A priori prediction of local failure in brain metastasis after hypo-fractionated stereotactic radiotherapy using quantitative MRI and machine learning

Abstract

This study investigated the effectiveness of pre-treatment quantitative MRI and clinical features along with machine learning techniques to predict local failure in patients with brain metastasis treated with hypo-fractionated stereotactic radiation therapy (SRT). The predictive models were developed using the data from 100 patients (141 lesions) and evaluated on an independent test set with data from 20 patients (30 lesions). Quantitative MRI radiomic features were derived from the treatment-planning contrast-enhanced T1w and T2-FLAIR images. A multi-phase feature reduction and selection procedure was applied to construct an optimal quantitative MRI biomarker for predicting therapy outcome. The performance of standard clinical features in therapy outcome prediction was evaluated using a similar procedure. Survival analyses were conducted to compare the long-term outcome of the two patient cohorts (local control/failure) identified based on prediction at pre-treatment, and standard clinical criteria at last patient follow-up after SRT. The developed quantitative MRI biomarker consists of four features with two features quantifying heterogeneity in the edema region, one feature characterizing intra-tumour heterogeneity, and one feature describing tumour morphology. The predictive models with the radiomic and clinical feature sets yielded an AUC of 0.87 and 0.62, respectively on the independent test set. Incorporating radiomic features into the clinical predictive model improved the AUC of the model by up to 16%, relatively. A statistically significant difference was observed in survival of the two patient cohorts identified at pre-treatment using the radiomics-based predictive model, and at post-treatment using the the RANO-BM criteria. Results of this study revealed a good potential for quantitative MRI radiomic features at pre-treatment in predicting local failure in relatively large brain metastases undergoing SRT, and is a step forward towards a precision oncology paradigm for brain metastasis.

The emerging potential of quantitative MRI biomarkers for the early prediction of brain metastasis response after stereotactic radiosurgery: a scoping review

“…They found that the addition of the top 10 radiomics features provided additional information regarding the standard routinely available clinical variables for predicting LF in BM following SRS. Similarly, Jaberipour et al ( 32 ) developed a predictive model using the pretreatment qMRI and clinical features of 100 patients, which was evaluated using an independent test set with data from 20 patients. All of the patients with BMs underwent SRT with a total dose of 22.5–35 Gy over 5 fractions.…”

“…With the development of imaging and analysis technologies, qMRI biomarkers for predicting treatment response have gradually been acquired. Several studies (24,25) focused on the quantification of the peritumoral region before irradiation, while others (26)(27)(28)(29)(30)(31)(32)(33)(34)(35) developed optimal quantitative prognostic models (with or without clinical data) by examining multiple geometrical and textural features of MR images pre-SRS with different sophisticated radiomics analysis frameworks to predict early treatment response. However, since the algorithms for image quantification were not standardized, the robustness and reproducibility of the relevant results were poor.…”

Performance sensitivity analysis of brain metastasis stereotactic radiosurgery outcome prediction using MRI radiomics

“…Jiang et al saw no increase in AUC when using radiomic features alone compared to using radiomic and clinical features, though no baseline of using clinical features alone was established 15 . Studies on post-operative BM SRS or SRT found radiomic features outperformed clinical features and that clinical features decreased accuracy when combined with radiomic features 17 , 18 .…”

“…They investigated the use of radiomic features from multiple MRI sequences, the planned SRS dose distribution, and the peri-tumoural region beyond the treated BM [12][13][14][15][16] . There have also been similar studies for BM SRT and post-surgical resection SRS using Gamma Knife [17][18][19] .…”

Artificial Intelligence for Survival Prediction in Brain Tumors on Neuroimaging

“…ML models have been established to predict response to stereotactic radiosurgery or radiation therapy in patients with brain metastasis (BM), specifically BM velocity, 71 local control, [72][73][74][75][76] and to classify true progression. 77,78 Two studies aimed to predict survival in patients with non-small-cell lung cancer and BM.…”