Analysis of the difference between Alzheimer's disease, mild cognitive impairment and normal people by using fractal dimensions and small-world network.

This research examined the distinctions in brain network characteristics among individuals with Alzheimer's disease (AD), mild cognitive impairment (MCI), and a control group. Magnetic resonance imaging (MRI) and mini-mental state examination (MMSE) data were retrieved from the Alzheimer's Disease Neuroimaging Initiative (ANDI) database, comprising 40 subjects in each group. Correlation maps for evaluating brain network connectivity were generated using fractal dimension (FD) analysis, a method capable of quantifying morphological changes in cortical and cerebral regions. Employing graph theory, each parcellated brain region was represented as a node, and edges between nodes were utilized to compute small-world network properties for each group. In the comparison between control and AD demonstrated the significantly lower FD values (P<0.05) in temporal lobe, motor cortex, part of occipital and parietal, hippocampus, amygdala, and entorhinal cortex, which present the atrophy. Similarly, comparing control group to MCIs, regions closely associated with memory, such as the hippocampus, showed significantly lower FD values. Furthermore, both AD and MCI groups displayed diminished connectivity and decreased network efficiency. In conclusion, fractal dimension (FD) analysis illustrate the progression of structural declination from mild cognitive impairment (MCI) to Alzheimer's disease (AD). Additionally, structural small-world network analysis presents itself as a potential method for assessing network efficiency and the progression of AD. Moving forward, further clinical assessments are warranted to validate the findings observed in this study.

Shortened Cerebral Circulation Time Predicts Resistance to Obliteration in High-Flow Brain Arteriovenous Malformations After Stereotactic Radiosurgery.

BACKGROUND AND OBJECTIVES: Treatment selection for brain arteriovenous malformations (BAVMs) is complicated by BAVM size, location, and hemodynamics. Quantitative digital subtraction angiography is used to quantify the hemodynamic impact of BAVMs on cerebral circulation. This study investigated the association between cerebral circulation time and the complete obliteration (CO) rate of BAVMs after stereotactic radiosurgery (SRS). METHODS: We analyzed the data of 143 patients who underwent SRS for BAVMs between January 2011 and December 2019 in our institute. Their pre-SRS magnetic resonance imaging and angiography images were analyzed to acquire BAVM characteristics and quantitative digital subtraction angiography parameters. Modified cerebral circulation time (mCCT) was defined as the time difference between the bolus arrival time of the ipsilateral cavernous internal carotid artery and that of the parietal vein, as determined from the lateral view of images obtained using digital subtraction angiography. Cox regression with hazard ratios and Kaplan-Meier analyses were conducted to determine the associations between the parameters and BAVM CO after SRS. RESULTS: Of the 143 patients, 101 (70.6%) achieved BAVM CO. According to the multivariate analyses, an increased mCCT (hazard ratio: 1.24, P = .041) was the independent factor associated with BAVM CO after adjustment for age, sex, hemorrhagic presentation, a BAVM volume of >5 cm3, and a margin dose of >18 Gy. Individuals with an mCCT of ≤2.32 s had a lower 36-month probability of BAVM CO than did those with an mCCT of >2.32 s (44.1% ± 6.8% vs 63.3% ± 5.6%, P = .034). CONCLUSION: The hemodynamic impact of high-flow BAVM demonstrated by a shortened mCCT is associated with a lower BAVM CO rate after SRS.

Vascular compactness of unruptured brain arteriovenous malformation predicts risk of hemorrhage after stereotactic radiosurgery.

