eICAB: A novel deep learning pipeline for Circle of Willis multiclass segmentation and analysis.

BACKGROUND: The accurate segmentation, labeling and quantification of cerebral blood vessels on MR imaging is important for basic and clinical research, yet results are not generalizable, and often require user intervention. New methods are needed to automate this process. PURPOSE: To automatically segment, label and quantify Circle of Willis (CW) arteries on Magnetic Resonance Angiography images using deep convolutional neural networks. MATERIALS AND METHODS: MRA images were pooled from three public and private databases. A total of 116 subjects (mean age 56 years ± 21 [standard deviation]; 72 women) were used to make up the training set (N=101) and the testing set (N=15). In each image, fourteen arterial segments making up or surrounding the CW were manually annotated and validated by a clinical expert. Convolutional neural network (CNN) models were trained on a training set to be finally combined in an ensemble to develop eICAB. Model performances were evaluated using (1) quantitative analysis (dice score on test set) and (2) qualitative analysis (external datasets, N=121). The reliability was assessed using multiple MRAs of healthy participants (ICC of vessel diameters and volumes on test-retest). RESULTS: Qualitative analysis showed that eICAB correctly predicted the large, medium and small arteries in 99±0.4%, 97±1% and 88±7% of all images, respectively. For quantitative assessment, the average dice score coefficients for the large (ICAs, BA), medium (ACAs, MCAs, PCAs-P2), and small (AComm, PComm, PCAs-P1) vessels were 0.76±0.07, 0.76±0.08 and 0.41±0.27, respectively. These results were similar and, in some cases, statistically better (p<0.05) than inter-expert annotation variability and robust to image SNR. Finally, test-retest analysis showed that the model yielded high diameter and volume reliability (ICC=0.99). CONCLUSION: We have developed a quick and reliable open-source CNN-based method capable of accurately segmenting and labeling the CW in MRA images. This method is largely independent of image quality. In the future, we foresee this approach as a critical step towards fully automated analysis of MRA databases in basic and clinical research.

Skull Base Meningiomas in Patients with Neurofibromatosis Type 2: An International Multicenter Study Evaluating Stereotactic Radiosurgery.

Objective Meningiomas are the second most common tumors in neurofibromatosis type 2 (NF-2). Microsurgery is challenging in NF-2 patients presenting with skull base meningiomas due to the intrinsic risks and need for multiple interventions over time. We analyzed treatment outcomes and complications after primary Gamma Knife radiosurgery (GKRS) to delineate its role in the management of these tumors. Methods An international multicenter retrospective study approved by the International Radiosurgery Research Foundation was performed. NF-2 patients with at least one growing and/or symptomatic skull base meningioma and 6-month follow-up after primary GKRS were included. Clinical and radiosurgical parameters were recorded for analysis. Results In total, 22 NF-2 patients with 54 skull base meningiomas receiving GKRS as primary treatment met inclusion criteria. Median age at GKRS was 38 years (10-79 years). Most lesions were located in the posterior fossa (55.6%). Actuarial progression free survival (PFS) rates were 98.1% at 2 years and 90.0% at 5 and 10 years. The median follow-up time after initial GKRS was 5.0 years (0.6-25.5 years). Tumor volume at GKRS was a predictor of tumor control. Lesions >5.5 cc presented higher chances to progress after radiosurgery ( p = 0.043). Three patients (13.64%) developed adverse radiation effects. No malignant transformation or death due to meningioma or radiosurgery was reported. Conclusions GKRS is effective and safe in the management of skull base meningiomas in NF-2 patients. Tumor volume deserve greater relevance during clinical decision-making regarding the most appropriate time to treat. GKRS offers a minimally invasive approach of particular interest in this specific group of patients.

Tractostorm 2: Optimizing tractography dissection reproducibility with segmentation protocol dissemination.

The segmentation of brain structures is a key component of many neuroimaging studies. Consistent anatomical definitions are crucial to ensure consensus on the position and shape of brain structures, but segmentations are prone to variation in their interpretation and execution. White-matter (WM) pathways are global structures of the brain defined by local landmarks, which leads to anatomical definitions being difficult to convey, learn, or teach. Moreover, the complex shape of WM pathways and their representation using tractography (streamlines) make the design and evaluation of dissection protocols difficult and time-consuming. The first iteration of Tractostorm quantified the variability of a pyramidal tract dissection protocol and compared results between experts in neuroanatomy and nonexperts. Despite virtual dissection being used for decades, in-depth investigations of how learning or practicing such protocols impact dissection results are nonexistent. To begin to fill the gap, we evaluate an online educational tractography course and investigate the impact learning and practicing a dissection protocol has on interrater (groupwise) reproducibility. To generate the required data to quantify reproducibility across raters and time, 20 independent raters performed dissections of three bundles of interest on five Human Connectome Project subjects, each with four timepoints. Our investigation shows that the dissection protocol in conjunction with an online course achieves a high level of reproducibility (between 0.85 and 0.90 for the voxel-based Dice score) for the three bundles of interest and remains stable over time (repetition of the protocol). Suggesting that once raters are familiar with the software and tasks at hand, their interpretation and execution at the group level do not drastically vary. When compared to previous work that used a different method of communication for the protocol, our results show that incorporating a virtual educational session increased reproducibility. Insights from this work may be used to improve the future design of WM pathway dissection protocols and to further inform neuroanatomical definitions.

Stereotactic radiosurgery for clinoid meningiomas: a multi-institutional study.

