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.

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.

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.

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.

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.

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.

Technical note: On the development of an outcome-driven frequency filter for improving radiomics-based modeling of human papillomavirus (HPV) in patients with oropharyngeal squamous cell carcinoma.

PURPOSE: To implement an outcome-driven frequency filter for improving radiomics-based modeling of human papillomavirus (HPV) for patients with oropharyngeal squamous cell carcinoma (OPSCC). METHODS AND MATERIALS: One hundred twenty-eight OPSCC patients with known HPV status (60-HPV+ and 68-HPV-, confirmed by immunohistochemistry-P16 protein testing) were retrospectively studied. A 3D Discrete Fourier Transform was applied on contrast-enhanced computed tomography (CE-CT) images of patient gross tumor volumes (GTVs) to transform intensity distributions to the frequency domain and estimate frequency power spectrums of HPV- and HPV+ patient cohorts. Statistical analyses were performed to rank frequency bands contributing toward the prediction of HPV status. An outcome-driven frequency filter was designed accordingly and applied to GTV frequency information. A 3D inverse discrete Fourier transform was applied to reconstruct HPV-related frequency-filtered images. Radiomics features (11 feature-categories) were extracted from pre- and post-frequency filtered images using our previously published "ROdiomiX" software. Least-absolute-shrinkage-and-selection-operation (Lasso) combined with a generalized linear model (Lasso-GLM) was developed to identify and rank feature subsets with the optimal information for prediction of HPV+/-. Radiomics-based Lasso-GLM classifiers (pre- and post-frequency filtered) were constructed and validated using random permutation sampling and nested cross-validation (CV) techniques. Average area under the receiver operating characteristic (AUC), and positive and negative predictive values (PPV and NPV) were computed to estimate generalization error and prediction performance. RESULTS: Among 192 radiomic features, 15 features were found to be statistically significant discriminators between HPV+/- cohorts on post-frequency filtered CE-CT images. Fourteen such radiomic features were observed on pre-frequency filtered datasets. Discriminant features included tumor morphology and intensity contrast. Performances for prediction of HPV for the pre- and post-frequency filtered Lasso-GLM classifiers were as follows: AUC/PPV/NPV = 0.789/0.755/0.805 and 0.850/0.808/0.877, respectively. Nested CV performances for prediction of HPV for the pre- and post-frequency filtered Lasso-GLM classifiers were as follows: AUC/PPV/NPV = 0.814/0.725/0.877 and 0.890/0.820/0.911, respectively. CONCLUSION: Albeit subject to confirmation in a larger cohort, this pilot study presents encouraging results on the importance of frequency analysis prior to radiomic feature extraction toward enhancement of model performance for characterizing HPV in patients with OPSCC.

Technical Note: ROdiomiX: A validated software for radiomics analysis of medical images in radiation oncology.

PURPOSE: This study introduces an in-house-designed software platform (ROdiomiX) for the radiomics analysis of medical images in radiation oncology. ROdiomiX is a MATLAB-based framework for the computation of radiomic features and feature aggregation techniques in compliance with the Image-Biomarker-Standardization-Initiative (IBSI) guidelines, which includes preprocessing protocols and quantitative benchmark results for analysis of computational phantom images. METHODS AND MATERIALS: The ROdiomiX software system consists of a series of computation cores implemented on the basis of the guidelines proposed by the IBSI. It is capable of quantitative computation of the following 11 different feature categories: Local-Intensity, Intensity-Histogram, Intensity-Based-Statistical, Intensity-Volume-Histogram, Gray-Level-Co-occurrence, Gray-Level-Run-Length, Gray-Level-Size-Zone, Gray-Level-Distance-Zone, Neighborhood-Grey-Tone-Difference, Neighboring-Grey-Level-Dependence, and Morphological feature. ROdiomiX was validated against benchmark values for the IBSI 3D digital phantom, as well as one designed in-house (HFH). The intraclass correlation coefficient (ICC) for estimating the degree of absolute agreement between ROdiomiX computation and benchmark values for different features at the 95% confidence level (CL) was used for comparison. RESULTS: Among the 11 feature categories with 149 total features including 10 different feature aggregation methods (following the IBSI guidelines), the percent difference between absolute feature values computed by the ROdiomiX software and benchmark values reported for IBSI and HFH digital phantoms were 0.14% + 0.43% and 0.11% + 0.27%, respectively. The ICC values were >0.997 for all ten feature categories for both the IBSI and HFH digital phantoms. CONCLUSION: The authors successfully developed a platform for computation of quantitative radiomic features. The image preprocessing and computational software cores were designed following the procedures specified by the IBSI. Benchmarking testing was in excellent agreement against the IBSI- and HFH-designed computational phantoms.

