MR multitasking-based dynamic imaging for cerebrovascular evaluation (MT-DICE): Simultaneous quantification of permeability and leakage-insensitive perfusion by dynamic T 1 / T 2 * mapping.

PURPOSE: To develop an MR multitasking-based dynamic imaging for cerebrovascular evaluation (MT-DICE) technique for simultaneous quantification of permeability and leakage-insensitive perfusion with a single-dose contrast injection. METHODS: MT-DICE builds on a saturation-recovery prepared multi-echo fast low-angle shot sequence. The k-space is randomly sampled for 7.6 min, with single-dose contrast agent injected 1.5 min into the scan. MR multitasking is used to model the data into six dimensions, including three spatial dimensions for whole-brain coverage, a saturation-recovery time dimension, and a TE dimension for dynamic T 1 $$ {\mathrm{T}}_1 $$ and T 2 * $$ {\mathrm{T}}_2^{\ast } $$ quantification, respectively, and a contrast dynamics dimension for capturing contrast kinetics. The derived pixel-wise T 1 / T 2 * $$ {\mathrm{T}}_1/{\mathrm{T}}_2^{\ast } $$ time series are converted into contrast concentration-time curves for calculation of kinetic metrics. The technique was assessed for its agreement with reference methods in T 1 $$ {\mathrm{T}}_1 $$ and T 2 * $$ {\mathrm{T}}_2^{\ast } $$ measurements in eight healthy subjects and, in three of them, inter-session repeatability of permeability and leakage-insensitive perfusion parameters. Its feasibility was also demonstrated in four patients with brain tumors. RESULTS: MT-DICE T 1 / T 2 * $$ {\mathrm{T}}_1/{\mathrm{T}}_2^{\ast } $$ values of normal gray matter and white matter were in excellent agreement with reference values (intraclass correlation coefficients = 0.860/0.962 for gray matter and 0.925/0.975 for white matter ). Both permeability and perfusion parameters demonstrated good to excellent intersession agreement with the lowest intraclass correlation coefficients at 0.694. Contrast kinetic parameters in all healthy subjects and patients were within the literature range. CONCLUSION: Based on dynamic T 1 / T 2 * $$ {\mathrm{T}}_1/{\mathrm{T}}_2^{\ast } $$ mapping, MT-DICE allows for simultaneous quantification of permeability and leakage-insensitive perfusion metrics with a single-dose contrast injection.

A quantitative characterization of the spatial distribution of brain metastases from breast cancer and respective molecular subtypes.

PURPOSE: Brain metastases (BM) remain a significant cause of morbidity and mortality in breast cancer (BC) patients. Specific factors promoting the process of BM and predilection for selected neuro-anatomical regions remain unknown, yet may have major implications for prevention or treatment. Anatomical spatial distributions of BM from BC suggest a predominance of metastases in the hindbrain and cerebellum. Systematic approaches to quantifying BM location or location-based analyses based on molecular subtypes, however, remain largely unavailable. METHODS: We analyzed stereotactic Cartesian coordinates derived from 134 patients undergoing gamma- knife radiosurgery (GKRS) for treatment of 407 breast cancer BMs to quantitatively study BM spatial distribution along principal component axes and by intrinsic molecular subtype (ER, PR, Herceptin). We used kernel density estimators (KDE) to highlight clustering and distribution regions in the brain, and we used the metric of mutual information (MI) to tease out subtle differences in the BM distributions associated with different molecular subtypes of BC. BM location maps according to vascular and anatomical distributions using Cartesian coordinates to aid in systematic classification of tumor locations were additionally developed. RESULTS: We corroborated that BC BMs show a consistent propensity to arise posteriorly and caudally, and that Her2+ tumors are relatively more likely to arise medially rather than laterally. To compare the distributions among varying BC molecular subtypes, the mutual information metric reveal that the ER-PR-Her2+ and ER-PR-Her2- subtypes show the smallest amount of mutual information and are most molecularly distinct. The kernel density contour plots show a propensity for triple negative BC to arise in more superiorly or cranially situated BMs. CONCLUSIONS: We present a novel and shareable workflow for characterizing and comparing spatial distributions of BM which may aid in identifying therapeutic or diagnostic targets and interactions with the tumor microenvironment. Further characterization of these patterns with larger multi-institutional data-sets may have major impacts on treatment or management of cancer patients.

Six-dimensional quantitative DCE MR Multitasking of the entire abdomen: Method and application to pancreatic ductal adenocarcinoma.

