Intracranial solitary fibrous tumor/hemangiopericytoma: tumor reclassification and assessment of treatment outcome via the 2016 WHO classification

Development of an MRI-Based Comprehensive Model Fusing Clinical, Radiomics and Deep Learning Models for Preoperative Histological Stratification in Intracranial Solitary Fibrous Tumor

BACKGROUND

Accurate preoperative histological stratification (HS) of intracranial solitary fibrous tumors (ISFTs) can help predict patient outcomes and develop personalized treatment plans. However, the role of a comprehensive model based on clinical, radiomics and deep learning (CRDL) features in preoperative HS of ISFT remains unclear.

PURPOSE

To investigate the feasibility of a CRDL model based on magnetic resonance imaging (MRI) in preoperative HS in ISFT.

STUDY TYPE

Retrospective.

POPULATION

Three hundred and ninety-eight patients from Beijing Tiantan Hospital, Capital Medical University (primary training cohort) and 49 patients from Lanzhou University Second Hospital (external validation cohort) with ISFT based on histopathological findings (237 World Health Organization [WHO] tumor grade 1 or 2, and 210 WHO tumor grade 3).

FIELD STRENGTH/SEQUENCE

3.0 T/T1-weighted imaging (T1) by using spin echo sequence, T2-weighted imaging (T2) by using fast spin echo sequence, and T1-weighted contrast-enhanced imaging (T1C) by using two-dimensional fast spin echo sequence.

ASSESSMENT

Area under the receiver operating characteristic curve (AUC) was used to assess the performance of the CRDL model and a clinical model (CM) in preoperative HS in the external validation cohort. The decision curve analysis (DCA) was used to evaluate the clinical net benefit provided by the CRDL model.

STATISTICAL TESTS

Cohen's kappa, intra-/inter-class correlation coefficients (ICCs), Chi-square test, Fisher's exact test, Student's t-test, AUC, DCA, calibration curves, DeLong test. A P value <0.05 was considered statistically significant.

RESULTS

The CRDL model had significantly better discrimination ability than the CM (AUC [95% confidence interval, CI]: 0.895 [0.807-0.912] vs. 0.810 [0.745-0.874], respectively) in the external validation cohort. The CRDL model can provide a clinical net benefit for preoperative HS at a threshold probability >20%.

DATA CONCLUSION

The proposed CRDL model holds promise for preoperative HS in ISFT, which is important for predicting patient outcomes and developing personalized treatment plans.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Evaluation of preoperative magnetic resonance imaging features and diagnostic effectiveness of grades II and III intracranial solitary fibroma

OBJECTIVES

To explore the value of preoperative magnetic resonance imaging (MRI) characterization of intracranial solitary fibrous tumors (ISFT) and to evaluate the effectiveness of preoperative MRI features in predicting pathological grading.

MATERIALS AND METHODS

This retrospective analysis comprised the clinical and preoperative MRI characterization of 55 patients with ISFT in our hospital, including 27 grade II cases and 28 grade III cases confirmed by postoperative pathology. Variables included age, sex, tumor location, cross-midline status, signal characteristics of T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), T2-fluid-attenuated inversion recovery (T2-FLAIR), and diffusion‑weighted imaging (DWI), peritumoral edema, intralesional hemorrhage, focal necrosis/cystic degeneration, tumor empty vessel, maximum tumor diameter, maximum, minimum, and average values of apparent diffusion coefficient (ADCmax, ADCmin, and ADCmean), tumors enhancement mode, meningeal tail sign, skull invasion, cerebral parenchymal invasion, and venous sinus involvement. The independent samples t test or Mann-Whitney U test was performed to compare continuous data between the two groups, and the Pearson chi-squared test or Fisher's exact test was used to compare categorical data. In addition, bivariate logistic regression was performed to construct a comprehensive model, and receiver operating characteristic (ROC) curves were generated to calculate the areas under the curve (AUCs), thereby determining the value of each parameter in the differential diagnosis of grades II and III ISFT.