The aim of the study was to investigate whether morphology (i.e. compact/diffuse) of brain arteriovenous malformations (bAVMs) correlates with the incidence of hemorrhagic events in patients receiving Stereotactic Radiosurgery (SRS) for unruptured bAVMs. This retrospective study included 262 adult patients with unruptured bAVMs who underwent upfront SRS. Hemorrhagic events were defined as evidence of blood on CT or MRI. The morphology of bAVMs was evaluated using automated segmentation which calculated the proportion of vessel, brain tissue, and cerebrospinal fluid in bAVMs on T2-weighted MRI. Compactness index, defined as the ratio of vessel to brain tissue, categorized bAVMs into compact and diffuse types based on the optimal cutoff. Cox proportional hazard model was used to identify the independent factors for post-SRS hemorrhage. The median clinical follow-ups was 62.1 months. Post-SRS hemorrhage occurred in 13 (5.0%) patients and one of them had two bleeds, resulting in an annual bleeding rate of 0.8%. Multivariable analysis revealed bAVM morphology (compact versus diffuse), bAVM volume, and prescribed margin dose were significant predictors. The post-SRS hemorrhage rate increased with larger bAVM volume only among the diffuse nidi (1.7 versus 14.9 versus 30.6 hemorrhage per 1000 person-years in bAVM volume < 20 cm3 versus 20-40 cm3 versus > 40 cm3; p = 0.022). The significantly higher post-SRS hemorrhage rate of Spetzler-Martin grade IV-V compared with grade I-III bAVMs (20.0 versus 3.3 hemorrhages per 1000 person-years; p = 0.001) mainly originated from the diffuse bAVMs rather than the compact subgroup (30.9 versus 4.8 hemorrhages per 1000 person-years; p = 0.035). Compact and smaller bAVMs, with higher prescribed margin dose harbor lower risks of post-SRS hemorrhage. The post-SRS hemorrhage rate exceeded 2.2% annually within the diffuse and large (> 40 cm3) bAVMs and the diffuse Spetzler-Martin IV-V bAVMs. These findings may help guide patient selection of SRS for the unruptured bAVMs.

Natural History and Histopathology of Expanding Cysts and Hematomas After Stereotactic Radiosurgery for Arteriovenous Malformations of the Brain: A Case Series.

BACKGROUND: We reviewed the clinical course and histopathologic findings for cases involving the formation of expanding cysts and/or hematomas after gamma knife surgery (GKS) for arteriovenous malformations (AVMs). METHODS: We report a single-center retrospective review of 18 patients who presented with cyst and/or hematoma expansion after GKS for AVMs between 1993 and 2023. Expanding cysts and hematomas were defined as well-demarcated cavities filled with fluid or well-marginated heterogenous hematomas presenting with expansion proximal to or in the location of the original AVM, respectively. Patient demographics, AVM characteristics, history of interventions and surgeries, and imaging and histopathologic features of expanding cysts and hematomas were collected for analysis. RESULTS: Among 1072 AVM patients treated using GKS, 18 presented with expanding cysts or hematomas during a total follow-up period of 16,757 patient-years (0.11 case/100 persons/patient-year). The time to cyst or hematoma identification was 4-13 years after initial GKS, with a mean duration of 8.6 years. Among the patients examined, 7 (38.9%) presented mainly with hematoma, 10 (55.6%) presented mainly with cysts, and 1 presented with approximately equal components of both. Among the 18 patients, 13 (72.2%) underwent craniotomy to treat cyst or hematoma expansion. All the specimens had similar histopathologic characteristics, including organizing hematoma with fresh and old hemorrhage, fibrinoid necrosis of the vessels, gliosis of normal brain tissue, infiltration of hemosiderin-laden histiocytes, and extravascular protein leakage. CONCLUSIONS: Our findings suggest that the formation of these 2 complications can be attributed to a common mechanism involving radiation-induced vascular damage in brain tissue adjacent to the AVM and subsequent chronic inflammation and capillary dilatation.

Stereotactic radiosurgery for orbital cavernous hemangiomas.