PURPOSE: To develop a quantitative DCE MRI technique enabling entire-abdomen coverage, free-breathing acquisition, 1-second temporal resolution, and T1 -based quantification of contrast agent concentration and kinetic modeling for the characterization of pancreatic ductal adenocarcinoma (PDAC). METHODS: Segmented FLASH readouts following saturation-recovery preparation with randomized 3D Cartesian undersampling was used for incoherent data acquisition. MR Multitasking was used to reconstruct 6-dimensional images with 3 spatial dimensions, 1 T1 recovery dimension for dynamic T1 quantification, 1 respiratory dimension to resolve respiratory motion, and 1 DCE time dimension to capture the contrast kinetics. Sixteen healthy subjects and 14 patients with pathologically confirmed PDAC were recruited for the in vivo studies, and kinetic parameters vp , Ktrans , ve , and Kep were evaluated for each subject. Intersession repeatability of Multitasking DCE was assessed in 8 repeat healthy subjects. One-way unbalanced analysis of variance was performed between control and patient groups. RESULTS: In vivo studies demonstrated that vp , Ktrans , and Kep of PDAC were significantly lower compared with nontumoral regions in the patient group (P = .002, .003, .004, respectively) and normal pancreas in the control group (P = .011, <.001, <.001, respectively), while ve was significantly higher than nontumoral regions (P < .001) and healthy pancreas (P < .001). The kinetic parameters showed good in vivo repeatability (interclass correlation coefficient: vp , 0.95; Ktrans , 0.98; ve , 0.96; Kep , 0.99). CONCLUSION: The proposed Multitasking DCE is promising for the quantification of vascular properties of PDAC. Quantitative DCE parameters were repeatable in vivo and showed significant differences between normal pancreas and both tumor and nontumoral regions in patients with PDAC.

Improved vessel-tissue contrast and image quality in 3D radial sampling-based 4D-MRI.

PURPOSE: In radiation treatment planning for thoracic and abdominal tumors, 4D-MRI has shown promise in respiratory motion characterization with improved soft-tissue contrast compared to clinical standard, 4D computed tomography (4D-CT). This study aimed to further improve vessel-tissue contrast and overall image quality in 3D radial sampling-based 4D-MRI using a slab-selective (SS) excitation approach. METHODS: The technique was implemented in a 3D radial sampling with self-gating-based k-space sorting sequence. The SS excitation approach was compared to a non-selective (NS) approach in six cancer patients and two healthy volunteers at 3T. Improvements in vessel-tissue contrast ratio (CR) and vessel signal-to-noise ratio (SNR) were analyzed in five of the eight subjects. Image quality was visually assessed in all subjects on a 4-point scale (0: poor; 3: excellent). Tumor (patients) and pancreas (healthy) motion trajectories were compared between the two imaging approaches. RESULTS: Compared with NS-4D-MRI, SS-4D-MRI significantly improved the overall vessel-tissue CR (2.60 ± 3.97 vs. 1.03 ± 1.44, P < 0.05), SNR (63.33 ± 38.45 vs. 35.74 ± 28.59, P < 0.05), and image quality score (2.6 ± 0.5 vs. 1.4 ± 0.5, P = 0.02). Motion trajectories from the two approaches exhibited strong correlation in the superior-inferior (0.96 ± 0.06), but weaker in the anterior-posterior (0.78 ± 0.24) and medial-lateral directions (0.46 ± 0.44). CONCLUSIONS: The proposed 4D-MRI with slab-selectively excited 3D radial sampling allows for improved blood SNR, vessel-tissue CR, and image quality.

Four-dimensional MRI using three-dimensional radial sampling with respiratory self-gating to characterize temporal phase-resolved respiratory motion in the abdomen.

PURPOSE: To develop a four-dimensional MRI (4D-MRI) technique to characterize the average respiratory tumor motion for abdominal radiotherapy planning. METHODS: A continuous spoiled gradient echo sequence was implemented with 3D radial trajectory and 1D self-gating for respiratory motion detection. Data were retrospectively sorted into different respiratory phases based on their temporal locations within a respiratory cycle, and each phase was reconstructed by means of a self-calibrating CG-SENSE program. Motion phantom, healthy volunteer and patient studies were performed to validate the respiratory motion detected by the proposed method against that from a 2D real-time protocol. RESULTS: The proposed method successfully visualized the respiratory motion in phantom and human subjects. The 4D-MRI and real-time 2D-MRI yielded comparable superior-inferior (SI) motion amplitudes (intraclass correlation = 0.935) with up-to one pixel mean absolute differences in SI displacements over 10 phases and high cross-correlation between phase-resolved displacements (phantom: 0.985; human: 0.937-0.985). Comparable anterior-posterior and left-right displacements of the tumor or gold fiducial between 4D and real-time 2D-MRI were also observed in the two patients, and the hysteresis effect was shown in their 3D trajectories. CONCLUSION: We demonstrated the feasibility of the proposed 4D-MRI technique to characterize abdominal respiratory motion, which may provide valuable information for radiotherapy planning.

Clinical experience using a video-guided spirometry system for deep inhalation breath-hold radiotherapy of left-sided breast cancer.

