Incorporating Supramaximal Resection into Survival Stratification of IDH-Wildtype Glioblastoma: A Refined Multi-institutional Recursive Partitioning Analysis.

PURPOSE: To propose a novel recursive partitioning analysis (RPA) classification model in patients with IDH-wildtype glioblastomas that incorporates the recently expanded conception of the extent of resection (EOR) in terms of both supramaximal and total resections. EXPERIMENTAL DESIGN: This multicenter cohort study included a developmental cohort of 622 patients with IDH-wildtype glioblastomas from a single institution (Severance Hospital) and validation cohorts of 536 patients from three institutions (Seoul National University Hospital, Asan Medical Center, and Heidelberg University Hospital). All patients completed standard treatment including concurrent chemoradiotherapy and underwent testing to determine their IDH mutation and MGMTp methylation status. EORs were categorized into either supramaximal, total, or non-total resections. A novel RPA model was then developed and compared to a previous RTOG RPA model. RESULTS: In the developmental cohort, the RPA model included age, MGMTp methylation status, KPS, and EOR. Younger patients with MGMTp methylation and supramaximal resections showed a more favorable prognosis (class I: median overall survival [OS] 57.3 months), while low-performing patients with non-total resections and without MGMTp methylation showed the worst prognosis (class IV: median OS 14.3 months). The prognostic significance of the RPA was subsequently confirmed in the validation cohorts, which revealed a greater separation between prognostic classes for all cohorts compared to the previous RTOG RPA model. CONCLUSIONS: The proposed RPA model highlights the impact of supramaximal versus total resections and incorporates clinical and molecular factors into survival stratification. The RPA model may improve the accuracy of assessing prognostic groups.

Added value of dynamic contrast-enhanced MR imaging in deep learning-based prediction of local recurrence in grade 4 adult-type diffuse gliomas patients.

Local recurrences in patients with grade 4 adult-type diffuse gliomas mostly occur within residual non-enhancing T2 hyperintensity areas after surgical resection. Unfortunately, it is challenging to distinguish non-enhancing tumors from edema in the non-enhancing T2 hyperintensity areas using conventional MRI alone. Quantitative DCE MRI parameters such as Ktrans and Ve convey permeability information of glioblastomas that cannot be provided by conventional MRI. We used the publicly available nnU-Net to train a deep learning model that incorporated both conventional and DCE MRI to detect the subtle difference in vessel leakiness due to neoangiogenesis between the non-recurrence area and the local recurrence area, which contains a higher proportion of high-grade glioma cells. We found that the addition of Ve doubled the sensitivity while nonsignificantly decreasing the specificity for prediction of local recurrence in glioblastomas, which implies that the combined model may result in fewer missed cases of local recurrence. The deep learning model predictive of local recurrence may enable risk-adapted radiotherapy planning in patients with grade 4 adult-type diffuse gliomas.

Added prognostic value of 3D deep learning-derived features from preoperative MRI for adult-type diffuse gliomas.

BACKGROUND: To investigate the prognostic value of spatial features from whole-brain MRI using a three-dimensional (3D) convolutional neural network for adult-type diffuse gliomas. METHODS: In a retrospective, multicenter study, 1925 diffuse glioma patients were enrolled from 5 datasets: SNUH (n = 708), UPenn (n = 425), UCSF (n = 500), TCGA (n = 160), and Severance (n = 132). The SNUH and Severance datasets served as external test sets. Precontrast and postcontrast 3D T1-weighted, T2-weighted, and T2-FLAIR images were processed as multichannel 3D images. A 3D-adapted SE-ResNeXt model was trained to predict overall survival. The prognostic value of the deep learning-based prognostic index (DPI), a spatial feature-derived quantitative score, and established prognostic markers were evaluated using Cox regression. Model evaluation was performed using the concordance index (C-index) and Brier score. RESULTS: The MRI-only median DPI survival prediction model achieved C-indices of 0.709 and 0.677 (BS = 0.142 and 0.215) and survival differences (P < 0.001 and P = 0.002; log-rank test) for the SNUH and Severance datasets, respectively. Multivariate Cox analysis revealed DPI as a significant prognostic factor, independent of clinical and molecular genetic variables: hazard ratio = 0.032 and 0.036 (P < 0.001 and P = 0.004) for the SNUH and Severance datasets, respectively. Multimodal prediction models achieved higher C-indices than models using only clinical and molecular genetic variables: 0.783 vs. 0.774, P = 0.001, SNUH; 0.766 vs. 0.748, P = 0.023, Severance. CONCLUSIONS: The global morphologic feature derived from 3D CNN models using whole-brain MRI has independent prognostic value for diffuse gliomas. Combining clinical, molecular genetic, and imaging data yields the best performance.

