T2w Magnetic Resonance Imaging Research Articles

High-resolution 3T to 7T ADC map synthesis with a hybrid CNN-transformer model.

7 Tesla (7T) apparent diffusion coefficient (ADC) maps derived from diffusion-weighted imaging (DWI) demonstrate improved image quality and spatial resolution over 3 Tesla (3T) ADC maps. However, 7T magnetic resonance imaging (MRI) currently suffers from limited clinical unavailability, higher cost, and increased susceptibility to artifacts. To address these issues, we propose a hybrid CNN-transformer model to synthesize high-resolution 7T ADC maps from multimodal 3T MRI. The Vision CNN-Transformer (VCT), composed of both Vision Transformer (ViT) blocks and convolutional layers, is proposed to produce high-resolution synthetic 7T ADC maps from 3T ADC maps and 3T T1-weighted (T1w) MRI. ViT blocks enabled global image context while convolutional layers efficiently captured fine detail. The VCT model was validated on the publicly available Human Connectome Project Young Adult dataset, comprising 3T T1w, 3T DWI, and 7T DWI brain scans. The Diffusion Imaging in Python library was used to compute ADC maps from the DWI scans. A total of 171 patient cases were randomly divided into 130 training cases, 20 validation cases, and 21 test cases. The synthetic ADC maps were evaluated by comparing their similarity to the ground truth volumes with the following metrics: peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and mean squared error (MSE). In addition, RESULTS: The results are as follows: PSNR: 27.0±0.9dB, SSIM: 0.945±0.010, and MSE: 2.0E-3±0.4E-3. Both qualitative and quantitative results demonstrate that VCT performs favorably against other state-of-the-art methods. We have introduced various efficiency improvements, including the implementation of flash attention and training on 176×208 resolution images. These enhancements have resulted in the reduction of parameters and training time per epoch by 50% in comparison to ResViT. Specifically, the training time per epoch has been shortened from 7.67 min to 3.86 min. We propose a novel method to predict high-resolution 7T ADC maps from low-resolution 3T ADC maps and T1w MRI. Our predicted images demonstrate better spatial resolution and contrast compared to 3T MRI and prediction results made by ResViT and pix2pix. These high-quality synthetic 7T MR images could be beneficial for disease diagnosis and intervention, producing higher resolution and conformal contours, and as an intermediate step in generating synthetic CT for radiation therapy, especially when 7T MRI scanners are unavailable.

Robust thalamic nuclei segmentation from T1-weighted MRI using polynomial intensity transformation.

Accurate segmentation of thalamic nuclei, crucial for understanding their role in healthy cognition and in pathologies, is challenging to achieve on standard T1-weighted (T1w) magnetic resonance imaging (MRI) due to poor image contrast. White-matter-nulled (WMn) MRI sequences improve intrathalamic contrast but are not part of clinical protocols or extant databases. In this study, we introduce histogram-based polynomial synthesis (HIPS), a fast preprocessing transform step that synthesizes WMn-like image contrast from standard T1w MRI using a polynomial approximation for intensity transformation. HIPS was incorporated into THalamus Optimized Multi-Atlas Segmentation (THOMAS) pipeline, a method developed and optimized for WMn MRI. HIPS-THOMAS was compared to a convolutional neural network (CNN)-based segmentation method and THOMAS modified for the use of T1w images (T1w-THOMAS). The robustness and accuracy of the three methods were tested across different image contrasts (MPRAGE, SPGR, and MP2RAGE), scanner manufacturers (PHILIPS, GE, and Siemens), and field strengths (3T and 7T). HIPS-transformed images improved intra-thalamic contrast and thalamic boundaries, and HIPS-THOMAS yielded significantly higher mean Dice coefficients and reduced volume errors compared to both the CNN method and T1w-THOMAS. Finally, all three methods were compared using the frequently travelling human phantom MRI dataset for inter- and intra-scanner variability, with HIPS displaying the least inter-scanner variability and performing comparably with T1w-THOMAS for intra-scanner variability. In conclusion, our findings highlight the efficacy and robustness of HIPS in enhancing thalamic nuclei segmentation from standard T1w MRI.

Pixelwise Gradient Model with GAN for Virtual Contrast Enhancement in MRI Imaging.

