Radiomics outperforms semantic features for prediction of response to stereotactic radiosurgery in brain metastases

Gutsche, Robin; Lohmann, Philipp; Hoevels, Mauritius; Rueß, Daniel; Galldiks, Norbert; Visser-Vanderwalle, Veerle; Treuer, Harald; Ruge, Maximilian I.; Köcher, Martin

doi:10.1016/j.radonc.2021.11.010

Cited by 13 publications

(19 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The exception was the study of Jiang et al, but since their methodology rejected BMs < 10 mm in diameter and did not find volume to be a univariate predictor of SRS response, it is not surprising that no volume-correlated radiomic features were found to be important 15 . Gutsche et al removed volume-correlated radiomic features, but only at a correlation coefficient > 0.9, and so retained many features that remained strongly correlated with volume 16 .…”

Section: Discussionmentioning

confidence: 99%

“…Given the drop in accuracy when including the Avanto scanner, it is likely that current literature results are optimistic compared to expected results during external validation using a different scanner model. Some studies in this area have used datasets with more than one scanner 13 , 16 , 17 . Mulford et al employed a 1.5 T and 3 T scanner, but 96% of the data was from the 1.5 T scanner, likely masking any 3 T scanner effects.…”

Section: Discussionmentioning

confidence: 99%

“…Previous studies have reported on prediction of SRS outcomes for BMs treated with Gamma Knife or Cyber Knife. 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] .…”

mentioning

confidence: 99%

See 2 more Smart Citations

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

DeVries

Lagerwaard

Zindler

et al. 2022

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

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

DeVries

Lagerwaard

Zindler

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…One group compared radiomic features to CE patterns defined by three radiologists as either homogenous, heterogeneous, or necrotic ring-like from CE-T1W, T2W, and FLAIR images as predictors of patient response to SRS. 67 Their best-performing model integrated both radiomic and semantic features for classification by a random forest algorithm.…”

Section: Radiomics As a Clinical Toolmentioning

confidence: 99%

“…Moreover, despite the inherent advantages of high-order image analysis, it is not a complete replacement for traditional semantic analyses performed by radiologists, as evident by several publications outlined in this review. 64 , 67 Multi-dimensional data integration will be a key feature in future radiomics studies. This will expand past clinically relevant data such as patient age, sex, and primary site of origin to also include pathologic and genetic information to improve model performance.…”

Section: Radiomics As a Clinical Toolmentioning

confidence: 99%

Radiomics as an emerging tool in the management of brain metastases

Nowakowski

Lahijanian

Panet-Raymond

et al. 2022

Neuro-Oncology Advances

View full text Add to dashboard Cite

Brain metastases (BM) are associated with significant morbidity and mortality in patients with advanced cancer. Despite significant advances in surgical, radiation, and systemic therapy in recent years, the median overall survival of patients with BM is less than one year. The acquisition of medical images, such as computed tomography (CT) and magnetic resonance imaging (MRI), is critical for the diagnosis and stratification of patients to appropriate treatments. Radiomic analyses have the potential to improve the standard of care for patients with BM by applying artificial intelligence (AI) with already acquired medical images to predict clinical outcomes and direct the personalized care of BM patients. Herein, we outline the existing literature applying radiomics for the clinical management of BM. This includes predicting patient response to radiotherapy and identifying radiation necrosis, performing virtual biopsies to predict tumor mutation status, and determining the cancer of origin in brain tumors identified via imaging. With further development, radiomics has the potential to aid in BM patient stratification while circumventing the need for invasive tissue sampling, particularly for patients not eligible for surgical resection.

show abstract

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

Habibi,

Rashidi,

Habibzadeh

et al. 2024

Neurosurg Rev

View full text Add to dashboard Cite

Radiomics outperforms semantic features for prediction of response to stereotactic radiosurgery in brain metastases

Cited by 13 publications

References 23 publications

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

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

Radiomics as an emerging tool in the management of brain metastases

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

Contact Info

Product

Resources

About