Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis

Artzi, Moran; Bressler, Idan; Bashat, Dafna Ben

doi:10.1002/jmri.26643

Cited by 126 publications

(109 citation statements)

References 35 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…A recent study explored four machine learning algorithms using radiomic features to differentiate glioblastoma from brain metastasis, reporting that SVM showed good performance 35 . Compared to their study, we included only solitary and supratentorial tumors for which imaging diagnosis is challenging and used deep learning in addition to traditional machine learning.…”

Section: Discussionmentioning

confidence: 99%

Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation

Bae

Ahn

et al. 2020

Sci Rep

View full text Add to dashboard Cite

We evaluated the diagnostic performance and generalizability of traditional machine learning and deep learning models for distinguishing glioblastoma from single brain metastasis using radiomics. The training and external validation cohorts comprised 166 (109 glioblastomas and 57 metastases) and 82 (50 glioblastomas and 32 metastases) patients, respectively. Two-hundred-and-sixty-five radiomic features were extracted from semiautomatically segmented regions on contrast-enhancing and peritumoral T2 hyperintense masks and used as input data. For each of a deep neural network (DNN) and seven traditional machine learning classifiers combined with one of five feature selection methods, hyperparameters were optimized through tenfold cross-validation in the training cohort. The diagnostic performance of the optimized models and two neuroradiologists was tested in the validation cohort for distinguishing glioblastoma from metastasis. In the external validation, DNN showed the highest diagnostic performance, with an area under receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.956 (95% confidence interval [CI], 0.918-0.990), 90.6% (95% CI, 80.5-100), 88.0% (95% CI, 79.0-97.0), and 89.0% (95% CI, 82.3-95.8), respectively, compared to the best-performing traditional machine learning model (adaptive boosting combined with tree-based feature selection; AUC, 0.890 (95% CI, 0.823-0.947)) and human readers (AUC, 0.774 [95% CI, 0.685-0.852] and 0.904 [95% CI, 0.852-0.951]). The results demonstrated deep learning using radiomic features can be useful for distinguishing glioblastoma from metastasis with good generalizability. Glioblastoma and brain metastasis are the most common malignant brain tumors in adults 1. Differentiation of these two types of tumors is important for planning further diagnostic workup and treatment 2. In case of a suspected brain metastasis, a full workup is required to identify the primary tumor and its dissemination status. Furthermore, treatment strategies differ for these tumors 3 ; En bloc resection is preferred for metastasis and stereotactic radiosurgery can be performed for metastases less than 3-4 cm 4 , whereas maximal safe resection followed by molecular classification and concurrent chemoradiotherapy should be considered for glioblastomas 5 .

show abstract

Section: Discussionmentioning

confidence: 99%

Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation

Bae

Ahn

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Artzi et al (46) extracted 760 radiomics features from contrast-enhanced MR images of 439 patients with brain metastases (n = 227) or glioblastoma (n = 212). After image preprocessing and semi-automatic tumor segmentation using a region-growing algorithm, feature selection, and model generation were performed.…”

Section: Differentiation Of Brain Metastases From Glioblastomamentioning

confidence: 99%

PET/MRI Radiomics in Patients With Brain Metastases

et al. 2020

View full text Add to dashboard Cite

Although a variety of imaging modalities are used or currently being investigated for patients with brain tumors including brain metastases, clinical image interpretation to date uses only a fraction of the underlying complex, high-dimensional digital information from routinely acquired imaging data. The growing availability of high-performance computing allows the extraction of quantitative imaging features from medical images that are usually beyond human perception. Using machine learning techniques and advanced statistical methods, subsets of such imaging features are used to generate mathematical models that represent characteristic signatures related to the underlying tumor biology and might be helpful for the assessment of prognosis or treatment response, or the identification of molecular markers. The identification of appropriate, characteristic image features as well as the generation of predictive or prognostic mathematical models is summarized under the term radiomics. This review summarizes the current status of radiomics in patients with brain metastases.

show abstract

“…Following dimensional reduction and classification of the BRAF mutation status, several support vector machine (SVM) classifier types were tested, including linear, quadratic, cubic, fine gaussian, medium gaussian, and coarse gaussian. This algorithm was chosen after having been shown to produce better results in various brain tumors classification tasks compared to other conventional machine-learning classifiers [21][22][23] . The results were evaluated by means of a 5-fold cross-validation scheme of randomly splitting the data into training and validation sets (42 and 11 patients, respectively), while maintaining the correct patient representation in each of the five data sets.…”

Section: Methodsmentioning

confidence: 99%

Virtual biopsy using MRI radiomics for prediction of BRAF status in melanoma brain metastasis

Shofty

Artzi

Shtrozberg

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

Brain metastases are common in patients with advanced melanoma and constitute a major cause of morbidity and mortality. Between 40% and 60% of melanomas harbor BRAF mutations. Selective BRAf inhibitor therapy has yielded improvement in clinical outcome; however, genetic discordance between the primary lesion and the metastatic tumor has been shown to occur. currently, the only way to characterize the genetic landscape of a brain metastasis is by tissue sampling, which carries risks and potential complications. the aim of this study was to investigate the use of radiomics analysis for non-invasive identification of BRAF mutation in patients with melanoma brain metastases, based on conventional magnetic resonance imaging (MRi) data. We applied a machine-learning method, based on MRi radiomics features for noninvasive characterization of the BRAf status of brain metastases from melanoma (BMM) and applied it to BMM patients from two tertiary neuro-oncological centers. All patients underwent surgical resection for BMM, and their BRAf mutation status was determined as part of their oncological work-up. their routine preoperative MRi study was used for radiomicsbased analysis in which 195 features were extracted and classified according to their BRAF status via a support vector machine. The BRAF status of 53 study patients, with 54 brain metastases (25 positive, 29 negative for BRAF mutation) was predicted with mean accuracy = 0.79 ± 0.13, mean precision = 0.77 ± 0.14, mean sensitivity = 0.72 ± 0.20, mean specificity = 0.83 ± 0.11 and with a 0.78 area under the receiver operating characteristic curve for positive BRAf mutation prediction. Radiomics-based noninvasive genetic characterization is feasible and should be further verified using large prospective cohorts. Melanoma is the third most common cutaneous tumor after basal cell carcinoma and squamous cell carcinoma. Melanomas account for up to 1.6% of newly diagnosed malignancies in the developed world 1. The worldwide incidence of malignant melanoma is rising, with approximately 290,000 new cases diagnosed per year, resulting in up to 60,000 mortalities 2. Systemic melanoma carries a high risk of central nervous system (CNS) spread 3. Up to 75% of stage IV patients with systemic melanoma eventually develop CNS metastases, which account for up to 50% of melanoma-related mortalities 4,5. The risk of brain metastases from melanoma (BMM) rises with disease duration. While 20-30% of patients will develop BMM in one year, 30-40% will develop BMM in 3 years 6. Identification of BRAF activating mutation as a key oncogene in approximately half of all melanomas has dramatically changed the current treatment strategy for metastatic melanoma 7-10. BRAF mutation has been assumed to be an early evolutionary event in tumor maturation, and play a central role in melanoma pathogenesis 11. At the cellular level, BRAF mutations drive oncogenic behavior of melanoma cells, leading to unrestricted cell growth, increased cell survival, and local invasion through activation of the mitogen-...

show abstract

Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis

Cited by 126 publications

References 35 publications

Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation

Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation

PET/MRI Radiomics in Patients With Brain Metastases

Virtual biopsy using MRI radiomics for prediction of BRAF status in melanoma brain metastasis

Contact Info

Product

Resources

About