Computational Radiomics System to Decode the Radiographic Phenotype

Griethuysen, Joost J.M. van; Fedorov, Andriy; Parmar, Chintan; Hosny, Ahmed; Aucoin, Nicole; Narayan, Vivek; Beets‐Tan, Regina G. H.; Fillion‐Robin, Jean‐Christophe; Pieper, Steve; Aerts, Hugo J.W.L.

doi:10.1158/0008-5472.can-17-0339

Cited by 3,753 publications

(2,279 citation statements)

References 14 publications

Supporting

Mentioning

2,260

Contrasting

Unclassified

Order By: Relevance

“…This step was performed by Pyradiomics [26], which can extract a wide range of radiomic features from brain tumor MRI. For each modality, 105 3D-Radiomic features were extracted, including 18 first-order features, 13 shape features, and 74 texture features.…”

Section: Resultsmentioning

confidence: 99%

Computer-Aided Grading of Gliomas Combining Automatic Segmentation and Radiomics

Chen

Liu

Peng

et al. 2018

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

Gliomas are the most common primary brain tumors, and the objective grading is of great importance for treatment. This paper presents an automatic computer-aided diagnosis of gliomas that combines automatic segmentation and radiomics, which can improve the diagnostic ability. The MRI data containing 220 high-grade gliomas and 54 low-grade gliomas are used to evaluate our system. A multiscale 3D convolutional neural network is trained to segment whole tumor regions. A wide range of radiomic features including first-order features, shape features, and texture features is extracted. By using support vector machines with recursive feature elimination for feature selection, a CAD system that has an extreme gradient boosting classifier with a 5-fold cross-validation is constructed for the grading of gliomas. Our CAD system is highly effective for the grading of gliomas with an accuracy of 91.27%, a weighted macroprecision of 91.27%, a weighted macrorecall of 91.27%, and a weighted macro-F1 score of 90.64%. This demonstrates that the proposed CAD system can assist radiologists for high accurate grading of gliomas and has the potential for clinical applications.

show abstract

Section: Resultsmentioning

confidence: 99%

Computer-Aided Grading of Gliomas Combining Automatic Segmentation and Radiomics

Chen

Liu

Peng

et al. 2018

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

show abstract

“…Radiomic features of the tumor were extracted from the standardized uptake value (SUV) map of the PET scan for each patient [36]. In particular, 11 morphologic features were extracted from the tumor region.…”

Section: Methodsmentioning

confidence: 99%

Unsupervised machine learning of radiomic features for predicting treatment response and overall survival of early stage non-small cell lung cancer patients treated with stereotactic body radiation therapy

Galperin-Aizenberg

Pryma

et al. 2018

Radiotherapy and Oncology

View full text Add to dashboard Cite

Background and purpose: To predict treatment response and survival of NSCLC patients receiving stereotactic body radiation therapy (SBRT), we develop an unsupervised machine learning method for stratifying patients and extracting meta-features simultaneously based on imaging data. Material and methods: This study was performed based on an 18F-FDG-PET dataset of 100 consecutive patients who were treated with SBRT for early stage NSCLC. Each patient’s tumor was characterized by 722 radiomic features. An unsupervised two-way clustering method was used to identify groups of patients and radiomic features simultaneously. The groups of patients were compared in terms of survival and freedom from nodal failure. Meta-features were computed for building survival models to predict survival and free of nodal failure. Results: Differences were found between 2 groups of patients when the patients were clustered into 3 groups in terms of both survival (p = 0.003) and freedom from nodal failure (p = 0.038). Average concordance measures for predicting survival and nodal failure were 0.640 ± 0.029 and 0.664 ± 0.063 respectively, better than those obtained by prediction models built upon clinical variables (p < 0.04). Conclusions: The evaluation results demonstrate that our method allows us to stratify patients and predict survival and freedom from nodal failure with better performance than current alternative methods.

show abstract

“…For each ROI, 10 image-derived features were calculated and taken from [17–19], see Table 1. Morphological traits are commonly recognized as clinically indicative of tumor aggressiveness and are similar to previous radiogenomic studies [1–4, 6].…”

Section: Methodsmentioning

confidence: 99%

Using deep neural networks for radiogenomic analysis

Smedley

Hsu

2018

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)

View full text Add to dashboard Cite

Radiogenomic studies have suggested that biological heterogeneity of tumors is reflected radiographically through visible features on magnetic resonance (MR) images. We apply deep learning techniques to map between tumor gene expression profiles and tumor morphology in pre-operative MR studies of glioblastoma patients. A deep autoencoder was trained on 528 patients, each with 12,042 gene expressions. Then, the autoencoder’s weights were used to initialize a supervised deep neural network. The supervised model was trained using a subset of 109 patients with both gene and MR data. For each patient, 20 morphological image features were extracted from contrast-enhancing and peritumoral edema regions. We found that neural network pre-trained with an autoencoder and dropout had lower errors than linear regression in predicting tumor morphology features by an average of 16.98% mean absolute percent error and 0.0114 mean absolute error, where several features were significantly different (adjusted p-value < 0.05). These results indicate neural networks, which can incorporate nonlinear, hierarchical relationships between gene expressions, may have the representational power to find more predictive radiogenomic associations than pairwise or linear methods.

show abstract

Computational Radiomics System to Decode the Radiographic Phenotype

Cited by 3,753 publications

References 14 publications

Computer-Aided Grading of Gliomas Combining Automatic Segmentation and Radiomics

Computer-Aided Grading of Gliomas Combining Automatic Segmentation and Radiomics

Unsupervised machine learning of radiomic features for predicting treatment response and overall survival of early stage non-small cell lung cancer patients treated with stereotactic body radiation therapy

Using deep neural networks for radiogenomic analysis

Contact Info

Product

Resources

About