OBJECTIVE: The goal of this study was to assess the safety and efficacy of single-session Gamma Knife radiosurgery (GKRS) for orbital cavernous hemangiomas (OCHs). METHODS: Patients who presented with an OCH between September 1999 and May 2022 and were treated with single-session GKRS were included in this single-center cohort study. RESULTS: There were 23 patients (7 males and 16 females) in this study. The median margin dose was 12 Gy (range 11-13 Gy). The median clinical and radiological follow-ups were 45 months (range 5-190 months) and 45 months (range 6-190 months), respectively. Nine (69.2%) of 13 patients with visual acuity impairment had improvement in best corrected visual acuity. Of the 8 patients with visual field defects, 5 patients (62.5%) had complete resolution. Tumor regression was observed in 22 patients (95.7%). The mean relative reduction in tumor volume was 82.6% ± 23.7%. The relative reductions in tumor volume were 33%, 49%, 72%, 84%, and 89% at 6, 12, 24, 36, and 48 months, respectively. Adverse effects of radiation were not observed. CONCLUSIONS: GKRS appears to be safe and efficacious for treating OCHs over long-term follow-up. The treatment is associated with a high rate of regression in OCHs and remarkable improvement in both visual acuity and visual field deficits.

Is it advisable to perform radiosurgery for EGFR-TKI-controlled brain metastases? A retrospective study of the role of radiosurgery in lung cancer treatment.

PURPOSE: Given the availability of TKIs with high central nervous system efficacy, the question arises as to whether upfront SRS provides additional clinical benefits. The goal of this study was to characterize the clinical outcomes of SRS as salvage therapy for TKI-uncontrolled BMs. METHODS: This retrospective study included EGFR-mutant NSCLC patients presenting BMs at the time of primary tumor diagnosis. BMs were categorized into three subgroups, referred to as "Nature of TKI-treated BMs", "TKI-controlled brain metastases ± SRS", and "SRS salvage therapy". The first subgroup analysis characterized the effects of TKIs on tumor behavior. In the second subgroup, we compared outcomes of TKI-controlled BMs treated with TKI alone versus those treated with combined TKI-SRS therapy. The third subgroup characterized the outcomes of TKI-uncontrolled BMs treated with SRS as salvage therapy Clinical outcomes include local and distant tumor control. RESULTS: This study included 106 patients with a total of 683 BMs. TKI treatment achieved control in 63% of local tumors at 24 months. Among the TKI-controlled BMs, local tumor control was significantly higher in the combined TKI-SRS group (93%) than in the TKI-alone group (65%) at 24 months (p < 0.001). No differences were observed between the two groups in terms of distant tumor control (p = 0.832). In dealing with TKI-uncontrolled BMs, salvage SRS achieved local tumor control in 58% of BMs at 24 months. CONCLUSIONS: While upfront TKI alone proved highly effective in BM control, this study also demonstrated the outcomes of SRS when implemented concurrently with TKI or as salvage therapy for TKI-uncontrolled BMs. This study also presents a strategy of the precise timing and targeting of SRS to lesions in progression.

Improved survival and intracranial tumor control of EGFR-mutated NSCLC patients with newly developed brain metastases following stereotactic radiosurgery and EGFR-TKI: a large retrospective cohort study and meta-analyses.

PURPOSE: To examine the differential effects of SRS and TKI on EGFR-mutated NSCLC patients with brain metastases (BMs) and outcomes following continuation of the same TKI agent in case of new BMs. METHODS: This study included 608 NSCLC patients (2,274 BMs) while meta-analyses included 1,651 NSCLC patients (> 3,944 BMs). Overall survival (OS) and intracranial progression free survival (iPFS) were estimated using Kaplan-Meier methods. Hazard ratios (95% CI) of prognostic factors were estimated using Cox regression models. RESULTS: The median OS/iPFS (95% CI) (months) for patients with wildtype EGFR/ALK, EGFR mutations, and ALK rearrangements were 17.7 (12.9-23.6)/12.1 (9.8-15.6), 28.9 (23.8-33.3)/17.7 (14.8-21.2), and 118.0 (not reached)/71.7 (15.1-not reached), respectively. In EGFR-mutated patients, meta-analyses combining our data showed significantly improved OS and iPFS of patients who received SRS and TKI (OS:35.1 months, iPFS:20.0 months) when compared to those who have SRS alone (OS:20.8 months, iPFS:11.8 months) or TKI alone (OS:24.3 months, iPFS:13.8 months). Having SRS for newly diagnosed BMs while keeping the existing TKI agent yielded OS (30.0 vs. 32.1 months, p = 0.200) non-inferior to patients who started combined SRS and TKI therapy for their newly diagnosed NSCLC with BMs. Multivariable analyses showed that good performance score and TKI therapy were associated with improved outcomes. CONCLUSIONS: Combined SRS and TKI resulted in favorable outcomes in EGFR-mutated NSCLC patients with newly diagnosed BMs. Continuation of the same TKI agent plus SRS in case of new brain metastases yielded good clinical outcomes and may be considered a standard-of-care treatment.

