1
|
Meng X, Gao D, He H, Sun S, Liu A, Jin H, Li Y. A Machine Learning Model Predicts the Outcome of SRS for Residual Arteriovenous malformations after partial embolization- A Real-World Clinical Obstacle. World Neurosurg 2022; 163:e73-e82. [PMID: 35276397 DOI: 10.1016/j.wneu.2022.03.007] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2021] [Revised: 02/28/2022] [Accepted: 03/01/2022] [Indexed: 11/30/2022]
Abstract
PURPOSE To propose a machine learning (ML) model predicting the favorable outcome of stereotactic radiosurgery (SRS) for residual brain arteriovenous malformation (bAVM) after partial embolization. MATERIALS AND METHODS One hundred and thirty bAVM patients who underwent partial embolization followed by SRS were retrospectively reviewed. Patients were randomly split into training datasets (n=100) and testing datasets (n=30). Radiomics and dosimetric features were extracted from pre-SRS treatment images. Feature selection was performed to select appropriate radiomics and dosimetric features. Three ML algorithms were applied to construct models using selected features respectively. A total of 9 models were trained to predict favorable outcomes (obliteration without complication) of bAVMs. The efficacy of these models was evaluated on the testing dataset using mean accuracy (ACC) and area under the receiver operating characteristic curve (AUROC). RESULTS The obliteration rate of this cohort was 70.77% (92/130) with a mean follow-up period of 43.8 (Range 12-108 months) months. Favorable outcomes were achieved in 89 (68.46%) patients. Four radiomics features and 7 dosimetric features were selected for ML model construction. The dosimetric SVM showed the best performance on the training dataset, with an ACC and AUC of 0.74 and 0.78 respectively. The dosimetric SVM model also showed the best performance on the testing dataset where the ACC and AUC were 0.83 and 0.77 respectively. CONCLUSION Dosimetric features are good predictors of prognosis for patients with partially embolized bAVM followed by SRS therapy. The use of ML models is an innovative method for predicting favorable outcomes of partially embolized bAVM followed by SRS therapy.
Collapse
Affiliation(s)
- Xiangyu Meng
- Department of Interventional Neuroradiology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; Department of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Dezhi Gao
- Department of Interventional Neuroradiology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; Department of Gamma-Knife Center, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Hongwei He
- Department of Interventional Neuroradiology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; Department of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Shibin Sun
- Department of Interventional Neuroradiology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; Department of Gamma-Knife Center, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Ali Liu
- Department of Interventional Neuroradiology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; Department of Gamma-Knife Center, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Hengwei Jin
- Department of Interventional Neuroradiology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; Department of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
| | - Youxiang Li
- Department of Interventional Neuroradiology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China; Department of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China; Beijing Engineering Research Center, Beijing, China.
| |
Collapse
|
3
|
Xu MC, Khattab MH, Luo G, Sherry AD, Morales-Paliza M, Chaballout BH, Anderson JL, Attia A, Cmelak AJ. Effects of cone versus multi-leaf collimation on dosimetry and neurotoxicity in patients with small arteriovenous malformations treated by stereotactic radiosurgery. JOURNAL OF RADIOSURGERY AND SBRT 2021; 7:287-294. [PMID: 34631230 PMCID: PMC8492055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Subscribe] [Scholar Register] [Received: 10/18/2020] [Accepted: 02/15/2021] [Indexed: 06/13/2023]
Abstract
PURPOSE/OBJECTIVE Linear accelerator (LINAC) based stereotactic radiosurgery (SRS) for arteriovenous malformations (AVMs) is delivered with cone or multileaf collimators (MLCs), and favorable dosimetry is associated with reduced radionecrosis in normal brain tissue. This study aims to determine whether cones or MLCs has better dosimetric characteristics, to predict differences in toxicity. METHODS All patients treated for AVMs using LINAC SRS from 2003-2017 were examined retrospectively. Demographic data, volumes of normal tissue exposed to 12Gy (V12Gy[cc]) and 4Gy (V4Gy[cc]), maximal dose, and dose gradient were analyzed. Univariate and multivariate analyses were used to evaluate relationships between collimator type, dosimetric parameters, and toxicity. Propensity score matching was used to adjust for AVM size. RESULTS Compared to MLC, cones were independently associated with reduced V12Gy[cc] after propensity score matching (p=0.008) and reduced neurotoxicity (p=0.016). Higher V12Gy[cc] (p=0.0008) and V4Gy[cc] (p=0.002) were associated with increased neurotoxicity. CONCLUSIONS Treating AVMs with cone-based SRS over MLC-based SRS may improve dosimetry and reduce toxicities.
