Central Neurocytoma Treated Using Supratentorial Ventricle Radiotherapy: A Single-Institution Analysis of Five Cases in Adjuvant or Salvage Settings After Surgery.

INTRODUCTION: Central neurocytoma (CN) is an extremely rare tumor primarily located in the supratentorial ventricular system, categorized as a glioneuronal or neuronal tumor. METHODS: This study presented a retrospective analysis of five CN patients who received adjuvant or salvage radiotherapy. Patients, aged 31-59 years, underwent radiation doses ranging from 60 Gy to 50.4 Gy over 27-30 fractions. RESULTS: All patients achieved effective local tumor control without severe complications. The median follow-up period was 51.7 months, demonstrating 100% overall and progression-free survival rates. DISCUSSION: Our study's clinical outcomes align with previous research, despite the limitation of a small sample size. Emphasizing the necessity for additional research, our findings added to the potential evidence of radiotherapy in managing CN. Larger, long-term studies were needed to confirm these promising results.

Mutant IDH inhibitors induce lineage differentiation in IDH-mutant oligodendroglioma.

A subset of patients with IDH-mutant glioma respond to inhibitors of mutant IDH (IDHi), yet the molecular underpinnings of such responses are not understood. Here, we profiled by single-cell or single-nucleus RNA-sequencing three IDH-mutant oligodendrogliomas from patients who derived clinical benefit from IDHi. Importantly, the tissues were sampled on-drug, four weeks from treatment initiation. We further integrate our findings with analysis of single-cell and bulk transcriptomes from independent cohorts and experimental models. We find that IDHi treatment induces a robust differentiation toward the astrocytic lineage, accompanied by a depletion of stem-like cells and a reduction of cell proliferation. Furthermore, mutations in NOTCH1 are associated with decreased astrocytic differentiation and may limit the response to IDHi. Our study highlights the differentiating potential of IDHi on the cellular hierarchies that drive oligodendrogliomas and suggests a genetic modifier that may improve patient stratification.

Integrative spatial analysis reveals a multi-layered organization of glioblastoma.

Glioma contains malignant cells in diverse states. Here, we combine spatial transcriptomics, spatial proteomics, and computational approaches to define glioma cellular states and uncover their organization. We find three prominent modes of organization. First, gliomas are composed of small local environments, each typically enriched with one major cellular state. Second, specific pairs of states preferentially reside in proximity across multiple scales. This pairing of states is consistent across tumors. Third, these pairwise interactions collectively define a global architecture composed of five layers. Hypoxia appears to drive the layers, as it is associated with a long-range organization that includes all cancer cell states. Accordingly, tumor regions distant from any hypoxic/necrotic foci and tumors that lack hypoxia such as low-grade IDH-mutant glioma are less organized. In summary, we provide a conceptual framework for the organization of cellular states in glioma, highlighting hypoxia as a long-range tissue organizer.

Region-specific DNA hydroxymethylation along the malignant progression of IDH-mutant gliomas.

The majority of low-grade isocitrate dehydrogenase-mutant (IDHmt) gliomas undergo malignant progression (MP), but their underlying mechanism remains unclear. IDHmt gliomas exhibit global DNA methylation, and our previous report suggested that MP could be partly attributed to passive demethylation caused by accelerated cell cycles. However, during MP, there is also active demethylation mediated by ten-eleven translocation, such as DNA hydroxymethylation. Hydroxymethylation is reported to potentially contribute to gene expression regulation, but its role in MP remains under investigation. Therefore, we conducted a comprehensive analysis of hydroxymethylation during MP of IDHmt astrocytoma. Five primary/malignantly progressed IDHmt astrocytoma pairs were analyzed with oxidative bisulfite and the Infinium EPIC methylation array, detecting 5-hydroxymethyl cytosine at over 850,000 locations for region-specific hydroxymethylation assessment. Notably, we observed significant sharing of hydroxymethylated genomic regions during MP across the samples. Hydroxymethylated CpGs were enriched in open sea and intergenic regions (p < 0.001), and genes undergoing hydroxymethylation were significantly associated with cancer-related signaling pathways. RNA sequencing data integration identified 91 genes with significant positive/negative hydroxymethylation-expression correlations. Functional analysis suggested that positively correlated genes are involved in cell-cycle promotion, while negatively correlated ones are associated with antineoplastic functions. Analyses of The Cancer Genome Atlas clinical data on glioma were in line with these findings. Motif-enrichment analysis suggested the potential involvement of the transcription factor KLF4 in hydroxymethylation-based gene regulation. Our findings shed light on the significance of region-specific DNA hydroxymethylation in glioma MP and suggest its potential role in cancer-related gene expression and IDHmt glioma malignancy.