The 2021 WHO Classification for Gliomas and Implications on Imaging Diagnosis: Part 3-Summary of Imaging Findings on Glioneuronal and Neuronal Tumors.

The fifth edition of the World Health Organization classification of central nervous system tumors published in 2021 reflects the current transitional state between traditional classification system based on histopathology and the state-of-the-art molecular diagnostics. This Part 3 Review focuses on the molecular diagnostics and imaging findings of glioneuronal and neuronal tumors. Histological and molecular features in glioneuronal and neuronal tumors often overlap with pediatric-type diffuse low-grade gliomas and circumscribed astrocytic gliomas (discussed in the Part 2 Review). Due to this overlap, in several tumor types of glioneuronal and neuronal tumors the diagnosis may be inconclusive with histopathology and genetic alterations, and imaging features may be helpful to distinguish difficult cases. Thus, it is crucial for radiologists to understand the underlying molecular diagnostics as well as imaging findings for application on clinical practice. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 3.

Validation of Ultrasound and Computed Tomography-Based Risk Stratification System and Biopsy Criteria for Cervical Lymph Nodes in Preoperative Patients With Thyroid Cancer.

OBJECTIVE: This study aimed to validate the risk stratification system (RSS) and biopsy criteria for cervical lymph nodes (LNs) proposed by the Korean Society of Thyroid Radiology (KSThR). MATERIALS AND METHODS: This retrospective study included a consecutive series of preoperative patients with thyroid cancer who underwent LN biopsy, ultrasound (US), and computed tomography (CT) between December 2006 and June 2015. LNs were categorized as probably benign, indeterminate, or suspicious according to the current US- and CT-based RSS and the size thresholds for cervical LN biopsy as suggested by the KSThR. The diagnostic performance and unnecessary biopsy rates were calculated. RESULTS: A total of 277 LNs (53.1% metastatic) in 228 patients (mean age ± standard deviation, 47.4 years ± 14) were analyzed. In US, the malignancy risks were significantly different among the three categories (all P < 0.001); however, CT-detected probably benign and indeterminate LNs showed similarly low malignancy risks (P = 0.468). The combined US + CT criteria stratified the malignancy risks among the three categories (all P < 0.001) and reduced the proportion of indeterminate LNs (from 20.6% to 14.4%) and the malignancy risk in the indeterminate LNs (from 31.6% to 12.5%) compared with US alone. In all image-based classifications, nodal size did not affect the malignancy risks (short diameter [SD] ≤ 5 mm LNs vs. SD > 5 mm LNs, P ≥ 0.177). The criteria covering only suspicious LNs showed higher specificity and lower unnecessary biopsy rates than the current criteria, while maintaining sensitivity in all imaging modalities. CONCLUSION: Integrative evaluation of US and CT helps in reducing the proportion of indeterminate LNs and the malignancy risk among them. Nodal size did not affect the malignancy risk of LNs, and the addition of indeterminate LNs to biopsy candidates did not have an advantage in detecting LN metastases in all imaging modalities.

Deep learning based on dynamic susceptibility contrast MR imaging for prediction of local progression in adult-type diffuse glioma (grade 4).

Adult-type diffuse glioma (grade 4) has infiltrating nature, and therefore local progression is likely to occur within surrounding non-enhancing T2 hyperintense areas even after gross total resection of contrast-enhancing lesions. Cerebral blood volume (CBV) obtained from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) is a parameter that is well-known to be a surrogate marker of both histologic and angiographic vascularity in tumors. We built two nnU-Net deep learning models for prediction of early local progression in adult-type diffuse glioma (grade 4), one using conventional MRI alone and one using multiparametric MRI, including conventional MRI and DSC-PWI. Local progression areas were annotated in a non-enhancing T2 hyperintense lesion on preoperative T2 FLAIR images, using the follow-up contrast-enhanced (CE) T1-weighted (T1W) images as the reference standard. The sensitivity was doubled with the addition of nCBV (80% vs. 40%, P = 0.02) while the specificity was decreased nonsignificantly (29% vs. 48%, P = 0.39), suggesting that fewer cases of early local progression would be missed with the addition of nCBV. While the diagnostic performance of CBV model is still poor and needs improving, the multiparametric deep learning model, which presumably learned from the subtle difference in vascularity between early local progression and non-progression voxels within perilesional T2 hyperintensity, may facilitate risk-adapted radiotherapy planning in adult-type diffuse glioma (grade 4) patients.

