Risk factors for unclear margin in cold snare polypectomy for colorectal polyp.

OBJECTIVES: Cold snare polypectomy (CSP) is a common, simple, and safe procedure; however, it has a high rate of unclear margins. We analyzed the risk factors for unclear margins of colorectal polyp. METHODS: We retrospectively investigated colorectal polyps treated with CSP between July 2021 and July 2022, excluding those that could not be retrieved or pathologically nonneoplastic and hyperplastic polyps without margin evaluation. The clinicopathological features and risk factors for unclear margins were analyzed. Furthermore, the polyps were divided into two groups: those resected by experts and those resected by trainees. A 1 : 1 propensity score matching was performed. After matching, the risk factors for unclear margins in each group were analyzed as secondary outcomes. RESULTS: We analyzed 237 patients with 572 polyps; the margins were negative in 58.6% (negative group) and unclear in 41.4% (unclear group). The unclear margin was significantly higher at straddling folds (P = 0.0001), flexure points (P = 0.005), and in the procedures performed by trainees (P < 0.0001). Altogether, 198 propensity score matched pairs were explored for secondary outcomes. There were no significant differences in risk factors for unclear margins in the expert group, while in the trainee group, the unclear margin was significantly higher at the straddling folds (P = 0.0004) and flexure points (P = 0.005). CONCLUSIONS: We demonstrated that straddling folds, flexure points, and procedures performed by the trainees were significant risk factors for unclear margins, and we hypothesized that the rate of unclear margins will reduce as the trainees accumulate experience at difficult sites.

A Novel Characteristic Gastric Mucus Named "Web-like Mucus" Potentially Induced by Vonoprazan.

Background: In the absence of Helicobacter pylori (HP) infection, a characteristic gastric mucus adhesion may appear during the use of vonoprazan. We named this novel characteristic mucus "web-like mucus" (WLM). This study aimed to determine the incidence and risk factors for WLM. Methods: Between January 2017 and January 2022, 5665 patients were enrolled in this study. The patients were divided into a proton-pump inhibitor (PPI)-prescribed group (n = 2000), a vonoprazan-prescribed group (n = 268), and a no-PPI/vonoprazan-prescribed (n = 3397) group, and the presence of WLM was examined. After excluding four patients with autoimmune gastritis, the remaining 264 patients in the vonoprazan group were divided into WLM and non-WLM groups, and their clinical features were analyzed. Results: A total of 55 (21%) patients had WLM, all in the vonoprazan-prescribed group. There were no significant differences in factors such as, sex, age, chronic kidney disease, diabetes mellitus, HP eradication history, smoking, or alcohol consumption between the WLM and non-WLM groups. The median duration from the start of vonoprazan administration to the endoscopic detection of WLM was 2 (1-24) months. Conclusions: WLM appears to be a characteristic feature in patients treated with vonoprazan.

New liver window width in detecting hepatocellular carcinoma on dynamic contrast-enhanced computed tomography with deep learning reconstruction.

Changing a window width (WW) alters appearance of noise and contrast of CT images. The aim of this study was to investigate the impact of adjusted WW for deep learning reconstruction (DLR) in detecting hepatocellular carcinomas (HCCs) on CT with DLR. This retrospective study included thirty-five patients who underwent abdominal dynamic contrast-enhanced CT. DLR was used to reconstruct arterial, portal, and delayed phase images. The investigation of the optimal WW involved two blinded readers. Then, five other blinded readers independently read the image sets for detection of HCCs and evaluation of image quality with optimal or conventional liver WW. The optimal WW for detection of HCC was 119 (rounded to 120 in the subsequent analyses) Hounsfield unit (HU), which was the average of adjusted WW in the arterial, portal, and delayed phases. The average figures of merit for the readers for the jackknife alternative free-response receiver operating characteristic analysis to detect HCC were 0.809 (reader 1/2/3/4/5, 0.765/0.798/0.892/0.764/0.827) in the optimal WW (120 HU) and 0.765 (reader 1/2/3/4/5, 0.707/0.769/0.838/0.720/0.791) in the conventional WW (150 HU), and statistically significant difference was observed between them (p < 0.001). Image quality in the optimal WW was superior to those in the conventional WW, and significant difference was seen for some readers (p < 0.041). The optimal WW for detection of HCC was narrower than conventional WW on dynamic contrast-enhanced CT with DLR. Compared with the conventional liver WW, optimal liver WW significantly improved detection performance of HCC.

