Toward a noninvasive estimate of interstitial fluid pressure by dynamic contrast-enhanced MRI in a rat model of cerebral tumor.

PURPOSE: This study demonstrates a DCE-MRI estimate of tumor interstitial fluid pressure (TIFP) and hydraulic conductivity in a rat model of glioblastoma, with validation against an invasive wick-in-needle (WIN) technique. An elevated TIFP is considered a mark of aggressiveness, and a decreased TIFP a predictor of response to therapy. METHODS: The DCE-MRI studies were conducted in 36 athymic rats (controls and posttreatment animals) with implanted U251 cerebral tumors, and with TIFP measured using a WIN method. Using a model selection paradigm and a novel application of Patlak and Logan plots to DCE-MRI data, the MRI parameters required for estimating TIFP noninvasively were estimated. Two models, a fluid-mechanical model and a multivariate empirical model, were used for estimating TIFP, as verified against WIN-TIFP. RESULTS: Using DCE-MRI, the mean estimated hydraulic conductivity (MRI-K) in U251 tumors was (2.3 ± 3.1) × 10-5 (mm2 /mmHg-s) in control studies. Significant positive correlations were found between WIN-TIFP and MRI-TIFP in both mechanical and empirical models. For instance, in the control group of the fluid-mechanical model, MRI-TIFP was a strong predictor of WIN-TIFP (R2 = 0.76, p < .0001). A similar result was found in the bevacizumab-treated group of the empirical model (R2 = 0.93, p = .014). CONCLUSION: This research suggests that MRI dynamic studies contain enough information to noninvasively estimate TIFP in this, and possibly other, tumor models, and thus might be used to assess tumor aggressiveness and response to therapy.

An adaptive model for rapid and direct estimation of extravascular extracellular space in dynamic contrast enhanced MRI studies.

Extravascular extracellular space (ve ) is a key parameter to characterize the tissue of cerebral tumors. This study introduces an artificial neural network (ANN) as a fast, direct, and accurate estimator of ve from a time trace of the longitudinal relaxation rate, ΔR1 (R1  = 1/T1 ), in DCE-MRI studies. Using the extended Tofts equation, a set of ΔR1 profiles was simulated in the presence of eight different signal to noise ratios. A set of gain- and noise-insensitive features was generated from the simulated ΔR1 profiles and used as the ANN training set. A K-fold cross-validation method was employed for training, testing, and optimization of the ANN. The performance of the optimal ANN (12:6:1, 12 features as input vector, six neurons in hidden layer, and one output) in estimating ve at a resolution of 10% (error of ±5%) was 82%. The ANN was applied on DCE-MRI data of 26 glioblastoma patients to estimate ve in tumor regions. Its results were compared with the maximum likelihood estimation (MLE) of ve . The two techniques showed a strong agreement (r = 0.82, p < 0.0001). Results implied that the perfected ANN was less sensitive to noise and outperformed the MLE method in estimation of ve .

An extended vascular model for less biased estimation of permeability parameters in DCE-T1 images.

One of the key elements in dynamic contrast enhanced (DCE) image analysis is the arterial input function (AIF). Traditionally, in DCE studies a global AIF sampled from a major artery or vein is used to estimate the vascular permeability parameters; however, not addressing dispersion and delay of the AIF at the tissue level can lead to biased estimates of these parameters. To find less biased estimates of vascular permeability parameters, a vascular model of the cerebral vascular system is proposed that considers effects of dispersion of the AIF in the vessel branches, as well as extravasation of the contrast agent (CA) to the extravascular-extracellular space. Profiles of the CA concentration were simulated for different branching levels of the vascular structure, combined with the effects of vascular leakage. To estimate the permeability parameters, the extended model was applied to these simulated signals and also to DCE-T1 (dynamic contrast enhanced T1 ) images of patients with glioblastoma multiforme tumors. The simulation study showed that, compared with the case of solving the pharmacokinetic equation with a global AIF, using the local AIF that is corrected by the vascular model can give less biased estimates of the permeability parameters (Ktrans , vp and Kb ). Applying the extended model to signals sampled from different areas of the DCE-T1 image showed that it is able to explain the CA concentration profile in both the normal areas and the tumor area, where effects of vascular leakage exist. Differences in the values of the permeability parameters estimated in these images using the local and global AIFs followed the same trend as the simulation study. These results demonstrate that the vascular model can be a useful tool for obtaining more accurate estimation of parameters in DCE studies.