Transcriptomic and epigenetic dissection of spinal ependymoma (SP-EPN) identifies clinically relevant subtypes enriched for tumors with and without NF2 mutation.

Ependymomas encompass multiple clinically relevant tumor types based on localization and molecular profiles. Tumors of the methylation class "spinal ependymoma" (SP-EPN) represent the most common intramedullary neoplasms in children and adults. However, their developmental origin is ill-defined, molecular data are scarce, and the potential heterogeneity within SP-EPN remains unexplored. The only known recurrent genetic events in SP-EPN are loss of chromosome 22q and NF2 mutations, but neither types and frequency of these alterations nor their clinical relevance have been described in a large, epigenetically defined series. Transcriptomic (n = 72), epigenetic (n = 225), genetic (n = 134), and clinical data (n = 112) were integrated for a detailed molecular overview on SP-EPN. Additionally, we mapped SP-EPN transcriptomes to developmental atlases of the developing and adult spinal cord to uncover potential developmental origins of these tumors. The integration of transcriptomic ependymoma data with single-cell atlases of the spinal cord revealed that SP-EPN display the highest similarities to mature adult ependymal cells. Unsupervised hierarchical clustering of transcriptomic data together with integrated analysis of methylation profiles identified two molecular SP-EPN subtypes. Subtype A tumors primarily carried previously known germline or sporadic NF2 mutations together with 22q loss (bi-allelic NF2 loss), resulting in decreased NF2 expression. Furthermore, they more often presented as multilocular disease and demonstrated a significantly reduced progression-free survival as compared to SP-EP subtype B. In contrast, subtype B predominantly contained samples without NF2 mutation detected in sequencing together with 22q loss (monoallelic NF2 loss). These tumors showed regular NF2 expression but more extensive global copy number alterations. Based on integrated molecular profiling of a large multi-center cohort, we identified two distinct SP-EPN subtypes with important implications for genetic counseling, patient surveillance, and drug development priorities.

Predictive models of long-term survival outcomes following radical cystectomy.

BACKGROUND: Identifying the likelihood of life-threatening recurrence after radical cystectomy by reliable and user-friendly predictive models remains an unmet need in the clinical management of invasive bladder cancer. METHODS: A total of 204 consecutive patients undergoing open radical cystectomy (ORC) for bladder cancer were retrospectively enrolled between May 2005 and August 2020. Clinicopathological and peri-ORC therapeutic data were extracted from clinical records. We explored predictive factors that significantly affected the primary endpoint of overall survival (OS) and secondary endpoints of cancer-specific survival (CSS) and recurrence-free survival (RFS). RESULTS: During a median follow-up of 3.9 years, 42 (20.6%) and 10 (4.9%) patients died due to bladder cancer and other causes, respectively. Five-year RFS, CSS, and OS were 66.5%, 77.6%, and 75.4%, respectively. Pathological T and N categories and lymphovascular invasion (LVI) significantly affected RFS by Cox regression analysis. Accordingly, clinical T and pathological N categories and LVI significantly affected CSS. Clinical T and pathological N categories, LVI, age, and ORC tumor grade significantly affected OS. Based on the assessment score for each independent risk factor, we developed the Gunma University Oncology Study Group (GUOSG) score, which predicts RFS, CSS, and OS. The GUOSG score classified four groups for RFS, three for CSS, and five for OS, with statistically significant distribution for nearly all comparisons. CONCLUSIONS: The GUOSG model is helpful to show individualized prognosis and functions as a risk-stratified historical cohort for assessing the lifelong efficacy of new salvage treatment regimens.

Anesthetic management of a patient with achalasia, a disease with a considerable risk for aspiration under anesthesia.