The purpose was to report clinical experience of a video-guided spirometry system in applying deep inhalation breath-hold (DIBH) radiotherapy for left-sided breast cancer, and to study the systematic and random uncertainties, intra- and interfraction motion and impact on cardiac dose associated with DIBH. The data from 28 left-sided breast cancer patients treated with spirometer-guided DIBH radiation were studied. Dosimetric comparisons between free-breathing (FB) and DIBH plans were performed. The distance between the heart and chest wall measured on the digitally reconstructed radiographs (DRR) and MV portal images, dDRR(DIBH) and dport(DIBH), respectively, was compared as a measure of DIBH setup uncertainty. The difference (Δd) between dDRR(DIBH) and dport(DIBH) was defined as the systematic uncertainty. The standard deviation of Δd for each patient was defined as the random uncertainty. MV cine images during radiation were acquired. Affine registrations of the cine images acquired during one fraction and multiple fractions were performed to study the intra- and interfraction motion of the chest wall. The median chest wall motion was used as the metric for intra- and interfraction analysis. Breast motions in superior-inferior (SI) direction and "AP" (defined on the DRR or MV portal image as the direction perpendicular to the SI direction) are reported. Systematic and random uncertainties of 3.8 mm and 2mm, respectively, were found for this spirometer-guided DIBH treatment. MV cine analysis showed that intrafraction chest wall motions during DIBH were 0.3mm in "AP" and 0.6 mm in SI. The interfraction chest wall motions were 3.6 mm in "AP" and 3.4 mm in SI. Utilization of DIBH with this spirometry system led to a statistically significant reduction of cardiac dose relative to FB treatment. The DIBH using video-guided spirometry provided reproducible cardiac sparing with minimal intra- and interfraction chest wall motion, and thus is a valuable adjunct to modern breast treatment techniques.

A repository of grade 1 and 2 meningioma MRIs in a public dataset for radiomics reproducibility tests.

PURPOSE: Meningiomas are the most common primary brain tumors in adults with management varying widely based on World Health Organization (WHO) grade. However, there are limited datasets available for researchers to develop and validate radiomic models. The purpose of our manuscript is to report on the first dataset of meningiomas in The Cancer Imaging Archive (TCIA). ACQUISITION AND VALIDATION METHODS: The dataset consists of pre-operative MRIs from 96 patients with meningiomas who underwent resection from 2010-2019 and include axial T1post and T2-FLAIR sequences-55 grade 1 and 41 grade 2. Meningioma grade was confirmed based on the 2016 WHO Bluebook classification guideline by two neuropathologists and one neuropathology fellow. The hyperintense T1post tumor and hyperintense T2-FLAIR regions were manually contoured on both sequences and resampled to an isotropic resolution of 1 × 1 × 1 mm3 . The entire dataset was reviewed by a certified medical physicist. DATA FORMAT AND USAGE NOTES: The data was imported into TCIA for storage and can be accessed at https://doi.org/10.7937/0TKV-1A36. The total size of the dataset is 8.8GB, with 47 519 individual Digital Imaging and Communications in Medicine (DICOM) files consisting of 384 image series, and 192 structures. POTENTIAL APPLICATIONS: Grade 1 and 2 meningiomas have different treatment paradigms and are often treated based on radiologic diagnosis alone. Therefore, predicting grade prior to treatment is essential in clinical decision-making. This dataset will allow researchers to create models to auto-differentiate grade 1 and 2 meningiomas as well as evaluate for other pathologic features including mitotic index, brain invasion, and atypical features. Limitations of this study are the small sample size and inclusion of only two MRI sequences. However, there are no meningioma datasets on TCIA and limited datasets elsewhere although meningiomas are the most common intracranial tumor in adults.

Paired conditional generative adversarial network for highly accelerated liver 4D MRI.

Purpose.4D MRI with high spatiotemporal resolution is desired for image-guided liver radiotherapy. Acquiring densely sampling k-space data is time-consuming. Accelerated acquisition with sparse samples is desirable but often causes degraded image quality or long reconstruction time. We propose the Reconstruct Paired Conditional Generative Adversarial Network (Re-Con-GAN) to shorten the 4D MRI reconstruction time while maintaining the reconstruction quality.Methods.Patients who underwent free-breathing liver 4D MRI were included in the study. Fully- and retrospectively under-sampled data at 3, 6 and 10 times (3×, 6× and 10×) were first reconstructed using the nuFFT algorithm. Re-Con-GAN then trained input and output in pairs. Three types of networks, ResNet9, UNet and reconstruction swin transformer (RST), were explored as generators. PatchGAN was selected as the discriminator. Re-Con-GAN processed the data (3D +t) as temporal slices (2D +t). A total of 48 patients with 12 332 temporal slices were split into training (37 patients with 10 721 slices) and test (11 patients with 1611 slices). Compressed sensing (CS) reconstruction with spatiotemporal sparsity constraint was used as a benchmark. Reconstructed image quality was further evaluated with a liver gross tumor volume (GTV) localization task using Mask-RCNN trained from a separate 3D static liver MRI dataset (70 patients; 103 GTV contours).Results.Re-Con-GAN consistently achieved comparable/better PSNR, SSIM, and RMSE scores compared to CS/UNet models. The inference time of Re-Con-GAN, UNet and CS are 0.15, 0.16, and 120 s. The GTV detection task showed that Re-Con-GAN and CS, compared to UNet, better improved the dice score (3× Re-Con-GAN 80.98%; 3× CS 80.74%; 3× UNet 79.88%) of unprocessed under-sampled images (3× 69.61%).Conclusion.A generative network with adversarial training is proposed with promising and efficient reconstruction results demonstrated on an in-house dataset. The rapid and qualitative reconstruction of 4D liver MR has the potential to facilitate online adaptive MR-guided radiotherapy for liver cancer.