RESULTS

The mean age at onset was similar between patients with grades II and III ISFT (46.77 ± 14.66 years and 45.82 ± 12.07 years, respectively). The proportions of men among patients with grades II and III ISFT were slightly higher than those of female patients (male/female: 1.25 [15/12] and 1.33 [16/12], respectively). There were significant differences between grades II and III ISFT in the T2-FLAIR and DWI signal characteristics, maximum, minimum, and average values of the apparent diffusion coefficient (ADCmax, ADCmin, and ADCmean), tumor location, and skull invasion (P = 0.001, P = 0.018, P = 0.000, P = 0.000, P = 0.000, P = 0.010, and P = 0.032, respectively). However, no significant differences were noted between grades II and III ISFT in age, sex, cross-midline status, T1WI and T2WI signal characteristics, peritumoral edema, intralesional hemorrhage, focal necrosis/cystic degeneration, tumor empty vessel shadow, enhancement mode, meningeal tail sign, maximum tumor diameter, brain parenchyma invasion, or venous sinus involvement (all P > 0.05). Moreover, binary logistic regression analysis showed that the model accuracy was 89.1% when ADCmin was included in the regression equation. Moreover, ROC curve analysis showed that the AUC of ADCmin was 0.805 (0.688, 0.922), sensitivity was 74.1%, specificity was 75.0%, and the cutoff value was 672 mm2/s.

CONCLUSIONS

Grade III ISFT patients displayed more mixed T2-FLAIR signal characteristics and DWI signal characteristics than grade II patients, as shown by higher skull invasion and tumor mass collapse midline distribution and lower ADCmax, ADCmean, and ADCmin values. The ADCmin value was significant in the preoperative assignment of grades II and III ISFT, thereby contributing to enhanced accuracy in the imaging grading diagnosis of the disease.

Intracranial solitary fibrous tumors: Clinical, radiological, and histopathological insights along with review of literature

BACKGROUND

Intracranial solitary fibrous tumors (SFTs) are rare mesenchymal neoplasms, often challenging to diagnose due to their resemblance to meningiomas and other central nervous system tumors. While advancements in molecular genetics have aided in classification, diagnostic nuances and optimal management strategies remain areas of interest.

MATERIALS AND METHODS

This retrospective study analyzed 11 cases of intracranial SFTs treated at a neurosurgical centre in India between February 2020 and January 2024. Clinical data, radiological findings, histopathological features, and follow-up details were reviewed. Immunohistochemistry, particularly STAT6, facilitated diagnosis confirmation.

RESULTS

The median age of presentation was 32 years, with a male predominance. Headache was the most common presenting symptom, often leading to misdiagnosis as meningiomas on radiological imaging. Histologically, SFTs exhibited spindle to ovoid cells with staghorn vessels and collagenized stroma, posing challenges in differential diagnosis. WHO grading predominantly revealed grade 1 tumors, though recurrence occurred, emphasizing the importance of long-term follow-up. Immunohistochemistry, particularly STAT6, played a pivotal role in distinguishing SFTs from other entities.

CONCLUSION

Intracranial SFTs present diagnostic challenges due to overlapping features with other tumors, warranting a comprehensive approach integrating clinical, radiological, and histopathological findings. Immunohistochemistry, particularly STAT6, emerges as a valuable diagnostic tool. Long-term follow-up is essential for monitoring recurrence and potential malignant transformation. Further research is needed to delineate optimal treatment strategies, including the role of radiotherapy in SFT management.

Efficacy and toxicity of photon, proton, and carbon ion radiotherapy in the treatment of intracranial solitary fibrous tumor/hemangiopericytoma

BACKGROUND

Solitary fibrous tumors (SFT) of the central nervous system are rare and treatment options are not well established. The aim of this study was to evaluate the clinical outcomes of radiotherapy (RT) and re-radiotherapy (re-RT) for de novo intracranial SFT and recurrent intracranial SFT.

METHODS

This retrospective study analyzed efficacy and toxicity of different RT modalities in patients who received radiotherapy (RT) for intracranial SFT at Heidelberg University Hospital between 2000 and 2020 following initial surgery after de novo diagnosis ("primary group"). We further analyzed the patients of this cohort who suffered from tumor recurrence and received re-RT at our institution ("re-irradiation (re-RT) group"). Median follow-up period was 54.0 months (0-282) in the primary group and 20.5 months (0-72) in the re-RT group. RT modalities included 3D-conformal RT (3D-CRT), intensity-modulated RT (IMRT), stereotactic radiosurgery (SRS), proton RT, and carbon-ion RT (C12-RT). Response rates were analyzed according to RECIST 1.1 criteria.