A parametric model of the brain vascular system for estimation of the arterial input function (AIF) at the tissue level.

In this paper, we introduce a novel model of the brain vascular system, which is developed based on laws of fluid dynamics and vascular morphology. This model is used to address dispersion and delay of the arterial input function (AIF) at different levels of the vascular structure and to estimate the local AIF in DCE images. We developed a method based on the simplex algorithm and Akaike information criterion to estimate the likelihood of the contrast agent concentration signal sampled in DCE images belonging to different layers of the vascular tree or being a combination of different signal levels from different nodes of this structure. To evaluate this method, we tested the method on simulated local AIF signals at different levels of this structure. Even down to a signal to noise ratio of 5.5 our method was able to accurately detect the branching level of the simulated signals. When two signals with the same power level were combined, our method was able to separate the base signals of the composite AIF at the 50% threshold. We applied this method to dynamic contrast enhanced computed tomography (DCE-CT) data, and using the parameters estimated by our method we created an arrival time map of the brain. Our model corrected AIF can be used for solving the pharmacokinetic equations for more accurate estimation of vascular permeability parameters in DCE imaging studies.

DCE-MRI prediction of survival time for patients with glioblastoma multiforme: using an adaptive neuro-fuzzy-based model and nested model selection technique.

This pilot study investigates the construction of an Adaptive Neuro-Fuzzy Inference System (ANFIS) for the prediction of the survival time of patients with glioblastoma multiforme (GBM). ANFIS is trained by the pharmacokinetic (PK) parameters estimated by the model selection (MS) technique in dynamic contrast enhanced-magnetic resonance imaging (DCE-MRI) data analysis, and patient age. DCE-MRI investigations of 33 treatment-naïve patients with GBM were studied. Using the modified Tofts model and MS technique, the following physiologically nested models were constructed: Model 1, no vascular leakage (normal tissue); Model 2, leakage without efflux; Model 3, leakage with bidirectional exchange (influx and efflux). For each patient, the PK parameters of the three models were estimated as follows: blood plasma volume (vp ) for Model 1; vp and volume transfer constant (Ktrans ) for Model 2; vp , Ktrans and rate constant (kep ) for Model 3. Using Cox regression analysis, the best combination of the estimated PK parameters, together with patient age, was identified for the design and training of ANFIS. A K-fold cross-validation (K = 33) technique was employed for training, testing and optimization of ANFIS. Given the survival time distribution, three classes of survival were determined and a confusion matrix for the correct classification fraction (CCF) of the trained ANFIS was estimated as an accuracy index of ANFIS's performance. Patient age, kep and ve (Ktrans /kep ) of Model 3, and Ktrans of Model 2, were found to be the most effective parameters for training ANFIS. The CCF of the trained ANFIS was 84.8%. High diagonal elements of the confusion matrix (81.8%, 90.1% and 81.8% for Class 1, Class 2 and Class 3, respectively), with low off-diagonal elements, strongly confirmed the robustness and high performance of the trained ANFIS for predicting the three survival classes. This study confirms that DCE-MRI PK analysis, combined with the MS technique and ANFIS, allows the construction of a DCE-MRI-based fuzzy integrated predictor for the prediction of the survival of patients with GBM.

MEG Coherence and DTI Connectivity in mTLE.