High-angular resolution diffusion imaging generation using 3d u-net.

PURPOSE: To investigate the effects on tractography of artificial intelligence-based prediction of motion-probing gradients (MPGs) in diffusion-weighted imaging (DWI). METHODS: The 251 participants in this study were patients with brain tumors or epileptic seizures who underwent MRI to depict tractography. DWI was performed with 64 MPG directions and b = 0 s/mm2 images. The dataset was divided into a training set of 191 (mean age 45.7 [± 19.1] years), a validation set of 30 (mean age 41.6 [± 19.1] years), and a test set of 30 (mean age 49.6 [± 18.3] years) patients. Supervised training of a convolutional neural network was performed using b = 0 images and the first 32 axes of MPG images as the input data and the second 32 axes as the reference data. The trained model was applied to the test data, and tractography was performed using (a) input data only; (b) input plus prediction data; and (c) b = 0 images and the 64 MPG data (as a reference). RESULTS: In Q-ball imaging tractography, the average dice similarity coefficient (DSC) of the input plus prediction data was 0.715 (± 0.064), which was significantly higher than that of the input data alone (0.697 [± 0.070]) (p < 0.05). In generalized q-sampling imaging tractography, the average DSC of the input plus prediction data was 0.769 (± 0.091), which was also significantly higher than that of the input data alone (0.738 [± 0.118]) (p < 0.01). CONCLUSION: Diffusion tractography is improved by adding predicted MPG images generated by an artificial intelligence model.

Age-Dependent Hemorrhage Risk and Obliteration Benefit After Radiosurgery for Brain Arteriovenous Malformation.

PURPOSE: Because patients with untreated brain arteriovenous malformations (BAVMs) are at variable risks of cerebral hemorrhage and associated mortality and morbidity, it is essential to identify patient populations who benefit most from prophylactic interventions. This study aimed to examine age-dependent differences in the therapeutic effect of stereotactic radiosurgery (SRS) on BAVMs. METHODS AND MATERIALS: This retrospective observational study enrolled patients with BAVMs who underwent SRS at our institution between 1990 and 2017. The primary outcome was post-SRS hemorrhage, and the secondary outcomes included nidus obliteration, post-SRS early signal changes, and mortality. To investigate age-related differences in outcomes after SRS, we performed age-stratified analyses using the Kaplan-Meier analysis and weighted logistic regression with the inverse probability of censoring weighting (IPCW). To address significant differences in patient baseline characteristics, we also performed inverse probability of treatment weighting (IPTW) adjusted for possible confounders to investigate age-related differences in outcomes after SRS. RESULTS: A total of 735 patients with 738 BAVMs were stratified by age. Age-stratified analysis using a weighted logistic regression model with IPCW showed a direct correlation between patient age and post-SRS hemorrhage (odds ratio [OR], 95% confidence interval [CI], and P value: 2.20, 1.34-3.63, and .002 at 18 months; 1.86, 1.17-2.93, and .008 at 36 months; and 1.61, 1.05-2.48, and .030 at 54 months, respectively). The age-stratified analysis also showed an inverse relationship between age and obliteration over the first 42 months after SRS (OR, 95% CI, and P value: 0.05, 0.02-0.12, and <.001 at 6 months; 0.55, 0.44-0.70, and <.001 at 24 months; and 0.76, 0.63-0.91, and .002 at 42 months, respectively). These results were also confirmed with the IPTW analyses. CONCLUSIONS: Our analysis demonstrated that patients' age at SRS is significantly associated with hemorrhage and the nidus obliteration rate after treatment. In particular, younger patients are more likely to exhibit reduced cerebral hemorrhages and achieve earlier nidus obliteration compared with older patients.