RESULTS

While the primary group consisted of 34 patients (f: 16; m:18), the re-RT group included 12 patients (f: 9; m: 3). Overall response rate (ORR) for the primary group was 38.3% (N = 11), with 32.4% (N = 11) complete remissions (CR) and 5.9% (N = 2) partial remissions (PR). Stable disease (SD) was confirmed in 5.9% (N = 2), while 41.2% (N = 14) experienced progressive disease (PD). 14% (N = 5) were lost to follow up. The re-RT group had 25.0% CR and 17.0% PR with 58.0% PD. The 1-, 3-, and 5-year progression-free survival rates were 100%, 96%, and 86%, respectively, in the primary group, and 81%, 14%, and 14%, respectively, in the re-RT group. Particle irradiation (N = 11) was associated with a lower likelihood of developing a recurrence in the primary setting than photon therapy (N = 18) (OR = 0.038; p = 0.002), as well as doses ≥ 60.0 Gy (N = 15) versus < 60.0 Gy (N = 14) (OR = 0.145; p = 0.027). Risk for tumor recurrence was higher for women than for men (OR = 8.07; p = 0.014) with men having a median PFS of 136.3 months, compared to women with 66.2 months.

CONCLUSION

The data suggests RT as an effective treatment option for intracranial SFT, with high LPFS and PFS rates. Radiation doses ≥ 60 Gy could be associated with lower tumor recurrence. Particle therapy may be associated with a lower risk of recurrence in the primary setting, likely due to the feasibility of higher RT-dose application.

Extradural disconnection of the cavernous sinus with preservation of the internal carotid artery: indication and technique

BACKGROUND

Extradural disconnection of the cavernous sinus (CS) with preservation of the internal carotid artery (ICA) is indicated for aggressive and recurrent tumors, in patients presenting loss of oculomotor function and non-functional circle of Willis.

METHOD

Extradural resection of the anterior clinoid process disconnects the CS anteriorly. The ICA is dissected in the foramen lacerum via extradural subtemporal approach. The intracavernous tumor is split and removed following the ICA. Bleeding control of the inferior and superior petrosal and intercavernous sinuses completes posterior CS disconnection.

CONCLUSION

This technique can be proposed for recurrent CS tumors and need of ICA preservation.

Impact of extent of resection and postoperative radiotherapy on survival outcomes in intracranial solitary fibrous tumors: a systematic review and meta-analysis

The knowledge of optimal treatments for patients with intracranial solitary fibrous tumor (SFT) is limited, with inconclusive results from previous studies. In this study, we conducted a meta-analysis of relevant studies to identify the prognostic impact of the extent of resection (EOR) and postoperative radiotherapy (PORT) on survival outcomes of patients with intracranial SFT. We searched the Medline, Embase, and Cochrane Central Register of Controlled Trials (CENTRAL) to identify relevant studies published till April 2022. Progression-free survival (PFS) and overall survival (OS) were the outcomes of interest. Differences between two cohorts (gross total resection [GTR] vs. subtotal resection [STR] and PORT vs. surgery only) were estimated by calculating hazard ratios. Twenty-seven studies were selected for the meta-analysis, including data of 1348 patients (GTR, n = 819 vs. STR, n = 381 and PORT, n = 723 vs. surgery only, n = 578). Pooled hazard ratios of PFS (1, 3, 5, and 10 years) and OS (3, 5, and 10 years) revealed that the GTR cohort showed sustained superiority over the STR cohort. In addition, the PORT cohort was superior to the surgery-only cohort with respect to all PFS periods. Although the 10-year OS between the two cohorts was not statistically different, PORT showed significantly better 3- and 5-year OS than surgery only. The study findings suggest that GTR and PORT provide significant benefits for PFS and OS. Aggressive surgical resection of tumors to achieve GTR followed by PORT should be implemented as optimal treatments for all patients with intracranial SFT when feasible.

The value of whole-volume apparent diffusion coefficient histogram analysis in preoperatively distinguishing intracranial solitary fibrous tumor and transitional meningioma

Purpose

To investigate the value of whole-volume apparent diffusion coefficient (ADC) histogram analysis in preoperatively distinguishing intracranial solitary fibrous tumors (SFT) from transitional meningiomas (TM), thereby assisting the establishment of the treatment protocol.