Risk estimation for idiopathic normal-pressure hydrocephalus: development and validation of a brain morphometry-based nomogram.

OBJECTIVES: To develop and validate a nomogram based on MRI features for predicting iNPH. METHODS: Patients aged ≥ 60 years (clinically diagnosed with iNPH, Parkinson's disease, or Alzheimer's disease or healthy controls) who underwent MRI including three-dimensional T1-weighted volumetric MRI were retrospectively identified from two tertiary referral hospitals (one hospital for derivation set and the other for validation set). Clinical and imaging features for iNPH were assessed. Deep learning-based brain segmentation software was used for 3D volumetry. A prediction model was developed using logistic regression and transformed into a nomogram. The performance of the nomogram was assessed with respect to discrimination and calibration abilities. The nomogram was internally and externally validated. RESULTS: A total of 452 patients (mean age ± SD, 73.2 ± 6.5 years; 200 men) were evaluated as the derivation set. One hundred eleven and 341 patients were categorized into the iNPH and non-iNPH groups, respectively. In multivariable analysis, high-convexity tightness (odds ratio [OR], 35.1; 95% CI: 4.5, 275.5), callosal angle < 90° (OR, 12.5; 95% CI: 3.1, 50.0), and normalized lateral ventricle volume (OR, 4.2; 95% CI: 2.7, 6.7) were associated with iNPH. The nomogram combining these three variables showed an area under the curve of 0.995 (95% CI: 0.991, 0.999) in the study sample, 0.994 (95% CI: 0.990, 0.998) in the internal validation sample, and 0.969 (95% CI: 0.940, 0.997) in the external validation sample. CONCLUSION: A brain morphometry-based nomogram including high-convexity tightness, callosal angle < 90°, and normalized lateral ventricle volume can help accurately estimate the probability of iNPH. KEY POINTS: • The nomogram with MRI findings (high-convexity tightness, callosal angle, and normalized lateral ventricle volume) helped in predicting the probability of idiopathic normal-pressure hydrocephalus. • The nomogram may facilitate the prediction of idiopathic normal-pressure hydrocephalus and consequently avoid unnecessary invasive procedures such as the cerebrospinal fluid tap test, drainage test, and cerebrospinal fluid shunt surgery.

Fully Automated MRI Segmentation and Volumetric Measurement of Intracranial Meningioma Using Deep Learning.

BACKGROUND: Accurate and rapid measurement of the MRI volume of meningiomas is essential in clinical practice to determine the growth rate of the tumor. Imperfect automation and disappointing performance for small meningiomas of previous automated volumetric tools limit their use in routine clinical practice. PURPOSE: To develop and validate a computational model for fully automated meningioma segmentation and volume measurement on contrast-enhanced MRI scans using deep learning. STUDY TYPE: Retrospective. POPULATION: A total of 659 intracranial meningioma patients (median age, 59.0 years; interquartile range: 53.0-66.0 years) including 554 women and 105 men. FIELD STRENGTH/SEQUENCE: The 1.0 T, 1.5 T, and 3.0 T; three-dimensional, T1 -weighted gradient-echo imaging with contrast enhancement. ASSESSMENT: The tumors were manually segmented by two neurosurgeons, H.K. and C.-K.P., with 10 and 26 years of clinical experience, respectively, for use as the ground truth. Deep learning models based on U-Net and nnU-Net were trained using 459 subjects and tested for 100 patients from a single institution (internal validation set [IVS]) and 100 patients from other 24 institutions (external validation set [EVS]), respectively. The performance of each model was evaluated with the Sørensen-Dice similarity coefficient (DSC) compared with the ground truth. STATISTICAL TESTS: According to the normality of the data distribution verified by the Shapiro-Wilk test, variables with three or more categories were compared by the Kruskal-Wallis test with Dunn's post hoc analysis. RESULTS: A two-dimensional (2D) nnU-Net showed the highest median DSCs of 0.922 and 0.893 for the IVS and EVS, respectively. The nnU-Nets achieved superior performance in meningioma segmentation than the U-Nets. The DSCs of the 2D nnU-Net for small meningiomas less than 1 cm3 were 0.769 and 0.780 with the IVS and EVS, respectively. DATA CONCLUSION: A fully automated and accurate volumetric measurement tool for meningioma with clinically applicable performance for small meningioma using nnU-Net was developed. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Validation of MRI-Based Models to Predict MGMT Promoter Methylation in Gliomas: BraTS 2021 Radiogenomics Challenge.

