A radiomics-based model for predicting local control of resected brain metastases receiving adjuvant SRS

Prediction of the treatment response and local failure of patients with brain metastasis treated with stereotactic radiosurgery using machine learning: A systematic review and meta-analysis

BACKGROUND

Stereotactic radiosurgery (SRS) effectively treats brain metastases. It can provide local control, symptom relief, and improved survival rates, but it poses challenges in selecting optimal candidates, determining dose and fractionation, monitoring for toxicity, and integrating with other modalities. Practical tools to predict patient outcomes are also needed. Machine learning (ML) is currently used to predict treatment outcomes. We aim to investigate the accuracy of ML in predicting treatment response and local failure of brain metastasis treated with SRS.

METHODS

PubMed, Scopus, Web of Science (WoS), and Embase were searched until April 16th, which was repeated on October 17th, 2023 to find possible relevant papers. The study preparation adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline. The statistical analysis was performed by the MIDAS package of STATA v.17.

RESULTS

A total of 17 articles were reviewed, of which seven and eleven were related to the clinical use of ML in predicting local failure and treatment response. The ML algorithms showed sensitivity and specificity of 0.89 (95% CI: 0.84-0.93) and 0.87 (95% CI: 0.81-0.92) for predicting treatment response. The positive likelihood ratio was 7.1 (95% CI: 4.5-11.1), the negative likelihood ratio was 0.13 (95% CI: 0.08-0.19), and the diagnostic odds ratio was 56 (95% CI: 25-125). Moreover, the pooled estimates for sensitivity and specificity of ML algorithms for predicting local failure were 0.93 (95% CI: 0.76-0.98) and 0.80 (95% CI: 0.53-0.94). The positive likelihood ratio was 4.7 (95% CI: 1.6-14.0), the negative likelihood ratio was 0.09 (95% CI: 0.02-0.39), and the diagnostic odds ratio was 53 (95% CI: 5-606).

CONCLUSION

ML holds promise in predicting treatment response and local failure in brain metastasis patients receiving SRS. However, further studies and improvements in the treatment process can refine the models and effectively integrate them into clinical practice.

Predicting stereotactic radiosurgery outcomes with multi-observer qualitative appearance labelling versus MRI radiomics

Qualitative observer-based and quantitative radiomics-based analyses of T1w contrast-enhanced magnetic resonance imaging (T1w-CE MRI) have both been shown to predict the outcomes of brain metastasis (BM) stereotactic radiosurgery (SRS). Comparison of these methods and interpretation of radiomics-based machine learning (ML) models remains limited. To address this need, we collected a dataset of n = 123 BMs from 99 patients including 12 clinical features, 107 pre-treatment T1w-CE MRI radiomic features, and BM post-SRS progression scores. A previously published outcome model using SRS dose prescription and five-way BM qualitative appearance scoring was evaluated. We found high qualitative scoring interobserver variability across five observers that negatively impacted the model's risk stratification. Radiomics-based ML models trained to replicate the qualitative scoring did so with high accuracy (bootstrap-corrected AUC = 0.84-0.94), but risk stratification using these replicated qualitative scores remained poor. Radiomics-based ML models trained to directly predict post-SRS progression offered enhanced risk stratification (Kaplan-Meier rank-sum p = 0.0003) compared to using qualitative appearance. The qualitative appearance scoring enabled interpretation of the progression radiomics-based ML model, with necrotic BMs and a subset of heterogeneous BMs predicted as being at high-risk of post-SRS progression, in agreement with current radiobiological understanding. Our study's results show that while radiomics-based SRS outcome models out-perform qualitative appearance analysis, qualitative appearance still provides critical insight into ML model operation.

Application of artificial intelligence to stereotactic radiosurgery for intracranial lesions: detection, segmentation, and outcome prediction

BACKGROUND

Rapid evolution of artificial intelligence (AI) prompted its wide application in healthcare systems. Stereotactic radiosurgery served as a good candidate for AI model development and achieved encouraging result in recent years. This article aimed at demonstrating current AI application in radiosurgery.