Multi-modal fusion and feature enhancement U-Net coupling with stem cell niches proximity estimation for voxel-wise GBM recurrence prediction.

Objective.We aim to develop a Multi-modal Fusion and Feature Enhancement U-Net (MFFE U-Net) coupling with stem cell niche proximity estimation to improve voxel-wise Glioblastoma (GBM) recurrence prediction.Approach.57 patients with pre- and post-surgery magnetic resonance (MR) scans were retrospectively solicited from 4 databases. Post-surgery MR scans included two months before the clinical diagnosis of recurrence and the day of the radiologicaly confirmed recurrence. The recurrences were manually annotated on the T1ce. The high-risk recurrence region was first determined. Then, a sparse multi-modal feature fusion U-Net was developed. The 50 patients from 3 databases were divided into 70% training, 10% validation, and 20% testing. 7 patients from the 4th institution were used as external testing with transfer learning. Model performance was evaluated by recall, precision, F1-score, and Hausdorff Distance at the 95% percentile (HD95). The proposed MFFE U-Net was compared to the support vector machine (SVM) model and two state-of-the-art neural networks. An ablation study was performed.Main results.The MFFE U-Net achieved a precision of 0.79 ± 0.08, a recall of 0.85 ± 0.11, and an F1-score of 0.82 ± 0.09. Statistically significant improvement was observed when comparing MFFE U-Net with proximity estimation couple SVM (SVMPE), mU-Net, and Deeplabv3. The HD95 was 2.75 ± 0.44 mm and 3.91 ± 0.83 mm for the 10 patients used in the model construction and 7 patients used for external testing, respectively. The ablation test showed that all five MR sequences contributed to the performance of the final model, with T1ce contributing the most. Convergence analysis, time efficiency analysis, and visualization of the intermediate results further discovered the characteristics of the proposed method.Significance. We present an advanced MFFE learning framework, MFFE U-Net, for effective voxel-wise GBM recurrence prediction. MFFE U-Net performs significantly better than the state-of-the-art networks and can potentially guide early RT intervention of the disease recurrence.

Contrast-Enhanced Liver Magnetic Resonance Image Synthesis Using Gradient Regularized Multi-Modal Multi-Discrimination Sparse Attention Fusion GAN.

PURPOSES: To provide abdominal contrast-enhanced MR image synthesis, we developed an gradient regularized multi-modal multi-discrimination sparse attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. METHODS: With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). A Turing test and experts' contours evaluated the image synthesis quality. RESULTS: The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values < 0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, which is close to random guessing, supporting the model's effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90 compared to the inter-operator DICE of 0.91. CONCLUSION: We demonstrated the function of a novel multi-modal MR image synthesis neural network GRMM-GAN for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment.

A cross-sectional study to test equivalence of low- versus intermediate-flip angle dynamic susceptibility contrast MRI measures of relative cerebral blood volume in patients with high-grade gliomas at 1.5 Tesla field strength.

Introduction: 1.5 Tesla (1.5T) remain a significant field strength for brain imaging worldwide. Recent computer simulations and clinical studies at 3T MRI have suggested that dynamic susceptibility contrast (DSC) MRI using a 30° flip angle ("low-FA") with model-based leakage correction and no gadolinium-based contrast agent (GBCA) preload provides equivalent relative cerebral blood volume (rCBV) measurements to the reference-standard acquisition using a single-dose GBCA preload with a 60° flip angle ("intermediate-FA") and model-based leakage correction. However, it remains unclear whether this holds true at 1.5T. The purpose of this study was to test this at 1.5T in human high-grade glioma (HGG) patients. Methods: This was a single-institution cross-sectional study of patients who had undergone 1.5T MRI for HGG. DSC-MRI consisted of gradient-echo echo-planar imaging (GRE-EPI) with a low-FA without preload (30°/P-); this then subsequently served as a preload for the standard intermediate-FA acquisition (60°/P+). Both normalized (nrCBV) and standardized relative cerebral blood volumes (srCBV) were calculated using model-based leakage correction (C+) with IBNeuro™ software. Whole-enhancing lesion mean and median nrCBV and srCBV from the low- and intermediate-FA methods were compared using the Pearson's, Spearman's and intraclass correlation coefficients (ICC). Results: Twenty-three HGG patients composing a total of 31 scans were analyzed. The Pearson and Spearman correlations and ICCs between the 30°/P-/C+ and 60°/P+/C+ acquisitions demonstrated high correlations for both mean and median nrCBV and srCBV. Conclusion: Our study provides preliminary evidence that for HGG patients at 1.5T MRI, a low FA, no preload DSC-MRI acquisition can be an appealing alternative to the reference standard higher FA acquisition that utilizes a preload.