Application of radiomics for the prediction of HPV status for patients with head and neck cancers.

PURPOSE: To perform radiomic analysis of primary tumors extracted from pretreatment contrast-enhanced computed tomography (CE-CT) images for patients with oropharyngeal cancers to identify discriminant features and construct an optimal classifier for the characterization and prediction of human papilloma virus (HPV) status. MATERIALS AND METHODS: One hundred and eighty seven patients with oropharyngeal cancers with known HPV status (confirmed by immunohistochemistry-p16 protein testing) were retrospectively studied as follows: Group A: 95 patients (19HPV- and 76HPV+) from the MICAII grand challenge. Group B: 92 patients (52HPV- and 40HPV+) from our institution. Radiomic features (172) were extracted from pretreatment diagnostic CE-CT images of the gross tumor volume (GTV). Levene and Kolmogorov-Smirnov's tests with absolute biserial correlation (>0.48) were used to identify the discriminant features between the HPV+ and HPV- groups. The discriminant features were used to train and test eight different classifiers. Area under receiver operating characteristic (AUC), positive predictive and negative predictive values (PPV and NPV, respectively) were used to evaluate the performance of the classifiers. Principal component analysis (PCA) was applied on the discriminant feature set and seven PCs were used to train and test a generalized linear model (GLM) classifier. RESULTS: Among 172 radiomic features only 12 radiomic features (from 3 categories) were significantly different (P < 0.05, |BSC| > 0.48) between the HPV+ and HPV- groups. Among the eight classifiers trained and applied for prediction of HPV status, the GLM showed the highest performance for each discriminant feature and the combined 12 features: AUC/PPV/NPV = 0.878/0.834/0.811. The GLM high prediction power was AUC/PPV/NPV = 0.849/0.731/0.788 and AUC/PPV/NPV = 0.869/0.807/0.870 for unseen test datasets for groups A and B, respectively. After eliminating the correlation among discriminant features by applying PCA analysis, the performance of the GLM was improved by 3.3%, 2.2%, and 1.8% for AUC, PPV, and NPV, respectively. CONCLUSIONS: Results imply that GTV's for HPV+ patients exhibit higher intensities, smaller lesion size, greater sphericity/roundness, and higher spatial intensity-variation/heterogeneity. Results are suggestive that radiomic features primarily associated with the spatial arrangement and morphological appearance of the tumor on contrast-enhanced diagnostic CT datasets may be potentially used for classification of HPV status.

Detection of Dominant Intra-prostatic Lesions in Patients With Prostate Cancer Using an Artificial Neural Network and MR Multi-modal Radiomics Analysis.

Purpose: The aim of this study was to identify and rank discriminant radiomics features extracted from MR multi-modal images to construct an adaptive model for characterization of Dominant Intra-prostatic Lesions (DILs) from normal prostatic gland tissues (NT). Methods and Materials: Two cohorts were retrospectively studied: Group A consisted of 98 patients and Group B 19 patients. Two image modalities were acquired using a 3.0T MR scanner: Axial T2 Weighted (T2W) and axial diffusion weighted (DW) imaging. A linear regression method was used to construct apparent diffusion coefficient (ADC) maps from DW images. DILs and the NT in the mirrored location were drawn on each modality. One hundred and sixty-eight radiomics features were extracted from DILs and NT. A Partial-Least-Squares-Correlation (PLSC) with one-way ANOVA along with bootstrapping ratio techniques were recruited to identify and rank the most discriminant latent variables. An artificial neural network (ANN) was constructed based on the optimal latent variable feature to classify the DILs and NTs. Nineteen patients were randomly chosen to test the contour variability effect on the radiomics analysis and the performance of the ANN. Finally, the trained ANN and a two dimension (2D) convolutional sampling method were combined and used to estimate DIL-NT probability map for two test cases. Results: Among 168 radiomics-based latent variables, only the first four variables of each modality in the PLSC space were found to be significantly different between the DILs and NTs. Area Under Receiver Operating Characteristic (AUROC), Positive Predictive and Negative Predictive values (PPV and NPV) for the conventional method were 94%, 0.95, and 0.92, respectively. When the feature vector was randomly permuted 10,000 times, a very strong permutation-invariant efficiency (p < 0.0001) was achieved. The radiomic-based latent variables of the NTs and DILs showed no statistically significant differences (Fstatistic < Fc = 4.11 with Confidence Level of 95% for all 8 variables) against contour variability. Dice coefficients between DIL-NT probability map and physician contours for the two test cases were 0.82 and 0.71, respectively. Conclusion: This study demonstrates the high performance of combining radiomics information extracted from multimodal MR information such as T2WI and ADC maps, and adaptive models to detect DILs in patients with PCa.