BACKGROUND: Achalasia is a rare condition characterized by dysfunction of esophageal motility and impaired relaxation of the lower esophageal sphincter. Anesthetic management of these patients is challenging due to the elevated risk of regurgitation and aspiration. CASE PRESENTATION: A 53-year-old man diagnosed with achalasia was scheduled for renal cancer surgery before esophageal myotomy. Since his severe dysphagia suggested the possibility of vomiting and aspiration under anesthesia, a stomach tube was inserted before induction of general anesthesia. After preoxygenation, rapid sequence induction was performed and an antiemetic was administered to prevent postoperative vomiting. Although anesthetic management was uneventful, the inserted stomach tube coiled up in the dilated esophagus and substantial residue was aspirated via the tube even after a prolonged fasting period. CONCLUSION: Anesthesiologists should be familiar with achalasia even though it is an uncommon disease, since affected patients are at risk of regurgitation and aspiration under anesthesia.

The utility of the [-2]pro-prostate-specific antigen level as a prognostic marker in patients with castration-resistant prostate cancer treated with enzalutamide.

BACKGROUND: The prostate health index (phi) derived using [-2]pro-prostate-specific antigen (p2PSA), a precursor of PSA, has been shown to predict cancer in the gray zone. However, the utility of p2PSA in predicting outcomes for castration-resistant prostate cancer (CRPC) patients remains unknown. Therefore, in this study, we aimed to evaluate the usefulness of p2PSA in predicting the efficacy and prognosis of enzalutamide treatment in CRPC patients. METHODS: We conducted a prospective study of CRPC patients treated with enzalutamide at our institution, measuring p2PSA levels in 98 pre-treatment serum samples. All patients were divided into two groups based on the median values of each parameter. The PSA progression-free survival (PSA-PFS) and overall survival (OS) were compared using the Kaplan-Meier method. This study was approved by the Institutional Review Board of Gunma University Hospital (IRB No. 2021-092, 1983). RESULTS: The median PSA level before enzalutamide treatment was 25.59 ng/mL, the median p2PSA level was 208.75 pg/mL, and the median phi was 187.95. PSA, p2PSA, and phi were not all predictors of PSA-PFS. However, the OS was significantly better in the low-value groups (log-rank p-values of PSA, p2PSA, and phi were 0.024, 0.034, and 0.018, respectively). In the docetaxel (DOC)-naive group (n = 58), PSA was not a predictor of OS, but p2PSA and phi were significantly associated with better OS in the low group. This relationship was not observed in the DOC-treated group. CONCLUSIONS: Our study elucidates the usefulness of p2PSA in predicting outcomes for CRPC patients treated with enzalutamide. It suggests that p2PSA and phi may be prognostic markers after enzalutamide administration in CRPC patients.

Retroperitoneal urothelial carcinoma arising after bladder diverticulectomy: a case report.

BACKGROUND: Urothelial carcinoma arises from the inner urothelial membrane of the renal pelvis, ureter, and bladder and often causes macrohematuria. Here, we report a rare case in which the patient developed non-symptomatic urothelial carcinoma anatomically outside the bladder wall 17 years after bladder diverticulectomy. CASE PRESENTATION: An 82-year-old male patient previously underwent gastrectomy for stomach cancer and partial hepatectomy for intrahepatic cholangiocarcinoma. Follow-up computed tomography revealed a tumor in the retroperitoneal space, where a bladder diverticulum was removed 17 years earlier. Multiparametric magnetic resonance imaging suggested that the tumor was malignant with rectal invasion. Subsequent computed tomography-guided percutaneous biopsy revealed that the tumor was urothelial carcinoma. The patient underwent two courses of neoadjuvant chemotherapy followed by pelvic exenteration with pelvic lymph node dissection. He is currently receiving adjuvant therapy with an immune checkpoint inhibitor and has had no recurrence for 3 months. CONCLUSIONS: Multiparametric magnetic resonance imaging is a helpful tool for predicting both tumor malignancy and invasion before a pathologically confirmed diagnosis. Although this case is rare, urologists should be aware of the occurrence of urothelial carcinoma after bladder diverticulectomy in cases of incomplete resection of the diverticulum.

Recurrent glioblastoma metastatic to the lumbar vertebra: A case report and literature review: Surgical oncology.