METHODS

Literatures published in PubMed during 2010-2022, discussing AI application in stereotactic radiosurgery were reviewed.

RESULTS

AI algorithms, especially machine learning/deep learning models, have been administered to different aspect of stereotactic radiosurgery. Spontaneous tumor detection and automated lesion delineation or segmentation were two of the promising application, which could be further extended to longitudinal treatment follow-up. Outcome prediction utilized machine learning algorithms with radiomic-based analysis was another well-established application.

CONCLUSIONS

Stereotactic radiosurgery has taken a lead role in AI development. Current achievement, limitation, and further investigation was summarized in this article.

Dual-center validation of using magnetic resonance imaging radiomics to predict stereotactic radiosurgery outcomes

Background

MRI radiomic features and machine learning have been used to predict brain metastasis (BM) stereotactic radiosurgery (SRS) outcomes. Previous studies used only single-center datasets, representing a significant barrier to clinical translation and further research. This study, therefore, presents the first dual-center validation of these techniques.

Methods

SRS datasets were acquired from 2 centers (n = 123 BMs and n = 117 BMs). Each dataset contained 8 clinical features, 107 pretreatment T1w contrast-enhanced MRI radiomic features, and post-SRS BM progression endpoints determined from follow-up MRI. Random decision forest models were used with clinical and/or radiomic features to predict progression. 250 bootstrap repetitions were used for single-center experiments.

Results

Training a model with one center's dataset and testing it with the other center's dataset required using a set of features important for outcome prediction at both centers, and achieved area under the receiver operating characteristic curve (AUC) values up to 0.70. A model training methodology developed using the first center's dataset was locked and externally validated with the second center's dataset, achieving a bootstrap-corrected AUC of 0.80. Lastly, models trained on pooled data from both centers offered balanced accuracy across centers with an overall bootstrap-corrected AUC of 0.78.

Conclusions

Using the presented validated methodology, radiomic models trained at a single center can be used externally, though they must utilize features important across all centers. These models' accuracies are inferior to those of models trained using each individual center's data. Pooling data across centers shows accurate and balanced performance, though further validation is required.

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

Recent studies have used T1w contrast-enhanced (T1w-CE) magnetic resonance imaging (MRI) radiomic features and machine learning to predict post-stereotactic radiosurgery (SRS) brain metastasis (BM) progression, but have not examined the effects of combining clinical and radiomic features, BM primary cancer, BM volume effects, and using multiple scanner models. To investigate these effects, a dataset of n = 123 BMs from 99 SRS patients with 12 clinical features, 107 pre-treatment T1w-CE radiomic features, and BM progression determined by follow-up MRI was used with a random decision forest model and 250 bootstrapped repetitions. Repeat experiments assessed the relative accuracy across primary cancer sites, BM volume groups, and scanner model pairings. Correction for accuracy imbalances across volume groups was investigated by removing volume-correlated features. We found that using clinical and radiomic features together produced the most accurate model with a bootstrap-corrected area under the receiver operating characteristic curve of 0.77. Accuracy also varied by primary cancer site, BM volume, and scanner model pairings. The effect of BM volume was eliminated by removing features at a volume-correlation coefficient threshold of 0.25. These results show that feature type, primary cancer, volume, and scanner model are all critical factors in the accuracy of radiomics-based prognostic models for BM SRS that must be characterised and controlled for before clinical translation.

The effect of time delay for magnetic resonance contrast-enhanced scan on imaging for small-volume brain metastases

PURPOSE

To study the effect of different enhancement timings of magnetic resonance (MR) on small-volume brain metastases (BM) visualisation and provide a basis for the contour of tumour targets.

METHOD

We prospectively enrolled 101 patients with BM who received radiotherapy. All patients underwent computed tomography (CT) and MR simulations. Contrast-enhanced MR scans at 1, 3, 5, 10, 18, and 20 min after injection of contrast medium were performed. The tumour target was determined on MR images at different enhancement times, and the differences of tumour target volume, maximum diameter, and MR signal intensity were compared.