Methods

Preoperative diffusion-weighted imaging datasets of 24 patients with SFT and 28 patients with TM were used to extract whole-volume ADC histogram parameters, including variance, skewness, kurtosis, and mean, as well as 1st (AP1), 10th (AP10), 50th (AP50), 90th (AP90), and 99th (AP99) percentiles of ADC using MaZda software. The independent t-test or Mann-Whitney U test was used to compare the differences between ADC histogram parameters of SFT and TM. Receiver operating characteristic (ROC) curves were generated to evaluate the performance of significant ADC histogram parameters. Spearman's correlation coefficients were calculated to evaluate correlations between these parameters and the Ki-67 expression levels.

Results

SFT exhibited significantly higher variance, and lower AP1 and AP10 (all P < 0.05) than TM. The best diagnostic performance was obtained by variance, with an area under the ROC curve of 0.848 (0.722-0.933). However, there was no significant difference in skewness, kurtosis, mean, or other percentiles of ADC between the two groups (all P > 0.05). Significant correlations were also observed between the Ki-67 proliferation index and variance (r = 0.519), AP1 (r = -0.425), and AP10 (r = -0.372) (all P < 0.05).

Conclusion

Whole-volume ADC histogram analysis is a feasible tool for non-invasive preoperative discrimination between intracranial SFT and TM, with variance being the most promising prospective parameter.

A Single-Center Retrospective Analysis of Intracranial and Spinal Solitary Fibrous Tumor/Hemangiopericytoma Clinical Outcomes: Sex Association With Aggressiveness

BACKGROUND

Solitary fibrous tumor/hemangiopericytoma (SFT/HPCT) is a rare tumor characterized by high recurrence rate and metastatic potential, even after surgical resection. We report on the clinical outcomes and risk factors for metastasis and progression-free survival (PFS) of patients diagnosed with SFT/HPCT.

METHODS

We retrospectively identified patients with intracranial or spinal SFT/HPCT who underwent surgical resection and/or radiation therapy at our institution between 1995 and 2021. Baseline demographics, tumor characteristics, and outcome data were collected, and factors associated with PFS and metastasis were analyzed.

RESULTS

Thirty-four subjects (mean age, 46.4 years; 44% female) with a histopathologically proven diagnosis of SFT/HPCT were included; the median follow-up was 89.7 months. Twenty-two tumors were supratentorial (67%), 6 (18%) were infratentorial, and 5 (15%) were spinal. Eleven patients had documented occurrence of metastasis (32%). Detailed preoperative and postoperative data were available for 25 patients (74%) who received treatment at our institution after their initial diagnosis. Of those, 20 (80%) underwent gross total resection (GTR), and 12 (48%) received either adjuvant or salvage radiotherapy. Univariate analyses revealed that males had a shorter mean PFS compared with females (25 months vs. 78 months; P = 0.01), and that patients who underwent GTR had a longer mean PFS compared with those who underwent subtotal resection (54 months vs. 23 months; P = 0.02). Male sex was the sole risk factor for metastasis (odds ratio, 6.75; 95% confidence interval, 1.19-38.02).

CONCLUSIONS

Our data demonstrate a strong association between male sex and the outcomes of shorter PFS and higher risk for metastases. Further research is warranted to understand the clinical characteristics and outcomes of this rare tumor.

Effect of Different Treatments for Intracranial Solitary Fibrous Tumors: Retrospective Analysis of 31 Patients

OBJECTIVE

An intracranial solitary fibrous tumor (SFT) is a rare mesenchymal neoplasm with a high predisposition toward recurrence and metastasis. The definition of SFT was updated according to the 2021 World Health Organization (WHO) classification. Given its rarity and resemblance to meningiomas, SFT is often misdiagnosed and there remains a debate on the treatment for it. We provide a retrospective analysis of SFTs and conclude the outcomes of different treatments.

METHODS

Patients who accepted operation and were diagnosed with intracranial SFTs in our hospital were included between 2008 and 2021. The medical records on clinical characteristics and outcomes were summarized for analysis. Cox regressions were used to determine the hazard ratio (HR).