Magnetoencephalography (MEG) is a noninvasive imaging method for localization of focal epileptiform activity in patients with epilepsy. Diffusion tensor imaging (DTI) is a noninvasive imaging method for measuring the diffusion properties of the underlying white matter tracts through which epileptiform activity is propagated. This study investigates the relationship between the cerebral functional abnormalities quantified by MEG coherence and structural abnormalities quantified by DTI in mesial temporal lobe epilepsy (mTLE). Resting state MEG data was analyzed using MEG coherence source imaging (MEG-CSI) method to determine the coherence in 54 anatomical sites in 17 adult mTLE patients with surgical resection and Engel class I outcome, and 17 age- and gender- matched controls. DTI tractography identified the fiber tracts passing through these same anatomical sites of the same subjects. Then, DTI nodal degree and laterality index were calculated and compared with the corresponding MEG coherence and laterality index. MEG coherence laterality, after Bonferroni adjustment, showed significant differences for right versus left mTLE in insular cortex and both lateral orbitofrontal and superior temporal gyri (p < 0.017). Likewise, DTI nodal degree laterality, after Bonferroni adjustment, showed significant differences for right versus left mTLE in gyrus rectus, insular cortex, precuneus and superior temporal gyrus (p < 0.017). In insular cortex, MEG coherence laterality correlated with DTI nodal degree laterality ([Formula: see text] in the cases of mTLE. None of these anatomical sites showed statistically significant differences in coherence laterality between right and left sides of the controls. Coherence laterality was in agreement with the declared side of epileptogenicity in insular cortex (in 82 % of patients) and both lateral orbitofrontal (88 %) and superior temporal gyri (88 %). Nodal degree laterality was also in agreement with the declared side of epileptogenicity in gyrus rectus (in 88 % of patients), insular cortex (71 %), precuneus (82 %) and superior temporal gyrus (94 %). Combining all significant laterality indices improved the lateralization accuracy to 94 % and 100 % for the coherence and nodal degree laterality indices, respectively. The associated variations in diffusion properties of fiber tracts quantified by DTI and coherence measures quantified by MEG with respect to epileptogenicity possibly reflect the chronic microstructural cerebral changes associated with functional interictal activity. The proposed methodology for using MEG and DTI to investigate diffusion abnormalities related to focal epileptogenicity and propagation may provide a further means of noninvasive lateralization.

Peritumoral tissue compression is predictive of exudate flux in a rat model of cerebral tumor: an MRI study in an embedded tumor.

MRI estimates of extracellular volume and tumor exudate flux in peritumoral tissue are demonstrated in an experimental model of cerebral tumor. Peritumoral extracellular volume predicted the tumor exudate flux. Eighteen RNU athymic rats were inoculated intracerebrally with U251MG tumor cells and studied with dynamic contrast enhanced MRI (DCE-MRI) approximately 18 days post implantation. Using a model selection paradigm and a novel application of Patlak and Logan plots to DCE-MRI data, the distribution volume (i.e. tissue porosity) in the leaky rim of the tumor and that in the tissue external to the rim (the outer rim) were estimated, as was the tumor exudate flow from the inner rim of the tumor through the outer rim. Distribution volume in the outer rim was approximately half that of the inner adjacent region (p < 1 × 10(-4)). The distribution volume of the outer ring was significantly correlated (R(2) = 0.9) with tumor exudate flow from the inner rim. Thus, peritumoral extracellular volume predicted the rate of tumor exudate flux. One explanation for these data is that perfusion, i.e. the delivery of blood to the tumor, was regulated by the compression of the mostly normal tissue of the tumor rim, and that the tumor exudate flow was limited by tumor perfusion.

Dynamic contrast enhanced MRI parameters and tumor cellularity in a rat model of cerebral glioma at 7 T.

PURPOSE: To test the hypothesis that a noninvasive dynamic contrast enhanced MRI (DCE-MRI) derived interstitial volume fraction (ve ) and/or distribution volume (VD ) were correlated with tumor cellularity in cerebral tumor. METHODS: T1 -weighted DCE-MRI studies were performed in 18 athymic rats implanted with U251 xenografts. After DCE-MRI, sectioned brain tissues were stained with Hematoxylin and Eosin for cell counting. Using a Standard Model analysis and Logan graphical plot, DCE-MRI image sets during and after the injection of a gadolinium contrast agent were used to estimate the parameters plasma volume (vp ), forward transfer constant (K(trans) ), ve , and VD . RESULTS: Parameter values in regions where the standard model was selected as the best model were: (mean ± S.D.): vp = (0.81 ± 0.40)%, K(trans) = (2.09 ± 0.65) × 10(-2) min(-1) , ve = (6.65 ± 1.86)%, and VD = (7.21 ± 1.98)%. The Logan-estimated VD was strongly correlated with the standard model's vp + ve (r = 0.91, P < 0.001). The parameters, ve and/or VD , were significantly correlated with tumor cellularity (r ≥ -0.75, P < 0.001 for both). CONCLUSION: These data suggest that tumor cellularity can be estimated noninvasively by DCE-MRI, thus supporting its utility in assessing tumor pathophysiology.