Automatic segmentation of high-risk clinical target volume for tandem-and-ovoids brachytherapy patients using an asymmetric dual-path convolutional neural network.

PURPOSES: Preimplant diagnostic magnetic resonance imaging is the gold standard for image-guided tandem-and-ovoids (T&O) brachytherapy for cervical cancer. However, high dose rate brachytherapy planning is typically done on postimplant CT-based high-risk clinical target volume (HR-CTVCT ) because the transfer of preimplant Magnetic resonance (MR)-based HR-CTV (HR-CTVMR ) to the postimplant planning CT is difficult due to anatomical changes caused by applicator insertion, vaginal packing, and the filling status of the bladder and rectum. This study aims to train a dual-path convolutional neural network (CNN) for automatic segmentation of HR-CTVCT on postimplant planning CT with guidance from preimplant diagnostic MR. METHODS: Preimplant T2-weighted MR and postimplant CT images for 65 (48 for training, eight for validation, and nine for testing) patients were retrospectively solicited from our institutional database. MR was aligned to the corresponding CT using rigid registration. HR-CTVCT and HR-CTVMR were manually contoured on CT and MR by an experienced radiation oncologist. All images were then resampled to a spatial resolution of 0.5 × 0.5 × 1.25 mm. A dual-path 3D asymmetric CNN architecture with two encoding paths was built to extract CT and MR image features. The MR was masked by HR-CTVMR contour while the entire CT volume was included. The network put an asymmetric weighting of 18:6 for CT: MR. Voxel-based dice similarity coefficient (DSCV ), sensitivity, precision, and 95% Hausdorff distance (95-HD) were used to evaluate model performance. Cross-validation was performed to assess model stability. The study cohort was divided into a small tumor group (<20 cc), medium tumor group (20-40 cc), and large tumor group (>40 cc) based on the HR-CTVCT for model evaluation. Single-path CNN models were trained with the same parameters as those in dual-path models. RESULTS: For this patient cohort, the dual-path CNN model improved each of our objective findings, including DSCV , sensitivity, and precision, with an average improvement of 8%, 7%, and 12%, respectively. The 95-HD was improved by an average of 1.65 mm compared to the single-path model with only CT images as input. In addition, the area under the curve for different networks was 0.86 (dual-path with CT and MR) and 0.80 (single-path with CT), respectively. The dual-path CNN model with asymmetric weighting achieved the best performance with DSCV of 0.65 ± 0.03 (0.61-0.70), 0.79 ± 0.02 (0.74-0.85), and 0.75 ± 0.04 (0.68-0.79) for small, medium, and large group. 95-HD were 7.34 (5.35-10.45) mm, 5.48 (3.21-8.43) mm, and 6.21 (5.34-9.32) mm for the three size groups, respectively. CONCLUSIONS: An asymmetric CNN model with two encoding paths from preimplant MR (masked by HR-CTVMR ) and postimplant CT images was successfully developed for automatic segmentation of HR-CTVCT for T&O brachytherapy patients.

Voxelwise Prediction of Recurrent High-Grade Glioma via Proximity Estimation-Coupled Multidimensional Support Vector Machine.