Background: The development of advanced computational models for medical imaging is crucial for improving diagnostic accuracy in healthcare. This paper introduces a novel approach for virtual contrast enhancement (VCE) in magnetic resonance imaging (MRI), particularly focusing on nasopharyngeal cancer (NPC). Methods: The proposed model, Pixelwise Gradient Model with GAN for Virtual Contrast Enhancement (PGMGVCE), makes use of pixelwise gradient methods with Generative Adversarial Networks (GANs) to enhance T1-weighted (T1-w) and T2-weighted (T2-w) MRI images. This approach combines the benefits of both modalities to simulate the effects of gadolinium-based contrast agents, thereby reducing associated risks. Various modifications of PGMGVCE, including changing hyperparameters, using normalization methods (z-score, Sigmoid and Tanh) and training the model with T1-w or T2-w images only, were tested to optimize the model's performance. Results: PGMGVCE demonstrated a similar accuracy to the existing model in terms of mean absolute error (MAE) (8.56 ± 0.45 for Li's model; 8.72 ± 0.48 for PGMGVCE), mean square error (MSE) (12.43 ± 0.67 for Li's model; 12.81 ± 0.73 for PGMGVCE) and structural similarity index (SSIM) (0.71 ± 0.08 for Li's model; 0.73 ± 0.12 for PGMGVCE). However, it showed improvements in texture representation, as indicated by total mean square variation per mean intensity (TMSVPMI) (0.124 ± 0.022 for ground truth; 0.079 ± 0.024 for Li's model; 0.120 ± 0.027 for PGMGVCE), total absolute variation per mean intensity (TAVPMI) (0.159 ± 0.031 for ground truth; 0.100 ± 0.032 for Li's model; 0.153 ± 0.029 for PGMGVCE), Tenengrad function per mean intensity (TFPMI) (1.222 ± 0.241 for ground truth; 0.981 ± 0.213 for Li's model; 1.194 ± 0.223 for PGMGVCE) and variance function per mean intensity (VFPMI) (0.0811 ± 0.005 for ground truth; 0.0667 ± 0.006 for Li's model; 0.0761 ± 0.006 for PGMGVCE). Conclusions: PGMGVCE presents an innovative and safe approach to VCE in MRI, demonstrating the power of deep learning in enhancing medical imaging. This model paves the way for more accurate and risk-free diagnostic tools in medical imaging.

Radiomics for residual tumour detection and prognosis in newly diagnosed glioblastoma based on postoperative [11C] methionine PET and T1c-w MRI

Personalized treatment strategies based on non-invasive biomarkers have potential to improve patient management in patients with newly diagnosed glioblastoma (GBM). The residual tumour burden after surgery in GBM patients is a prognostic imaging biomarker. However, in clinical patient management, its assessment is a manual and time-consuming process that is at risk of inter-rater variability. Furthermore, the prediction of patient outcome prior to radiotherapy may identify patient subgroups that could benefit from escalated radiotherapy doses. Therefore, in this study, we investigate the capabilities of traditional radiomics and 3D convolutional neural networks for automatic detection of the residual tumour status and to prognosticate time-to-recurrence (TTR) and overall survival (OS) in GBM using postoperative [11C] methionine positron emission tomography (MET-PET) and gadolinium-enhanced T1-w magnetic resonance imaging (MRI). On the independent test data, the 3D-DenseNet model based on MET-PET achieved the best performance for residual tumour detection, while the logistic regression model with conventional radiomics features performed best for T1c-w MRI (AUC: MET-PET 0.95, T1c-w MRI 0.78). For the prognosis of TTR and OS, the 3D-DenseNet model based on MET-PET integrated with age and MGMT status achieved the best performance (Concordance-Index: TTR 0.68, OS 0.65). In conclusion, we showed that both deep-learning and conventional radiomics have potential value for supporting image-based assessment and prognosis in GBM. After prospective validation, these models may be considered for treatment personalization.