RESULTS

Thirty-one SFT patients were included with a median follow-up time of 67 months. Tumor recurrence was observed in 12 (38.7%) patients, with 1 and 5-year recurrence rates of 6.5% and 22.6%, respectively. In univariate analysis, gross total resection (GTR) was significantly associated with decreased recurrence (P = 0.022), while subtotal resection (STR) (HR = 9.237; P = 0.020) and tumor location of tentorium (HR = 4.692; P = 0.022) were correlated with increased recurrence. In multivariate analysis, GTR (P = 0.040) and GTR plus radiotherapy (GTR + RT) (HR = 0.002; P = 0.020) were associated with reduced recurrence, while STR (HR = 40.835; P = 0.012) was a risk factor for recurrence.

CONCLUSIONS

GTR and postoperative RT are beneficial for preventing tumor recurrence. Larger studies and long-term follow-up are warranted to further identify the effect of postoperative RT.

Gamma Knife radiosurgery for a recurrent craniocervical junction solitary fibrous tumour

Spinal solitary fibrous tumour (SFT) is an uncommon tumour with few cases reported in the literature. It rarely originates at the craniocervical junction. To our knowledge, only eight cases of spinal SFT located at the craniocervical junction have been reported in the literature. We presented a patient with a craniocervical junction SFT and discussed its clinical presentation, radiological features, pathology, management and outcome. This was the first patient reported in the literature with a recurrent craniocervical junction SFT treated with Gamma Knife radiosurgery. The treatment reduced the tumour volume by more than 85% within 12 months.

Sixteen-Year Follow-Up in a Cavernous Sinus Hemangiopericytoma: Improved Outcomes over Radiotherapy Advances

Intracranial hemangiopericytomas are rare tumors, accounting for 1% of all central nervous system malignancies. This tumor is considered at high risk of local and also distant metastases. Surgical excision is the gold standard for treatment, but it is seldom curative by itself. Adjuvant radiotherapy is often recommended. We report an overview and update of the available literature on one such rare but aggressive mesenchymal tumor, using the case of a 46-year-old woman affected by hemangiopericytoma of the cavernous sinus surgically removed and treated with adjuvant radiotherapy at our institution. After seven years, the patient underwent a local recurrence and was treated with exeresis and Gamma Knife radiotherapy. Sixteen years after the initial diagnosis, she is still well with stable disease.

Delayed pulmonary metastasis and recurrence of intracranial malignant solitary fibrous tumor/hemangiopericytoma: Case report and literature review

Solitary fibrous tumors/hemangiopericytomas (SFTs/HPCs) are intracranial spindle cell tumors that originate from interstitial tissue. SFTs/HPCs that are primary malignant intracranial tumors are exceedingly uncommon. A case of intracranial malignant SFT/HPC that originated intracranially and spread to the pulmonary region is described herein. Furthermore, the specimens from two surgical resections obtained when the patient had undergone two prior procedures for intracranial ‘meningiomas’ were also reviewed. The results of the lung biopsy matched the morphologic appearance of the intracranial tumor. The patient died ~2 years after the chest pain started. In addition, the literature was reviewed. According to previous studies, STAT6 expression was positive in 100% of SFTs/HPCs and radiologic characteristics assisted in determining the tumor pathology and grade. Surgical management has been the mainstay treatment for SFTs. In cases of incomplete resection, adjuvant radiotherapy is effective and rigorous follow-up is required to monitor for recurrence.

Are bone erosion and peripheral feeding vessels hallmarks of intracranial solitary fibrous tumor/hemangiopericytoma?

An 86-year-old man sustained progressive motor weakness in the left lower extremity for 1 month. Cranial computed tomography (CT) revealed an isodense mass in the right parietal lobe, with a smooth-contoured focal erosion in the adjacent parietal bone. The extra-axial tumor appeared isointense on T1- and hyperintense on T2-weighted magnetic resonance imaging with intense enhancement. On three-dimensional CT angiography, the ectatic left occipital artery coursed into the right parietal foramina and connected with a dilated meningeal vessel supplying the tumor. The focal erosion formed in the inner parietal bone was located adjacent to the feeding vessel. A total tumor resection was achieved. The microscopic findings of the resected specimen were consistent with a World Health Organization grade III hemangiopericytoma (HPC). Bone erosion and peripheral feeding vessels may be characteristic findings of intracranial solitary fibrous tumor (SFT)/HPC. Careful interpretation of neuroimages could help detect clues for distinguishing an SFT/HPC masquerading as a meningioma from a true meningioma.