Correction: Data mining MR image features of select structures for lateralization of mesial temporal lobe epilepsy.

[This corrects the article DOI: 10.1371/journal.pone.0199137.].

Principal component analysis modeling of Head-and-Neck anatomy using daily Cone Beam-CT images.

PURPOSE: To model Head-and-Neck anatomy from daily Cone Beam-CT (CBCT) images over the course of fractionated radiotherapy using principal component analysis (PCA). METHODS AND MATERIALS: Eighteen oropharyngeal Head-and-Neck cancer patients, treated with volumetric modulated arc therapy (VMAT), were included in this retrospective study. Normal organs, including the parotid and submandibular glands, mandible, pharyngeal constrictor muscles (PCMs), and spinal cord were contoured using daily CBCT image datasets. PCA models for each organ were developed for individual patients (IP) and the entire patient cohort/population (PP). The first 10 principal components (PCs) were extracted for all models. Analysis included cumulative and individual PCs for each organ and patient, as well as the aggregate organ/patient population; comparisons were made using the root-mean-square (RMS) of the percentage predicted spatial displacement for each PC. RESULTS: Overall, spatial displacement prediction was achieved at the 95% confidence level (CL) for the first three to four PCs for all organs, based on IP models. For PP models, the first four PCs predicted spatial displacement at the 80%-89% CL. Differences in percentage predicted spatial displacement between mean IP models for each organ ranged from 2.8% ± 1.8% (1st PC) to 0.6% ± 0.4% (4th PC). Differences in percentage predicted spatial displacement between IP models vs the mean IP model for each organ based on the 1st PC were <12.9% ± 6.9% for all organs. Differences in percentage predicted spatial displacement between IP and PP models based on all organs and patients for the 1st and 2nd PC were <11.7% ± 2.2%. CONCLUSION: Tissue changes during fractionated radiotherapy observed on daily CBCT in patients with Head-and-Neck cancers, were modeled using PCA. In general, spatial displacement for organs-at-risk was predicted for the first 4 principal components at the 95% confidence levels (CL), for individual patient (IP) models, and at the 80%-89% CL for population-based patient (PP) models. The IP and PP models were most predictive of changes in glandular organs and pharyngeal constrictor muscles, respectively.

Data mining MR image features of select structures for lateralization of mesial temporal lobe epilepsy.

PURPOSE: This study systematically investigates the predictive power of volumetric imaging feature sets extracted from select neuroanatomical sites in lateralizing the epileptogenic focus in mesial temporal lobe epilepsy (mTLE) patients. METHODS: A cohort of 68 unilateral mTLE patients who had achieved an Engel class I outcome postsurgically was studied retrospectively. The volumes of multiple brain structures were extracted from preoperative magnetic resonance (MR) images in each. The MR image data set consisted of 54 patients with imaging evidence for hippocampal sclerosis (HS-P) and 14 patients without (HS-N). Data mining techniques (i.e., feature extraction, feature selection, machine learning classifiers) were applied to provide measures of the relative contributions of structures and their correlations with one another. After removing redundant correlated structures, a minimum set of structures was determined as a marker for mTLE lateralization. RESULTS: Using a logistic regression classifier, the volumes of both hippocampus and amygdala showed correct lateralization rates of 94.1%. This reflected about 11.7% improvement in accuracy relative to using hippocampal volume alone. The addition of thalamic volume increased the lateralization rate to 98.5%. This ternary-structural marker provided a 100% and 92.9% mTLE lateralization accuracy, respectively, for the HS-P and HS-N groups. CONCLUSIONS: The proposed tristructural MR imaging biomarker provides greater lateralization accuracy relative to single- and double-structural biomarkers and thus, may play a more effective role in the surgical decision-making process. Also, lateralization of the patients with insignificant atrophy of hippocampus by the proposed method supports the notion of associated structural changes involving the amygdala and thalamus.

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.