Investigating the impact of motion in the scanner on brain age predictions

Abstract Brain Age Gap (BAG) is defined as the difference between the brain’s predicted age and the chronological age of an individual. Magnetic resonance imaging (MRI)-based BAG can quantify acceleration of brain aging, and is used to infer brain health as aging and disease interact. Motion in the scanner is a common occurrence that can affect the acquired MRI data and act as a major confound in the derived models. As such, age-related changes in head motion may impact the observed age-related differences. However, the relationship between head motion and BAG as estimated by structural MRI has not been systematically examined. The aim of this study is to assess the impact of motion on voxel-based morphometry (VBM) based BAG. Data were obtained from two sources: i) T1-weighted (T1w) MRIs from the Cambridge Centre for Ageing and Neuroscience (CamCAN) were used to train the brain age prediction model, and ii) T1w MRIs from the Movement-related artifacts (MR-ART) dataset were used to assess the impact of motion on BAG. MR-ART includes one motion-free and two motion-affected (one low and one high) 3D T1w MRIs. We also visually rated the motion levels of the MR-ART MRIs from 0 to 5, with 0 meaning no motion and 5 high motion levels. All images were pre-processed through a standard VBM pipeline. GM density across cortical and subcortical regions were then used to train the brain age prediction model and assess the relationship between BAG and MRI motion. Principal component analysis was used to perform dimension reduction and extract the VBM-based features. BAG was estimated by regressing out the portion of delta age explained by chronological age. Linear mixed-effects models were used to investigate the relationship between BAG and motion session as well as motion severity, including participant IDs as random effects. We repeated the same analysis using cortical thickness based on FreeSurfer 7.4.1 and to compare the results for volumetric versus surface-based measures of brain morphometry. In contrast with the session with no induced motion, predicted delta age was significantly higher for high motion sessions 2.35 years (t = 5.17, p < 0.0001), with marginal effect for low motion sessions 0.95 years (t = 2.11, p = 0.035) for VBM analysis as well as 3.46 years (t = 11.45, p < 0.0001) for high motion and 2.28 years (t = 7.54, p < 0.0001) for low motion based on cortical thickness. In addition, delta age was significantly associated with motion severity as evaluated by visual rating 0.45 years per rating level (t = 4.59, p < 0.0001) for VBM analysis and 0.83 years per motion level (t = 12.89, p < 0.0001) for cortical thickness analysis. Motion in the scanner can significantly impact brain age estimates, and needs to be accounted for as a confound, particularly when studying populations that are known to have higher levels of motion in the scanner. These results have significant implications for brain age studies in aging and neurodegeneration. Based on these findings, we recommend assessment and inclusion of visual motion ratings in such studies. In cases that the visual rating proves prohibitive, we recommend the inclusion of normalized Euler number from FreeSurfer as defined in the manuscript as a covariate in the models.

Magnetic resonance imaging techniques for indirect assessment of myelin content in the brain using standard T1w and T2w MRI sequences and postprocessing analysis.

Magnetic Resonance Imaging (MRI) has revolutionized our ability to non-invasively study the brain's structural and functional properties. However, detecting myelin, a crucial component of white matter, remains challenging due to its indirect visibility on conventional MRI scans. Myelin plays a vital role in neural signal transmission and is associated with various neurological conditions. Understanding myelin distribution and content is crucial for insights into brain development, aging, and neurological disorders. Although specialized MRI sequences can estimate myelin content, these are time-consuming. Also, many patients sent to specialized neurological centers have an MRI of the brain already scanned. In this study, we focused on techniques utilizing standard MRI T1-weighted (T1w) and T2 weighted (T2w) sequences commonly used in brain imaging protocols. We evaluated the applicability of the T1w/T2w ratio in assessing myelin content by comparing it to quantitative T1 mapping (qT1). Our study included 1 healthy adult control and 7 neurologic patients (comprising both pediatric and adult populations) with epilepsy originating from focal epileptogenic lesions visible on MRI structural scans. Following image acquisition on a 3T Siemens Vida scanner, datasets were co registered, and segmented into anatomical regions using the Fastsurfer toolbox, and T1w/T2w ratio maps were calculated in Matlab software. We further assessed interhemispheric differences in volumes of individual structures, their signal intensity, and the correlation of the T1w/T2w ratio to qT1. Our data demonstrate that in situations where a dedicated myelin-sensing sequence such as qT1 is not available, the T1w/T2w ratio provides significantly better information than T1w alone. By providing indirect information about myelin content, this technique offers a valuable tool for understanding the neurobiology of myelin-related conditions using basic brain scans.