Intratumor distribution and test-retest comparisons of physiological parameters quantified by dynamic contrast-enhanced MRI in rat U251 glioma.

The distribution of dynamic contrast-enhanced MRI (DCE-MRI) parametric estimates in a rat U251 glioma model was analyzed. Using Magnevist as contrast agent (CA), 17 nude rats implanted with U251 cerebral glioma were studied by DCE-MRI twice in a 24 h interval. A data-driven analysis selected one of three models to estimate either (1) plasma volume (vp), (2) vp and forward volume transfer constant (K(trans)) or (3) vp, K(trans) and interstitial volume fraction (ve), constituting Models 1, 2 and 3, respectively. CA distribution volume (VD) was estimated in Model 3 regions by Logan plots. Regions of interest (ROIs) were selected by model. In the Model 3 ROI, descriptors of parameter distributions--mean, median, variance and skewness--were calculated and compared between the two time points for repeatability. All distributions of parametric estimates in Model 3 ROIs were positively skewed. Test-retest differences between population summaries for any parameter were not significant (p ≥ 0.10; Wilcoxon signed-rank and paired t tests). These and similar measures of parametric distribution and test-retest variance from other tumor models can be used to inform the choice of biomarkers that best summarize tumor status and treatment effects.

Measurement of rat brain tumor kinetics using an intravascular MR contrast agent and DCE-MRI nested model selection.

PURPOSE: Using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in a rat glioma model, and nested model selection (NMS), to compare estimates of the pharmacokinetic parameters vp , K(trans) , and ve for two different contrast agents (CAs)-gadofosveset, which reversibly binds to human serum albumin, and gadopentetate dimeglumine, which does not. MATERIALS AND METHODS: DCE-MRI studies were performed on nine Fisher 344 rats inoculated intracerebrally with 9L gliosarcoma cells using both gadofosveset and gadopentetate. The parameters vp , K(trans) , and ve were estimated using NMS. RESULTS: K(trans) estimates using gadofosveset, compared to gadopentetate, differed in their means (gadofosveset 0.025 ± 0.008 min(-1) vs. gadopentetate 0.046 ± 0.011 min(-1) ; P = 0.0039). This difference notwithstanding, the intraclass correlation coefficient (ICC) for the two estimates of K(trans) showed nearly perfect linear dependence (ICC = 0.8479 by Pearson's r). Other estimates, ve (gadofosveset 22.7 ± 4.7% vs. gadopentetate 23.6 ± 5.6%; P = 0.4258) and vp (gadofosveset 1.5 ± 0.5% vs. gadopentetate 1.6 ± 0.4%; P = 0.25), were not different in their means between the two CAs, and there was almost perfect agreement for ve (ICC = 0.8798) and substantial agreement for vp (ICC = 0.7981) between the two CAs. CONCLUSION: Estimates of K(trans) were statistically different using gadofosveset and gadopentetate, whereas ve and vp were similar with two CAs. NMS produced robust estimates of pharmacokinetic parameters using DCE-MRI that show promise as important measures of tumor physiology and microenvironment.

Probabilistic Nested Model Selection in Pharmacokinetic Analysis of DCE-MRI Data in Animal Model of Cerebral Tumor.