PURPOSE: To provide early and localized glioblastoma (GBM) recurrence prediction, we introduce a novel postsurgery multiparametric magnetic resonance-based support vector machine (SVM) method coupling with stem cell niche (SCN) proximity estimation. METHODS AND MATERIALS: This study used postsurgery magnetic resonance imaging (MRI) scans from 50 patients with recurrent GBM, obtained approximately 2 months before clinically diagnosed recurrence. The main prediction pipeline consisted of a proximity-based estimator to identify regions with high risk of recurrence (HRRs) and an SVM classifier to provide voxelwise prediction in HRRs. The HRRs were estimated using the weighted sum of inverse distances to 2 possible origins of recurrence-the SCN and the tumor cavity. Subsequently, multiparametric voxels (from T1, T1 contrast-enhanced, fluid-attenuated inversion recovery, T2, and apparent diffusion coefficient) within the HRR were grouped into recurrent (warped from the clinical diagnosis) and nonrecurrent subregions and fed into the proximity estimation-coupled SVM classifier (SVMPE). The cohort was randomly divided into 40% and 60% for training and testing, respectively. The trained SVMPE was then extrapolated to an earlier time point for earlier recurrence prediction. As an exploratory analysis, the SVMPE predictive cluster sizes and the image intensities from the 5 magnetic resonance sequences were compared across time to assess the progressive subclinical traces. RESULTS: On 2-month prerecurrence MRI scans from 30 test cohort patients, the SVMPE classifier achieved a recall of 0.80, a precision of 0.69, an F1-score of 0.73, and a mean boundary distance of 7.49 mm. Exploratory analysis at early time points showed spatially consistent but significantly smaller subclinical clusters and significantly increased T1 contrast-enhanced and apparent diffusion coefficient values over time. CONCLUSIONS: We demonstrated a novel voxelwise early prediction method, SVMPE, for GBM recurrence based on clinical follow-up MR scans. The SVMPE is promising in localizing subclinical traces of recurrence 2 months ahead of clinical diagnosis and may be used to guide more effective personalized early salvage therapy.

Single projection driven real-time multi-contrast (SPIDERM) MR imaging using pre-learned spatial subspace and linear transformation.

Objective.To develop and test the feasibility of a novel Single ProjectIon DrivEn Real-time Multi-contrast (SPIDERM) MR imaging technique that can generate real-time 3D images on-the-fly with flexible contrast weightings and a low latency.Approach.In SPIDERM, a 'prep' scan is first performed, with sparse k-space sampling periodically interleaved with the central k-space line (navigator data), to learn a subject-specific model, incorporating a spatial subspace and a linear transformation between navigator data and subspace coordinates. A 'live' scan is then performed by repeatedly acquiring the central k-space line only to dynamically determine subspace coordinates. With the 'prep'-learned subspace and 'live' coordinates, real-time 3D images are generated on-the-fly with computationally efficient matrix multiplication. When implemented based on a multi-contrast pulse sequence, SPIDERM further allows for data-driven image contrast regeneration to convert real-time contrast-varying images into contrast-frozen images at user's discretion while maintaining motion states. Both digital phantom andin-vivoexperiments were performed to evaluate the technical feasibility of SPIDERM.Main results.The elapsed time from the input of the central k-space line to the generation of real-time contrast-frozen 3D images was approximately 45 ms, permitting a latency of 55 ms or less. Motion displacement measured from SPIDERM and reference images showed excellent correlation (R2≥0.983). Geometric variation from the ground truth in the digital phantom was acceptable as demonstrated by pancreas contour analysis (Dice ≥ 0.84, mean surface distance ≤ 0.95 mm). Quantitative image quality metrics showed good consistency between reference images and contrast-varying SPIDREM images inin-vivostudies (meanNMRSE=0.141,PSNR=30.12,SSIM=0.88).Significance.SPIDERM is capable of generating real-time multi-contrast 3D images with a low latency. An imaging framework based on SPIDERM has the potential to serve as a standalone package for MR-guided radiation therapy by offering adaptive simulation through a 'prep' scan and real-time image guidance through a 'live' scan.

Automatic differentiation of Grade I and II meningiomas on magnetic resonance image using an asymmetric convolutional neural network.

The Grade of meningioma has significant implications for selecting treatment regimens ranging from observation to surgical resection with adjuvant radiation. For most patients, meningiomas are diagnosed radiologically, and Grade is not determined unless a surgical procedure is performed. The goal of this study is to train a novel auto-classification network to determine Grade I and II meningiomas using T1-contrast enhancing (T1-CE) and T2-Fluid attenuated inversion recovery (FLAIR) magnetic resonance (MR) images. Ninety-six consecutive treatment naïve patients with pre-operative T1-CE and T2-FLAIR MR images and subsequent pathologically diagnosed intracranial meningiomas were evaluated. Delineation of meningiomas was completed on both MR images. A novel asymmetric 3D convolutional neural network (CNN) architecture was constructed with two encoding paths based on T1-CE and T2-FLAIR. Each path used the same 3 × 3 × 3 kernel with different filters to weigh the spatial features of each sequence separately. Final model performance was assessed by tenfold cross-validation. Of the 96 patients, 55 (57%) were pathologically classified as Grade I and 41 (43%) as Grade II meningiomas. Optimization of our model led to a filter weighting of 18:2 between the T1-CE and T2-FLAIR MR image paths. 86 (90%) patients were classified correctly, and 10 (10%) were misclassified based on their pre-operative MRs with a model sensitivity of 0.85 and specificity of 0.93. Among the misclassified, 4 were Grade I, and 6 were Grade II. The model is robust to tumor locations and sizes. A novel asymmetric CNN with two differently weighted encoding paths was developed for successful automated meningioma grade classification. Our model outperforms CNN using a single path for single or multimodal MR-based classification.

