Prediction of Glioma Grades Using Deep Learning with Wavelet Radiomic Features

Abstract

Gliomas are the most common primary brain tumors. They are classified into 4 grades (Grade I–II-III–IV) according to the guidelines of the World Health Organization (WHO). The accurate grading of gliomas has clinical significance for planning prognostic treatments, pre-diagnosis, monitoring and administration of chemotherapy. The purpose of this study is to develop a deep learning-based classification method using radiomic features of brain tumor glioma grades with deep neural network (DNN). The classifier was combined with the discrete wavelet transform (DWT) the powerful feature extraction tool. This study primarily focuses on the four main aspects of the radiomic workflow, namely tumor segmentation, feature extraction, analysis, and classification. We evaluated data from 121 patients with brain tumors (Grade II, n = 77; Grade III, n = 44) from The Cancer Imaging Archive, and 744 radiomic features were obtained by applying low sub-band and high sub-band 3D wavelet transform filters to the 3D tumor images. Quantitative values were statistically analyzed with MannWhitney U tests and 126 radiomic features with significant statistical properties were selected in eight different wavelet filters. Classification performances of 3D wavelet transform filter groups were measured using accuracy, sensitivity, F1 score, and specificity values using the deep learning classifier model. The proposed model was highly effective in grading gliomas with 96.15% accuracy, 94.12% precision, 100% recall, 96.97% F1 score, and 98.75% Area under the ROC curve. As a result, deep learning and feature selection techniques with wavelet transform filters can be accurately applied using the proposed method in glioma grade classification.

Current Status and Quality of Machine Learning-Based Radiomics Studies for Glioma Grading: A Systematic Review

“…6. Vague patient population: In our review, five studies mentioned the exact number of patients in each grade[37,38,40,42,43]. Other papers have used patients in LGG and HGG classes.…”

CNN-based bi-directional and directional long-short term memory network for determination of face mask

“…CNN, which is a deep learning method, is highly preferred in different discipline applications at present since it can easily distinguish small details that the human eye cannot notice in image recognition applications. The fact that they do not require much preprocessing and recognize visual patterns directly from pixel images is the most important feature of CNNs [32] , [33] , [34] , [35] .…”

Stability and Reproducibility of Radiomic Features Based Various Segmentation Technique on MR Images of Hepatocellular Carcinoma (HCC)

“…Wavelet features are obtained by transforming domain representations of tumour intensity and textural features. These features were applied as either a high (H) or low pass (L) filter in each of the three dimensions—X-axis, Y-axis, and Z-axis: wavelet-LHL, wavelet-LHH, wavelet-HLL, wavelet-LLH, wavelet-HLH, wavelet-HHH, wavelet-HHL, and wavelet-LLL [ 14 ]. Eight decomposed volumes of images were used on the intensity and textural features in the volume of interest, which resulted in a total of 576 (8 × 72) wavelet transforms features [ 7 , 23 ].…”

“…Recently, uses of radiomics in cancer related field shows significant progress. Radiomics application is said to be one of the fundamental methods for machine learning development in the medical imaging field [ 14 , 15 ]. Extraction of radiomic features from various sources of medical images also overcomes the limitation of visual image interpretation [ 16 ].…”