Improving detection performance of hepatocellular carcinoma and interobserver agreement for liver imaging reporting and data system on CT using deep learning reconstruction.

PURPOSE: This study aimed to compare the hepatocellular carcinoma (HCC) detection performance, interobserver agreement for Liver Imaging Reporting and Data System (LI-RADS) categories, and image quality between deep learning reconstruction (DLR) and conventional hybrid iterative reconstruction (Hybrid IR) in CT. METHODS: This retrospective study included patients who underwent abdominal dynamic contrast-enhanced CT between October 2021 and March 2022. Arterial, portal, and delayed phase images were reconstructed using DLR and Hybrid IR. Two blinded readers independently read the image sets with detecting HCCs, scoring LI-RADS, and evaluating image quality. RESULTS: A total of 26 patients with HCC (mean age, 73 years ± 12.3) and 23 patients without HCC (mean age, 66 years ± 14.7) were included. The figures of merit (FOM) for the jackknife alternative free-response receiver operating characteristic analysis in detecting HCC averaged for the readers were 0.925 (reader 1, 0.937; reader 2, 0.913) in DLR and 0.878 (reader 1, 0.904; reader 2, 0.851) in Hybrid IR, and the FOM in DLR were significantly higher than that in Hybrid IR (p = 0.038). The interobserver agreement (Cohen's weighted kappa statistics) for LI-RADS categories was moderate for DLR (0.595; 95% CI, 0.585-0.605) and significantly superior to Hybrid IR (0.568; 95% CI, 0.553-0.582). According to both readers, DLR was significantly superior to Hybrid IR in terms of image quality (p ≤ 0.021). CONCLUSION: DLR improved HCC detection, interobserver agreement for LI-RADS categories, and image quality in evaluations of HCC compared to Hybrid IR in abdominal dynamic contrast-enhanced CT.

Stereotactic Radiosurgery Provides Long-Term Safety for Patients With Arteriovenous Malformations in the Diencephalon and Brainstem: The Optimal Dose Selection and Long-Term Outcomes.

BACKGROUND: Arteriovenous malformations (AVMs) of the diencephalon (DC) and brainstem (BS) are difficult to treat. Stereotactic radiosurgery (SRS) is a reasonable option; however, an optimal radiosurgical dose needs to be established to optimize long-term outcomes. OBJECTIVE: To evaluate dose-dependent long-term outcomes of SRS for DC/BS-AVMs. METHODS: We retrospectively analyzed the long-term outcomes of 118 patients who had SRS-treated DC/BS-AVMs. The outcomes included post-SRS hemorrhage, AVM obliteration, neurological outcomes, and disease-specific survival. According to margin doses, the patients were classified into low (<18 Gy), medium (18-20 Gy), and high (>20 Gy) dose groups. RESULTS: SRS reduced the annual hemorrhage rate from 8.6% to 1.6% before obliteration and 0.0% after obliteration. The cumulative hemorrhage rate in the low dose group was likely to be higher than that in the other groups ( P = .113). The cumulative obliteration rates in the entire cohort were 74% and 83% at 5 and 10 years, respectively, and were significantly lower in the low dose group than in the other groups (vs medium dose: P = .027, vs high dose: P = .016). Multivariate analyses demonstrated that low dose SRS was significantly associated with worse obliteration rates (hazard ratio 0.18, 95% CI 0.04-0.79; P = .023). CONCLUSION: SRS with a margin dose of 18 to 20 Gy for DC/BS-AVMs may be optimal, providing a higher obliteration rate and lower risk of post-SRS hemorrhage than lower dose SRS. Dose reduction to <18 Gy should only be optional when higher doses are intolerable.

MRI-Based Radiomics Differentiates Skull Base Chordoma and Chondrosarcoma: A Preliminary Study.