O6-methylguanine-DNA methyl transferase (MGMT) methylation prediction models were developed using only small datasets without proper external validation and achieved good diagnostic performance, which seems to indicate a promising future for radiogenomics. However, the diagnostic performance was not reproducible for numerous research teams when using a larger dataset in the RSNA-MICCAI Brain Tumor Radiogenomic Classification 2021 challenge. To our knowledge, there has been no study regarding the external validation of MGMT prediction models using large-scale multicenter datasets. We tested recent CNN architectures via extensive experiments to investigate whether MGMT methylation in gliomas can be predicted using MR images. Specifically, prediction models were developed and validated with different training datasets: (1) the merged (SNUH + BraTS) (n = 985); (2) SNUH (n = 400); and (3) BraTS datasets (n = 585). A total of 420 training and validation experiments were performed on combinations of datasets, convolutional neural network (CNN) architectures, MRI sequences, and random seed numbers. The first-place solution of the RSNA-MICCAI radiogenomic challenge was also validated using the external test set (SNUH). For model evaluation, the area under the receiver operating characteristic curve (AUROC), accuracy, precision, and recall were obtained. With unexpected negative results, 80.2% (337/420) and 60.0% (252/420) of the 420 developed models showed no significant difference with a chance level of 50% in terms of test accuracy and test AUROC, respectively. The test AUROC and accuracy of the first-place solution of the BraTS 2021 challenge were 56.2% and 54.8%, respectively, as validated on the SNUH dataset. In conclusion, MGMT methylation status of gliomas may not be predictable with preoperative MR images even using deep learning.

Validation of Ultrasound Risk Stratification Systems for Cervical Lymph Node Metastasis in Patients with Thyroid Cancer.

A malignancy risk stratification system (RSS) for cervical lymph nodes (LNs) has not been fully established. This study aimed to validate the current RSS for the diagnosis of cervical LN metastasis in thyroid cancer. In total, 346 LNs from 282 consecutive patients between December 2006 and June 2015 were included. We determined the malignancy risk of each ultrasound (US) feature and performed univariable and multivariable logistic regression analyses. Each risk category from the Korean Society of Thyroid Radiology (KSThR) and the European Thyroid Association (ETA) was applied to calculate malignancy risks. The effects of size, number of suspicious features, and primary tumor characteristics were analyzed to refine the current RSS. Suspicious features including echogenic foci, cystic change, hyperechogenicity, and abnormal vascularity were independently predictive of malignancy (p ≤ 0.045). The malignancy risks of probably benign, indeterminate, and suspicious categories were 2.2-2.5%, 26.8-29.0%, and 85.8-87.4%, respectively, according to the KSThR and ETA criteria. According to the ETA criteria, 15.1% of LNs were unclassifiable. In indeterminate LNs, multiplicity of the primary tumor was significantly associated with malignancy (odds ratio, 6.53; p = 0.004). We refined the KSThR system and proposed a US RSS for LNs in patients with thyroid cancer.

Deep learning model for diagnosing gastric mucosal lesions using endoscopic images: development, validation, and method comparison.

