Differentiation of lung and breast cancer brain metastases: Comparison of texture analysis and deep convolutional neural networks

Abstract

PurposeMetastases are the most common neoplasm in the adult brain. In order to initiate the treatment, an extensive diagnostic workup is usually required. Radiomics is a discipline aimed at transforming visual data in radiological images into reliable diagnostic information. We aimed to examine the capability of deep learning methods to classify the origin of metastatic lesions in brain MRIs and compare the deep Convolutional Neural Network (CNN) methods with image texture based features.MethodsOne hundred forty three patients with 157 metastatic brain tumors were included in the study. The statistical and texture based image features were extracted from metastatic tumors after manual segmentation process. Three powerful pre‐trained CNN architectures and the texture‐based features on both 2D and 3D tumor images were used to differentiate lung and breast metastases. Ten‐fold cross‐validation was used for evaluation. Accuracy, precision, recall, and area under curve (AUC) metrics were calculated to analyze the diagnostic performance.ResultsThe texture‐based image features on 3D volumes achieved better discrimination results than 2D image features. The overall performance of CNN architectures with 3D inputs was higher than the texture‐based features. Xception architecture, with 3D volumes as input, yielded the highest accuracy (0.85) while the AUC value was 0.84. The AUC values of VGG19 and the InceptionV3 architectures were 0.82 and 0.81, respectively.ConclusionCNNs achieved superior diagnostic performance in differentiating brain metastases from lung and breast malignancies than texture‐based image features. Differentiation using 3D volumes as input exhibited a higher success rate than 2D sagittal images.

A novel diagnostic tool to differentiate primary origin of brain metastases: Deep learning‐based radiomics

“…We have read with great interest the recently published study by Gultekin et al, who compared texture analysis and three different deep-learning models to differentiate lung and breast brain metastases (BM). 1 The deep learning architectures were based on convolutional neural networks (CNN) commonly used in image analysis and with extensive data sets. While the study has demonstrated the CNN models using radiomic features achieve excellent results, it has several critical limitations.…”