Chordoma and chondrosarcoma share common radiographic characteristics yet are distinct clinically. A radiomic machine learning model differentiating these tumors preoperatively would help plan surgery. MR images were acquired from 57 consecutive patients with chordoma (N = 32) or chondrosarcoma (N = 25) treated at the University of Tokyo Hospital between September 2012 and February 2020. Preoperative T1-weighted images with gadolinium enhancement (GdT1) and T2-weighted images were analyzed. Datasets from the first 47 cases were used for model creation, and those from the subsequent 10 cases were used for validation. Feature extraction was performed semi-automatically, and 2438 features were obtained per image sequence. Machine learning models with logistic regression and a support vector machine were created. The model with the highest accuracy incorporated seven features extracted from GdT1 in the logistic regression. The average area under the curve was 0.93 ± 0.06, and accuracy was 0.90 (9/10) in the validation dataset. The same validation dataset was assessed by 20 board-certified neurosurgeons. Diagnostic accuracy ranged from 0.50 to 0.80 (median 0.60, 95% confidence interval 0.60 ± 0.06%), which was inferior to that of the machine learning model (p = 0.03), although there are some limitations, such as the risk of overfitting and the lack of an extramural cohort for truly independent final validation. In summary, we created a novel MRI-based machine learning model to differentiate skull base chordoma and chondrosarcoma from multiparametric signatures.

Hemodynamic changes during the obliteration process for cerebral arteriovenous malformations after radiosurgery.

OBJECTIVE: The process of cerebral arteriovenous malformation (AVM) obliteration following radiosurgery is poorly understood. Authors of this retrospective study aimed to assess the changes in AVM hemodynamics after stereotactic radiosurgery (SRS) by using 3D flow magnetic resonance imaging (MRI) to elucidate the process of AVM obliteration. METHODS: Twenty-four patients with AVMs treated with SRS between July 2015 and December 2017 were included in this study and classified into two groups depending on the duration of AVM obliteration: group A, obliteration within 3 years (n = 15); and group B, obliteration taking more than 3 years or no obliteration (n = 9). Blood flow (ml/min) in the largest feeding artery was measured before and after SRS by using time-averaged 3D flow MRI. The decreasing rate of blood flow in the feeding artery after SRS was calculated as the percent change from baseline blood flow. A Wilcoxon rank-sum test was used to compare the decreasing blood flow rate between the two groups at 4 and 12 months after SRS. RESULTS: For the entire cohort, the mean decrease in blood flow in the feeding artery from baseline was 29% at 4 months and 71% at 12 months after SRS. In general, blood flow after SRS decreased faster in group A and slower in group B. The decreasing rates in blood flow at 4 and 12 months after SRS were significantly different between the two groups (p = 0.02 and < 0.001, respectively). CONCLUSIONS: Tracking changes in AVM hemodynamics after SRS may be useful for assessing the progress of AVM obliteration and the therapeutic effects of SRS, possibly contributing to the prediction of subsequent obliteration outcome.

Accurate Preoperative Identification of Motor Speech Area as Termination of Arcuate Fasciculus Depicted by Q-Ball Imaging Tractography.

BACKGROUND: Tractography is one way to predict the distribution of cortical functional domains preoperatively. Diffusion tensor tractography (DTT) is commonly used in clinical practice, but is known to have limitations in delineating crossed fibers, which can be overcome by Q-ball imaging tractography (QBT). We aimed to compare the reliability of these 2 methods based on the spatial correlation between the arcuate fasciculus depicted by tractography and direct cortical stimulation during awake surgery. METHODS: In this study, 15 patients with glioma underwent awake surgery with direct cortical stimulation. Tractography was depicted in a three-dimensional computer graphic model preoperatively, which was integrated with a photograph of the actual brain cortex using our novel mixed-reality technology. The termination of the arcuate fasciculus depicted by either DTT or QBT and the results of direct cortical stimulation were compared, and sensitivity and specificity were calculated in speech-associated brain gyri: pars triangularis, pars opercularis, ventral precentral gyrus, and middle frontal gyrus. RESULTS: QBT had significantly better sensitivity and lower false-positive rate than DTT in the pars opercularis. The same trend was noted for the other gyri. CONCLUSIONS: QBT is more reliable than DTT in identification of the motor speech area and may be clinically useful in brain tumor surgery.