Collapse
Affiliation(s)
- Mark C Xu
- Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Mohamed H Khattab
- Department of Radiation Oncology, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Guozhen Luo
- Department of Radiation Oncology, Vanderbilt University Medical Center, Nashville, TN, USA
| | | | - Manuel Morales-Paliza
- Department of Radiation Oncology, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Basil H. Chaballout
- University of South Carolina School of Medicine Greenville, Greenville, SC, USA
| | | | - Albert Attia
- Department of Radiation Oncology, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Anthony J Cmelak
- Department of Radiation Oncology, Vanderbilt University Medical Center, Nashville, TN, USA
| |
Collapse
|
4
|
Jacob J, Reyns N, Valéry CA, Feuvret L, Simon JM, Mazeron JJ, Jenny C, Cuttat M, Maingon P, Pasquier D. Radiotherapy of non-tumoral refractory neurological pathologies. Cancer Radiother 2020; 24:523-533. [PMID: 32859467 DOI: 10.1016/j.canrad.2020.06.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2020] [Revised: 06/09/2020] [Accepted: 06/12/2020] [Indexed: 10/23/2022]
Abstract
Intracranial radiotherapy has been improved, primarily because of the development of stereotactic approaches. While intracranial stereotactic body radiotherapy is mainly indicated for treatment of benign or malignant tumors, this procedure is also effective in the management of other neurological pathologies; it is delivered using GammaKnife® and linear accelerators. Thus, brain arteriovenous malformations in patients who are likely to experience permanent neurological sequelae can be managed by single session intracranial stereotactic body radiotherapy, or radiosurgery, in specific situations, with an advantageous benefit/risk ratio. Radiosurgery can be recommended for patients with disabling symptoms, which are poorly controlled by medication, such as trigeminal neuralgia, and tremors, whether they are essential or secondary to Parkinson's disease. This literature review aims at defining the place of intracranial stereotactic body radiotherapy in the management of patients suffering from non-tumoral refractory neurological pathologies. It is clear that the multidisciplinary collaboration of experienced teams from Neurosurgery, Neurology, Neuroradiology, Radiation Oncology and Medical Physics is needed for the procedures using high precision radiotherapy techniques, which deliver high doses to locations near functional brain areas.
Collapse
Affiliation(s)
- J Jacob
- Sorbonne Université, Assistance Publique-Hôpitaux de Paris, Groupe Hospitalier Pitié-Salpêtrière-Charles-Foix, Department of Radiation Oncology, 47-83, boulevard de l'Hôpital, 75013 Paris, France.
| | - N Reyns
- Centre Hospitalier Régional Universitaire de Lille, Department of Neurosurgery and Neuro-Oncology, Neurosurgery service, 2, avenue Oscar-Lambret, 59000 Lille, France; Lille University, Inserm, U1189-ONCO-THAI-Image Assisted Laser Therapy for Oncology, 1, avenue Oscar-Lambret, 59000 Lille, France
| | - C-A Valéry
- Sorbonne Université, Assistance Publique-Hôpitaux de Paris, Groupe Hospitalier Pitié-Salpêtrière-Charles-Foix, Department of Neurosurgery, 47-83, boulevard de l'Hôpital, 75013 Paris, France
| | - L Feuvret
- Sorbonne Université, Assistance Publique-Hôpitaux de Paris, Groupe Hospitalier Pitié-Salpêtrière-Charles-Foix, Department of Radiation Oncology, 47-83, boulevard de l'Hôpital, 75013 Paris, France
| | - J-M Simon
- Sorbonne Université, Assistance Publique-Hôpitaux de Paris, Groupe Hospitalier Pitié-Salpêtrière-Charles-Foix, Department of Radiation Oncology, 47-83, boulevard de l'Hôpital, 75013 Paris, France
| | - J-J Mazeron
- Sorbonne Université, Assistance Publique-Hôpitaux de Paris, Groupe Hospitalier Pitié-Salpêtrière-Charles-Foix, Department of Radiation Oncology, 47-83, boulevard de l'Hôpital, 75013 Paris, France
| | - C Jenny
- Sorbonne Université, Assistance Publique-Hôpitaux de Paris, Groupe Hospitalier Pitié-Salpêtrière-Charles-Foix, Department of Medical Physics, 47-83, boulevard de l'Hôpital, 75013 Paris, France
| | - M Cuttat
- Sorbonne Université, Assistance Publique-Hôpitaux de Paris, Groupe Hospitalier Pitié-Salpêtrière-Charles-Foix, Department of Medical Physics, 47-83, boulevard de l'Hôpital, 75013 Paris, France
| | - P Maingon
- Sorbonne Université, Assistance Publique-Hôpitaux de Paris, Groupe Hospitalier Pitié-Salpêtrière-Charles-Foix, Department of Radiation Oncology, 47-83, boulevard de l'Hôpital, 75013 Paris, France
| | - D Pasquier
- Centre Oscar-Lambret, Academic Department of Radiation Oncology, 3, rue Frédéric-Combemale, 59000 Lille, France; Lille University, Centre de Recherche en Informatique, Signal et Automatique de Lille, CRIStAL UMR 9189, Scientific Campus, bâtiment Esprit, avenue Henri-Poincaré, 59655 Villeneuve-d'Ascq, France
| |
Collapse
|