 ; Prada et al, 2014b , 2015 ; Cepeda et al, 2021b ).…”

“…Elastosonography demonstrates HGGs to be usually softer than the healthy brain parenchyma ( Figure 6 ), thus helping to discern between HGGs and LGGs ( Cepeda et al, 2021b ). Quantitative analysis made possible by SWE is particularly interesting for the creation of algorithms to discern intraoperatively the nature of the lesion, such as distinguishing HGGs from solitary brain metastases ( Prada et al, 2016b , 2019 ; Cepeda et al, 2021b ; Yin et al, 2021 ). SE and SWE are useful even for assisting tumoral resection ( Newman and Rozycki, 1998 ).…”

“…It can provide details about the mechanical properties of the tumor compared with the parenchyma of the surrounding normal brain. For instance, the use of algorithms based on elastosonography appears to be more accurate than those from B-mode in differentiating intraoperatively HGGs and metastasis ( Cepeda et al, 2021b ). Technically, two methodologies, namely, strain elastography (SE) and shear wave elastography (SWE), are available.…”