Speciation of tin ions in oxide glass containing iron oxide through solvent extraction and inductively coupled plasma atomic emission spectrometry after the decomposition utilizing ascorbic acid.

Determining the concentrations of different Sn ions in glass containing iron oxide by wet chemical analysis is a challenge because a redox reaction occurs between Sn2+ and Fe3+. A chemical analysis method for determining the concentrations of Sn2+ and Sn4+ in soda lime glass containing iron oxide was proposed. A mixture of ascorbic acid, hydrochloric acid, and hydrofluoric acid was used to decompose the sample in a vessel with nitrogen flow. Ascorbic acid functioned as a reductant for Fe3+. Subsequently, the Sn2+ were separated as a diethyldithiocarbamate complex. Furthermore, inductively coupled plasma atomic emission spectroscopy was used to determine the concentrations of Sn4+ and total Sn, from which the concentration of Sn2+ can be calculated. The results were validated by comparing ratios of Sn2+ to total Sn to results obtained using Mössbauer spectroscopy. The results were in agreement, thereby validating the use of the proposed approach.

Correlation of Inflow Velocity Ratio Detected by Phase Contrast Magnetic Resonance Angiography with the Bleb Color of Unruptured Intracranial Aneurysms.

BACKGROUND: Intraoperative rupture is the most fatal and catastrophic complication of surgery for unruptured intracranial aneurysms (UIAs); thus, it is extremely useful to predict reddish and thin-walled regions of the UIA before surgery. Although several studies have reported a relationship between the hemodynamic characteristics and intracranial aneurysm wall thickness, a consistent opinion is lacking. We aimed to investigate the relationship between objectively and quantitatively evaluated bleb wall color and hemodynamic characteristics using phase-contrast magnetic resonance angiography (PC-MRA). METHODS: Ten patients diagnosed with UIA who underwent surgical clipping and preoperative magnetic resonance imaging along with PC-MRA were included in this study. Bleb wall color was evaluated from an intraoperative video. Based on the Red (R), Green, and Blue values, bleb wall redness (modified R value; mR) was calculated and compared with the hemodynamic characteristics obtained from PC-MRA. RESULTS: The wall redness distribution of 18 blebs in 11 UIAs in 10 patients was analyzed. Bleb/neck inflow velocity ratio (Vb/Va: r = 0.66, P = 0.003) strongly correlated with mR, whereas bleb/neck inflow rate ratio (r = 0.58, P = 0.012) correlated moderately. Multivariate regression analysis revealed that only Vb/Va (P = 0.017) significantly correlated with mR. There was no correlation between wall shear stress and mR. CONCLUSIONS: The bleb redness of UIAs and Vb/Va, calculated using PC-MRA, showed a significantly greater correlation. Thus, it is possible to predict bleb thickness noninvasively before surgery. This will facilitate more detailed pre- and intraoperative strategies for clipping and coiling for safe surgery.

Rotational Angiography-Based Gamma Knife Radiosurgery for Brain Arteriovenous Malformations: Preliminary Therapeutic Outcomes of the Novel Method.

BACKGROUND: High-definition vascular imaging is desirable for treatment planning in Gamma Knife radiosurgery (GKRS; Elekta AB) for brain arteriovenous malformations (BAVMs). Currently, rotational angiography (RA) provides the clearest 3-dimensional visualization of niduses with high spatial resolution; however, its efficacy for GKRS has not been clarified. At our institution, RA has been integrated into GKRS (RA-GKRS) for better treatment planning and outcomes since 2015. OBJECTIVE: To evaluate RA-GKRS outcomes of BAVMs and compare them with conventional GKRS (c-GKRS) outcomes. METHODS: We retrospectively analyzed the radiosurgical outcomes of 50 BAVMs treated with RA-GKRS compared with the 306 BAVMs treated with c-GKRS. Considering possible differences in the baseline characteristics, we also created propensity score-matched cohorts and compared the radiosurgical outcomes between them to ensure comparability. RESULTS: The obliteration time was shorter in the RA-GKRS group (cumulative rate, 88% vs 65% at 4 yr [P = .001]). Multivariate Cox proportional hazards analysis demonstrated that the RA-GKRS group (hazard ratio 2.38, 95% CI 1.58-3.60; P = .001) had a better obliteration rate. The cumulative 4-yr post-GKRS hemorrhage rates were 4.0% and 2.6% in the RA-GKRS and c-GKRS groups, respectively (P = .558). There was a trend toward early post-GKRS signal change in the RA-GKRS group compared with the c-GKRS group (cumulative rate, 38% vs 29% at 2 yr; P = .118). Those results were also confirmed in the matched cohort analyses. CONCLUSION: The integration of RA into GKRS is promising and may provide earlier nidus obliteration.