Purpose Best current practice in the analysis of dynamic contrast enhanced (DCE)-MRI is to employ a voxel-by-voxel model selection from a hierarchy of nested models. This nested model selection (NMS) assumes that the observed time-trace of contrast-agent (CA) concentration within a voxel, corresponds to a singular physiologically nested model. However, admixtures of different models may exist within a voxel's CA time-trace. This study introduces an unsupervised feature engineering technique (Kohonen-Self-Organizing-Map (K-SOM)) to estimate the voxel-wise probability of each nested model. Methods Sixty-six immune-compromised-RNU rats were implanted with human U-251N cancer cells, and DCE-MRI data were acquired from all the rat brains. The time-trace of change in the longitudinal-relaxivity (ΔR 1 ) for all animals' brain voxels was calculated. DCE-MRI pharmacokinetic (PK) analysis was performed using NMS to estimate three model regions: Model-1: normal vasculature without leakage, Model-2: tumor tissues with leakage without back-flux to the vasculature, Model-3: tumor vessels with leakage and back-flux. Approximately two hundred thirty thousand (229,314) normalized ΔR 1 profiles of animals' brain voxels along with their NMS results were used to build a K-SOM (topology-size: 8x8, with competitive-learning algorithm) and probability map of each model. K -fold nested-cross-validation (NCV, k = 10) was used to evaluate the performance of the K-SOM probabilistic-NMS (PNMS) technique against the NMS technique. Results The K-SOM PNMS's estimation for the leaky tumor regions were strongly similar (Dice-Similarity-Coefficient, DSC = 0.774 [CI: 0.731-0.823], and 0.866 [CI: 0.828-0.912] for Models 2 and 3, respectively) to their respective NMS regions. The mean-percent-differences (MPDs, NCV, k = 10) for the estimated permeability parameters by the two techniques were: -28%, + 18%, and + 24%, for v p , K trans , and v e , respectively. The KSOM-PNMS technique produced microvasculature parameters and NMS regions less impacted by the arterial-input-function dispersion effect. Conclusion This study introduces an unsupervised model-averaging technique (K-SOM) to estimate the contribution of different nested-models in PK analysis and provides a faster estimate of permeability parameters.

Model selection in measures of vascular parameters using dynamic contrast-enhanced MRI: experimental and clinical applications.

A review of the selection of models in dynamic contrast-enhanced MRI (DCE-MRI) is conducted, with emphasis on the balance between the bias and variance required to produce stable and accurate estimates of vascular parameters. The vascular parameters considered as a first-order model are the forward volume transfer constant K(trans) , the plasma volume fraction vp and the interstitial volume fraction ve . To illustrate the critical issues in model selection, a data-driven selection of models in an animal model of cerebral glioma is followed. Systematic errors and extended models are considered. Studies with nested and non-nested pharmacokinetic models are reviewed; models considering water exchange are considered.

Radiomics characterization of tissues in an animal brain tumor model imaged using dynamic contrast enhanced (DCE) MRI.

Here, we investigate radiomics-based characterization of tumor vascular and microenvironmental properties in an orthotopic rat brain tumor model measured using dynamic-contrast-enhanced (DCE) MRI. Thirty-two immune compromised-RNU rats implanted with human U-251N cancer cells were imaged using DCE-MRI (7Tesla, Dual-Gradient-Echo). The aim was to perform pharmacokinetic analysis using a nested model (NM) selection technique to classify brain regions according to vasculature properties considered as the source of truth. A two-dimensional convolutional-based radiomics analysis was performed on the raw-DCE-MRI of the rat brains to generate dynamic radiomics maps. The raw-DCE-MRI and respective radiomics maps were used to build 28 unsupervised Kohonen self-organizing-maps (K-SOMs). A Silhouette-Coefficient (SC), k-fold Nested-Cross-Validation (k-fold-NCV), and feature engineering analyses were performed on the K-SOMs' feature spaces to quantify the distinction power of radiomics features compared to raw-DCE-MRI for classification of different Nested Models. Results showed that eight radiomics features outperformed respective raw-DCE-MRI in prediction of the three nested models. The average percent difference in SCs between radiomics features and raw-DCE-MRI was: 29.875% ± 12.922%, p < 0.001. This work establishes an important first step toward spatiotemporal characterization of brain regions using radiomics signatures, which is fundamental toward staging of tumors and evaluation of tumor response to different treatments.

An uncertainty-aware deep learning architecture with outlier mitigation for prostate gland segmentation in radiotherapy treatment planning.