Background: Glioblastoma is a malignant tumor, and its prognosis is as poor as 1.5 to 2 years. Most cases recur within one year even under the standard treatment. The majority of recurrences are local, and in rare cases, metastasize mostly within the centra nervous system. Extradural metastasis of glioma is exceedingly rare. Here, we present a case of vertebral metastasis of glioblastoma. Case presentation: We present a 21-year-old man post total resection of the right parietal glioblastoma, diagnosed with lumbar metastasis. He originally presented with impaired consciousness and left hemiplegia and underwent gross total resection of the tumor. Given the diagnosis of glioblastoma, he was treated with radiotherapy combined with concurrent and adjuvant temozolomide. Six months after tumor resection, the patient presented with severe back pain, and was diagnosed as metastatic glioblastoma on the first lumbar vertebrae. Posterior decompression with fixation and postoperative radiotherapy were conducted. He went on to receive temozolomide and bevacizumab. However, at 3 months after the diagnosis of lumbar metastasis, further disease progression was noted, and his care was transitioned to best supportive care. Comparison on copy number status between primary and metastatic lesions on methylation array analysis revealed more enhanced chromosomal instability including 7p loss, 7q gain and 8 gain in the metastatic lesion. Conclusion: Based upon the literature review and our case, younger age of initial presentation, multiple surgical interventions, and long overall survival seem to be the risk factors of vertebral metastasis. As the prognosis of glioblastoma improves over time, its vertebral metastasis is seemingly more common. Therefore, extradural metastasis should be kept in mind in the treatment of glioblastoma. Further, detailed genomic analysis on multiple paired specimens is mandated to elucidate the molecular mechanisms of vertebral metastasis.

Two cases of CRPC with BRCA mutation treated by olaparib after favorable response to cisplatin.

Introduction: Several prostate cancers carry homologous recombination repair mutations that respond to olaparib. Because of the mechanism, the efficacy of platinum-based therapy can be used to predict the efficacy of poly(adenosine diphosphate-ribose) polymerase inhibitors such as olaparib. Case presentation: We experienced two neuroendocrine prostate cancer patients who achieved a response duration of more than 1 year with platinum-based therapy. Case 1 had a BRCA2 mutation in the germline and case 2 had a BRCA2 mutation in a somatic chromosome only. Both patients responded well to olaparib. Conclusion: Cisplatin and olaparib may overlap in response due to their medicinal action. It may be useful to consider genetic testing in some CRPC patients who have responded to cisplatin.

Changes in Renal Function of Patients With Prostate Cancer: Focus on Androgen Deprivation Therapy.

BACKGROUND/AIM: To investigate the association between androgen deprivation therapy (ADT) and changes in the estimated glomerular filtration rate (eGFR) in male Japanese patients with prostate cancer, based on post-hoc analysis of data from a previous prospective study. PATIENTS AND METHODS: Among 103 patients with prostate cancer in whom renal function changes were tracked over 5 years, 88 were divided into a group who completed ADT within 3 years (short ADT group; n=47) and a group who continued with ADT for more than 5 years (continuous ADT group; n=41). We compared the groups in terms of the eGFR, calculated based on age and serum creatinine (mg/dl) before ADT initiation and every other year over the next 5 years. RESULTS: The eGFR decreased by 4.91 and 2.89 ml/min in the short and continuous ADT groups, respectively, over the 5-year period following ADT initiation. The respective decreases in the eGFR were 0.98 and 0.58 ml/min/year. No significant difference in the eGFR was observed between the two groups at any measurement point. Patients treated with ADT showed a decrease in the eGFR of 0.58-0.98 ml/min/year over a 5-year period, which is about twice as high as that of normal Japanese males. No significant difference in the eGFR by ADT duration was observed. CONCLUSION: The eGFR decreased by 0.58-0.98 ml/min/year in our ADT patients, which was about twice as high as the rate of decrease in normal Japanese males, and approximately the same as in urine protein-positive male patients. We suggest that a large decrease in the eGFR may not play a role in the development of acute kidney injury. In addition, the duration of ADT does not appear to have a significant effect on the eGFR.

Novel case of primary intracranial solitary plasmacytoma presenting with significant intratumoral hemorrhage.

Background: Solitary plasmacytoma is a localized lesion comprising monoclonal neoplastic proliferation of plasma cells. This disease is rarely encountered and few reports have described primary intracranial solitary plasmacytoma (PISP). Case Description: We report a case of PISP that presented initially as status epilepticus and exhibited massive intratumoral hemorrhage at the subcortical area. To the best of our knowledge, this is the first recorded presentation of this pathology in this manner. Following evacuation of the hematoma and decompressive craniectomy, the patient underwent radiation therapy and showed no sign of tumor recurrence at 3 years after diagnosis. Conclusion: This case reveals that PISP can present as subcortical intraparenchymal hemorrhage. It should be emphasized that the precise diagnosis of this disease is of utmost importance, because solitary plasmacytoma without a background of multiple myeloma responds well to radiation therapy.