Anatomical and topographical variations in the distribution of brain metastases based on primary cancer origin and molecular subtypes: a systematic review.

BACKGROUND: While it has been suspected that different primary cancers have varying predilections for metastasis in certain brain regions, recent advances in neuroimaging and spatial modeling analytics have facilitated further exploration into this field. METHODS: A systematic electronic database search for studies analyzing the distribution of brain metastases (BMs) from any primary systematic cancer published between January 1990 and July 2020 was conducted using PRISMA guidelines. RESULTS: Two authors independently reviewed 1957 abstracts, 46 of which underwent full-text analysis. A third author arbitrated both lists; 13 studies met inclusion/exclusion criteria. All were retrospective single- or multi-institution database reviews analyzing over 8227 BMs from 2599 patients with breast (8 studies), lung (7 studies), melanoma (5 studies), gastrointestinal (4 studies), renal (3 studies), and prostate (1 study) cancers. Breast, lung, and colorectal cancers tended to metastasize to more posterior/caudal topographic and vascular neuroanatomical regions, particularly the cerebellum, with notable differences based on subtype and receptor expression. HER-2-positive breast cancers were less likely to arise in the frontal lobes or subcortical region, while ER-positive and PR-positive breast metastases were less likely to arise in the occipital lobe or cerebellum. BM from lung adenocarcinoma tended to arise in the frontal lobes and squamous cell carcinoma in the cerebellum. Melanoma metastasized more to the frontal and temporal lobes. CONCLUSION: The observed topographical distribution of BM likely develops based on primary cancer type, molecular subtype, and genetic profile. Further studies analyzing this association and relationships to vascular distribution are merited to potentially improve patient treatment and outcomes.

Bladder surface dose modeling in prostate cancer radiotherapy: An analysis of motion-induced variations and the cumulative dose across the treatment.

PURPOSE: To introduce a novel surface-based dose mapping method to improve quantitative bladder dosimetric assessment in prostate cancer (PC) radiotherapy. METHODS: Based on the planning and daily pre and postfraction MRIs of 12 PC patients, bladder surface models (SMs) were generated on manually delineated contours and regionally aligned via surface-based registration. Subsequently, bladder surface dose models (SDMs) were created using face-wise dose sampling. To determine the bladder intrafractional and interfractional motion and dose variation, we performed a pose analysis between pre and postfraction bladder SMs, as well as surface mapping for fractional SMs. Discrepancies between the received dose, accumulated from daily SDMs, and the planned dose were then assessed on the corresponding SDMs. Complementary to the surface dose mapping, dose surface histogram (DSH)-based comparisons were also performed. RESULTS: The intrafraction pose analysis revealed a significant (p < 0.05) bladder expansion, as well as an anterior/superior drift during the treatment. The intrafraction motion substantially altered dose to mid-bladder body, but not the bladder surface areas distal to or contiguous with the target. A similar pattern of dose variations was also detected by interfraction comparisons. With surface registration to the common SM, the cumulative bladder dose significantly differs from the planned dose. The discrepancy is evident in the mid-posterior range that corresponds to a mid- to high-dose region. The received DSH significantly differs from the planned DSH after permutation correction (p = 0.0122), while the overall surface-based comparison after multiple comparison correction is nonsignificant (p = 0.0800). CONCLUSIONS: We developed a novel surface-based intra and interdose mapping framework applied to a unique daily MR dataset for image-guided radiotherapy. The framework identified significant intrafraction bladder positional changes, localized the intra and interfraction variations, and quantified planned versus received dose differences on the bladder surface. The result indicates the importance of adopting the motion-integrated bladder SDM for bladder dose management.

Quantitative Characterization of Tumor Proximity to Stem Cell Niches: Implications on Recurrence and Survival in GBM Patients.