Federated Learning: A Cross-Institutional Feasibility Study of Deep Learning Based Intracranial Tumor Delineation Framework for Stereotactic Radiosurgery.

BACKGROUND: Deep learning-based segmentation algorithms usually required large or multi-institute data sets to improve the performance and ability of generalization. However, protecting patient privacy is a key concern in the multi-institutional studies when conventional centralized learning (CL) is used. PURPOSE: To explores the feasibility of a proposed lesion delineation for stereotactic radiosurgery (SRS) scheme for federated learning (FL), which can solve decentralization and privacy protection concerns. STUDY TYPE: Retrospective. SUBJECTS: 506 and 118 vestibular schwannoma patients aged 15-88 and 22-85 from two institutes, respectively; 1069 and 256 meningioma patients aged 12-91 and 23-85, respectively; 574 and 705 brain metastasis patients aged 26-92 and 28-89, respectively. FIELD STRENGTH/SEQUENCE: 1.5T, spin-echo, and gradient-echo [Correction added after first online publication on 21 August 2023. Field Strength has been changed to "1.5T" from "5T" in this sentence.]. ASSESSMENT: The proposed lesion delineation method was integrated into an FL framework, and CL models were established as the baseline. The effect of image standardization strategies was also explored. The dice coefficient was used to evaluate the segmentation between the predicted delineation and the ground truth, which was manual delineated by neurosurgeons and a neuroradiologist. STATISTICAL TESTS: The paired t-test was applied to compare the mean for the evaluated dice scores (p < 0.05). RESULTS: FL performed the comparable mean dice coefficient to CL for the testing set of Taipei Veterans General Hospital regardless of standardization and parameter; for the Taichung Veterans General Hospital data, CL significantly (p < 0.05) outperformed FL while using bi-parameter, but comparable results while using single-parameter. For the non-SRS data, FL achieved the comparable applicability to CL with mean dice 0.78 versus 0.78 (without standardization), and outperformed to the baseline models of two institutes. DATA CONCLUSION: The proposed lesion delineation successfully implemented into an FL framework. The FL models were applicable on SRS data of each participating institute, and the FL exhibited comparable mean dice coefficient to CL on non-SRS dataset. Standardization strategies would be recommended when FL is used. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 1.

Association Between Pseudoprogression of Vestibular Schwannoma After Radiosurgery and Radiological Features of Solid and Cystic Components.

BACKGROUND AND OBJECTIVES: The pathophysiology of vestibular schwannoma (VS) pseudoprogression after Gamma Knife radiosurgery (GKRS) remains unclear. Radiological features in pretreatment magnetic resonance images may help predict VS pseudoprogression. This study used VS radiological features quantified using an automated segmentation algorithm to predict pseudoprogression after GKRS treatment. METHODS: This is a retrospective study comprising 330 patients with VS who received GKRS. After image preprocessing and T2W/contrast-enhanced T1-weighted image (CET1W) image generation, with fuzzy C-means clustering, VSs were segmented into solid and cystic components and classified as solid and cystic. Relevant radiological features were then extracted. The response to GKRS was classified into "nonpseudoprogression" and "pseudoprogression/fluctuation". The Z test for two proportions was used to compare solid and cystic VS for the likelihood of pseudoprogression/fluctuation. Logistic regression was used to assess the correlation between clinical variables and radiological features and response to GKRS. RESULTS: The likelihood of pseudoprogression/fluctuation after GKRS was significantly higher for solid VS compared with cystic VS (55% vs 31%, P < .001). For the entire VS cohort, multivariable logistic regression revealed that a lower mean tumor signal intensity (SI) in T2W/CET1W images was associated with pseudoprogression/fluctuation after GKRS ( P = .001). For the solid VS subgroup, a lower mean tumor SI in T2W/CET1W images ( P = .035) was associated with pseudoprogression/fluctuation after GKRS. For the cystic VS subgroup, a lower mean SI of the cystic component in T2W/CET1W images ( P = .040) was associated with pseudoprogression/fluctuation after GKRS. CONCLUSION: Pseudoprogression is more likely to occur in solid VS compared with cystic VS. Quantitative radiological features in pretreatment magnetic resonance images were associated with pseudoprogression after GKRS. In T2W/CET1W images, solid VS with a lower mean tumor SI and cystic VS with a lower mean SI of cystic component were more likely to have pseudoprogression after GKRS. These radiological features can help predict the likelihood of pseudoprogression after GKRS.