Utilization of a hybrid finite-element based registration method to quantify heterogeneous tumor response for adaptive treatment for lung cancer patients.

Tumor response to radiation treatment (RT) can be evaluated from changes in metabolic activity between two positron emission tomography (PET) images. Activity changes at individual voxels in pre-treatment PET images (PET1), however, cannot be derived until their associated PET-CT (CT1) images are appropriately registered to during-treatment PET-CT (CT2) images. This study aimed to investigate the feasibility of using deformable image registration (DIR) techniques to quantify radiation-induced metabolic changes on PET images. Five patients with non-small-cell lung cancer (NSCLC) treated with adaptive radiotherapy were considered. PET-CTs were acquired two weeks before RT and 18 fractions after the start of RT. DIR was performed from CT1 to CT2 using B-Spline and diffeomorphic Demons algorithms. The resultant displacements in the tumor region were then corrected using a hybrid finite element method (FEM). Bitmap masks generated from gross tumor volumes (GTVs) in PET1 were deformed using the four different displacement vector fields (DVFs). The conservation of total lesion glycolysis (TLG) in GTVs was used as a criterion to evaluate the quality of these registrations. The deformed masks were united to form a large mask which was then partitioned into multiple layers from center to border. The averages of SUV changes over all the layers were 1.0 ± 1.3, 1.0 ± 1.2, 0.8 ± 1.3, 1.1 ± 1.5 for the B-Spline, B-Spline + FEM, Demons and Demons + FEM algorithms, respectively. TLG changes before and after mapping using B-Spline, Demons, hybrid-B-Spline, and hybrid-Demons registrations were 20.2%, 28.3%, 8.7%, and 2.2% on average, respectively. Compared to image intensity-based DIR algorithms, the hybrid FEM modeling technique is better in preserving TLG and could be useful for evaluation of tumor response for patients with regressing tumors.

Multimodal Imaging in a Patient with Hemidystonia Responsive to GPi Deep Brain Stimulation.

BACKGROUND: Dystonia is a syndrome with varied phenomenology but our understanding of its mechanisms is deficient. With neuroimaging techniques, such as fiber tractography (FT) and magnetoencephalography (MEG), pathway connectivity can be studied to that end. We present a hemidystonia patient treated with deep brain stimulation (DBS). METHODS: After 10 years of left axial hemidystonia, a 45-year-old male underwent unilateral right globus pallidus internus (GPi) DBS. Whole brain MEG before and after anticholinergic medication was performed prior to surgery. 26-direction diffusion tensor imaging (DTI) was obtained in a 3 T MRI machine along with FT. The patient was assessed before and one year after surgery by using the Burke-Fahn-Marsden Dystonia Rating Scale (BFMDRS). RESULTS: In the eyes-closed MEG study there was an increase in brain coherence in the gamma band after medication in the middle and inferior frontal region. FT demonstrated over 50% more intense ipsilateral connectivity in the right hemisphere compared to the left. After DBS, BFMDRS motor and disability scores both dropped by 71%. CONCLUSION: Multimodal neuroimaging techniques can offer insights into the pathophysiology of dystonia and can direct choices for developing therapeutics. Unilateral pallidal DBS can provide significant symptom control in axial hemidystonia poorly responsive to medication.

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.

On the impact of smoothing and noise on robustness of CT and CBCT radiomics features for patients with head and neck cancers.