BACKGROUND AND AIMS: Endoscopic differential diagnoses of gastric mucosal lesions (benign gastric ulcer, early gastric cancer [EGC], and advanced gastric cancer) remain challenging. We aimed to develop and validate convolutional neural network-based artificial intelligence (AI) models: lesion detection, differential diagnosis (AI-DDx), and invasion depth (AI-ID; pT1a vs pT1b among EGC) models. METHODS: This study included 1366 consecutive patients with gastric mucosal lesions from 2 referral centers in Korea. One representative endoscopic image from each patient was used. Histologic diagnoses were set as the criterion standard. Performance of the AI-DDx (training/internal/external validation set, 1009/112/245) and AI-ID (training/internal/external validation set, 620/68/155) was compared with visual diagnoses by independent endoscopists (stratified by novice [<1 year of experience], intermediate [2-3 years of experience], and expert [>5 years of experience]) and EUS results, respectively. RESULTS: The AI-DDx showed good diagnostic performance for both internal (area under the receiver operating characteristic curve [AUROC] = .86) and external validation (AUROC = .86). The performance of the AI-DDx was better than that of novice (AUROC = .82, P = .01) and intermediate endoscopists (AUROC = .84, P = .02) but was comparable with experts (AUROC = .89, P = .12) in the external validation set. The AI-ID showed a fair performance in both internal (AUROC = .78) and external validation sets (AUROC = .73), which were significantly better than EUS results performed by experts (internal validation, AUROC = .62; external validation, AUROC = .56; both P < .001). CONCLUSIONS: The AI-DDx was comparable with experts and outperformed novice and intermediate endoscopists for the differential diagnosis of gastric mucosal lesions. The AI-ID performed better than EUS for evaluation of invasion depth.

Deep Learning for Detection of Pulmonary Metastasis on Chest Radiographs.

Background A computer-aided detection (CAD) system may help surveillance for pulmonary metastasis at chest radiography in situations where there is limited access to CT. Purpose To evaluate whether a deep learning (DL)-based CAD system can improve diagnostic yield for newly visible lung metastasis on chest radiographs in patients with cancer. Materials and Methods A regulatory-approved CAD system for lung nodules was implemented to interpret chest radiographs from patients referred by the medical oncology department in clinical practice. In this retrospective diagnostic cohort study, chest radiographs interpreted with assistance from a CAD system after the implementation (January to April 2019, CAD-assisted interpretation group) and those interpreted before the implementation (September to December 2018, conventional interpretation group) of the CAD system were consecutively included. The diagnostic yield (frequency of true-positive detections) and false-referral rate (frequency of false-positive detections) of formal reports of chest radiographs for newly visible lung metastasis were compared between the two groups using generalized estimating equations. Propensity score matching was performed between the two groups for age, sex, and primary cancer. Results A total of 2916 chest radiographs from 1521 patients (1546 men, 1370 women; mean age, 62 years) and 5681 chest radiographs from 3456 patients (2941 men, 2740 women; mean age, 62 years) were analyzed in the CAD-assisted interpretation and conventional interpretation groups, respectively. The diagnostic yield for newly visible metastasis was higher in the CAD-assisted interpretation group (0.86%, 25 of 2916 [95% CI: 0.58, 1.3] vs 0.32%, 18 of 568 [95% CI: 0.20, 0.50%]; P = .004). The false-referral rate in the CAD-assisted interpretation group (0.34%, 10 of 2916 [95% CI: 0.19, 0.64]) was not inferior to that in the conventional interpretation group (0.25%, 14 of 5681 [95% CI: 0.15, 0.42]) at the noninferiority margin of 0.5% (95% CI of difference: -0.15, 0.35). Conclusion A deep learning-based computer-aided detection system improved the diagnostic yield for newly visible metastasis on chest radiographs in patients with cancer with a similar false-referral rate. © RSNA, 2021 Online supplemental material is available for this article.

Prediction of Prognosis in Glioblastoma Using Radiomics Features of Dynamic Contrast-Enhanced MRI.