Risk for Brain Arteriovenous Malformation Rupture During Pregnancy and Puerperium.

BACKGROUND: The hemorrhage risk of unruptured and untreated cerebral arteriovenous malformations (AVMs) has been shown to be higher for female patients than male patients in their child bearing ages. Although it has been neurosurgical practice to advise female patients in their childbearing ages to postpone pregnancy until proven AVM obliteration, there is no literature consensus regarding this potential hemorrhage risk increase. OBJECTIVE: To accurately quantify the risk increase for AVM hemorrhage during pregnancy. METHODS: This study is based on data from previous publications, consisting of known age at the first AVM hemorrhage in 3425 patients. The risk increase during pregnancy could be calculated from the difference in age distribution for the first AVM hemorrhage between male patients and female patients, taking the average pregnancy time per female into account. A comparison was also made with data for all hospital discharges (13 751) in Germany 2008 to 2018 with the diagnosis brain AVM. RESULTS: The average pregnancy and puerperium time was 1.54 years per female in the patient population, which was used to determine the annual AVM hemorrhage risk during pregnancy to be around 9%. The increased risk during pregnancy was further evidenced by analysis of a subgroup of 105 female patients, for which pregnancy status at the time of hemorrhage was known. CONCLUSION: The quantified annual risk for AVM hemorrhage during pregnancy is about 3 times higher than that of male patients at corresponding age. This provides an important basis for advising female patients with patent AVMs about the increased risk for hemorrhage that a pregnancy would entail.

Predicting survival after radiosurgery in patients with lung cancer brain metastases using deep learning of radiomics and EGFR status.

The early prediction of overall survival (OS) in patients with lung cancer brain metastases (BMs) after Gamma Knife radiosurgery (GKRS) can facilitate patient management and outcome improvement. However, the disease progression is influenced by multiple factors, such as patient characteristics and treatment strategies, and hence satisfactory performance of OS prediction remains challenging. Accordingly, we proposed a deep learning approach based on comprehensive predictors, including clinical, imaging, and genetic information, to accomplish reliable and personalized OS prediction in patients with BMs after receiving GKRS. Overall 1793 radiomic features extracted from pre-GKRS magnetic resonance images (MRI), clinical information, and epidermal growth factor receptor (EGFR) mutation status were retrospectively collected from 237 BM patients who underwent GKRS. DeepSurv, a multi-layer perceptron model, with 4 different aggregation methods of radiomics was applied to predict personalized survival curves and survival status at 3, 6, 12, and 24 months. The model combining clinical features, EGFR status, and radiomics from the largest BM showed the best prediction performance with concordance index of 0.75 and achieved areas under the curve of 0.82, 0.80, 0.84, and 0.92 for predicting survival status at 3, 6, 12, and 24 months, respectively. The DeepSurv model showed a significant improvement (p < 0.001) in concordance index compared to the validated lung cancer BM prognostic molecular markers. Furthermore, the model provided a novel estimate of the risk-of-death period for patients. The personalized survival curves generated by the DeepSurv model effectively predicted the risk-of-death period which could facilitate personalized management of patients with lung cancer BMs.

