Results of Surgical Resection for Progression of Brain Metastases Previously Treatedby Gamma Knife Radiosurgery

Truong, Minh Tam; Clair, Eric G. St.; Donahue, Bernadine R.; Rush, Stephen; Miller, Douglas C.; Formenti, Silvia C.; Knopp, Edmond A.; Han, Kerry; Golfinos, John G.

doi:10.1227/01.neu.0000243287.91167.a7

Cited by 19 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The local outcome was categorized as either LC (complete response, partial response, or stable disease) or LF (progressive disease) based on the response determined in the last follow-up session. Using serial imaging (including perfusion MRI) and/or histological confirmation, the adverse radiation effect (ARE) was diagnosed and distinguished from local progression [ 25 ], based on the report by Sneed et al [ 11 ]. Following these criteria, a total of 93 and 63 lesions were classified as LC and LF, respectively.…”

Section: Methodsmentioning

confidence: 99%

Impact of Tumour Segmentation Accuracy on Efficacy of Quantitative MRI Biomarkers of Radiotherapy Outcome in Brain Metastasis

Jalalifar

Soliman

Sahgal

et al. 2022

Cancers

View full text Add to dashboard Cite

Significantly affecting patients’ clinical course and quality of life, a growing number of cancer cases are diagnosed with brain metastasis (BM) annually. Stereotactic radiotherapy is now a major treatment option for patients with BM. However, it may take months before the local response of BM to stereotactic radiation treatment is apparent on standard follow-up imaging. While machine learning in conjunction with radiomics has shown great promise in predicting the local response of BM before or early after radiotherapy, further development and widespread application of such techniques has been hindered by their dependency on manual tumour delineation. In this study, we explored the impact of using less-accurate automatically generated segmentation masks on the efficacy of radiomic features for radiotherapy outcome prediction in BM. The findings of this study demonstrate that while the effect of tumour delineation accuracy is substantial for segmentation models with lower dice scores (dice score ≤ 0.85), radiomic features and prediction models are rather resilient to imperfections in the produced tumour masks. Specifically, the selected radiomic features (six shared features out of seven) and performance of the prediction model (accuracy of 80% versus 80%, AUC of 0.81 versus 0.78) were fairly similar for the ground-truth and automatically generated segmentation masks, with dice scores close to 0.90. The positive outcome of this work paves the way for adopting high-throughput automatically generated tumour masks for discovering diagnostic and prognostic imaging biomarkers in BM without sacrificing accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

Impact of Tumour Segmentation Accuracy on Efficacy of Quantitative MRI Biomarkers of Radiotherapy Outcome in Brain Metastasis

Jalalifar

Soliman

Sahgal

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…According to the first domain of the QUADAS-2 criteria, shown in supplementary Fig. 1.A, patient selection showed a high risk of bias in 12 out of 37 studies [29][30][31][32][33][34][35][36][37][38][39][40]. Some of these studies used selection criteria which could induce bias, such as excluding patients who used dexamethasone or showed clinical deterioration [33,34].…”

Section: Methodological Quality Of the Included Studiesmentioning

confidence: 99%

“…In the index test domain, 16 out of 37 studies showed a high risk of bias, because for these studies it was unknown if the results of the index test were interpreted with or without knowledge of the reference test [30,35,36,[40][41][42][43][44][45][46][47][48][49][50][51][52]. Also, in many studies (n = 17), a predefined cut-off value of the index test was missing [30,31,[33][34][35][36][37][38]41,42,[44][45][46][53][54][55][56]. In the reference test domain, 9 out of 37 studies showed a high risk of bias [30,31,33,37,47,50-5 2,57], mainly because of the choice of the reference test.…”

Section: Methodological Quality Of the Included Studiesmentioning

confidence: 99%

“…In the reference test domain, 9 out of 37 studies showed a high risk of bias [30,31,33,37,47,50-5 2,57], mainly because of the choice of the reference test. In the flow and timing domain, 17 out of 37 studies showed a high risk of bias [4,[30][31][32][33][36][37][38]41,42,44,45,51,52,56,58,59], which was mostly due to the fact that it was not always clear if all patients had the same reference test. It was also not always clear what the timing of the reference test was.…”