PURPOSE: Task automation is essential for efficient and consistent image segmentation in radiation oncology. We report on a deep learning architecture, comprising a U-Net and a variational autoencoder (VAE) for automatic contouring of the prostate gland incorporating interobserver variation for radiotherapy treatment planning. The U-Net/VAE generates an ensemble set of segmentations for each image CT slice. A novel outlier mitigation (OM) technique was implemented to enhance the model segmentation accuracy. METHODS: The primary source dataset (source_prim) consisted of 19 200 CT slices (from 300 patient planning CT image datasets) with manually contoured prostate glands. A smaller secondary source dataset (source_sec) comprised 640 CT slices (from 10 patient CT datasets), where prostate glands were segmented by 5 independent physicians on each dataset to account for interobserver variability. Data augmentation via random rotation (<5 degrees), cropping, and horizontal flipping was applied to each dataset to increase sample size by a factor of 100. A probabilistic hierarchical U-Net with VAE was implemented and pretrained using the augmented source_prim dataset for 30 epochs. Model parameters of the U-Net/VAE were fine-tuned using the augmented source_sec dataset for 100 epochs. After the first round of training, outlier contours in the training dataset were automatically detected and replaced by the most accurate contours (based on Dice similarity coefficient, DSC) generated by the model. The U-Net/OM-VAE was retrained using the revised training dataset. Metrics for comparison included DSC, Hausdorff distance (HD, mm), normalized cross-correlation (NCC) coefficient, and center-of-mass (COM) distance (mm). RESULTS: Results for U-Net/OM-VAE with outliers replaced in the training dataset versus U-Net/VAE without OM were as follows: DSC = 0.82 ± 0.01 versus 0.80 ± 0.02 (p = 0.019), HD = 9.18 ± 1.22 versus 10.18 ± 1.35 mm (p = 0.043), NCC = 0.59 ± 0.07 versus 0.62 ± 0.06, and COM = 3.36 ± 0.81 versus 4.77 ± 0.96 mm over the average of 15 contours. For the average of 15 highest accuracy contours, values were as follows: DSC = 0.90 ± 0.02 versus 0.85 ± 0.02, HD = 5.47 ± 0.02 versus 7.54 ± 1.36 mm, and COM = 1.03 ± 0.58 versus 1.46 ± 0.68 mm (p < 0.03 for all metrics). Results for the U-Net/OM-VAE with outliers removed were as follows: DSC = 0.78 ± 0.01, HD = 10.65 ± 1.95 mm, NCC = 0.46 ± 0.10, COM = 4.17 ± 0.79 mm for the average of 15 contours, and DSC = 0.88 ± 0.02, HD = 7.00 ± 1.17 mm, COM = 1.58 ± 0.63 mm for the average of 15 highest accuracy contours. All metrics for U-Net/VAE trained on the source_prim and source_sec datasets via pretraining, followed by fine-tuning, show statistically significant improvement over that trained on the source_sec dataset only. Finally, all metrics for U-Net/VAE with or without OM showed statistically significant improvement over those for the standard U-Net. CONCLUSIONS: A VAE combined with a hierarchical U-Net and an OM strategy (U-Net/OM-VAE) demonstrates promise toward capturing interobserver variability and produces accurate prostate auto-contours for radiotherapy planning. The availability of multiple contours for each CT slice enables clinicians to determine trade-offs in selecting the "best fitting" contour on each CT slice. Mitigation of outlier contours in the training dataset improves prediction accuracy, but one must be wary of reduction in variability in the training dataset.

A new architecture combining convolutional and transformer-based networks for automatic 3D multi-organ segmentation on CT images.