Gamma Knife Radiosurgery Irradiation of Surgical Cavity of Brain Metastases: Factor Analysis and Gene Mutations.

(1) Background: Surgical resection for the removal of brain metastases often fails to prevent tumor recurrence within the surgical cavity; hence, researchers are divided as to the benefits of radiation treatment following surgical resection. This retrospective study assessed the effects of post-operative stereotactic radiosurgery (SRS) on local tumor control and overall survival. (2) Methods: This study examined the demographics, original tumor characteristics, and surgical outcomes of 97 patients who underwent Gamma Knife Radiosurgery (GKRS) treatment (103 brain metastases). Kaplan-Meier plots and Cox regression were used to correlate clinical features to tumor control and overall survival. (3) Results: The overall tumor control rate was 75.0% and overall 12-month survival was 89.6%. Tumor control rates in the radiation group versus the non-radiation group were as follows: 12 months (83.1% vs. 57.7%) and 24 months (66.1% vs. 50.5%). During the 2-year follow-up period after SRS, the intracranial response rate was higher in the post-craniotomy radiation group than in the non-radiation group (p = 0.027). Cox regression multivariate analysis determined that post-craniotomy irradiation of the surgical cavity is predictive of tumor control (p = 0.035). However, EGFR mutation was not predictive of overall survival or tumor control. (4) Conclusions: Irradiating the surgical cavity after surgery can enhance local tumor control; however, it does not have a significant effect on overall survival.

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.

Stereotactic radiosurgery for pituitary and cavernous sinus metastases.

PURPOSE: Metastases extending to the pituitary gland and cavernous sinus are extremely rare; however, advances in neuroimaging have increased the reported incidence. Stereotactic radiosurgery (SRS) affords the precise delivery of focused radiation to minimize adverse radiation effects. This study assessed the efficacy and safety of SRS in the treatment of pituitary and cavernous sinus metastases. METHODS: Analysis was performed on 23 patients with pituitary and cavernous sinus metastases who underwent treatment using SRS between 1996 and 2021. The cohort was categorized into 2 groups in terms of metastasis location: pituitary involvement (Group 1, n = 11) and cavernous sinus involvement (Group 2, n = 12). Overall survival, local tumor control, and distal tumor control rates were compared between the two groups using Kaplan-Meier analysis. RESULTS: The median age of the cohort was 52.2 years and the median tumor volume was 4.5 mL. Overall survival rates were as follows: 1 year (72.9%), 2 years (51.8%), and 3 years (45.3%). Local tumor control rates were as follows: 1 year (82.3%), 2 years (82.3%), and 3 years (65.9%). Visual deficit and hypopituitarism were the most common presentations in Group 1, whereas cranial nerve deficit was the most common presentation in Group 2. CONCLUSIONS: SRS appears to be a safe and effective therapy for the treatment of pituitary and cavernous sinus metastases. GKRS is a relatively simple procedure, which places minimal stress on the patient, thereby facilitating further anti-cancer treatment. Considering the limited survival duration in cases of metastasis, it is very likely that post-GKRS complications (e.g., new onset cranial nerve deficit and hypopituitarism) would not become an issue before patient passes away.

Magnetic resonance imaging signal characteristics associated with prognosis of skull base chordoma after gamma knife radiosurgery.

OBJECTIVE: To investigate the association between the magnetic resonance imaging (MRI) signal characteristics of skull base chordoma and radiosurgical outcomes. METHODS: Twenty-four patients with skull base chordomas treated with Gamma Knife radiosurgery (GKRS) after previous surgical resection were retrospectively (2001-2021) examined. Pre-GKRS MRIs were analyzed for RT2 (tumor-to-brainstem signal intensity ratio on T2-weighted imaging), RCE (tumor-to-brainstem signal intensity ratio on contrast-enhanced T1-weighted imaging), and mean apparent diffusion coefficient (ADC). Correlations of the parameters with patient survival and local tumor progression were made by using Cox regression and Kaplan-Meier analyses. RESULTS: During a median follow-up of 46 months after GKRS, 9 patients died with significantly more local tumor progression events (median number: 2 vs 0, P = .012) than did 15 alive patients. On multivariable analysis, higher mean ADC was associated with longer patient survival (P = .016) after GKRS. The actuarial 5-year overall survival rates were 88.9% versus 54.7% for chordomas with an ADC of ≥ 1270 × 10-6 mm2/s versus < 1270 × 10-6 mm2/s. RT2 < 1.5 (P = .038) and RCE > 1.57 (P = .022) were associated with a lower probability of local tumor control. CONCLUSION: Lower mean ADC values are associated with shorter patient survival in skull base chordomas after GKRS. Diffusion-weighted imaging may help in GKRS planning and outcome prediction for these patients.