Gene expression profiling of 19q-loss astrocytomas suggest a specific pattern associated with the better prognosis.

PURPOSE: We previously reported that there was a subgroup of IDH-mutated astrocytomas harboring only 19q-loss showing oligodendroglioma-like morphology and significantly longer overall survival (OS) compared with 19q-intact astrocytomas. The aim of this study was to further explore the biological characteristics of this possible subgroup and obtain insight into the mechanism of their relatively benign clinical behavior. METHODS: We compared gene expression pattern between five 19q-loss and five 19q-intact IDH-mutated astrocytomas by microarray analysis. RESULTS: By comparing expression levels of genes of 19q-loss astrocytomas to those of 19q-intact astrocytomas, 102 up-regulated genes and 162 down-regulated genes were extracted. The down-regulated genes clustered heavily to 19q and 4p while the up-regulated genes clustered to 4q. It was noteworthy that fibroblast growth factor 1 associated with stem cell maintenance and multiple genes associated with glioma progression were down-regulated in 19q-loss astrocytomas, and these results were validated with the independent TCGA data set. On t-SNE analysis of the 19q-loss astrocytomas with other IDH-mutant glioma subgroups from the TCGA datasets, the expression pattern of the 19q-loss astrocytomas showed no shift toward oligodendrogliomas with 1p/19q codeletion but rather constituted a subgroup of astrocytoma. CONCLUSIONS: These findings suggested that 19q-loss in astrocytomas is more likely acquired event rather than an early event in oncogenesis like the 1p/19q-codeletion in oligodendrogliomas, and that the biological features of 19q-loss astrocytomas are possibly related to differentially expressed genes associated with stem cell maintenance and glioma progression.

A Novel Topical Fluorescent Probe for Detection of Glioblastoma.

PURPOSE: Five-aminolevulinic acid (5-ALA) is widely used as an intraoperative fluorescent probe for radical resection of high-grade glioma, and thus aids in extending progression-free survival of patients. However, there exist some cases where 5-ALA fails to fluoresce. In some other cases, it may undergo fluorescence quenching but cannot be orally readministered during surgery. This study aimed to develop a novel hydroxymethyl rhodamine green (HMRG)-based fluorescence labeling system that can be repeatedly administered as a topical spray during surgery for the detection of glioblastoma. EXPERIMENTAL DESIGN: We performed a three-stage probe screening using tumor lysates and fresh tumor tissues with our probe library consisting of a variety of HMRG probes with different dipeptides. We then performed proteome and transcript expression analyses to detect candidate enzymes responsible for cleaving the probe. Moreover, in vitro and ex vivo studies using U87 glioblastoma cell line were conducted to validate the findings. RESULTS: The probe screening identified proline-arginine-HMRG (PR-HMRG) as the optimal probe that distinguished tumors from peritumoral tissues. Proteome analysis identified calpain-1 (CAPN1) to be responsible for cleaving the probe. CAPN1 was highly expressed in tumor tissues which reacted to the PR-HMRG probe. Knockdown of this enzyme suppressed fluorescence intensity in U87 glioblastoma cells. In situ assay using a mouse U87 xenograft model demonstrated marked contrast of fluorescence with the probe between the tumor and peritumoral tissues. CONCLUSIONS: The novel fluorescent probe PR-HMRG is effective in detecting glioblastoma when applied topically. Further investigations are warranted to assess the efficacy and safety of its clinical use.

Prognostic Factors in Hormone-sensitive Prostate Cancer Patients Treated With Combined Androgen Blockade: A Consecutive 15-year Study at a Single Japanese Institute.