OBJECTIVE: To develop a radiomics risk score based on dynamic contrast-enhanced (DCE) MRI for prognosis prediction in patients with glioblastoma. MATERIALS AND METHODS: One hundred and fifty patients (92 male [61.3%]; mean age ± standard deviation, 60.5 ± 13.5 years) with glioblastoma who underwent preoperative MRI were enrolled in the study. Six hundred and forty-two radiomic features were extracted from volume transfer constant (Ktrans), fractional volume of vascular plasma space (Vp), and fractional volume of extravascular extracellular space (Ve) maps of DCE MRI, wherein the regions of interest were based on both T1-weighted contrast-enhancing areas and non-enhancing T2 hyperintense areas. Using feature selection algorithms, salient radiomic features were selected from the 642 features. Next, a radiomics risk score was developed using a weighted combination of the selected features in the discovery set (n = 105); the risk score was validated in the validation set (n = 45) by investigating the difference in prognosis between the "radiomics risk score" groups. Finally, multivariable Cox regression analysis for progression-free survival was performed using the radiomics risk score and clinical variables as covariates. RESULTS: 16 radiomic features obtained from non-enhancing T2 hyperintense areas were selected among the 642 features identified. The radiomics risk score was used to stratify high- and low-risk groups in both the discovery and validation sets (both p < 0.001 by the log-rank test). The radiomics risk score and presence of isocitrate dehydrogenase (IDH) mutation showed independent associations with progression-free survival in opposite directions (hazard ratio, 3.56; p = 0.004 and hazard ratio, 0.34; p = 0.022, respectively). CONCLUSION: We developed and validated the "radiomics risk score" from the features of DCE MRI based on non-enhancing T2 hyperintense areas for risk stratification of patients with glioblastoma. It was associated with progression-free survival independently of IDH mutation status.

Radiomics-based neural network predicts recurrence patterns in glioblastoma using dynamic susceptibility contrast-enhanced MRI.

Glioblastoma remains the most devastating brain tumor despite optimal treatment, because of the high rate of recurrence. Distant recurrence has distinct genomic alterations compared to local recurrence, which requires different treatment planning both in clinical practice and trials. To date, perfusion-weighted MRI has revealed that perfusional characteristics of tumor are associated with prognosis. However, not much research has focused on recurrence patterns in glioblastoma: namely, local and distant recurrence. Here, we propose two different neural network models to predict the recurrence patterns in glioblastoma that utilizes high-dimensional radiomic profiles based on perfusion MRI: area under the curve (AUC) (95% confidence interval), 0.969 (0.903-1.000) for local recurrence; 0.864 (0.726-0.976) for distant recurrence for each patient in the validation set. This creates an opportunity to provide personalized medicine in contrast to studies investigating only group differences. Moreover, interpretable deep learning identified that salient radiomic features for each recurrence pattern are related to perfusional intratumoral heterogeneity. We also demonstrated that the combined salient radiomic features, or "radiomic risk score", increased risk of recurrence/progression (hazard ratio, 1.61; p = 0.03) in multivariate Cox regression on progression-free survival.

Absolute quantification of tumor-infiltrating immune cells in high-grade glioma identifies prognostic and radiomics values.

PURPOSE: To understand the tumor immune microenvironment precisely, it is important to secure the quantified data of tumor-infiltrating immune cells, since the immune cells are true working unit. We analyzed unit immune cell number per unit volume of core tumor tissue of high-grade gliomas (HGG) to correlate their immune microenvironment characteristics with clinical prognosis and radiomic signatures. METHODS: The number of tumor-infiltrating immune cells from 64 HGG core tissue were analyzed using flow cytometry and standardized. After sorting out patient groups according to diverse immune characteristics, the groups were tested if they have any clinical prognostic relevance and specific radiomic signature relationships. Sparse partial least square with discriminant analysis using multimodal magnetic resonance images was employed for all radiomic classifications. RESULTS: The median number of CD45 + cells per one gram of HGG core tissue counted 865,770 cells which was equivalent to 8.0% of total cells including tumor cells. There was heterogeneity in the distribution of immune cell subpopulations among patients. Overall survival was significantly better in T cell-deficient group than T cell-enriched group (p = 0.019), and T8 dominant group than T4 dominant group (p = 0.023). The number of tumor-associated macrophages (TAM) and M2-TAM was significantly decreased in isocitrate dehydrogenase mutated HGG. Radiomic signature classification showed good performance in predicting immune phenotypes especially with features extracted from apparent diffusion coefficient maps. CONCLUSIONS: Absolute quantification of tumor-infiltrating immune cells confirmed the heterogeneity of immune microenvironment in HGG which harbors prognostic impact. This immune microenvironment could be predicted by radiomic signatures non-invasively.

Improving the Reliability of Pharmacokinetic Parameters at Dynamic Contrast-enhanced MRI in Astrocytomas: A Deep Learning Approach.