RESULTS

(1) Of the 453 metastatic lesions, 24 (5.2 %) were not detected at 1 min and 8 (1.8 %) were not detected at 3 min; however, all metastases were detected after 5 min. The volume and maximum diameter of the 28 (6.2 %) metastases were stable at any time. (2) The average volume of metastatic lesions at 1, 3, 5, 10, 18, and 20 min was 0.09 cm³, 0.10 cm³, 0.12 cm³, 0.12 cm³, 0.13 cm³, and 0.13 cm³, respectively. Compared to 1 min, BM volume at other times increased by 13.1 %, 21.5 %, 31.6 %, 39.6 %, and 41.7 %, and the difference between the maximum and minimum volumes was statistically significant (p < 0.05). (3) The distribution of the maximum ratio of tumours to white matter mean signal intensity at different times were 39.6 %, 20 %, 14.6 %, 8.0 %, 10.4 %, and 10 %, respectively.

CONCLUSION

The visualisation of small-volume BM was significantly different at different enhancement times. Our results suggest that multi-timing enhancement scans for small-volume BM should be implemented and that scanning at >10 min is essential.

Artificial Intelligence for Survival Prediction in Brain Tumors on Neuroimaging

Survival prediction of patients affected by brain tumors provides essential information to guide surgical planning, adjuvant treatment selection, and patient counseling. Current reliance on clinical factors, such as Karnofsky Performance Status Scale, and simplistic radiological characteristics are, however, inadequate for survival prediction in tumors such as glioma that demonstrate molecular and clinical heterogeneity with variable survival outcomes. Advances in the domain of artificial intelligence have afforded powerful tools to capture a large number of hidden high-dimensional imaging features that reflect abundant information about tumor structure and physiology. Here, we provide an overview of current literature that apply computational analysis tools such as radiomics and machine learning methods to the pipeline of image preprocessing, tumor segmentation, feature extraction, and construction of classifiers to establish survival prediction models based on neuroimaging. We also discuss challenges relating to the development and evaluation of such models and explore ethical issues surrounding the future use of machine learning predictions.

Radiomics-guided radiation therapy: opportunities and challenges

Radiomics is an advanced image-processing framework, which extracts image features and considers them as biomarkers towards personalized medicine. Applications include disease detection, diagnosis, prognosis, and therapy response assessment/prediction. As radiation therapy aims for further individualized treatments, radiomics could play a critical role in various steps before, during and after treatment. Elucidation of the concept of radiomics-guided radiation therapy (RGRT) is the aim of this review, attempting to highlight opportunities and challenges underlying the use of radiomics to guide clinicians and physicists towards more effective radiation treatments. This work identifies the value of RGRT in various steps of radiotherapy from patient selection to follow-up, and subsequently provides recommendations to improve future radiotherapy using quantitative imaging features.

Measuring the bias of incorrect application of feature selection when using cross-validation in radiomics

BACKGROUND

Many studies in radiomics are using feature selection methods to identify the most predictive features. At the same time, they employ cross-validation to estimate the performance of the developed models. However, if the feature selection is performed before the cross-validation, data leakage can occur, and the results can be biased. To measure the extent of this bias, we collected ten publicly available radiomics datasets and conducted two experiments. First, the models were developed by incorrectly applying the feature selection prior to cross-validation. Then, the same experiment was conducted by applying feature selection correctly within cross-validation to each fold. The resulting models were then evaluated against each other in terms of AUC-ROC, AUC-F1, and Accuracy.

RESULTS

Applying the feature selection incorrectly prior to the cross-validation showed a bias of up to 0.15 in AUC-ROC, 0.29 in AUC-F1, and 0.17 in Accuracy.

CONCLUSIONS

Incorrect application of feature selection and cross-validation can lead to highly biased results for radiomic datasets.