Apparent diffusion coefficient histogram analysis to preoperative evaluate intracranial solitary fibrous tumor: Relationship to Ki-67 proliferation index

PURPOSE

To explore the value of apparent diffusion coefficient (ADC) histogram analysis in preoperative evaluating intracranial solitary fibrous tumor (SFT) and further investigate the relationship between ADC histogram parameters and the Ki-67 proliferation index.

METHODS

From January 2014 to March 2022, 37 patients with intracranial SFT (grade 2, n = 20; grade 3, n = 17) who underwent preoperative diffusion-weighted imaging were enrolled in this study. For each tumor, nine histogram parameters were automatically extracted and selected using MaZda software based on the axial ADC maps of the whole tumor, including mean, variance, skewness, kurtosis, as well as the 1st, 10th, 50th, 90th, and 99th percentile ADC (Perc.01, Perc.10, Perc.50, Perc.90, Perc.99). Differences in ADC histogram parameters between grade 2 and 3 intracranial SFT were compared. Receiver operating characteristic (ROC) curves were drawn to determine the diagnostic performance, and Pearson's correlation coefficient was used to investigate the relationship between these parameters and the Ki-67 proliferation index.

RESULTS

The mean, Perc.01, Perc.10, Perc.50, Perc.90, and Perc.99 were significantly lower in grade 3 than in grade 2 intracranial SFT (all P < 0.05). ROC analysis showed that these parameters can effectively distinguish between the two groups, with Perc.01 generating the best differentiation performance. Significant negative correlations were also observed between these parameters and the Ki-67 proliferation index (r = -0.436 ~ -0.522, all P < 0.05). However, there was no significant difference in variance, skewness, or kurtosis between the two groups (all P > 0.05).

CONCLUSIONS

ADC histogram analysis enables effective preoperative distinction of grade 2 and grade 3 intracranial SFT.

Recurrent Solitary Fibrous Tumor (Intracranial Hemangiopericytoma) Treated With a Novel Combined-Modality Radiosurgery Technique: A Case Report and Review of the Literature

Solitary Fibrous Tumor (SFT) is a rare and aggressive mesenchymal malignancy of the dura with a predilection for recurrence after treatment. We report a case of a SFT initially treated with subtotal surgical resection followed by a combination of Gamma Knife (GK) and linear accelerator-based radiosurgery. Forty-four days post-resection, the tumor had demonstrated radiographic evidence of recurrent disease within the post-operative bed. GK radiosurgery treatment was delivered in a "four-matrix" fashion targeting the entire surgical cavity as well as three nodular areas within this wide field. This treatment was delivered in one fraction with a stereotactic head frame for immobilization. A consolidation radiosurgery treatment course was then delivered over three additional fractions to the resection bed using a linear accelerator and mesh mask for immobilization. The total biologically effective dose (BED) was calculated as 32.50 Gy to the surgical bed and approximately 76.50 Gy to each nodular area. Almost three years post-operatively, the patient is alive and without radiographic or clinical evidence of disease recurrence. To our knowledge, no prior experiences have documented treatment of SFT using a mixed-modality, multi-fraction radiosurgery technique like the method detailed in this report. Our experience describes a combined modality, multi-fraction radiosurgery approach to treating recurrent SFT that maximizes radiation dose to the targets while minimizing complication risk. We believe this novel radiosurgery method should be considered in cases of grade II SFT post-resection.

Clinical Features, Management, and Prognostic Factors of Intracranial Solitary Fibrous Tumor

Background

Because of the low incidence and the constantly changing diagnostic and classification criteria, the clinical features, management, and prognostic factors of intracranial solitary fibrous tumor (ISFT) remain unclear and were thus analyzed in this study.

Method

A total of 38 patients with ISFTs who were diagnosed in our institution were enrolled in this study. Patient data including age, gender, clinical presentation, histopathological features, immunohistochemistry staining, tumor location, tumor size, treatment methods, and prognosis were extracted and retrospectively analyzed.