Background Pharmacokinetic (PK) parameters obtained from dynamic contrast agent-enhanced (DCE) MRI evaluates the microcirculation permeability of astrocytomas, but the unreliability from arterial input function (AIF) remains a challenge. Purpose To develop a deep learning model that improves the reliability of AIF for DCE MRI and to validate the reliability and diagnostic performance of PK parameters by using improved AIF in grading astrocytomas. Materials and Methods This retrospective study included 386 patients (mean age, 52 years ± 16 [standard deviation]; 226 men) with astrocytomas diagnosed with histopathologic analysis who underwent dynamic susceptibility contrast (DSC)-enhanced and DCE MRI preoperatively from April 2010 to January 2018. The AIF was obtained from each sequence: AIF obtained from DSC-enhanced MRI (AIFDSC) and AIF measured at DCE MRI (AIFDCE). The model was trained to translate AIFDCE into AIFDSC, and after training, outputted neural-network-generated AIF (AIFgenerated DSC) with input AIFDCE. By using the three different AIFs, volume transfer constant (Ktrans), fractional volume of extravascular extracellular space (Ve), and vascular plasma space (Vp) were averaged from the tumor areas in the DCE MRI. To validate the model, intraclass correlation coefficients and areas under the receiver operating characteristic curve (AUCs) of the PK parameters in grading astrocytomas were compared by using different AIFs. Results The AIF-generated, DSC-derived PK parameters showed higher AUCs in grading astrocytomas than those derived from AIFDCE (mean Ktrans, 0.88 [95% confidence interval {CI}: 0.81, 0.93] vs 0.72 [95% CI: 0.63, 0.79], P = .04; mean Ve, 0.87 [95% CI: 0.79, 0.92] vs 0.70 [95% CI: 0.61, 0.77], P = .049, respectively). Ktrans and Ve showed higher intraclass correlation coefficients for AIFgenerated DSC than for AIFDCE (0.91 vs 0.38, P < .001; and 0.86 vs 0.60, P < .001, respectively). In AIF analysis, baseline signal intensity (SI), maximal SI, and wash-in slope showed higher intraclass correlation coefficients with AIFgenerated DSC than AIFDCE (0.77 vs 0.29, P < .001; 0.68 vs 0.42, P = .003; and 0.66 vs 0.45, P = .01, respectively. Conclusion A deep learning algorithm improved both reliability and diagnostic performance of MRI pharmacokinetic parameters for differentiating astrocytoma grades. © RSNA, 2020 Online supplemental material is available for this article.

Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network.

BACKGROUND: The aim of this study was to predict isocitrate dehydrogenase (IDH) genotypes of gliomas using an interpretable deep learning application for dynamic susceptibility contrast (DSC) perfusion MRI. METHODS: Four hundred sixty-three patients with gliomas who underwent preoperative MRI were enrolled in the study. All the patients had immunohistopathologic diagnoses of either IDH-wildtype or IDH-mutant gliomas. Tumor subregions were segmented using a convolutional neural network followed by manual correction. DSC perfusion MRI was performed to obtain T2* susceptibility signal intensity-time curves from each subregion of the tumors: enhancing tumor, non-enhancing tumor, peritumoral edema, and whole tumor. These, with arterial input functions, were fed into a neural network as multidimensional inputs. A convolutional long short-term memory model with an attention mechanism was developed to predict IDH genotypes. Receiver operating characteristics analysis was performed to evaluate the model. RESULTS: The IDH genotype predictions had an accuracy, sensitivity, and specificity of 92.8%, 92.6%, and 93.1%, respectively, in the validation set (area under the curve [AUC], 0.98; 95% confidence interval [CI], 0.969-0.991) and 91.7%, 92.1%, and 91.5%, respectively, in the test set (AUC, 0.95; 95% CI, 0.898-0.982). In temporal feature analysis, T2* susceptibility signal intensity-time curves obtained from DSC perfusion MRI with attention weights demonstrated high attention on the combination of the end of the pre-contrast baseline, up/downslopes of signal drops, and/or post-bolus plateaus for the curves used to predict IDH genotype. CONCLUSIONS: We developed an explainable recurrent neural network model based on DSC perfusion MRI to predict IDH genotypes in gliomas.

