Contrast-enhanced T1-weighted image radiomics of brain metastases may predict EGFR mutation status in primary lung cancer

Abstract

Identification of EGFR mutations is critical to the treatment of primary lung cancer and brain metastases (BMs). Here, we explored whether radiomic features of contrast-enhanced T1-weighted images (T1WIs) of BMs predict EGFR mutation status in primary lung cancer cases. In total, 1209 features were extracted from the contrast-enhanced T1WIs of 61 patients with 210 measurable BMs. Feature selection and classification were optimized using several machine learning algorithms. Ten-fold cross-validation was applied to the T1WI BM dataset (189 BMs for training and 21 BMs for the test set). Area under receiver operating characteristic curves (AUC), accuracy, sensitivity, and specificity were calculated. Subgroup analyses were also performed according to metastasis size. For all measurable BMs, random forest (RF) classification with RF selection demonstrated the highest diagnostic performance for identifying EGFR mutation (AUC: 86.81). Support vector machine and AdaBoost were comparable to RF classification. Subgroup analyses revealed that small BMs had the highest AUC (89.09). The diagnostic performance for large BMs was lower than that for small BMs (the highest AUC: 78.22). Contrast-enhanced T1-weighted image radiomics of brain metastases predicted the EGFR mutation status of lung cancer BMs with good diagnostic performance. However, further study is necessary to apply this algorithm more widely and to larger BMs.

Quality of Radiomics Research on Brain Metastasis: A Roadmap to Promote Clinical Translation

“…The characteristics of the 29 included radiomics studies [ 13 15 16 17 18 19 22 24 25 26 28 29 30 31 32 33 35 37 38 39 40 51 ] are documented in Table 1 . In the included studies, the median number of patients included was 77 (range, 24–439).…”

“…Although previous radiomics studies in the field of neuro-oncology have mainly focused on gliomas [ 7 8 9 10 11 12 ], there has been an increase in the number of studies on brain metastases. Indeed, radiomics studies have demonstrated promising results in the discrimination of brain metastasis from other tumors [ 13 14 15 16 17 18 19 20 ], identification of primary tumor types in patients with brain metastases [ 21 22 23 24 ], prediction of specific genetic mutations [ 25 26 27 28 29 ], prediction of survival [ 30 31 ], differentiation between radiation necrosis and brain metastasis [ 32 33 34 35 ], and prediction of outcome after radiosurgery [ 36 37 38 39 40 41 ]. However, such studies on brain metastases are confined within the limits of experimental settings, without translation into real-world clinical settings [ 42 ].…”

Current Advances and Challenges in Radiomics of Brain Tumors

“…Approximately 20% of the cancer patients with other primary sites develop brain metastases, outnumbering primary brain tumors 10:1, but the actual statistic is estimated to be even more since plenty of them do not go through regular MRI examination. The top three extracranial primary cancer types with high intracranial metastatic tendency are lung cancer, breast cancer, and melanoma, which respectively have incidences up to 20-56%, 5-20%, and 7-16% (107)(108)(109)(110). Meanwhile, the incidence of brain metastases' occurrence after primary cancer varies according to race, age, and primary cancer.…”

Predicting EGFR Mutation Status by a Deep Learning Approach in Patients with Non-Small Cell Lung Cancer Brain Metastases

“…Indeed DL methodologies have become the state-of-the-art approach in various computer imaging capabilities, with extensive applications in medical image analysis [19][20][21]. Several studies have investigated the feasibility of conventional machine learning methods for the differentiation of NSCLC molecular subtypes, 2 of which targeted BM and used a radiomics approach [22,23]. While radiomics has been suggested to have a real clinical impact in lung cancer [24], it also harbors some structured limitations [25,26].…”