PURPOSE: Deep learning-based networks have become increasingly popular in the field of medical image segmentation. The purpose of this research was to develop and optimize a new architecture for automatic segmentation of the prostate gland and normal organs in the pelvic, thoracic, and upper gastro-intestinal (GI) regions. METHODS: We developed an architecture which combines a shifted-window (Swin) transformer with a convolutional U-Net. The network includes a parallel encoder, a cross-fusion block, and a CNN-based decoder to extract local and global information and merge related features on the same scale. A skip connection is applied between the cross-fusion block and decoder to integrate low-level semantic features. Attention gates (AGs) are integrated within the CNN to suppress features in image background regions. Our network is termed "SwinAttUNet." We optimized the architecture for automatic image segmentation. Training datasets consisted of planning-CT datasets from 300 prostate cancer patients from an institutional database and 100 CT datasets from a publicly available dataset (CT-ORG). Images were linearly interpolated and resampled to a spatial resolution of (1.0 × 1.0× 1.5) mm3 . A volume patch (192 × 192 × 96) was used for training and inference, and the dataset was split into training (75%), validation (10%), and test (15%) cohorts. Data augmentation transforms were applied consisting of random flip, rotation, and intensity scaling. The loss function comprised Dice and cross-entropy equally weighted and summed. We evaluated Dice coefficients (DSC), 95th percentile Hausdorff Distances (HD95), and Average Surface Distances (ASD) between results of our network and ground truth data. RESULTS: SwinAttUNet, DSC values were 86.54 ± 1.21, 94.15 ± 1.17, and 87.15 ± 1.68% and HD95 values were 5.06 ± 1.42, 3.16 ± 0.93, and 5.54 ± 1.63 mm for the prostate, bladder, and rectum, respectively. Respective ASD values were 1.45 ± 0.57, 0.82 ± 0.12, and 1.42 ± 0.38 mm. For the lung, liver, kidneys and pelvic bones, respective DSC values were: 97.90 ± 0.80, 96.16 ± 0.76, 93.74 ± 2.25, and 89.31 ± 3.87%. Respective HD95 values were: 5.13 ± 4.11, 2.73 ± 1.19, 2.29 ± 1.47, and 5.31 ± 1.25 mm. Respective ASD values were: 1.88 ± 1.45, 1.78 ± 1.21, 0.71 ± 0.43, and 1.21 ± 1.11 mm. Our network outperformed several existing deep learning approaches using only attention-based convolutional or Transformer-based feature strategies, as detailed in the results section. CONCLUSIONS: We have demonstrated that our new architecture combining Transformer- and convolution-based features is able to better learn the local and global context for automatic segmentation of multi-organ, CT-based anatomy.

Dynamic contrast enhanced (DCE) MRI estimation of vascular parameters using knowledge-based adaptive models.

We introduce and validate four adaptive models (AMs) to perform a physiologically based Nested-Model-Selection (NMS) estimation of such microvascular parameters as forward volumetric transfer constant, Ktrans, plasma volume fraction, vp, and extravascular, extracellular space, ve, directly from Dynamic Contrast-Enhanced (DCE) MRI raw information without the need for an Arterial-Input Function (AIF). In sixty-six immune-compromised-RNU rats implanted with human U-251 cancer cells, DCE-MRI studies estimated pharmacokinetic (PK) parameters using a group-averaged radiological AIF and an extended Patlak-based NMS paradigm. One-hundred-ninety features extracted from raw DCE-MRI information were used to construct and validate (nested-cross-validation, NCV) four AMs for estimation of model-based regions and their three PK parameters. An NMS-based a priori knowledge was used to fine-tune the AMs to improve their performance. Compared to the conventional analysis, AMs produced stable maps of vascular parameters and nested-model regions less impacted by AIF-dispersion. The performance (Correlation coefficient and Adjusted R-squared for NCV test cohorts) of the AMs were: 0.914/0.834, 0.825/0.720, 0.938/0.880, and 0.890/0.792 for predictions of nested model regions, vp, Ktrans, and ve, respectively. This study demonstrates an application of AMs that quickens and improves DCE-MRI based quantification of microvasculature properties of tumors and normal tissues relative to conventional approaches.

Model selection for DCE-T1 studies in glioblastoma.

Dynamic contrast enhanced T(1)-weighted MRI using the contrast agent gadopentetate dimeglumine (Gd-DTPA) was performed on 10 patients with glioblastoma. Nested models with as many as three parameters were used to estimate plasma volume or plasma volume and forward vascular transfer constant (K(trans)) and the reverse vascular transfer constant (k(ep)). These constituted models 1, 2, and 3, respectively. Model 1 predominated in normal nonleaky brain tissue, showing little or no leakage of contrast agent. Model 3 predominated in regions associated with aggressive portions of the tumor, and model 2 bordered model 3 regions, showing leakage at reduced rates. In the patient sample, v(p) was about four times that of white matter in the enhancing part of the tumor. K(trans) varied by a factor of 10 between the model 2 (1.9 ↔ 10(-3) min(-1)) and model 3 regions (1.9 ↔ 10(-2) min(-1)). The mean calculated interstitial space (model 3) was 5.5%. In model 3 regions, excellent curve fits were obtained to summarize concentration-time data (mean R(2) = 0.99). We conclude that the three parameters of the standard model are sufficient to fit dynamic contrast enhanced T(1) data in glioblastoma under the conditions of the experiment.