PURPOSE: Resection of clinoid meningiomas can be associated with significant morbidity. Experience with stereotactic radiosurgery (SRS) for clinoid meningiomas remains limited. We studied the safety and effectiveness of SRS for clinoid meningiomas. METHODS: From twelve institutions participating in the International Radiosurgery Research Foundation, we pooled patients treated with SRS for radiologically suspected or histologically confirmed WHO grade I clinoid meningiomas. RESULTS: Two hundred seven patients (median age: 56 years) underwent SRS for clinoid meningiomas. Median treatment volume was 8.02 cm3, and 87% of tumors were immediately adjacent to the optic apparatus. The median tumor prescription dose was 12 Gy, and the median maximal dose to the anterior optic apparatus was 8.5 Gy. During a median post-SRS imaging follow-up of 51.1 months, 7% of patients experienced tumor progression. Greater margin SRS dose (HR = 0.700, p = 0.007) and pre-SRS radiotherapy (HR = 0.004, p < 0.001) were independent predictors of better tumor control. During median visual follow-up of 48 months, visual function declined in 8% of patients. Pre-SRS visual deficit (HR = 2.938, p = 0.048) and maximal radiation dose to the optic apparatus of ≥ 10 Gy (HR = 11.297, p = 0.02) independently predicted greater risk of post-SRS visual decline. Four patients experienced new post-SRS cranial nerve V neuropathy. CONCLUSIONS: SRS allows durable control of clinoid meningiomas and visual preservation in the majority of patients. Greater radiosurgical prescription dose is associated with better tumor control. Radiation dose to the optic apparatus of ≥ 10 Gy and visual impairment before the SRS increase risk of visual deterioration.

Stereotactic Radiosurgery for Perioptic Meningiomas: An International, Multicenter Study.

BACKGROUND: Stereotactic radiosurgery (SRS) is increasingly used for management of perioptic meningiomas. OBJECTIVE: To study the safety and effectiveness of SRS for perioptic meningiomas. METHODS: From 12 institutions participating in the International Radiosurgery Research Foundation (IRRF), we retrospectively assessed treatment parameters and outcomes following SRS for meningiomas located within 3 mm of the optic apparatus. RESULTS: A total of 438 patients (median age 51 yr) underwent SRS for histologically confirmed (29%) or radiologically suspected (71%) perioptic meningiomas. Median treatment volume was 8.01 cm3. Median prescription dose was 12 Gy, and median dose to the optic apparatus was 8.50 Gy. A total of 405 patients (93%) underwent single-fraction SRS and 33 patients (7%) underwent hypofractionated SRS. During median imaging follow-up of 55.6 mo (range: 3.15-239 mo), 33 (8%) patients experienced tumor progression. Actuarial 5-yr and 10-yr progression-free survival was 96% and 89%, respectively. Prescription dose of ≥12 Gy (HR: 0.310; 95% CI [0.141-0.679], P = .003) and single-fraction SRS (HR: 0.078; 95% CI [0.016-0.395], P = .002) were associated with improved tumor control. A total of 31 (10%) patients experienced visual decline, with actuarial 5-yr and 10-yr post-SRS visual decline rates of 9% and 21%, respectively. Maximum dose to the optic apparatus ≥10 Gy (HR = 2.370; 95% CI [1.086-5.172], P = .03) and tumor progression (HR = 4.340; 95% CI [2.070-9.097], P < .001) were independent predictors of post-SRS visual decline. CONCLUSION: SRS provides durable tumor control and quite acceptable rates of vision preservation in perioptic meningiomas. Margin dose of ≥12 Gy is associated with improved tumor control, while a dose to the optic apparatus of ≥10 Gy and tumor progression are associated with post-SRS visual decline.

Convexity Meningiomas in Patients with Neurofibromatosis Type 2: Long-Term Outcomes After Gamma Knife Radiosurgery.

BACKGROUND: Convexity meningiomas are common tumors requiring treatment in patients with neurofibromatosis type 2 (NF2). Although different therapeutic options are described for sporadic convexity meningioma, much less is known about these lesions in patients with NF2 despite their distinct biology and need for multiple treatments. We analyzed the value of Gamma Knife radiosurgery (GKRS) as definitive treatment for convexity meningiomas in patients with NF2. METHODS: This international multicenter retrospective study was approved by the International Radiosurgery Research Foundation. Patients with NF2 with at least 1 convexity meningioma and 6-month follow-up after primary GKRS were included. RESULTS: Inclusion criteria were met by 18 patients with NF2. A total of 120 convexity meningiomas (median treatment volume, 0.66 cm3 [range, 0.10-21.20 cm3]) were analyzed. Median follow-up after initial GKRS was 15.6 years (range, 0.6-25.5 years). Median age at GKRS was 32.5 years (range, 16-53 years). Median number of meningiomas per patient was 13 (range, 1-27), and median number of convexity lesions receiving GKRS per patient was 3.5 (range, 1-27). One case of tumor progression was reported 24 years after GKRS, leading to actuarial progression-free survival rates of 100% at 2, 5, and 10 years. No malignant transformation or death due to meningioma or radiosurgery was recorded. CONCLUSIONS: GKRS is safe and effective as definitive treatment of small to medium-sized convexity meningiomas in patients with NF2. Despite concerns about the particular mutational burden of these tumors, no malignant transformation manifested after treatment. GKRS represents a minimally invasive option that offers long-term tumor control to this specific group of patients.