Lesion delineation framework for vestibular schwannoma, meningioma and brain metastasis for gamma knife radiosurgery using stereotactic magnetic resonance images.

BACKGROUND AND OBJECTIVE: GKRS is an effective treatment for smaller intracranial tumors with a high control rate and low risk of complications. Target delineation in medical MR images is essential in the planning of GKRS and follow-up. A deep learning-based algorithm can effectively segment the targets from medical images and has been widely explored. However, state-of-the-art deep learning-based target delineation uses fixed sizes, and the isotropic voxel size may not be suitable for stereotactic MR images which use different anisotropic voxel sizes and numbers of slices according to the lesion size and location for clinical GKRS planning. This study developed an automatic deep learning-based segmentation scheme for stereotactic MR images. METHODS: We retrospectively collected stereotactic MR images from 506 patients with VS, 1,069 patients with meningioma and 574 patients with BM who had been treated using GKRS; the lesion contours and individual T1W+C and T2W MR images were extracted from the GammaPlan system. The three-dimensional patching-based training strategy and dual-pathway architecture were used to manage inconsistent FOVs and anisotropic voxel size. Furthermore, we used two-parametric MR image as training input to segment the regions with different image characteristics (e.g., cystic lesions) effectively. RESULTS: Our results for VS and BM demonstrated that the model trained using two-parametric MR images significantly outperformed the model trained using single-parametric images with median Dice coefficients (0.91, 0.05 versus 0.90, 0.06, and 0.82, 0.23 versus 0.78, 0.34, respectively), whereas predicted delineations in meningiomas using the dual-pathway model were dominated by single-parametric images (median Dice coefficients 0.83, 0.17 versus 0.84, 0.22). Finally, we combined three data sets to train the models, achieving the comparable or even higher testing median Dice (VS: 0.91, 0.07; meningioma: 0.83, 0.22; BM: 0.84, 0.23) in three diseases while using two-parametric as input. CONCLUSIONS: Our proposed deep learning-based tumor segmentation scheme was successfully applied to multiple types of intracranial tumor (VS, meningioma and BM) undergoing GKRS and for segmenting the tumor effectively from stereotactic MR image volumes for use in GKRS planning.

Leukoencephalopathy in patients with brain metastases who received radiosurgery with or without whole brain radiotherapy.

BACKGROUND: Whole brain radiation therapy (WBRT) for brain metastases (BMs) is a common cause of radiation-induced leukoencephalopathy; however the safety of alternative stereotactic radiosurgery (SRS) remains unclear. This study examined the incidence of leukoencephalopathy in patients treated with SRS alone versus WBRT plus SRS for BMs with a focus on the relationship between prognostic factors and leukoencephalopathy. METHODS: Analysis was performed between 2002 and 2021. The total enrollment was 993 patients with the distribution: WBRT plus SRS (n = 291) and SRS only (n = 702). Leukoencephalopathy was graded from 0 to 3 for changes in white matter indicated by the MRI after WBRT or SRS. Patient characteristics and SRS dosimetric parameters were reviewed to identify factors that contributed to the incidence of leukoencephalopathy or overall survival. RESULTS: The incidence of leukoencephalopathy was consistently higher in WBRT plus SRS group than in SRS alone group (p < 0.001). Leukoencephalopathy was also associated with a larger total tumor volume (≧28cm3; p = 0.028) and age (> 77 years; p = 0.025). Nonetheless, the SRS integral dose to skull in the subgroup of WBRT plus SRS treatment was not demonstrated significance in development of leukoencephalopathy (p = 0.986 for integral dose 1-2 J, p = 0.776 for integral dose > 2 J). CONCLUSIONS: This study revealed that SRS is safe for oligo-BMs in terms of leukoencephalopathy development. Patient age and total tumor volume were identified as important factors in assessing the development of leukoencephalopathy. The additional of SRS (even at an integral dose > 2 J) did not increase the incidence of leukoencephalopathy.