PURPOSE: We investigated the characteristics of radiomics features extracted from planning CT (pCT) and cone beam CT (CBCT) image datasets acquired for 18 oropharyngeal cancer patients treated with fractionated radiation therapy. Images were subjected to smoothing, sharpening, and noise to evaluate changes in features relative to baseline datasets. METHODS: Textural features were extracted from tumor volumes, contoured on pCT and CBCT images, according to the following eight different classes: intensity based histogram features (IBHF), gray level run length (GLRL), law's textural information (LAWS), discrete orthonormal stockwell transform (DOST), local binary pattern (LBP), two-dimensional wavelet transform (2DWT), Two dimensional Gabor filter (2DGF), and gray level co-occurrence matrix (GLCM). A total of 165 radiomics features were extracted. Images were post-processed prior to feature extraction using a Gaussian noise model with different signal-to-noise-ratios (SNR = 5, 10, 15, 20, 25, 35, 50, 75, 100, and 150). Gaussian filters with different cut off frequencies (varied discreetly from 0.0458 to 0.7321 cycles-mm-1 ) were applied to image datasets. Effect of noise and smoothing on each extracted feature was quantified using mean absolute percent change (MAPC) between the respective values on post-processed and baseline images. The Fisher method for combining Welch P-values was used for tests of significance. Three comparisons were investigated: (a) Baseline pCT versus modified pCT (with given filter applied); (b) Baseline CBCT versus modified CBCT, and (c) Baseline and modified pCT versus baseline and modified CBCT. RESULTS: Features extracted from CT and CBCT image datasets were robust to low-pass filtering (MAPC = 17.5%, pvalFisher¯ = 0.93 for CBCT and MAPC = 7.5%, pvalFisher¯ = 0.98 for pCT) and noise (MAPC = 27.1%, pvalFisher¯ =  0.89 for CBCT, and MAPC = 34.6%, pvalFisher¯ = 0.61 for pCT). Extracted features were significantly impacted (MAPC=187.7%, pvalFisher¯ < 0.0001 for CBCT, and MAPC = 180.6%, pvalFisher¯ < 0.01 for pCT) by LOG which is classified as a high-pass filter. Features most impacted by low pass filtering were LAWS (MAPC = 11.2%, pvalFisher¯ = 0.44), GLRL (MAPC = 9.7%, pvalFisher¯ = 0.70) and IBHF (MAPC = 21.7%, pvalFisher¯ = 0.83), for the pCT datasets, and LAWS (MAPC = 20.2%, pvalFisher¯ = 0.24), GLRL (MAPC = 14.5%, pvalFisher¯ = 0.44), and 2DGF (MAPC=16.3%, pvalFisher¯ = 0.52), for CBCT image datasets. For pCT datasets, features most impacted by noise were GLRL (MAPC = 29.7%, pvalFisher¯ = 0.06), LAWS (MAPC = 96.6%, pvalFisher¯ = 0.42), and GLCM (MAPC = 36.2%, pvalFisher¯ = 0.48), while the LBPF (MAPC = 5.2%, pvalFisher¯ = 0.99) was found to be relatively insensitive to noise. For CBCT datasets, GLRL (MAPC = 8.9%, pvalFisher¯ = 0.80) and LAWS (MAPC = 89.3%, pvalFisher¯ = 0.81) features were impacted by noise, while the LBPF (MAPC = 2.2%, pvalFisher¯ = 0.99) and DOST (MAPC = 13.7%, pvalFisher¯ = 0.98) features were noise insensitive. Apart from 15 features, no significant differences were observed for the remaining 150 textural features extracted from baseline pCT and CBCT image datasets (MAPC = 90.1%, pvalFisher¯ = 0.26). CONCLUSIONS: Radiomics features extracted from planning CT and daily CBCT image datasets for head/neck cancer patients were robust to low-power Gaussian noise and low-pass filtering, but were impacted by high-pass filtering. Textural features extracted from CBCT and pCT image datasets were similar, suggesting interchangeability of pCT and CBCT for investigating radiomics features as possible biomarkers for outcome.

Intravenous Formulation of HET0016 Decreased Human Glioblastoma Growth and Implicated Survival Benefit in Rat Xenograft Models.

Glioblastoma (GBM) is a hypervascular primary brain tumor with poor prognosis. HET0016 is a selective CYP450 inhibitor, which has been shown to inhibit angiogenesis and tumor growth. Therefore, to explore novel treatments, we have generated an improved intravenous (IV) formulation of HET0016 with HPßCD and tested in animal models of human and syngeneic GBM. Administration of a single IV dose resulted in 7-fold higher levels of HET0016 in plasma and 3.6-fold higher levels in tumor at 60 min than that in IP route. IV treatment with HPßCD-HET0016 decreased tumor growth, and altered vascular kinetics in early and late treatment groups (p < 0.05). Similar growth inhibition was observed in syngeneic GL261 GBM (p < 0.05). Survival studies using patient derived xenografts of GBM811, showed prolonged survival to 26 weeks in animals treated with focal radiation, in combination with HET0016 and TMZ (p < 0.05). We observed reduced expression of markers of cell proliferation (Ki-67), decreased neovascularization (laminin and αSMA), in addition to inflammation and angiogenesis markers in the treatment group (p < 0.05). Our results indicate that HPßCD-HET0016 is effective in inhibiting tumor growth through decreasing proliferation, and neovascularization. Furthermore, HPßCD-HET0016 significantly prolonged survival in PDX GBM811 model.

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 .