PURPOSE: Emerging evidence has linked glioblastoma multiforme (GBM) recurrence and survival to stem cell niches (SCNs). However, the traditional tumor-ventricle distance is insufficiently powered for an accurate prediction. We aimed to use a novel inverse distance map for improved prediction. METHODS AND MATERIALS: Two T1-magnetic resonance imaging data sets were included for a total of 237 preoperative scans for prognostic stratification and 55 follow-up scans for recurrent pattern identification. SCN, including the subventricular zone (SVZ) and subgranular zone (SGZ), were manually defined on a standard template. A proximity map was generated using the summed inverse distances to all SCN voxels. The mean and maximum proximity scores (PSm-SCN and PSmax-SCN) were calculated for each primary/recurrent tumor, deformably transformed into the template. The prognostic capacity of proximity score (PS)-derived metrics was assessed using Cox regression and log-rank tests. To evaluate the impact of SCNs on recurrence patterns, we performed group comparisons of PS-derived metrics between the primary and recurrent tumors. For comparison, the same analyses were conducted on PS derived from SVZ alone and traditional edge/center-to-ventricle metrics. RESULTS: Among all SCN-derived features, PSm-SCN was the strongest survival predictor (P < .0001). PSmax-SCN was the best in risk stratification, using either evenly sorted (P = .0001) or k-means clustering methods (P = .0045). PS metrics based on SVZ only also correlated with overall survival and risk stratification, but to a lesser degree of significance. In contrast, edge/center-to-ventricle metrics showed weak to no prediction capacities in either task. Moreover, PSm-SCN,PSm-SVZ, and center-to-ventricle metrics revealed a significantly closer SCN distribution of recurrence than primary tumors. CONCLUSIONS: We introduced a novel inverse distance-based metric to comprehensively capture the anatomic relationship between GBM tumors and SCN zones. The derived metrics outperformed traditional edge or center distance-based measurements in overall survival prediction, risk stratification, and recurrent pattern differentiation. Our results reveal the potential role of SGZ in recurrence aside from SVZ.

Surviving Over a Decade With Glioblastoma: A Clinical Course Characterized by Multiple Recurrences, Numerous Salvage Treatments, and Novel Use of Cesium-131 Tiles.

The prognosis for patients diagnosed with recurrent glioblastoma (GBM) remains poor, with no clear standard of care regarding salvage therapy. Common approaches include chemotherapy, re-resection, tumor treating fields, and reirradiation. However, most studies have shown these to have limited benefits. Reirradiation is particularly difficult due to concern for increased risk of toxicity to surrounding normal brain tissue. A novel intracranial brachytherapy system called GammaTile® (GT Medical Technologies, Tempe, Arizona) involves the placement of Cesium-131 radioactive tiles in the tumor cavity following maximal safe resection. This allows for a highly conformal dose distribution with rapid fall-off to minimize overlap with prior radiation fields and for the application of radiation directly to the high-risk tumor bed. This case report highlights a patient with GBM who survived 11.5 years through multiple recurrences and discusses the many salvage treatments he received, including bevacizumab, irinotecan, and stereotactic radiosurgery (SRS). This case exemplifies that aggressive systemic and local therapies can work well in select patients allowing for long-term survival with a good quality of life. Further efforts should be made to identify which patients may benefit from these therapies. The case study additionally reports on the use of GammaTile therapy. Due to prior external beam radiation therapy and SRS to the treatment site, further external beam radiation options were limited, and the patient was offered GammaTile as local therapy. Although it did not provide a survival benefit in this case due to progressive disease outside of the field of treatment, GammaTile serves as a valuable option in providing local therapy to patients who can no longer receive further radiation. It should be used with careful consideration in lesions characterized by aggressive local invasion.

Automatic detection and segmentation of multiple brain metastases on magnetic resonance image using asymmetric UNet architecture.

Detection of brain metastases is a paramount task in cancer management due both to the number of high-risk patients and the difficulty of achieving consistent detection. In this study, we aim to improve the accuracy of automated brain metastasis (BM) detection methods using a novel asymmetric UNet (asym-UNet) architecture. An end-to-end asymmetric 3D-UNet architecture, with two down-sampling arms and one up-sampling arm, was constructed to capture the imaging features. The two down-sampling arms were trained using two different kernels (3 × 3 × 3 and 1 × 1 × 3, respectively) with the kernel (1 × 1 × 3) dominating the learning. As a comparison, vanilla single 3D UNets were trained with different kernels and evaluated using the same datasets. Voxel-based Dice similarity coefficient (DSCv), sensitivity (S v), precision (P v), BM-based sensitivity (S BM), and false detection rate (F BM) were used to evaluate model performance. Contrast-enhanced T1 MR images from 195 patients with a total of 1034 BMs were solicited from our institutional stereotactic radiosurgery database. The patient cohort was split into training (160 patients, 809 lesions), validation (20 patients, 136 lesions), and testing (15 patients, 89 lesions) datasets. The lesions in the testing dataset were further divided into two subgroups based on the diameters (small S = 1-10 mm, large L = 11-26 mm). In the testing dataset, there were 72 and 17 BMs in the S and L sub-groups, respectively. Among all trained networks, asym-UNet achieved the highest DSCv of 0.84 and lowest F BM of 0.24. Although vanilla 3D-UNet with a single 1 × 1 × 3 kernel achieved the highest sensitivities for the S group, it resulted in the lowest precision and highest false detection rate. Asym-UNet was shown to balance sensitivity and false detection rate as well as keep the segmentation accuracy high. The novel asym-UNet segmentation network showed overall competitive segmentation performance and more pronounced improvement in hard-to-detect small BMs comparing to the vanilla single 3D UNet.