Assessment of axial spondyloarthritis activity using a magnetic resonance imaging-based multi-region-of-interest fusion model

BackgroundIdentifying axial spondyloarthritis (axSpA) activity early and accurately is essential for treating physicians to adjust treatment plans and guide clinical decisions promptly. The current literature is mostly focused on axSpA diagnosis, and there has been thus far, no study that reported the use of a radiomics approach for differentiating axSpA disease activity. In this study, the aim was to develop a radiomics model for differentiating active from non-active axSpA based on fat-suppressed (FS) T2-weighted (T2w) magnetic resonance imaging (MRI) of sacroiliac joints.MethodsThis retrospective study included 109 patients diagnosed with non-active axSpA (n = 68) and active axSpA (n = 41); patients were divided into training and testing cohorts at a ratio of 8:2. Radiomics features were extracted from 3.0 T sacroiliac MRI using two different heterogeneous regions of interest (ROIs, Circle and Facet). Various methods were used to select relevant and robust features, and different classifiers were used to build Circle-based, Facet-based, and a fusion prediction model. Their performance was compared using various statistical parameters. p < 0.05 is considered statistically significant.ResultsFor both Circle- and Facet-based models, 2284 radiomics features were extracted. The combined fusion ROI model accurately differentiated between active and non-active axSpA, with high accuracy (0.90 vs.0.81), sensitivity (0.90 vs. 0.75), and specificity (0.90 vs. 0.85) in both training and testing cohorts.ConclusionThe multi-ROI fusion radiomics model developed in this study differentiated between active and non-active axSpA using sacroiliac FS T2w-MRI. The results suggest MRI-based radiomics of the SIJ can distinguish axSpA activity, which can improve the therapeutic result and patient prognosis. To our knowledge, this is the only study in the literature that used a radiomics approach to determine axSpA activity.

Deep Learning Framework with Multi-Head Dilated Encoders for Enhanced Segmentation of Cervical Cancer on Multiparametric Magnetic Resonance Imaging.

T2-weighted magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) are essential components of cervical cancer diagnosis. However, combining these channels for the training of deep learning models is challenging due to image misalignment. Here, we propose a novel multi-head framework that uses dilated convolutions and shared residual connections for the separate encoding of multiparametric MRI images. We employ a residual U-Net model as a baseline, and perform a series of architectural experiments to evaluate the tumor segmentation performance based on multiparametric input channels and different feature encoding configurations. All experiments were performed on a cohort of 207 patients with locally advanced cervical cancer. Our proposed multi-head model using separate dilated encoding for T2W MRI and combined b1000 DWI and apparent diffusion coefficient (ADC) maps achieved the best median Dice similarity coefficient (DSC) score, 0.823 (confidence interval (CI), 0.595-0.797), outperforming the conventional multi-channel model, DSC 0.788 (95% CI, 0.568-0.776), although the difference was not statistically significant (p > 0.05). We investigated channel sensitivity using 3D GRAD-CAM and channel dropout, and highlighted the critical importance of T2W and ADC channels for accurate tumor segmentation. However, our results showed that b1000 DWI had a minor impact on the overall segmentation performance. We demonstrated that the use of separate dilated feature extractors and independent contextual learning improved the model's ability to reduce the boundary effects and distortion of DWI, leading to improved segmentation performance. Our findings could have significant implications for the development of robust and generalizable models that can extend to other multi-modal segmentation applications.

Increased perivascular space volume in white matter and basal ganglia is associated with cognition in Parkinson’s Disease

Perivascular spaces (PVS), fluid-filled compartments surrounding brain vasculature, are an essential component of the glymphatic system responsible for transport of waste and nutrients. Glymphatic system impairment may underlie cognitive deficits in Parkinson’s disease (PD). Studies have focused on the role of basal ganglia PVS with cognition in PD, but the role of white matter PVS is unknown. This study examined the relationship of white matter and basal ganglia PVS with domain-specific and global cognition in individuals with PD. Fifty individuals with PD underwent 3T T1w magnetic resonance imaging (MRI) to determine PVS volume fraction, defined as PVS volume normalized to total regional volume, within (i) centrum semiovale, (ii) prefrontal white matter (medial orbitofrontal, rostral middle frontal, superior frontal), and (iii) basal ganglia. A neuropsychological battery included assessment of global cognitive function (Montreal Cognitive Assessment, and global cognitive composite score), and cognitive-specific domains (executive function, memory, visuospatial function, attention, and language). Higher white matter rostral middle frontal PVS was associated with lower scores in both global cognitive and visuospatial function. In the basal ganglia higher PVS was associated with lower scores for memory with a trend towards lower global cognitive composite score. While previous reports have shown that greater amount of PVS in the basal ganglia is associated with decline in global cognition in PD, our findings suggest that increased white matter PVS volume may also underlie changes in cognition.

A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes.