Results

The median age at diagnosis was 45.5 years (range 28–66 years) and the male-to-female ratio was 1:1.53 in our series. The 3-, 5-, and 10-year progression-free survival (PFS) rate was 82.2%, 62.8%, and 21.4%, respectively; and the 3-, 5-, and 10-year overall survival rate was 97.1%, 86.9%, and 64.2%, respectively. Patients with high WHO grade (grade 3) ISFTs experienced impaired PFS (p < 0.05) and OS (p < 0.01). Subtotal resection (STR) was associated with worse PFS and OS (p < 0.001, respectively). Postoperative radiotherapy (PORT) improved PFS, especially local control rate, in patients with WHO grade 3 ISFTs (P = 0.025) or STR (p = 0.027). Moreover, CD34-negative immunostaining and a high Ki-67 index (>10%) were associated with impaired PFS in ISFTs.

Conclusion

Our study provides evidence that high tumor grade, subtotal tumor resection, CD34 negative immunostaining, and high Ki-67 index (>10%) were independent predictors for the poor prognosis of ISFTs. PORT can improve local control rate, and should be recommended for patients with high-grade ISFTs or STR.

Deep Learning Model for Intracranial Hemangiopericytoma and Meningioma Classification

Background

Intracranial hemangiopericytoma/solitary fibrous tumor (SFT/HPC) is a rare type of neoplasm containing malignancies of infiltration, peritumoral edema, bleeding, or bone destruction. However, SFT/HPC has similar radiological characteristics as meningioma, which had different clinical managements and outcomes. This study aims to discriminate SFT/HPC and meningioma via deep learning approaches based on routine preoperative MRI.

Methods

We enrolled 236 patients with histopathological diagnosis of SFT/HPC (n = 144) and meningioma (n = 122) from 2010 to 2020 in Xiangya Hospital. Radiological features were extracted manually, and a radiological diagnostic model was applied for classification. And a deep learning pretrained model ResNet-50 was adapted to train T1-contrast images for predicting tumor class. Deep learning model attention mechanism was visualized by class activation maps.

Results

Our study reports that SFT/HPC was found to have more invasion to venous sinus (p = 0.001), more cystic components (p < 0.001), and more heterogeneous enhancement patterns (p < 0.001). Deep learning model achieved a high classification accuracy of 0.889 with receiver-operating characteristic curve area under the curve (AUC) of 0.91 in the validation set. Feature maps showed distinct clustering of SFT/HPC and meningioma in the training and test cohorts, respectively. And the attention of the deep learning model mainly focused on the tumor bulks that represented the solid texture features of both tumors for discrimination.

Differentiation of intracranial solitary fibrous tumor/hemangiopericytoma from atypical meningioma using apparent diffusion coefficient histogram analysis

This study aimed to investigate the value of apparent diffusion coefficient (ADC) histogram analysis in differentiating intracranial solitary fibrous tumor/hemangiopericytoma (SFT/HPC) from atypical meningioma (ATM). Retrospective analyzed the clinical, magnetic resonance imaging, and pathological data of 20 and 25 patients with SFT/HPC and ATM, respectively. Histogram analysis was performed on the axial ADC images using MaZda software, and nine histogram parameters were obtained, including mean, variance, skewness, kurtosis, and the 1^st (ADC1), 10^th (ADC10), 50^th (ADC50), 90^th (ADC90), and 99^th (ADC99) percentile ADC. Differences in ADC histogram parameters between SFT/HPC and ATM were compared by an independent t test or Mann-Whitney U test, while the statistically significant histogram parameters were further analyzed by drawing receiver operating characteristic (ROC) curves to evaluate the differential diagnostic performance. Among the nine ADC histogram parameters we extracted, the mean, ADC1, ADC10, ADC50, and ADC90 in the SFT/HPC group were greater than those of ATM, and significant differences were observed (all P < 0.05). ROC analysis showed that the ADC1 generated the highest area under the curve (AUC) value of 0.920 in distinguishing the two tumors, when using 91.00 as the optimal threshold. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive value in distinguishing between SFT/HPC and ATM were 84.00%, 85.00%, 84.44%, 87.50%, and 81.00%, respectively. ADC histogram analysis can be a reliable tool to differentiate between SFT/HPC and ATM, with the ADC1 being the most promising potential parameter.