Section: Methodological Quality Of the Included Studiesmentioning

confidence: 99%

“…Besides anatomical images, all conventional MRI studies used additional analytical techniques (such as radiomics features). Seven studies used DWI [33,34,37,42,49,54,60], twelve DSC perfusion MRI [29,38,39,41,47,54,[58][59][60][62][63][64], four dynamic contrast enhanced (DCE) perfusion MRI [31,37,43,54], four magnetic resonance spectroscopy (MRS) [30,51,59,60], and one study used arterial spin labelling (ASL) perfusion MRI [35]. Lastly, six data sets (five derived from three studies and one separate study) used combined MRI techniques to calculate sensitivity and specificity [33,34,50,62].…”

Section: Diagnostic Accuracymentioning

confidence: 99%

See 2 more Smart Citations

Diagnostic accuracy of MRI techniques for treatment response evaluation in patients with brain metastasis: A systematic review and meta-analysis

Teunissen

Govaerts

Kramer

et al. 2022

Radiotherapy and Oncology

View full text Add to dashboard Cite

Predicting the outcome of radiotherapy in brain metastasis by integrating the clinical and MRI‐based deep learning features

et al. 2022

View full text Add to dashboard Cite

Background A considerable proportion of metastatic brain tumors progress locally despite stereotactic radiation treatment, and it can take months before such local progression is evident on follow‐up imaging. Prediction of radiotherapy outcome in terms of tumor local failure is crucial for these patients and can facilitate treatment adjustments or allow for early salvage therapies. Purpose In this work, a novel deep learning architecture is introduced to predict the outcome of local control/failure in brain metastasis treated with stereotactic radiation therapy using treatment‐planning magnetic resonance imaging (MRI) and standard clinical attributes. Methods At the core of the proposed architecture is an InceptionResentV2 network to extract distinct features from each MRI slice for local outcome prediction. A recurrent or transformer network is integrated into the architecture to incorporate spatial dependencies between MRI slices into the predictive modeling. A visualization method based on prediction difference analysis is coupled with the deep learning model to illustrate how different regions of each lesion on MRI contribute to the model's prediction. The model was trained and optimized using the data acquired from 99 patients (116 lesions) and evaluated on an independent test set of 25 patients (40 lesions). Results The results demonstrate the promising potential of the MRI deep learning features for outcome prediction, outperforming standard clinical variables. The prediction model with only clinical variables demonstrated an area under the receiver operating characteristic curve (AUC) of 0.68. The MRI deep learning models resulted in AUCs in the range of 0.72 to 0.83 depending on the mechanism to integrate information from MRI slices of each lesion. The best prediction performance (AUC = 0.86) was associated with the model that combined the MRI deep learning features with clinical variables and incorporated the inter‐slice dependencies using a long short‐term memory recurrent network. The visualization results highlighted the importance of tumor/lesion margins in local outcome prediction for brain metastasis. Conclusions The promising results of this study show the possibility of early prediction of radiotherapy outcome for brain metastasis via deep learning of MRI and clinical attributes at pre‐treatment and encourage future studies on larger groups of patients treated with other radiotherapy modalities.

show abstract

Results of Surgical Resection for Progression of Brain Metastases Previously Treatedby Gamma Knife Radiosurgery

Cited by 19 publications

References 28 publications

Impact of Tumour Segmentation Accuracy on Efficacy of Quantitative MRI Biomarkers of Radiotherapy Outcome in Brain Metastasis

Impact of Tumour Segmentation Accuracy on Efficacy of Quantitative MRI Biomarkers of Radiotherapy Outcome in Brain Metastasis

Diagnostic accuracy of MRI techniques for treatment response evaluation in patients with brain metastasis: A systematic review and meta-analysis

Predicting the outcome of radiotherapy in brain metastasis by integrating the clinical and MRI‐based deep learning features

Contact Info

Product

Resources

About