Extremely Small Pseudoparamagnetic Iron Oxide Nanoparticle as a Novel Blood Pool T1 Magnetic Resonance Contrast Agent for 3 T Whole-Heart Coronary Angiography in Canines: Comparison With Gadoterate Meglumine.

OBJECTIVE: The aim of this study was to evaluate an extremely small pseudoparamagnetic iron oxide nanoparticle (ESPIO), KEG3, as a potential blood pool agent in 3 T coronary magnetic resonance angiography (MRA) in canine models and compare its efficacy to that of a gadolinium-based contrast agent. MATERIALS AND METHODS: Nine mongrel dogs were subjected to whole-heart coronary MRA in 2 separate sessions at 7-day intervals with a 3 T scanner using the FLASH sequence with either gadoterate meglumine (Gd-DOTA) or the ESPIO (KEG3). Coronary MRA was performed twice at each MR examination: the first scan during the administration of the contrast agent and the subsequent second scan at 15 minutes after contrast injection. Objective measurements of the Gd-DOTA and ESPIO images, including the signal-to-noise ratios (SNRs) for the coronary arteries and cardiac veins, contrast-to-noise ratios (CNRs) between the vessels and fat (CNRfat) and the vessels and the myocardium (CNRmyocardium), and subjective image quality scores on a 4-point scale were evaluated and compared. RESULTS: The mean SNRs and CNRs of all vascular regions in the ESPIO images were similar to those of the corresponding regions in the Gd-DOTA images in the first scan (98.1 ± 32.5 vs 79.1 ± 38.4 for SNR of coronary arteries, P = 0.3; 74.2 ± 30.1 vs 61.4 ± 38.5 for CNR, P = 0.7) and more than 2 times higher than the latter in the second scan (95.2 ± 31.3 vs 32.1 ± 8.1 for SNR of coronary arteries, P = 0.008; 76.1 ± 35.8 vs 17.6 ± 19.2 for CNR, P 0.008). Similarly, the mean values of the subjective measurements of the ESPIO images were similar to those of the Gd-DOTA images (3.9 ± 0.3 vs 3.3 ± 0.8 for coronary arteries, P = 0.1) in the first scan and significantly better than the latter in the second scan (3.9 ± 0.2 vs 2.1 ± 0.6 for coronary arteries, P = 0.007). CONCLUSIONS: The experimental blood pool agent KEG3 offers equivalent image quality for whole-heart coronary MRA at 3 T upon contrast administration and persistent better quality in the subsequent scans, compared with a traditional extracellular gadolinium-based contrast agent.

Intestinal malrotation in patients with situs anomaly: Implication of the relative positions of the superior mesenteric artery and vein.

PURPOSE: To assess the usefulness of the relative position of the superior mesenteric artery (SMA) and superior mesenteric vein (SMV) in diagnosing intestinal malrotation in situs anomaly. MATERIALS AND METHODS: From January 2004 to April 2015, 33 patients with situs anomalies were enrolled in this study who underwent abdominal USG, CT or MRI as well as upper gastrointestinal series (UGIS) or surgery: situs inversus (n=16), left isomerism (n=10), and right isomerism (n=7); age 21.2±23.2years (mean±standard deviation), range 0-72 years. The intestinal malrotation was confirmed with UGIS and/or operation in 16 patients. Relative positions of the SMV to the SMA were classified into four groups by reviewing abdominal USG, CT, or MRI: right sided, left sided, ventral sided, and dorsal sided. The incidence of malrotation was analyzed for each group. RESULTS: In 16 patients with situs inversus, there was reversed SMA-SMV relationship: left sided (n=11) or ventral sided (n=5). One situs inversus patient with ventral sided SMV had intestinal malrotation (6.25%). 17 patients with situs ambiguus showed various SMA-SMV relationships (ventral sided, n=7; left sided, n=5; right sided, n=4; dorsal sided, n=1). Among them, 15 patients (88.2%) had intestinal malrotation. Two patients with normal rotation had either right sided or dorsal sided SMV. CONCLUSION: Situs ambiguus was commonly associated with intestinal malrotation with a variable SMA-SMV relationship. Reversal of the mesenteric vascular relationship was observed in situs inversus with normal rotation, not excluding the possibility of intestinal malrotation.