Malignant lateral lymph nodes (LLNs) in low, locally advanced rectal cancer can cause (ipsi-lateral) local recurrences ((L)LR). Accurate identification is, therefore, essential. This study explored LLN features to create an artificial intelligence prediction model, estimating the risk of (L)LR. This retrospective multicentre cohort study examined 196 patients diagnosed with rectal cancer between 2008 and 2020 from three tertiary centres in the Netherlands. Primary and restaging T2W magnetic resonance imaging and clinical features were used. Visible LLNs were segmented and used for a multi-channel convolutional neural network. A deep learning model was developed and trained for the prediction of (L)LR according to malignant LLNs. Combined imaging and clinical features resulted in AUCs of 0.78 and 0.80 for LR and LLR, respectively. The sensitivity and specificity were 85.7% and 67.6%, respectively. Class activation map explainability methods were applied and consistently identified the same high-risk regions with structural similarity indices ranging from 0.772-0.930. This model resulted in good predictive value for (L)LR rates and can form the basis of future auto-segmentation programs to assist in the identification of high-risk patients and the development of risk stratification models.

Automated segmentation of meningioma from contrast-enhanced T1-weighted MRI images in a case series using a marker-controlled watershed segmentation and fuzzy C-means clustering machine learning algorithm

Introduction and importanceAccurate segmentation of meningiomas from contrast-enhanced T1-weighted (CE T1-w) magnetic resonance imaging (MRI) is crucial for diagnosis and treatment planning. Manual segmentation is time-consuming and prone to variability. To evaluate an automated segmentation approach for meningiomas using marker-controlled watershed segmentation (MCWS) and fuzzy c-means (FCM) algorithms. Case presentation and methodsCE T1-w MRI of 3 female patients (aged 59, 44, 67 years) with right frontal meningiomas were analyzed. Images were converted to grayscale and preprocessed with Otsu's thresholding and FCM clustering. MCWS segmentation was performed. Segmentation accuracy was assessed by comparing automated segmentations to manual delineations. Clinical discussionThe approach successfully segmented meningiomas in all cases. Mean sensitivity was 0.8822, indicating accurate identification of tumors. Mean Dice similarity coefficient between Otsu's and FCM1 was 0.6599, suggesting good overlap between segmentation methods. ConclusionThe MCWS and FCM approach enables accurate automated segmentation of meningiomas from CE T1-w MRI. With further validation on larger datasets, this could provide an efficient tool to assist in delineating meningioma boundaries for clinical management.

Improving Structural MRI Preprocessing with Hybrid Transformer GANs.

Magnetic resonance imaging (MRI) is a technique that is widely used in practice to evaluate any pathologies in the human body. One of the areas of interest is the human brain. Naturally, MR images are low-resolution and contain noise due to signal interference, the patient's body's radio-frequency emissions and smaller Tesla coil counts in the machinery. There is a need to solve this problem, as MR tomographs that have the capability of capturing high-resolution images are extremely expensive and the length of the procedure to capture such images increases by the order of magnitude. Vision transformers have lately shown state-of-the-art results in super-resolution tasks; therefore, we decided to evaluate whether we can employ them for structural MRI super-resolution tasks. A literature review showed that similar methods do not focus on perceptual image quality because upscaled images are often blurry and are subjectively of poor quality. Knowing this, we propose a methodology called HR-MRI-GAN, which is a hybrid transformer generative adversarial network capable of increasing resolution and removing noise from 2D T1w MRI slice images. Experiments show that our method quantitatively outperforms other SOTA methods in terms of perceptual image quality and is capable of subjectively generalizing to unseen data. During the experiments, we additionally identified that the visual saliency-induced index metric is not applicable to MRI perceptual quality assessment and that general-purpose denoising networks are effective when removing noise from MR images.

Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm.

The recovery of semantics from corrupted images is a significant challenge in image processing. Noise can obscure features, interfere with accurate analysis, and bias results. To address this issue, the Regularized Neighborhood Pixel Similarity Wavelet algorithm (PixSimWave) was developed for denoising Nifti (magnetic resonance imaging (MRI)). The PixSimWave algorithm uses regularized pixel similarity detection to improve the accuracy of noise reduction by creating patches to analyze the intensity of pixels and locate matching pixels, as well as adaptive neighborhood filtering to estimate noisy pixel values by allocating each pixel a weight based on its similarity. The wavelet transform breaks down the image into scales and orientations, allowing a sparse image representation to allocate a soft threshold on its similarity to the original pixels. The proposed method was evaluated on simulated and raw T1w MRIs, outperforming other methods in terms of an SSIM value of 0.9908 for a low Rician noise level of 3% and 0.9881 for a high noise level of 17%. The addition of Gaussian noise improved PSNR and SSIM, with the results indicating that the proposed method outperformed other models while preserving edges and textures. In summary, the PixSimWave algorithm is a viable noise-elimination approach that employs both sparse wavelet coefficients and regularized similarity with decreased computation time, improving the accuracy of noise reduction in images.