BACKGROUND/AIM: There are several treatment options for metastatic hormone-sensitive prostate cancer (mHSPC) in the world. In recent years, the use of docetaxel, abiraterone, enzalutamide, and apalutamide has been used for mHSPC, but combined androgen blockade (CAB) therapy using first-generation antiandrogens has been widely used in Japan. There is a background. We performed a consecutive study of patients who received combined androgen blockade (CAB) at a single institute to determine the prognostic factors for mHSPC. PATIENTS AND METHODS: We conducted a consecutive study of 237 mHSPC patients treated with CAB from 2003 to 2017 at the Gunma University Hospital. Prostate-specific antigen progression-free survival (PSA-PFS) and overall survival (OS) were estimated by the Kaplan-Meier method. The associations between pre-treatment risk factors and the PSA response 3 months after starting CAB, PSA-PFS, and OS were evaluated by the Cox proportional hazards model. RESULTS: Among the 237 cases, the median PSA-PFS and OS times were 63.0 and 91.4 months, respectively. The median PSA-PFS and OS times of M1 cases (174 cases, 73.4% of all 237 cases) were 36.1 and 75.9 months, respectively. The Eastern Cooperative Oncology Group performance status (ECOG PS) score, hemoglobin (Hb), lactate dehydrogenase, extent of disease, visceral metastasis (no vs. yes), and PSA response after 3 months were significant predictors of OS according to Cox regression analysis of prognostic factors in M1 patients. The ECOG PS, Hb, visceral metastasis (no vs. yes), and PSA response after 3 months predicted OS high-risk patients in LATITUDE criteria. The OS was 92.1 months in the low-risk group (0-1 risk factors), 48.2 months in the intermediate-risk group (2 risk factors), and 16.9 months in the high-risk group (3-4 risk factors). CONCLUSION: CAB should be considered as a treatment option for strictly selected patients with mHSPC, even though novel treatments are available.

Author Correction: A single-cell and single-nucleus RNA-Seq toolbox for fresh and frozen human tumors.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

A single-cell and single-nucleus RNA-Seq toolbox for fresh and frozen human tumors.

Single-cell genomics is essential to chart tumor ecosystems. Although single-cell RNA-Seq (scRNA-Seq) profiles RNA from cells dissociated from fresh tumors, single-nucleus RNA-Seq (snRNA-Seq) is needed to profile frozen or hard-to-dissociate tumors. Each requires customization to different tissue and tumor types, posing a barrier to adoption. Here, we have developed a systematic toolbox for profiling fresh and frozen clinical tumor samples using scRNA-Seq and snRNA-Seq, respectively. We analyzed 216,490 cells and nuclei from 40 samples across 23 specimens spanning eight tumor types of varying tissue and sample characteristics. We evaluated protocols by cell and nucleus quality, recovery rate and cellular composition. scRNA-Seq and snRNA-Seq from matched samples recovered the same cell types, but at different proportions. Our work provides guidance for studies in a broad range of tumors, including criteria for testing and selecting methods from the toolbox for other tumors, thus paving the way for charting tumor atlases.

Radiomics Analysis for Glioma Malignancy Evaluation Using Diffusion Kurtosis and Tensor Imaging.

PURPOSE: A noninvasive diagnostic method to predict the degree of malignancy accurately would be of great help in glioma management. This study aimed to create a highly accurate machine learning model to perform glioma grading. METHODS AND MATERIALS: Preoperative magnetic resonance imaging acquired for cases of glioma operated on at our institution from October 2014 through January 2018 were obtained retrospectively. Six types of magnetic resonance imaging sequences (T2-weighted image, diffusion-weighted image, apparent diffusion coefficient [ADC], fractional anisotropy, and mean kurtosis [MK]) were chosen for analysis; 476 features were extracted semiautomatically for each sequence (2856 features in total). Recursive feature elimination was used to select significant features for a machine learning model that distinguishes glioblastoma from lower-grade glioma (grades 2 and 3). RESULTS: Fifty-five data sets from 54 cases were obtained (14 grade 2 gliomas, 12 grade 3 gliomas, and 29 glioblastomas), of which 44 and 11 data sets were used for machine learning and independent testing, respectively. We detected 504 features with significant differences (false discovery rate <0.05) between glioblastoma and lower-grade glioma. The most accurate machine learning model was created using 6 features extracted from the ADC and MK images. In the logistic regression, the area under the curve was 0.90 ± 0.05, and the accuracy of the test data set was 0.91 (10 out of 11); using a support vector machine, they were 0.93 ± 0.03 and 0.91 (10 out of 11), respectively (kernel, radial basis function; c = 1.0). CONCLUSIONS: Our machine learning model accurately predicted glioma tumor grade. The ADC and MK sequences produced particularly useful features.