Natural history of lung squamous cell brain metastases in patients treated with radiosurgery: a thirty-year experience at a tertiary medical center.

PURPOSE: In this study we report our 30-year experience in stereotactic radiosurgery (SRS) treatment of lung squamous cell carcinoma (LUSC) brain metastases (BMs). It will serve to provide detailed longitudinal outcomes and predictors of efficacy in treating LUSC-BMs with SRS. METHOD: We retrospectively reviewed 51 patients and 109 tumors treated with SRS at our center between 1993 and 2022. Patient demographics, PDL1 genotype, immunotherapy use and mortality cause were recorded. Radiological and clinical outcomes were followed at 1-3-month intervals post-SRS. Cox-regression analysis and Kaplan-Meier survival curves were performed in statistical analysis. RESULTS: We included 37 male and 14 female patients (median age 62.7 years at BM diagnosis). Median overall survival (OS) time was 6.9 months, 6-month OS rate was 62.1%, and Karnofsky performance scale (KPS) was the only independent predictor. Median time for local control maintenance was 7.6 months, 6-month local control rate was 69.1%, with TKI as the only independent predictor. Median time to distant failure was 5.13 months, 6-month distant failure rate was 51.1%, and factors with significant impact included gender (p = 0.002), presence of extracranial metastases (p < 0.001), use of immunotherapy(p < 0.001), PDL1 genotype (p = 0.034), and total intracranial metastases number (p = 0.008). However, no definitive benefits of immunotherapy were identified in patients with higher PDL1 mutational tumors. CONCLUSION: In this study we defined the natural history of disease progression and outcomes in SRS-treated LUSC-BM patients. We also identified predictors of OS and tumor control among these patients. The findings of this study will serve as a guide when counseling these patients for SRS.

Compactness index: a radiosurgery outcome predictor for patients with unruptured brain arteriovenous malformations.

OBJECTIVE: The goal of the study was to define and quantify brain arteriovenous malformation (bAVM) compactness and to assess its effect on outcomes after Gamma Knife radiosurgery (GKRS) for unruptured bAVMs. METHODS: Unsupervised machine learning with fuzzy c-means clustering was used to differentiate the tissue constituents of bAVMs on T2-weighted MR images. The percentages of vessel, brain, and CSF were quantified. The proposed compactness index, defined as the ratio of vasculature tissue to brain tissue, categorized bAVM morphology into compact, intermediate, and diffuse types according to the tertiles of this index. The outcomes of interest were complete obliteration and radiation-induced changes (RICs). RESULTS: A total of 209 unruptured bAVMs treated with GKRS were retrospectively included. The median imaging and clinical follow-up periods were 49.2 and 72.3 months, respectively. One hundred seventy-three bAVMs (82.8%) achieved complete obliteration after a median latency period of 43.3 months. The rates of RIC and permanent RIC were 76.1% and 3.8%, respectively. Post-GKRS hemorrhage occurred in 14 patients (6.7%), resulting in an annual bleeding risk of 1.0%. Compact bAVM, smaller bAVM volume, and exclusively superficial venous drainage were independent predictors of complete obliteration. Diffuse bAVM morphology, larger bAVM volume, and higher margin dose were independently associated with RICs. CONCLUSIONS: The compactness index quantitatively describes the compactness of unruptured bAVMs. Moreover, compact bAVMs may have a higher obliteration rate and a smaller risk of RICs than diffuse bAVMs. This finding could help guide decision-making regarding GKRS treatment for patients with unruptured bAVMs.