Lipid nanoparticles loaded with ribonucleoprotein-oligonucleotide complexes synthesized using a microfluidic device exhibit robust genome editing and hepatitis B virus inhibition.

The clustered regularly interspaced short palindromic repeats (CRISPR)-associated (Cas) system has considerable therapeutic potential for use in treating a wide range of intractable genetic and infectious diseases including hepatitis B virus (HBV) infections. While non-viral delivery technologies for the CRISPR/Cas system are expected to have clinical applications, difficulties associated with the clinically relevant synthesis of formulations and the poor efficiency of delivery severely hinder therapeutic genome editing. We report herein on the production of a lipid nanoparticle (LNP)-based CRISPR/Cas ribonucleoprotein (RNP) delivery nanoplatform synthesized using a clinically relevant mixer-equipped microfluidic device. DNA cleavage activity and the aggregation of Cas enzymes was completely avoided under the optimized synthetic conditions. The optimized formulation, which was identified through 2 steps of design of experiments, exhibited excellent gene disruption (up to 97%) and base substitution (up to 23%) without any apparent cytotoxicity. The addition of negative charges to the RNPs by complexing single-stranded oligonucleotide (ssON) significantly enhanced the delivery of both Cas9 and Cpf1 RNPs. The optimized formulation significantly suppressed both HBV DNA and covalently closed circular DNA (cccDNA) in HBV-infected human liver cells compared to adeno-associated virus type 2 (AAV2). These findings represent a significant contribution to the development of CRISPR/Cas RNP delivery technology and its practical applications in genome editing therapy.

Manipulating the function of tumor-associated macrophages by siRNA-loaded lipid nanoparticles for cancer immunotherapy.

The tumor-microenvironment contains large numbers of tumor-associated macrophages (TAMs) which are largely M2 phenotypes and are involved in pro-tumorous functions. Targeting TAMs so as to manipulate them and to modify their functions could be a novel immunotherapy for the treatment of cancer. Such a strategy would involve targeting TAMs with short interfering RNA (siRNA) to modify their functions by silencing certain genes that are responsible for their M2 polarization. In this study, a lipid nanoparticle (LNP) formulation was used to target and deliver siRNA to TAMs. The LNP was mainly composed of a novel, pH-sensitive cationic lipid, referred to as the CL4H6 lipid, which had previously been optimized to target hepatocytes. The optimized siRNA-loaded CL4H6-LNPs were selectively and efficiently taken up and showed strong gene silencing activity in TAMs in a human tumor xenograft model in nude mice. Furthermore, an anti-tumor therapeutic response in the same tumor model was obtained by targeting TAMs using the optimized siRNA-loaded CL4H6-LNPs. The anti-tumor therapeutic response was obtained through the silencing of the signal transducer and activator of transcription 3 (STAT3) and hypoxia inducible factor 1 α (HIF-1α), which resulted in an increase in the level of infiltrated macrophage (CD11b+ cells) into the tumor-microenvironment (TME) as well as a tendency to increase the concentration of M1 macrophages (CD169+ cells). The treatment also resulted in reversing the pro-tumorous functions of TAMs -mainly angiogenesis and tumor cell activation-, as evidenced by a decrease in the related gene expression at the mRNA level. This research has promising clinical and pharmaceutical applications for achieving novel macrophage-based cancer immunotherapy.

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.