Radiomics outperforms clinical factors in characterizing human papilloma virus (HPV) for patients with oropharyngeal squamous cell carcinomas.

Purpose.To utilize radiomic features extracted from CT images to characterize Human Papilloma Virus (HPV) for patients with oropharyngeal cancer squamous cell carcinoma (OPSCC).Methods.One hundred twenty-eight OPSCC patients with known HPV-status (60-HPV + and 68-HPV-, confirmed by immunohistochemistry-P16-protein testing) were retrospectively studied. Radiomic features (11 feature-categories) were extracted in 3D from contrast-enhanced (CE)-CT images of gross-tumor-volumes using 'in-house' software ('ROdiomiX') developed and validated following the image-biomarker-standardization-initiative (IBSI) guidelines. Six clinical factors were investigated: Age-at-Diagnosis, Gender, Total-Charlson, Alcohol-Use, Smoking-History, and T-Stage. A Least-Absolute-Shrinkage-and-Selection-Operation (Lasso) technique combined with a Generalized-Linear-Model (Lasso-GLM) were applied to perform regularization in the radiomic and clinical feature spaces to identify the ranking of optimal feature subsets with most representative information for prediction of HPV. Lasso-GLM models/classifiers based on clinical factors only, radiomics only, and combined clinical and radiomics (ensemble/integrated) were constructed using random-permutation-sampling. Tests of significance (One-way ANOVA), average Area-Under-Receiver-Operating-Characteristic (AUC), and Positive and Negative Predictive values (PPV and NPV) were computed to estimate the generalization-error and prediction performance of the classifiers.Results.Five clinical factors, including T-stage, smoking status, and age, and 14 radiomic features, including tumor morphology, and intensity contrast were found to be statistically significant discriminators between HPV positive and negative cohorts. Performances for prediction of HPV for the 3 classifiers were: Radiomics-Lasso-GLM: AUC/PPV/NPV = 0.789/0.755/0.805; Clinical-Lasso-GLM: 0.676/0.747/0.672, and Integrated/Ensemble-Lasso-GLM: 0.895/0.874/0.844. Results imply that the radiomics-based classifier enabled better characterization and performance prediction of HPV relative to clinical factors, and that the combination of both radiomics and clinical factors yields even higher accuracy characterization and predictive performance.Conclusion.Albeit subject to confirmation in a larger cohort, this pilot study presents encouraging results in support of the role of radiomic features towards characterization of HPV in patients with OPSCC.

Prostate cancer malignancy detection and localization from mpMRI using auto-deep learning as one step closer to clinical utilization.

Automatic diagnosis of malignant prostate cancer patients from mpMRI has been studied heavily in the past years. Model interpretation and domain drift have been the main road blocks for clinical utilization. As an extension from our previous work we trained on a public cohort with 201 patients and the cropped 2.5D slices of the prostate glands were used as the input, and the optimal model were searched in the model space using autoKeras. As an innovative move, peripheral zone (PZ) and central gland (CG) were trained and tested separately, the PZ detector and CG detector were demonstrated effective in highlighting the most suspicious slices out of a sequence, hopefully to greatly ease the workload for the physicians.

MRI estimation of gadolinium and albumin effects on water proton.

The longitudinal relaxivity on the protons of water of a Gd-chelate-albumin compound was measured at 7 T as a function of the macromolecular content of a cross-linked matrix. In agreement with previous works, the results demonstrate that the effect of gadolinium on water proton relaxivity is not constant, rising moderately with increase in the concentration of bovine serum albumin (BSA). About 35% variation in relaxivity was observed over a 0%-25% range of BSA concentrations (ℜ = 3.893 + 0.0502 × BSA [%], SE = 0.0119 and 0.1740, t = 4.215 and 22.383, p < 0.014 and 0.001).