Deep Network-Based Comprehensive Parotid Gland Tumor Detection

Salivary gland tumors constitute 2%-6% of all head and neck tumors and are most common in the parotid gland. Magnetic resonance (MR) imaging is the most sensitive imaging modality for diagnosis. Tumor type, localization, and relationship with surrounding structures are important factors for treatment. Therefore, parotid gland tumor segmentation is important. Specialists widely use manual segmentation in diagnosis and treatment. However, considering the development of artificial intelligence-based models today, it is seen that artificial intelligence-based automatic segmentation models can be used instead of manual segmentation, which is a time-consuming technique. Therefore, we segmented parotid gland tumor (PGT) using deep learning-based architectures in the paper. The dataset used in the study includes 102 T1-w, 102 contrast-enhanced T1-w (T1C-w), and 102 T2-w MR images. After cropping the raw and manually segmented images by experts, we obtained the masks of these images. After standardizing the image sizes, we split these images into approximately 80% training set and 20% test set. Hereabouts, we trained six models for these images using ResNet18 and Xception-based DeepLab v3+. We prepared a user-friendly Graphical User Interface application that includes each of these models. From the results, the accuracy and weighted Intersection over Union values of the ResNet18-based DeepLab v3+ architecture trained for T1C-w, which is the most successful model in the study, are equal to 0.96153 and 0.92601, respectively. Regarding the results and the literature, it can be seen that the proposed system is competitive in terms of both using MR images and training the models independently for T1-w, T1C-w, and T2-w. Expressing that PGT is usually segmented manually in the literature, we predict that our study can contribute significantly to the literature. In this study, we prepared and presented a software application that can be easily used by users for automatic PGT segmentation. In addition to predicting the reduction of costs and workload through the study, we developed models with meaningful performance metrics according to the literature.

Region-specific deep learning models for accurate segmentation of rectal structures on post-chemoradiation T2w MRI: a multi-institutional, multi-reader study.

For locally advanced rectal cancers, in vivo radiological evaluation of tumor extent and regression after neoadjuvant therapy involves implicit visual identification of rectal structures on magnetic resonance imaging (MRI). Additionally, newer image-based, computational approaches (e.g., radiomics) require more detailed and precise annotations of regions such as the outer rectal wall, lumen, and perirectal fat. Manual annotations of these regions, however, are highly laborious and time-consuming as well as subject to inter-reader variability due to tissue boundaries being obscured by treatment-related changes (e.g., fibrosis, edema). This study presents the application of U-Net deep learning models that have been uniquely developed with region-specific context to automatically segment each of the outer rectal wall, lumen, and perirectal fat regions on post-treatment, T2-weighted MRI scans. In multi-institutional evaluation, region-specific U-Nets (wall Dice = 0.920, lumen Dice = 0.895) were found to perform comparably to multiple readers (wall inter-reader Dice = 0.946, lumen inter-reader Dice = 0.873). Additionally, when compared to a multi-class U-Net, region-specific U-Nets yielded an average 20% improvement in Dice scores for segmenting each of the wall, lumen, and fat; even when tested on T2-weighted MRI scans that exhibited poorer image quality, or from a different plane, or were accrued from an external institution. Developing deep learning segmentation models with region-specific context may thus enable highly accurate, detailed annotations for multiple rectal structures on post-chemoradiation T2-weighted MRI scans, which is critical for improving evaluation of tumor extent in vivo and building accurate image-based analytic tools for rectal cancers.

Feasibility of online radial magnetic resonance imaging for adaptive radiotherapy of pancreatic tumors.

Online adaptive magnetic resonance (MR)-guided treatment planning for pancreatic tumors on 1.5T systems typically employs Cartesian 3D T 2w magnetic resonance imaging (MRI). The main disadvantage of this sequence is that respiratory motion results in substantial blurring in the abdomen, which can hamper delineation accuracy. This study investigated the use of two motion-robust radial MRI sequences as main delineation scan for pancreatic MR-guided radiotherapy. Twelve patients with pancreatic tumors were imaged with a 3D T 2w scan, a Periodically Rotated Overlapping ParallEL Lines with Enhanced Reconstruction (PROPELLER) scan (partially overlapping strips), and a 3D Vane scan (stack-of-stars), on a 1.5T MR-Linac under abdominal compression. The scans were assessed by three radiation oncologists for their suitability for online adaptive delineation. A quantitative comparison was made for gradient entropy and the effect of motion on apparent target position. The PROPELLER scans were selected as first preference in 56% of the cases, the 3D T 2w in 42% and the 3D Vane in 3%. PROPELLER scans sometimes contained a large interslice variation which would have compromised delineation. Gradient entropy was significantly higher in 3D T 2w patient scans. The apparent target position was more sensitive to motion amplitude in the PROPELLER scans, but substantial offsets did not occur under 10mm peak-to-peak. PROPELLER MRI may be a superior imaging sequence for pancreatic MRgRT compared to standard Cartesian sequences. The large interslice variation should be mitigated through further sequence optimization before PROPELLER can be adopted for online treatment adaptation.

Comparison of post contrast fluid attenuated inversion recovery, 3D T1-SPACE, and T1W MRI sequences with fat suppression in the diagnosis of infectious meningitis.

To assess the usefulness of post contrast Fluid attenuated inversion recovery (FLAIR), 3D T1-SPACE, and T1W magnetic resonance imaging (MRI) sequences with fat suppression in diagnosis of infectious meningitis. 75 patients with clinical suspicion of meningitis were evaluated with post contrast FLAIR (PC-FLAIR), post contrast T1-SPACE (PC-T1-SPACE), and post contrast T1WI (PC-T1WI). Sensitivity, specificity, positive predictive value, and negative predictive value of individual sequences were assessed. The sensitivity of PC-FLAIR (88.4%) was greater than PC-T1-SPACE (85.5%) and PC-T1WI (82.6%), considering cerebrospinal fluid (CSF) analysis as gold standard (p < 0.05). Kappa inter-rater agreement between two radiologists was 0.921 for PC-T1-SPACE, 0.921 for PC-T1WI, and 1.0 for PC-FLAIR with a p value <0.05. Both PC-T1-SPACE and PC-FLAIR performed equally in sulcal space enhancement. PC-T1-SPACE and PC-T1WI performed better in evaluation of pachymeningeal enhancement, ependymal enhancement in cases of ventriculitis, whereas PC-FLAIR was more sensitive in assessment of basal cistern enhancement and enhancement along the cerebellar folia. Meningeal enhancement could be better appreciated in PC-FLAIR image than PC-T1WI and PC-T1-SPACE. Enhancement in PC-T1-SPACE was comparable to that of PC-T1WI. Being a T1 based spin echo sequence, PC-T1-SPACE has all the advantages of PC-T1WI in addition to its ability to differentiate meningeal enhancement from leptomeningeal vessels. Hence, PC-T1WI can be replaced by PC-T1-SPACE and PC-FLAIR can be added to routine MRI protocol in suspected case of meningitis.

Multi-Class classification of prostate cancer MRI images based on UCLA score using RegNetY-320 model

Prostate cancer (PCa) is the most frequent non-skin cancer in males, and it represents a significant global healthcare problem. Another challenge is the development of an accurate classification model for the detection of PCa. As a result, developing an accurate classification model for PCa is extremely important and has potentially significant clinical implications. These models have the potential to boost the benefits of treatment while also increasing the likelihood of a patient's survival. The PCa is classified in this research based on the T2w magnetic resonance images (MRI), which are collected from the prostate dataset. In this work, a deep learning-based approach RegNetY-320 model is proposed to classify and detect the PCa. The RegNet model is a pre-trained deep transfer learning architecture, which is most commonly used for the image classification process. The proposed model is optimized using various optimizers, including Adam, AdaMax, SGD, RMSprop, Ftrl, and Nadam, and the optimized models are termed model-01 to model-06. For the evaluation, a multiclass classification system was employed to classify 845 patient records from a mpMRI dataset with a unique "UCLA" score of the ROI. Accuracy, precision, sensitivity, specificity, and the F1 score are all calculated based on the classification for the purpose of performance analysis. Finally, in accordance with the findings, the performances of the various proposed models are evaluated in order to determine their validity. When compared among proposed models, the proposed model RegNetY-320_Model-03 optimized using the RMSprop optimizer has obtained greater performance with 95.70 percent accuracy, which is the highest accuracy performance obtained in this research.

APOE-ε4 modulates the association between regional amyloid deposition and cognitive performance in cognitively unimpaired middle-aged individuals

PurposeTo determine whether the APOE-ε4 allele modulates the relationship between regional β-amyloid (Aβ) accumulation and cognitive change in middle-aged cognitively unimpaired (CU) participants.MethodsThe 352 CU participants (mean aged 61.1 [4.7] years) included completed two cognitive assessments (average interval 3.34 years), underwent [18F]flutemetamol Aβ positron emission tomography (PET), T1w magnetic resonance imaging (MRI), as well as APOE genotyping. Global and regional Aβ PET positivity was assessed across five regions-of-interest by visual reading (VR) and regional Centiloids. Linear regression models were developed to examine the interaction between regional and global Aβ PET positivity and APOE-ε4 status on longitudinal cognitive change assessed with the Preclinical Alzheimer’s Cognitive Composite (PACC), episodic memory, and executive function, after controlling for age, sex, education, cognitive baseline scores, and hippocampal volume.ResultsIn total, 57 participants (16.2%) were VR+ of whom 41 (71.9%) were APOE-ε4 carriers. No significant APOE-ε4*global Aβ PET interactions were associated with cognitive change for any cognitive test. However, APOE-ε4 carriers who were VR+ in temporal areas (n = 19 [9.81%], p = 0.04) and in the striatum (n = 8 [4.14%], p = 0.01) exhibited a higher decline in the PACC. The temporal areas findings were replicated when regional PET positivity was determined with Centiloid values. Regionally, VR+ in the striatum was associated with higher memory decline. As for executive function, interactions between APOE-ε4 and regional VR+ were found in temporal and parietal regions, and in the striatum.ConclusionCU APOE-ε4 carriers with a positive Aβ PET VR in regions known to accumulate amyloid at later stages of the Alzheimer’s disease (AD) continuum exhibited a steeper cognitive decline. This work supports the contention that regional VR of Aβ PET might convey prognostic information about future cognitive decline in individuals at higher risk of developing AD.ClinicalTrials.gov Identifier: NCT02485730. Registered 20 June 2015 https://clinicaltrials.gov/ct2/show/NCT02485730 and ClinicalTrials.gov Identifier:NCT02685969. Registered 19 February 2016 https://clinicaltrials.gov/ct2/show/NCT02685969.

Analysis of radiomic features derived from post-contrast T1-weighted images and apparent diffusion coefficient (ADC) maps for breast lesion evaluation: A retrospective study

IntroductionBreast cancer is the most common malignancy among women, and its diagnosis relies on medical imaging and the invasive, uncomforted biopsy. Recent advances in quantitative imaging and specifically the application of radiomics has proved to be a very promising technique, facilitating both diagnosis and therapy. The purpose of this study is to assess radiomic features derived from post-contrast T1w Magnetic Resonance Imaging (MRI) sequences and Apparent Diffusion Coefficient (ADC) maps for the evaluation of breast pathologies. MethodsMRI data from 52 women were retrospectively reviewed, involving 54 breast lesions, both malignant and benign. Diffusion Weighted Imaging (DWI) was applied as a standard MRΙ protocol, including dynamic contrast-enhanced (DCE) MRΙ in all cases. All patients were examined on a 1.5T MRI scanner, and 216 features were initially extracted from DCE-MRI images. Histological analysis of the breast lesions was performed, and a comparative analysis of the results was carried out to assess the accuracy of the method. ResultsFollowing surgery and histological analysis, 30 lesions were found to be malignant and 24 benign. Implementation of a Machine Learning (ML) classification algorithm with 5-fold cross-validation resulted in a sensitivity of 70%, specificity of 66%, Negative Predictive Value of 82% and overall accuracy of 67% in differentiating malignancy from benevolence. ConclusionTexture analysis and ML methodology based on the first post-contrast dynamic sequences and ADC maps may be employed to differentiate between malignant and benign breast lesions, offering a promising new tool for diagnostic analysis. Implications for practiceThe results of this study will enhance knowledge around application and performance of radiomics in breast MRI, thus helping MRI radiographers who use AI-enabled technologies to better delineate the pros and cons of these procedures.